summaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AMDGPU
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU')
-rw-r--r--llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-fma.ll37
-rw-r--r--llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll7
-rw-r--r--llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-copy.mir298
-rw-r--r--llvm/test/CodeGen/AMDGPU/addrspacecast.ll128
-rw-r--r--llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll36
-rw-r--r--llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll10
-rw-r--r--llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir1541
-rw-r--r--llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir1277
-rw-r--r--llvm/test/CodeGen/AMDGPU/indirect-call-set-from-other-function.ll73
-rw-r--r--llvm/test/CodeGen/AMDGPU/llc-pipeline.ll5
-rw-r--r--llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll56
-rw-r--r--llvm/test/CodeGen/AMDGPU/merge-sbuffer-load.mir725
-rw-r--r--llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll15
13 files changed, 3961 insertions, 247 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-fma.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-fma.ll
index b9846a6a555d..b2b433167fe4 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-fma.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-fma.ll
@@ -441,6 +441,43 @@ define amdgpu_vs <4 x float> @test_v4f16_v4f32_add_ext_fma_mul_rhs(<4 x float> %
ret <4 x float> %d
}
+define amdgpu_ps float @test_matching_source_from_unmerge(ptr addrspace(3) %aptr, float %b) {
+; GFX9-DENORM-LABEL: test_matching_source_from_unmerge:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: ds_read_b64 v[2:3], v0
+; GFX9-DENORM-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_mix_f32 v0, v2, v3, v1 op_sel:[1,1,0] op_sel_hi:[1,1,0]
+; GFX9-DENORM-NEXT: ; return to shader part epilog
+;
+; GFX10-LABEL: test_matching_source_from_unmerge:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: ds_read_b64 v[2:3], v0
+; GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10-NEXT: v_fma_mix_f32 v0, v2, v3, v1 op_sel:[1,1,0] op_sel_hi:[1,1,0]
+; GFX10-NEXT: ; return to shader part epilog
+;
+; GFX10-CONTRACT-LABEL: test_matching_source_from_unmerge:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: ds_read_b64 v[2:3], v0
+; GFX10-CONTRACT-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: v_fma_mix_f32 v0, v2, v3, v1 op_sel:[1,1,0] op_sel_hi:[1,1,0]
+; GFX10-CONTRACT-NEXT: ; return to shader part epilog
+;
+; GFX10-DENORM-LABEL: test_matching_source_from_unmerge:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: ds_read_b64 v[2:3], v0
+; GFX10-DENORM-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10-DENORM-NEXT: v_fma_mix_f32 v0, v2, v3, v1 op_sel:[1,1,0] op_sel_hi:[1,1,0]
+; GFX10-DENORM-NEXT: ; return to shader part epilog
+.entry:
+ %a = load <4 x half>, ptr addrspace(3) %aptr, align 16
+ %a_f32 = fpext <4 x half> %a to <4 x float>
+ %.a3_f32 = extractelement <4 x float> %a_f32, i64 3
+ %.a1_f32 = extractelement <4 x float> %a_f32, i64 1
+ %res = call float @llvm.fmuladd.f32(float %.a1_f32, float %.a3_f32, float %b)
+ ret float %res
+}
+
declare float @llvm.fmuladd.f32(float, float, float) #0
declare half @llvm.fmuladd.f16(half, half, half) #0
declare <4 x float> @llvm.fmuladd.v4f32(<4 x float>, <4 x float>, <4 x float>) #0
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll
index 9b9249b62b0b..66b88236bbb4 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll
@@ -7,10 +7,11 @@ target triple = "amdgcn-amd-amdhsa"
; Make sure flat_scratch_init is set
; GCN-LABEL: {{^}}stack_object_addrspacecast_in_kernel_no_calls:
-; RW-FLAT: s_add_u32 flat_scratch_lo, s4, s7
-; RW-FLAT: s_addc_u32 flat_scratch_hi, s5, 0
+; RW-FLAT: s_add_u32 s0, s0, s7
+; RW-FLAT: s_addc_u32 s1, s1, 0
; RO-FLAT-NOT: flat_scratch
-; GCN: flat_store_dword
+; RW-FLAT: buffer_store_dword
+; RO-FLAT: scratch_store_dword
; RO-FLAT-NOT: .amdhsa_user_sgpr_private_segment_buffer
; RW-FLAT: .amdhsa_user_sgpr_flat_scratch_init 1
; RO-FLAT-NOT: .amdhsa_user_sgpr_flat_scratch_init
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-copy.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-copy.mir
index 48de4838b78f..30c374ddee57 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-copy.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-copy.mir
@@ -1,6 +1,8 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx908 -run-pass=amdgpu-regbankselect -regbankselect-fast -verify-machineinstrs %s -o - | FileCheck %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx908 -run-pass=amdgpu-regbankselect -regbankselect-greedy -verify-machineinstrs %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -run-pass=amdgpu-regbankselect -regbankselect-fast -verify-machineinstrs %s -o - | FileCheck --check-prefix=WAVE32 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -run-pass=amdgpu-regbankselect -regbankselect-greedy -verify-machineinstrs %s -o - | FileCheck --check-prefix=WAVE32 %s
---
name: copy_s32_vgpr_to_vgpr
@@ -201,3 +203,299 @@ body: |
%2:vcc(s1) = COPY %1
S_ENDPGM 0, implicit %2
...
+
+---
+name: wave64_copy_sgpr_64_to_s1
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr4_sgpr5
+ ; CHECK-LABEL: name: wave64_copy_sgpr_64_to_s1
+ ; CHECK: liveins: $sgpr4_sgpr5
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vcc(s1) = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; CHECK-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: [[SELECT:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY]](s1), [[CONST1]], [[CONST2]]
+ %0:_(s1) = COPY $sgpr4_sgpr5
+ %1:_(s32) = G_ZEXT %0:_(s1)
+...
+
+---
+name: wave32_copy_sgpr_32_to_s1
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0
+ ; WAVE32-LABEL: name: wave32_copy_sgpr_32_to_s1
+ ; WAVE32: liveins: $sgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vcc(s1) = COPY $sgpr0
+ ; WAVE32-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; WAVE32-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; WAVE32-NEXT: [[SELECT:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY]](s1), [[CONST1]], [[CONST2]]
+ %0:_(s1) = COPY $sgpr0
+ %1:_(s32) = G_ZEXT %0:_(s1)
+...
+
+---
+name: wave64_copy2_sgpr_64_to_s1
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr4_sgpr5, $sgpr6_sgpr7
+ ; CHECK-LABEL: name: wave64_copy2_sgpr_64_to_s1
+ ; CHECK: liveins: $sgpr4_sgpr5, $sgpr6_sgpr7
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vcc(s1) = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vcc(s1) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; CHECK-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: [[SELECT1:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY1]](s1), [[CONST1]], [[CONST2]]
+ ; CHECK-NEXT: [[CONST3:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; CHECK-NEXT: [[CONST4:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: [[SELECT2:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY2]](s1), [[CONST3]], [[CONST4]]
+ %0:_(s1) = COPY $sgpr4_sgpr5
+ %1:_(s1) = COPY $sgpr6_sgpr7
+ %2:_(s32) = G_ZEXT %0:_(s1)
+ %3:_(s32) = G_ZEXT %1:_(s1)
+...
+
+---
+name: wave32_copy2_sgpr_32_to_s1
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0, $sgpr1
+ ; WAVE32-LABEL: name: wave32_copy2_sgpr_32_to_s1
+ ; WAVE32: liveins: $sgpr0, $sgpr1
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY1:%[0-9]+]]:vcc(s1) = COPY $sgpr0
+ ; WAVE32-NEXT: [[COPY2:%[0-9]+]]:vcc(s1) = COPY $sgpr1
+ ; WAVE32-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; WAVE32-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; WAVE32-NEXT: [[SELECT1:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY1]](s1), [[CONST1]], [[CONST2]]
+ ; WAVE32-NEXT: [[CONST3:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; WAVE32-NEXT: [[CONST4:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; WAVE32-NEXT: [[SELECT2:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY2]](s1), [[CONST3]], [[CONST4]]
+ %0:_(s1) = COPY $sgpr0
+ %1:_(s1) = COPY $sgpr1
+ %2:_(s32) = G_ZEXT %0:_(s1)
+ %3:_(s32) = G_ZEXT %1:_(s1)
+...
+
+---
+name: copy_sgpr_64_to_s1_vgpr
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr4_sgpr5
+ ; CHECK-LABEL: name: copy_sgpr_64_to_s1_vgpr
+ ; CHECK: liveins: $sgpr4_sgpr5
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s1) = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[ZEXT:%[0-9]+]]:vgpr(s32) = G_ZEXT [[COPY]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_sgpr_64_to_s1_vgpr
+ ; WAVE32: liveins: $sgpr4_sgpr5
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s1) = COPY $sgpr4_sgpr5
+ ; WAVE32-NEXT: [[ZEXT:%[0-9]+]]:vgpr(s32) = G_ZEXT [[COPY]](s1)
+ %0:vgpr(s1) = COPY $sgpr4_sgpr5
+ %1:_(s32) = G_ZEXT %0:vgpr(s1)
+...
+
+---
+name: copy_sgpr_32_to_s1_vgpr
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0
+ ; CHECK-LABEL: name: copy_sgpr_32_to_s1_vgpr
+ ; CHECK: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s1) = COPY $sgpr0
+ ; CHECK-NEXT: [[ZEXT:%[0-9]+]]:vgpr(s32) = G_ZEXT [[COPY]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_sgpr_32_to_s1_vgpr
+ ; WAVE32: liveins: $sgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s1) = COPY $sgpr0
+ ; WAVE32-NEXT: [[ZEXT:%[0-9]+]]:vgpr(s32) = G_ZEXT [[COPY]](s1)
+ %0:vgpr(s1) = COPY $sgpr0
+ %1:_(s32) = G_ZEXT %0:vgpr(s1)
+...
+
+---
+name: wave64_copy_sgpr_64_to_s1_vcc
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr4_sgpr5
+ ; CHECK-LABEL: name: wave64_copy_sgpr_64_to_s1_vcc
+ ; CHECK: liveins: $sgpr4_sgpr5
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vcc(s1) = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; CHECK-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: [[SELECT:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY]](s1), [[CONST1]], [[CONST2]]
+ %0:vcc(s1) = COPY $sgpr4_sgpr5
+ %1:_(s32) = G_ZEXT %0:vcc(s1)
+...
+
+---
+name: wave32_copy_sgpr_32_to_s1_vcc
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0
+ ; WAVE32-LABEL: name: wave32_copy_sgpr_32_to_s1_vcc
+ ; WAVE32: liveins: $sgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vcc(s1) = COPY $sgpr0
+ ; WAVE32-NEXT: [[CONST1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 1
+ ; WAVE32-NEXT: [[CONST2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+ ; WAVE32-NEXT: [[SELECT:%[0-9]+]]:vgpr(s32) = G_SELECT [[COPY]](s1), [[CONST1]], [[CONST2]]
+ %0:vcc(s1) = COPY $sgpr0
+ %1:_(s32) = G_ZEXT %0:vcc(s1)
+...
+
+---
+name: copy_virt_reg_to_s1
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; CHECK-LABEL: name: copy_virt_reg_to_s1
+ ; CHECK: liveins: $vgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s1) = COPY [[TRUNC]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_virt_reg_to_s1
+ ; WAVE32: liveins: $vgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; WAVE32-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; WAVE32-NEXT: [[COPY2:%[0-9]+]]:vgpr(s1) = COPY [[TRUNC]](s1)
+ %0:_(s32) = COPY $vgpr0
+ %1:_(s1) = G_TRUNC %0
+ %2:_(s1) = COPY %1
+...
+
+---
+name: copy_virt_reg_to_s1_vgpr
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; CHECK-LABEL: name: copy_virt_reg_to_s1_vgpr
+ ; CHECK: liveins: $vgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s1) = COPY [[TRUNC]](s1)
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr(s1) = COPY [[COPY2]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_virt_reg_to_s1_vgpr
+ ; WAVE32: liveins: $vgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; WAVE32-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; WAVE32-NEXT: [[COPY2:%[0-9]+]]:vgpr(s1) = COPY [[TRUNC]](s1)
+ ; WAVE32-NEXT: [[COPY3:%[0-9]+]]:vgpr(s1) = COPY [[COPY2]](s1)
+ %0:_(s32) = COPY $vgpr0
+ %1:_(s1) = G_TRUNC %0
+ %2:vgpr(s1) = COPY %1
+ %3:_(s1) = COPY %2
+...
+
+
+---
+name: copy_virt_reg_to_s1_vcc
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; CHECK-LABEL: name: copy_virt_reg_to_s1_vcc
+ ; CHECK: liveins: $vgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vcc(s1) = COPY [[TRUNC]](s1)
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vcc(s1) = COPY [[COPY2]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_virt_reg_to_s1_vcc
+ ; WAVE32: liveins: $vgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; WAVE32-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; WAVE32-NEXT: [[COPY2:%[0-9]+]]:vcc(s1) = COPY [[TRUNC]](s1)
+ ; WAVE32-NEXT: [[COPY3:%[0-9]+]]:vcc(s1) = COPY [[COPY2]](s1)
+ %0:_(s32) = COPY $vgpr0
+ %1:_(s1) = G_TRUNC %0
+ %2:vcc(s1) = COPY %1
+ %3:_(s1) = COPY %2
+...
+
+---
+name: copy_s1_to_sgpr_64
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; CHECK-LABEL: name: copy_s1_to_sgpr_64
+ ; CHECK: liveins: $vgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[TRUNC]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_s1_to_sgpr_64
+ ; WAVE32: liveins: $vgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; WAVE32-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; WAVE32-NEXT: $sgpr4_sgpr5 = COPY [[TRUNC]](s1)
+ %0:_(s32) = COPY $vgpr0
+ %1:_(s1) = G_TRUNC %0
+ $sgpr4_sgpr5 = COPY %1
+...
+
+---
+name: copy_s1_to_sgpr_32
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; CHECK-LABEL: name: copy_s1_to_sgpr_32
+ ; CHECK: liveins: $vgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr0 = COPY [[TRUNC]](s1)
+ ;
+ ; WAVE32-LABEL: name: copy_s1_to_sgpr_32
+ ; WAVE32: liveins: $vgpr0
+ ; WAVE32-NEXT: {{ $}}
+ ; WAVE32-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
+ ; WAVE32-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s1) = G_TRUNC [[COPY]](s32)
+ ; WAVE32-NEXT: $sgpr0 = COPY [[TRUNC]](s1)
+ %0:_(s32) = COPY $vgpr0
+ %1:_(s1) = G_TRUNC %0
+ $sgpr0 = COPY %1
+...
diff --git a/llvm/test/CodeGen/AMDGPU/addrspacecast.ll b/llvm/test/CodeGen/AMDGPU/addrspacecast.ll
index 1315d576a83e..4b1484e9bd95 100644
--- a/llvm/test/CodeGen/AMDGPU/addrspacecast.ll
+++ b/llvm/test/CodeGen/AMDGPU/addrspacecast.ll
@@ -5,22 +5,11 @@ target triple = "amdgcn-amd-amdhsa"
; HSA-LABEL: {{^}}use_group_to_flat_addrspacecast:
-; CI-DAG: s_load_dword [[PTR:s[0-9]+]], s[6:7], 0x0{{$}}
-; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x10{{$}}
-; CI-DAG: s_cmp_lg_u32 [[PTR]], -1
-; CI-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[APERTURE]], 0
-; CI-DAG: s_cselect_b32 s[[LO:[0-9]+]], [[PTR]], 0
-
-; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HIBASE:[0-9]+]]], src_shared_base
-
+; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[6:7], 0x0{{$}}
+; GFX9-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x0{{$}}
+; HSA-DAG: v_mov_b32_e32 [[PTR:v[0-9]+]], [[APERTURE]]
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
-; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
-
-; GFX9: s_cmp_lg_u32 [[PTR]], -1
-; GFX9-DAG: s_cselect_b32 s[[LO:[0-9]+]], s[[HIBASE]], 0
-; GFX9-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[PTR]], 0
-
-; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
+; HSA-DAG: ds_write_b32 [[PTR]], [[K]]
; HSA: .amdhsa_user_sgpr_private_segment_buffer 1
; HSA: .amdhsa_user_sgpr_dispatch_ptr 0
@@ -39,22 +28,8 @@ define amdgpu_kernel void @use_group_to_flat_addrspacecast(ptr addrspace(3) %ptr
; Test handling inside a non-kernel
; HSA-LABEL: {{^}}use_group_to_flat_addrspacecast_func:
-; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[6:7], 0x10{{$}}
-; CI-DAG: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], [[APERTURE]]
-; CI-DAG: v_cmp_ne_u32_e32 vcc, -1, v0
-; CI-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]], vcc
-; CI-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, v0
-
-; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HIBASE:[0-9]+]]], src_shared_base
-
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
-
-; GFX9-DAG: v_mov_b32_e32 v[[VREG_HIBASE:[0-9]+]], s[[HIBASE]]
-; GFX9-DAG: v_cmp_ne_u32_e32 vcc, -1, v0
-; GFX9-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, v0, vcc
-; GFX9-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, v[[VREG_HIBASE]], vcc
-
-; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
+; HSA-DAG: ds_write_b32 v0, [[K]]
define void @use_group_to_flat_addrspacecast_func(ptr addrspace(3) %ptr) #0 {
%stof = addrspacecast ptr addrspace(3) %ptr to ptr
store volatile i32 7, ptr %stof
@@ -63,23 +38,16 @@ define void @use_group_to_flat_addrspacecast_func(ptr addrspace(3) %ptr) #0 {
; HSA-LABEL: {{^}}use_private_to_flat_addrspacecast:
-; CI-DAG: s_load_dword [[PTR:s[0-9]+]], s[6:7], 0x0{{$}}
-; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x11{{$}}
-
-; CI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
-; CI-DAG: s_cmp_lg_u32 [[PTR]], -1
-; CI-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[APERTURE]], 0
-; CI-DAG: s_cselect_b32 s[[LO:[0-9]+]], [[PTR]], 0
-
-; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
-; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HIBASE:[0-9]+]]], src_private_base
-
-; GFX9-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
-; GFX9: s_cmp_lg_u32 [[PTR]], -1
-; GFX9: s_cselect_b32 s[[LO:[0-9]+]], s[[HIBASE]], 0
-; GFX9: s_cselect_b32 s[[HI:[0-9]+]], [[PTR]], 0
-
-; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
+; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[6:7], 0x0{{$}}
+; GFX9-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x0{{$}}
+; HSA-DAG: v_mov_b32_e32 [[PTR:v[0-9]+]], [[APERTURE]]
+; HSA-DAG: s_mov_b64 s[{{[0-9]+}}:[[RSRCHI:[0-9]+]]], s[2:3]
+; HSA-DAG: s_mov_b64 s[[[BASELO:[0-9]+]]:[[BASEHI:[0-9]+]]], s[0:1]
+; SI-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s9
+; GFX9-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s7
+; HSA-DAG: s_addc_u32 s[[BASEHI]], s[[BASEHI]], 0
+; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
+; HSA: buffer_store_dword [[K]], [[PTR]], s[[[BASELO]]:[[RSRCHI]]], 0 offen
; HSA: .amdhsa_user_sgpr_private_segment_buffer 1
; HSA: .amdhsa_user_sgpr_dispatch_ptr 0
@@ -97,10 +65,12 @@ define amdgpu_kernel void @use_private_to_flat_addrspacecast(ptr addrspace(5) %p
; HSA-LABEL: {{^}}use_global_to_flat_addrspacecast:
; HSA: s_load_dwordx2 s[[[PTRLO:[0-9]+]]:[[PTRHI:[0-9]+]]]
-; HSA-DAG: v_mov_b32_e32 v[[VPTRLO:[0-9]+]], s[[PTRLO]]
-; HSA-DAG: v_mov_b32_e32 v[[VPTRHI:[0-9]+]], s[[PTRHI]]
+; CI-DAG: v_mov_b32_e32 v[[VPTRLO:[0-9]+]], s[[PTRLO]]
+; CI-DAG: v_mov_b32_e32 v[[VPTRHI:[0-9]+]], s[[PTRHI]]
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
-; HSA: flat_store_dword v[[[VPTRLO]]:[[VPTRHI]]], [[K]]
+; CI: flat_store_dword v[[[VPTRLO]]:[[VPTRHI]]], [[K]]
+; GFX9-DAG: v_mov_b32_e32 [[ADDR:v[0-9]+]], 0
+; GFX9: global_store_dword [[ADDR]], [[K]], s[[[PTRLO]]:[[PTRHI]]]
; HSA: .amdhsa_user_sgpr_queue_ptr 0
define amdgpu_kernel void @use_global_to_flat_addrspacecast(ptr addrspace(1) %ptr) #0 {
@@ -112,9 +82,7 @@ define amdgpu_kernel void @use_global_to_flat_addrspacecast(ptr addrspace(1) %pt
; no-op
; HSA-LABEL: {{^}}use_constant_to_flat_addrspacecast:
; HSA: s_load_dwordx2 s[[[PTRLO:[0-9]+]]:[[PTRHI:[0-9]+]]]
-; HSA-DAG: v_mov_b32_e32 v[[VPTRLO:[0-9]+]], s[[PTRLO]]
-; HSA-DAG: v_mov_b32_e32 v[[VPTRHI:[0-9]+]], s[[PTRHI]]
-; HSA: flat_load_dword v{{[0-9]+}}, v[[[VPTRLO]]:[[VPTRHI]]]
+; HSA-DAG: s_load_dword s0, s[[[PTRLO]]:[[PTRHI]]], 0x0
define amdgpu_kernel void @use_constant_to_flat_addrspacecast(ptr addrspace(4) %ptr) #0 {
%stof = addrspacecast ptr addrspace(4) %ptr to ptr
%ld = load volatile i32, ptr %stof
@@ -215,14 +183,9 @@ define amdgpu_kernel void @use_flat_to_constant_addrspacecast(ptr %ptr) #0 {
}
; HSA-LABEL: {{^}}cast_0_group_to_flat_addrspacecast:
-; CI: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x10
-; CI-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[APERTURE]]
-
-; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HI:[0-9]+]]], src_shared_base
-
; HSA-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], 0{{$}}
; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 7{{$}}
-; HSA: {{flat|global}}_store_dword v[[[LO]]:[[HI]]], v[[K]]
+; HSA: ds_write_b32 v[[LO]], v[[K]]
define amdgpu_kernel void @cast_0_group_to_flat_addrspacecast() #0 {
%cast = addrspacecast ptr addrspace(3) null to ptr
store volatile i32 7, ptr %cast
@@ -240,10 +203,9 @@ define amdgpu_kernel void @cast_0_flat_to_group_addrspacecast() #0 {
}
; HSA-LABEL: {{^}}cast_neg1_group_to_flat_addrspacecast:
-; HSA: v_mov_b32_e32 v[[LO:[0-9]+]], 0{{$}}
; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 7{{$}}
-; HSA-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0{{$}}
-; HSA: {{flat|global}}_store_dword v[[[LO]]:[[HI]]], v[[K]]
+; HSA-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], -1
+; HSA: ds_write_b32 v[[LO]], v[[K]]
define amdgpu_kernel void @cast_neg1_group_to_flat_addrspacecast() #0 {
%cast = addrspacecast ptr addrspace(3) inttoptr (i32 -1 to ptr addrspace(3)) to ptr
store volatile i32 7, ptr %cast
@@ -262,14 +224,13 @@ define amdgpu_kernel void @cast_neg1_flat_to_group_addrspacecast() #0 {
; FIXME: Shouldn't need to enable queue ptr
; HSA-LABEL: {{^}}cast_0_private_to_flat_addrspacecast:
-; CI: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x11
-; CI-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[APERTURE]]
-
-; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HI:[0-9]+]]], src_private_base
-
-; HSA-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], 0{{$}}
+; HSA-DAG: s_mov_b64 s[{{[0-9]+}}:[[RSRCHI:[0-9]+]]], s[2:3]
+; HSA-DAG: s_mov_b64 s[[[BASELO:[0-9]+]]:[[BASEHI:[0-9]+]]], s[0:1]
+; CI-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s7
+; GFX9-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s5
+; HSA-DAG: s_addc_u32 s[[BASEHI]], s[[BASEHI]], 0
; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 7{{$}}
-; HSA: {{flat|global}}_store_dword v[[[LO]]:[[HI]]], v[[K]]
+; HSA: buffer_store_dword v[[K]], off, s[[[BASELO]]:[[RSRCHI]]], 0
define amdgpu_kernel void @cast_0_private_to_flat_addrspacecast() #0 {
%cast = addrspacecast ptr addrspace(5) null to ptr
store volatile i32 7, ptr %cast
@@ -286,13 +247,16 @@ define amdgpu_kernel void @cast_0_flat_to_private_addrspacecast() #0 {
ret void
}
-
; HSA-LABEL: {{^}}cast_neg1_private_to_flat_addrspacecast:
-; HSA: v_mov_b32_e32 v[[LO:[0-9]+]], 0{{$}}
+; HSA-DAG: s_mov_b64 s[{{[0-9]+}}:[[RSRCHI:[0-9]+]]], s[2:3]
+; HSA-DAG: s_mov_b64 s[[[BASELO:[0-9]+]]:[[BASEHI:[0-9]+]]], s[0:1]
+; CI-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s7
+; GFX9-DAG: s_add_u32 s[[BASELO]], s[[BASELO]], s5
+; HSA-DAG: s_addc_u32 s[[BASEHI]], s[[BASEHI]], 0
+; HSA-DAG: v_mov_b32_e32 [[PTR:v[0-9]+]], -1{{$}}
; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 7{{$}}
-; HSA-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0{{$}}
-; HSA: {{flat|global}}_store_dword v[[[LO]]:[[HI]]], v[[K]]
+; HSA: buffer_store_dword v[[K]], [[PTR]], s[[[BASELO]]:[[RSRCHI]]], 0 offen
; CI: .amdhsa_user_sgpr_queue_ptr 1
; GFX9: .amdhsa_user_sgpr_queue_ptr 0
@@ -342,16 +306,18 @@ end:
; Check for prologue initializing special SGPRs pointing to scratch.
; HSA-LABEL: {{^}}store_flat_scratch:
-; CI-DAG: s_mov_b32 flat_scratch_lo, s9
; CI-DAG: s_add_i32 [[ADD:s[0-9]+]], s8, s11
; CI-DAG: s_lshr_b32 flat_scratch_hi, [[ADD]], 8
-
-; GFX9: s_add_u32 flat_scratch_lo, s6, s9
-; GFX9: s_addc_u32 flat_scratch_hi, s7, 0
-
-; HSA: {{flat|global}}_store_dword
-; HSA: s_barrier
-; HSA: {{flat|global}}_load_dword
+; HSA: buffer_store_dword
+; HSA: s_barrier
+; HSA: buffer_load_dword [[K:v[0-9]+]], v{{[0-9]+}}, s[0:3], 0 offen glc
+; HSA-DAG: s_load_dwordx2
+; CI-DAG: s_mov_b32 flat_scratch_lo, s9
+; CI-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s4
+; CI-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s5
+; GFX9-DAG: v_mov_b32_e32 [[PTR:v[0-9]+]], 0
+; CI: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
+; GFX9: global_store_dword [[PTR]], [[K]]
define amdgpu_kernel void @store_flat_scratch(ptr addrspace(1) noalias %out, i32) #0 {
%alloca = alloca i32, i32 9, align 4, addrspace(5)
%x = call i32 @llvm.amdgcn.workitem.id.x() #2
diff --git a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll
index 43cdf85ed381..879bceaef97c 100644
--- a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll
+++ b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll
@@ -425,8 +425,7 @@ define amdgpu_kernel void @use_group_to_flat_addrspacecast(ptr addrspace(3) %ptr
;
; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@use_group_to_flat_addrspacecast
; ATTRIBUTOR_HSA-SAME: (ptr addrspace(3) [[PTR:%.*]]) #[[ATTR12:[0-9]+]] {
-; ATTRIBUTOR_HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(3) [[PTR]] to ptr
-; ATTRIBUTOR_HSA-NEXT: store volatile i32 0, ptr [[STOF]], align 4
+; ATTRIBUTOR_HSA-NEXT: store volatile i32 0, ptr addrspace(3) [[PTR]], align 4
; ATTRIBUTOR_HSA-NEXT: ret void
;
%stof = addrspacecast ptr addrspace(3) %ptr to ptr
@@ -443,8 +442,7 @@ define amdgpu_kernel void @use_private_to_flat_addrspacecast(ptr addrspace(5) %p
;
; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@use_private_to_flat_addrspacecast
; ATTRIBUTOR_HSA-SAME: (ptr addrspace(5) [[PTR:%.*]]) #[[ATTR12]] {
-; ATTRIBUTOR_HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(5) [[PTR]] to ptr
-; ATTRIBUTOR_HSA-NEXT: store volatile i32 0, ptr [[STOF]], align 4
+; ATTRIBUTOR_HSA-NEXT: store volatile i32 0, ptr addrspace(5) [[PTR]], align 4
; ATTRIBUTOR_HSA-NEXT: ret void
;
%stof = addrspacecast ptr addrspace(5) %ptr to ptr
@@ -478,11 +476,16 @@ define amdgpu_kernel void @use_flat_to_private_addrspacecast(ptr %ptr) #1 {
; No-op addrspacecast should not use queue ptr
define amdgpu_kernel void @use_global_to_flat_addrspacecast(ptr addrspace(1) %ptr) #1 {
-; HSA-LABEL: define {{[^@]+}}@use_global_to_flat_addrspacecast
-; HSA-SAME: (ptr addrspace(1) [[PTR:%.*]]) #[[ATTR1]] {
-; HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
-; HSA-NEXT: store volatile i32 0, ptr [[STOF]], align 4
-; HSA-NEXT: ret void
+; AKF_HSA-LABEL: define {{[^@]+}}@use_global_to_flat_addrspacecast
+; AKF_HSA-SAME: (ptr addrspace(1) [[PTR:%.*]]) #[[ATTR1]] {
+; AKF_HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
+; AKF_HSA-NEXT: store volatile i32 0, ptr [[STOF]], align 4
+; AKF_HSA-NEXT: ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@use_global_to_flat_addrspacecast
+; ATTRIBUTOR_HSA-SAME: (ptr addrspace(1) [[PTR:%.*]]) #[[ATTR1]] {
+; ATTRIBUTOR_HSA-NEXT: store volatile i32 0, ptr addrspace(1) [[PTR]], align 4
+; ATTRIBUTOR_HSA-NEXT: ret void
;
%stof = addrspacecast ptr addrspace(1) %ptr to ptr
store volatile i32 0, ptr %stof
@@ -490,11 +493,16 @@ define amdgpu_kernel void @use_global_to_flat_addrspacecast(ptr addrspace(1) %pt
}
define amdgpu_kernel void @use_constant_to_flat_addrspacecast(ptr addrspace(4) %ptr) #1 {
-; HSA-LABEL: define {{[^@]+}}@use_constant_to_flat_addrspacecast
-; HSA-SAME: (ptr addrspace(4) [[PTR:%.*]]) #[[ATTR1]] {
-; HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(4) [[PTR]] to ptr
-; HSA-NEXT: [[LD:%.*]] = load volatile i32, ptr [[STOF]], align 4
-; HSA-NEXT: ret void
+; AKF_HSA-LABEL: define {{[^@]+}}@use_constant_to_flat_addrspacecast
+; AKF_HSA-SAME: (ptr addrspace(4) [[PTR:%.*]]) #[[ATTR1]] {
+; AKF_HSA-NEXT: [[STOF:%.*]] = addrspacecast ptr addrspace(4) [[PTR]] to ptr
+; AKF_HSA-NEXT: [[LD:%.*]] = load volatile i32, ptr [[STOF]], align 4
+; AKF_HSA-NEXT: ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@use_constant_to_flat_addrspacecast
+; ATTRIBUTOR_HSA-SAME: (ptr addrspace(4) [[PTR:%.*]]) #[[ATTR1]] {
+; ATTRIBUTOR_HSA-NEXT: [[LD:%.*]] = load volatile i32, ptr addrspace(4) [[PTR]], align 4
+; ATTRIBUTOR_HSA-NEXT: ret void
;
%stof = addrspacecast ptr addrspace(4) %ptr to ptr
%ld = load volatile i32, ptr %stof
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
index 8ef2d89e76d4..032ec65fa851 100644
--- a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
@@ -38,15 +38,9 @@ define amdgpu_kernel void @kern_indirect_use_queue_ptr(i32) #1 {
}
; GCN-LABEL: {{^}}use_queue_ptr_addrspacecast:
-; CIVI: s_load_dword [[APERTURE_LOAD:s[0-9]+]], s[4:5], 0x0
-; CIVI: v_mov_b32_e32 v[[LO:[0-9]+]], 16
-; CIVI-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[APERTURE_LOAD]]
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], 0
+; GCN-DAG: ds_write_b32 v[[LO]], v[[LO]] offset:16
-; GFX9: s_mov_b64 s[{{[0-9]+}}:[[HI:[0-9]+]]], src_shared_base
-; GFX9-DAG: v_mov_b32_e32 v[[VGPR_HI:[0-9]+]], s[[HI]]
-; GFX9: {{flat|global}}_store_dword v{{\[[0-9]+}}:[[VGPR_HI]]]
-
-; CIVI: {{flat|global}}_store_dword v[[[LO]]:[[HI]]]
define hidden void @use_queue_ptr_addrspacecast() #1 {
%asc = addrspacecast ptr addrspace(3) inttoptr (i32 16 to ptr addrspace(3)) to ptr
store volatile i32 0, ptr %asc
diff --git a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir
index 2cd7b8a6424b..6ec296144bf1 100644
--- a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir
+++ b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir
@@ -23,10 +23,35 @@ body: |
bb.0:
; MUBUFW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0
; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 $sgpr32, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 12, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__inline_imm__fi_offset0_live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0_live_vcc
+ ; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0_live_vcc
; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 $sgpr32, implicit $exec
; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
@@ -49,35 +74,87 @@ body: |
bb.0:
; GFX7-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
; GFX7: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 16, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX8: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 16, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX900: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX90A: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX10: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 16, implicit-def $scc
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 12, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; GFX7-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
+ ; GFX7: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX7-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 16, killed $vgpr1, 0, implicit $exec
; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX8-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX8-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
; GFX8: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX8-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 16, killed $vgpr1, 0, implicit $exec
; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX900-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX900-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
; GFX900: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX90A-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
; GFX90A: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX10-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; GFX10-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
; GFX10: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 16, killed $vgpr1, implicit $exec
; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm___fi_offset_inline_imm_live_vcc
; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 16, implicit-def $scc
; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
@@ -100,10 +177,35 @@ body: |
bb.0:
; MUBUFW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0
; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 $sgpr32, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 68, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__literal__fi_offset0_live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0_live_vcc
+ ; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0_live_vcc
; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 $sgpr32, implicit $exec
; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
@@ -126,35 +228,87 @@ body: |
bb.0:
; GFX7-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
; GFX7: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 32, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX8: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 32, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX900: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX90A: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX10: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 68, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; GFX7-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
+ ; GFX7: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX7-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 32, killed $vgpr1, 0, implicit $exec
; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX8-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX8-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
; GFX8: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX8-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 32, killed $vgpr1, 0, implicit $exec
; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX900-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX900-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
; GFX900: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX90A-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
; GFX90A: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; GFX10-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; GFX10-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
; GFX10: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 32, killed $vgpr1, implicit $exec
; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
;
- ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__literal__fi_offset0__offset_inlineimm_live_vcc
; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 68, killed $vgpr1, implicit-def $vcc, implicit $exec
@@ -180,17 +334,17 @@ body: |
; MUBUFW64: liveins: $vgpr1
; MUBUFW64-NEXT: {{ $}}
; MUBUFW64-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
;
; FLATSCRW64-LABEL: name: v_add_co_u32_e32__vgpr__fi_offset0
; FLATSCRW64: liveins: $vgpr1
; FLATSCRW64-NEXT: {{ $}}
; FLATSCRW64-NEXT: $vgpr2 = V_MOV_B32_e32 $sgpr32, implicit $exec
- ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
- renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, %stack.0, implicit-def $vcc, implicit $exec
- SI_RETURN implicit $vgpr0, implicit $vcc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
...
@@ -210,16 +364,16 @@ body: |
; MUBUFW64: liveins: $vgpr1
; MUBUFW64-NEXT: {{ $}}
; MUBUFW64-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
;
; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset0__vgpr
; FLATSCRW64: liveins: $vgpr1
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr32, $vgpr1, implicit-def $vcc, implicit $exec
- ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
- renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0, $vgpr1, implicit-def $vcc, implicit $exec
- SI_RETURN implicit $vgpr0, implicit $vcc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr32, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0, $vgpr1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
...
@@ -240,53 +394,53 @@ body: |
; GFX7: liveins: $vgpr1
; GFX7-NEXT: {{ $}}
; GFX7-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX7-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX7-NEXT: $vgpr2, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr2, 0, implicit $exec
- ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
;
; GFX8-LABEL: name: v_add_co_u32_e32__vgpr__fi_literal_offset
; GFX8: liveins: $vgpr1
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX8-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX8-NEXT: $vgpr2, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr2, 0, implicit $exec
- ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
;
; GFX900-LABEL: name: v_add_co_u32_e32__vgpr__fi_literal_offset
; GFX900: liveins: $vgpr1
; GFX900-NEXT: {{ $}}
; GFX900-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX900-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
;
; GFX90A-LABEL: name: v_add_co_u32_e32__vgpr__fi_literal_offset
; GFX90A: liveins: $vgpr1
; GFX90A-NEXT: {{ $}}
; GFX90A-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX90A-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
;
; GFX10-LABEL: name: v_add_co_u32_e32__vgpr__fi_literal_offset
; GFX10: liveins: $vgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX10-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
;
; FLATSCRW64-LABEL: name: v_add_co_u32_e32__vgpr__fi_literal_offset
; FLATSCRW64: liveins: $vgpr1
; FLATSCRW64-NEXT: {{ $}}
; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
; FLATSCRW64-NEXT: $vgpr2 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
- ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def $vcc, implicit $exec
- ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
- renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, %stack.1, implicit-def $vcc, implicit $exec
- SI_RETURN implicit $vgpr0, implicit $vcc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
...
@@ -307,52 +461,52 @@ body: |
; GFX7: liveins: $vgpr1
; GFX7-NEXT: {{ $}}
; GFX7-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX7-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX7-NEXT: $vgpr2, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr2, 0, implicit $exec
- ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
;
; GFX8-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr
; GFX8: liveins: $vgpr1
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX8-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX8-NEXT: $vgpr2, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr2, 0, implicit $exec
- ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
;
; GFX900-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr
; GFX900: liveins: $vgpr1
; GFX900-NEXT: {{ $}}
; GFX900-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX900-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
;
; GFX90A-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr
; GFX90A: liveins: $vgpr1
; GFX90A-NEXT: {{ $}}
; GFX90A-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX90A-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
;
; GFX10-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr
; GFX10: liveins: $vgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX10-NEXT: $vgpr2 = V_ADD_U32_e32 128, killed $vgpr2, implicit $exec
- ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr2, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
;
; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr
; FLATSCRW64: liveins: $vgpr1
; FLATSCRW64-NEXT: {{ $}}
; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $sgpr4, $vgpr1, implicit-def $vcc, implicit $exec
- ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
- renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.1, $vgpr1, implicit-def $vcc, implicit $exec
- SI_RETURN implicit $vgpr0, implicit $vcc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 killed $sgpr4, $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.1, $vgpr1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
...
@@ -373,53 +527,53 @@ body: |
; GFX7: liveins: $sgpr8
; GFX7-NEXT: {{ $}}
; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX7-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX7-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
- ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
;
; GFX8-LABEL: name: v_add_co_u32_e32__sgpr__fi_literal_offset
; GFX8: liveins: $sgpr8
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
- ; GFX8-NEXT: $sgpr4 = S_MOV_B32 128
- ; GFX8-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
- ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
;
; GFX900-LABEL: name: v_add_co_u32_e32__sgpr__fi_literal_offset
; GFX900: liveins: $sgpr8
; GFX900-NEXT: {{ $}}
; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
- ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
;
; GFX90A-LABEL: name: v_add_co_u32_e32__sgpr__fi_literal_offset
; GFX90A: liveins: $sgpr8
; GFX90A-NEXT: {{ $}}
; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
- ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
;
; GFX10-LABEL: name: v_add_co_u32_e32__sgpr__fi_literal_offset
; GFX10: liveins: $sgpr8
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
- ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
;
; FLATSCRW64-LABEL: name: v_add_co_u32_e32__sgpr__fi_literal_offset
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
- ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def $vcc, implicit $exec
- ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
- renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, %stack.1, implicit-def $vcc, implicit $exec
- SI_RETURN implicit $vgpr0, implicit $vcc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
...
@@ -448,6 +602,54 @@ body: |
...
---
+name: v_add_co_u32_e64__inline_imm__fi_offset0__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__clamp
+ ; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__clamp
+ ; FLATSCRW64: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, $sgpr32, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, %stack.0, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset0__live_vcc_clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__live_vcc_clamp
+ ; MUBUFW64: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__live_vcc_clamp
+ ; FLATSCRW64: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 12, $sgpr32, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 12, %stack.0, 1, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vcc
+
+...
+
+---
name: v_add_co_u32_e64__fi_literal_offset__sgpr
tracksRegLiveness: true
stack:
@@ -527,3 +729,1186 @@ body: |
SI_RETURN implicit $vgpr0, implicit $vcc
...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; GFX7-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX7: liveins: $sgpr8
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $sgpr4 = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX8: liveins: $sgpr8
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $sgpr4 = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX900: liveins: $sgpr8
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX90A: liveins: $sgpr8
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX10: liveins: $sgpr8
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX940-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX940: liveins: $sgpr8
+ ; GFX940-NEXT: {{ $}}
+ ; GFX940-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX940-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; GFX940-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+ ; GFX940-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX11-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX11: liveins: $sgpr8
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX11-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 1, implicit $exec
+ ; GFX11-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX12-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+ ; GFX12: liveins: $sgpr8
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX12-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 1, implicit $exec
+ ; GFX12-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 %stack.1, $sgpr8, 1, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vcc
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; GFX7: liveins: $vgpr8
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; GFX8: liveins: $vgpr8
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; GFX900: liveins: $vgpr8
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; GFX90A: liveins: $vgpr8
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; GFX10: liveins: $vgpr8
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable dead $vcc = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; GFX7: liveins: $vgpr8
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; GFX8: liveins: $vgpr8
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; GFX900: liveins: $vgpr8
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; GFX90A: liveins: $vgpr8
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; GFX10: liveins: $vgpr8
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable dead $vcc = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; GFX7: liveins: $vgpr8
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $sgpr4 = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; GFX8: liveins: $vgpr8
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $sgpr4 = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $sgpr4_sgpr5 = V_ADD_CO_U32_e64 killed $sgpr4, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; GFX900: liveins: $vgpr8
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; GFX90A: liveins: $vgpr8
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; GFX10: liveins: $vgpr8
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $vgpr8, 0, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vcc
+
+...
+
+---
+name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 12, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel__live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel__live_vcc
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset0__kernel__live_vcc
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ renamable $vgpr0 = V_ADD_CO_U32_e32 12, %stack.0, implicit-def $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vcc
+
+...
+
+---
+name: v_add_co_u32_e32__inline_imm__fi_offset_literal__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 40, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset_literal__kernel
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__inline_imm__fi_offset_literal__kernel
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 12, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 12, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 40, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; GFX7-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX7: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX7-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX7-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX8: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX8-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX8-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX900: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX900-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX900-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX90A: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX90A-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX90A-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $vgpr1, 1, implicit $exec
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, 72, 1, implicit $exec
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX940-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX940: $sgpr4 = S_MOV_B32 72
+ ; GFX940-NEXT: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, killed $sgpr4, 1, implicit $exec
+ ; GFX940-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX11-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX11: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, 72, 1, implicit $exec
+ ; GFX11-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX12-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+ ; GFX12: renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, 72, 1, implicit $exec
+ ; GFX12-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, dead $vcc = V_ADD_CO_U32_e64 12, %stack.1, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX7: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX7-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX7-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX8: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX8-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX8-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX900: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX900-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX90A: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX90A-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX10: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX10-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX940-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX940: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX940-NEXT: {{ $}}
+ ; GFX940-NEXT: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX940-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX940-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; GFX940-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+ ; GFX940-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX940-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX940-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX11-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX11: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX11-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 0, implicit $exec
+ ; GFX11-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX11-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX12-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX12: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; GFX12-NEXT: renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 0, implicit $exec
+ ; GFX12-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX12-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable $vcc = V_ADD_CO_U32_e64 %stack.1, $sgpr8, 0, implicit $exec
+
+ S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX7: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX7-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX8: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX8-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX900: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX900-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX90A: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX90A-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; GFX10: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX10-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_literal_offset__sgpr__scavenge_spill_required
+ ; FLATSCRW64: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.2, addrspace 5)
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.2, addrspace 5)
+ ; FLATSCRW64-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $sgpr8, %stack.1, implicit-def dead $vcc, implicit $exec
+
+ S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8
+
+ ; GFX7-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; GFX7: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX7-NEXT: {{ $}}
+ ; GFX7-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX7-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX7-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX7-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX7-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX7-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX7-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX7-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX8-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; GFX8: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX8-NEXT: {{ $}}
+ ; GFX8-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX8-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX8-NEXT: $vcc_lo = S_MOV_B32 128
+ ; GFX8-NEXT: $vgpr1, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr1, 0, implicit $exec
+ ; GFX8-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX8-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX8-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX900-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; GFX900: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX900-NEXT: {{ $}}
+ ; GFX900-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX900-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX900-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX900-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX900-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX900-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX90A-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; GFX90A: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX90A-NEXT: {{ $}}
+ ; GFX90A-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX90A-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX90A-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX90A-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX90A-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX90A-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; GFX10-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; GFX10: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+ ; GFX10-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; GFX10-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; GFX10-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 132, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+ ; GFX10-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_literal_offset__vgpr__scavenge_spill_required
+ ; FLATSCRW64: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.2, addrspace 5)
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.2, addrspace 5)
+ ; FLATSCRW64-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr8, %stack.1, implicit-def dead $vcc, implicit $exec
+
+ S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUFW64: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr1, killed $vgpr2, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0 = V_ADD_CO_U32_e32 renamable $vgpr1, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_co_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUFW64: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 renamable $vgpr1, %stack.0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_co_u32_e64__kernel__other_vgpr_live_after__fi_offset0
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__kernel__other_vgpr_live_after__fi_offset0
+ ; MUBUFW64: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 0, $vgpr1, 0, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__kernel__other_vgpr_live_after__fi_offset0
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 0, $vgpr1, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0, renamable $sgpr8_sgpr9 = V_ADD_CO_U32_e64 %stack.0, renamable $vgpr1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_co_u32_e32__identity_vgpr__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, %stack.0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0, $vgpr0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__identity_vgpr__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable dead $vcc = V_ADD_CO_U32_e64 $vgpr0, %stack.0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_offset0__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable dead $vcc = V_ADD_CO_U32_e64 %stack.0, $vgpr0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_live_vcc
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_live_vcc
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, $vgpr0, implicit-def $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset0__identity_vgpr__kernel_live_vcc
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 0, $vgpr0, implicit-def $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0, $vgpr0, implicit-def $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vcc
+
+...
+
+---
+name: v_add_co_u32_e32__identity_vgpr__fi_offset32__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+
+---
+name: v_add_co_u32_e32__identity_vgpr__fi_offset72__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, killed $vgpr1, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 $vgpr0, %stack.1, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_offset72__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 72, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 72, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.1, $vgpr0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e32__fi_offset32__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 32, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_CO_U32_e32 32, $vgpr0, implicit-def dead $vcc, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.1, $vgpr0, implicit-def dead $vcc, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__identity_vgpr__fi_offset32__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUFW64-LABEL: name: v_add_co_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; MUBUFW64: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; MUBUFW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_co_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0, dead renamable $vcc = V_ADD_CO_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0, renamable dead $vcc = V_ADD_CO_U32_e64 $vgpr0, %stack.1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir
index 2d62d4238daa..af6823c1ab64 100644
--- a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir
+++ b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir
@@ -467,3 +467,1280 @@ body: |
SI_RETURN implicit $vgpr0
...
+
+---
+name: v_add_u32_e64__vgpr__fi_literal_offset
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset
+ ; MUBUF: liveins: $vgpr8
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUF-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $vgpr1, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset
+ ; MUBUFW32: liveins: $vgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $vgpr1 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
+ ; MUBUFW32-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $vgpr1, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $sgpr4, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset
+ ; FLATSCRW32: liveins: $vgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $sgpr4, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, %stack.1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__vgpr__fi_literal_offset__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset__clamp
+ ; MUBUF: liveins: $vgpr8
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUF-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $vgpr1, 1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset__clamp
+ ; MUBUFW32: liveins: $vgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $vgpr1 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
+ ; MUBUFW32-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $vgpr1, 1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset__clamp
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $sgpr4, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__vgpr__fi_literal_offset__clamp
+ ; FLATSCRW32: liveins: $vgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, killed $sgpr4, 1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 $vgpr8, %stack.1, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__fi_literal_offset__vgpr__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $vgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp
+ ; MUBUF: liveins: $vgpr8
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32, implicit $exec
+ ; MUBUF-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp
+ ; MUBUFW32: liveins: $vgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $vgpr1 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
+ ; MUBUFW32-NEXT: $vgpr1 = V_ADD_U32_e32 128, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $sgpr4, $vgpr8, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp
+ ; FLATSCRW32: liveins: $vgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $sgpr4, $vgpr8, 1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 %stack.1, $vgpr8, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__fi_literal_offset__vgpr__clamp__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+ - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp__kernel
+ ; MUBUF: liveins: $vgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 128, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $vgpr1, $vgpr8, 1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp__kernel
+ ; MUBUFW32: liveins: $vgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 128, $vgpr8, 1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp__kernel
+ ; FLATSCRW64: liveins: $vgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $sgpr4 = S_MOV_B32 128
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 killed $sgpr4, $vgpr8, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__fi_literal_offset__vgpr__clamp__kernel
+ ; FLATSCRW32: liveins: $vgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 128, $vgpr8, 1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 %stack.1, $vgpr8, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__inline_imm__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e32__inline_imm__fi_offset0__kernel
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__inline_imm__fi_offset0__kernel
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__inline_imm__fi_offset0__kernel
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__inline_imm__fi_offset0__kernel
+ ; FLATSCRW32: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 12, %stack.0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__inline_imm__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e64__inline_imm__fi_offset0__kernel
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 0, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__inline_imm__fi_offset0__kernel
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 0, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__inline_imm__fi_offset0__kernel
+ ; FLATSCRW64: renamable $vgpr0 = V_ADD_U32_e64 12, 0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__inline_imm__fi_offset0__kernel
+ ; FLATSCRW32: renamable $vgpr0 = V_ADD_U32_e64 12, 0, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 12, %stack.0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+
+
+---
+name: v_add_u32_e32__inline_imm__fi_literal__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 80, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e32__inline_imm__fi_literal__kernel
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__inline_imm__fi_literal__kernel
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__inline_imm__fi_literal__kernel
+ ; FLATSCRW64: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__inline_imm__fi_literal__kernel
+ ; FLATSCRW32: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 12, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 12, %stack.1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__inline_imm__fi_literal__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 80, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel
+ ; FLATSCRW64: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel
+ ; FLATSCRW32: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 12, %stack.1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__fi_literal__inline_imm__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 80, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e64__fi_literal__inline_imm__kernel
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 32, 12, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__fi_literal__inline_imm__kernel
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 32, 12, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__fi_literal__inline_imm__kernel
+ ; FLATSCRW64: renamable $vgpr0 = V_ADD_U32_e64 32, 12, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__fi_literal__inline_imm__kernel
+ ; FLATSCRW32: renamable $vgpr0 = V_ADD_U32_e64 32, 12, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 %stack.1, 12, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__inline_imm__fi_literal__kernel__clamp
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 80, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUF-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel__clamp
+ ; MUBUF: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel__clamp
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel__clamp
+ ; FLATSCRW64: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__inline_imm__fi_literal__kernel__clamp
+ ; FLATSCRW32: renamable $vgpr0 = V_ADD_U32_e64 12, 32, 1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 12, %stack.1, 1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: killed_reg_regression
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 80, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: killed_reg_regression
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr1 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr2 = V_MOV_B32_e32 15, implicit $exec
+ ; MUBUF-NEXT: SCRATCH_STORE_DWORD killed renamable $vgpr2, killed renamable $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (volatile store (s32), addrspace 5)
+ ; MUBUF-NEXT: renamable $vgpr0 = V_SUB_U32_e32 0, killed $vgpr0, implicit $exec
+ ; MUBUF-NEXT: dead renamable $vgpr0 = SCRATCH_LOAD_DWORD killed renamable $vgpr0, 124, 0, implicit $exec, implicit $flat_scr :: (volatile load (s32), addrspace 5)
+ ; MUBUF-NEXT: S_ENDPGM 0
+ ;
+ ; MUBUFW32-LABEL: name: killed_reg_regression
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr1 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr2 = V_MOV_B32_e32 15, implicit $exec
+ ; MUBUFW32-NEXT: SCRATCH_STORE_DWORD killed renamable $vgpr2, killed renamable $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (volatile store (s32), addrspace 5)
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_SUB_U32_e32 0, killed $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: dead renamable $vgpr0 = SCRATCH_LOAD_DWORD killed renamable $vgpr0, 124, 0, implicit $exec, implicit $flat_scr :: (volatile load (s32), addrspace 5)
+ ; MUBUFW32-NEXT: S_ENDPGM 0
+ ;
+ ; FLATSCRW64-LABEL: name: killed_reg_regression
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr1 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr2 = V_MOV_B32_e32 15, implicit $exec
+ ; FLATSCRW64-NEXT: SCRATCH_STORE_DWORD killed renamable $vgpr2, killed renamable $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (volatile store (s32), addrspace 5)
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_SUB_U32_e32 0, killed $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: dead renamable $vgpr0 = SCRATCH_LOAD_DWORD killed renamable $vgpr0, 124, 0, implicit $exec, implicit $flat_scr :: (volatile load (s32), addrspace 5)
+ ; FLATSCRW64-NEXT: S_ENDPGM 0
+ ;
+ ; FLATSCRW32-LABEL: name: killed_reg_regression
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr1 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr2 = V_MOV_B32_e32 15, implicit $exec
+ ; FLATSCRW32-NEXT: SCRATCH_STORE_DWORD killed renamable $vgpr2, killed renamable $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (volatile store (s32), addrspace 5)
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_SUB_U32_e32 0, killed $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: dead renamable $vgpr0 = SCRATCH_LOAD_DWORD killed renamable $vgpr0, 124, 0, implicit $exec, implicit $flat_scr :: (volatile load (s32), addrspace 5)
+ ; FLATSCRW32-NEXT: S_ENDPGM 0
+ renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+ renamable $vgpr1 = V_ADD_U32_e32 %stack.0, $vgpr0, implicit $exec
+ renamable $vgpr2 = V_MOV_B32_e32 15, implicit $exec
+ SCRATCH_STORE_DWORD killed renamable $vgpr2, killed renamable $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (volatile store (s32), addrspace 5)
+ renamable $vgpr0 = V_SUB_U32_e32 %stack.0, killed $vgpr0, implicit $exec
+ dead renamable $vgpr0 = SCRATCH_LOAD_DWORD killed renamable $vgpr0, 124, 0, implicit $exec, implicit $flat_scr :: (volatile load (s32), addrspace 5)
+ S_ENDPGM 0
+
+...
+
+---
+name: v_add_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUF-LABEL: name: v_add_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUF: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr1, killed $vgpr2, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUFW32: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr1, killed $vgpr2, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr1, killed $vgpr2, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW32: liveins: $vgpr1
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr1, killed $vgpr2, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0 = V_ADD_U32_e32 renamable $vgpr1, %stack.0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_u32_e32__kernel_other_vgpr_live_after__fi_offset0
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUF-LABEL: name: v_add_u32_e32__kernel_other_vgpr_live_after__fi_offset0
+ ; MUBUF: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__kernel_other_vgpr_live_after__fi_offset0
+ ; MUBUFW32: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__kernel_other_vgpr_live_after__fi_offset0
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__kernel_other_vgpr_live_after__fi_offset0
+ ; FLATSCRW32: liveins: $vgpr1
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0 = V_ADD_U32_e32 %stack.0, renamable $vgpr1, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_u32_e32__kernel_fi_offset0__sgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e32__kernel_fi_offset0__sgpr_live_after
+ ; MUBUF: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__kernel_fi_offset0__sgpr_live_after
+ ; MUBUFW32: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__kernel_fi_offset0__sgpr_live_after
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__kernel_fi_offset0__sgpr_live_after
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ renamable $vgpr0 = V_ADD_U32_e32 renamable $sgpr8, %stack.0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $sgpr8
+
+...
+
+---
+name: v_add_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr1
+ ; MUBUF-LABEL: name: v_add_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUF: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; MUBUFW32: liveins: $vgpr1, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW64: liveins: $vgpr1
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__kernel_fi_offset0__other_vgpr_live_after
+ ; FLATSCRW32: liveins: $vgpr1
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr1, 0, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
+ renamable $vgpr0 = V_ADD_U32_e64 renamable $vgpr1, %stack.0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $vgpr1
+
+...
+
+---
+name: v_add_u32_e32__kernel_fi_offset72__sgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 32, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e32__kernel_fi_offset72__sgpr_live_after
+ ; MUBUF: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__kernel_fi_offset72__sgpr_live_after
+ ; MUBUFW32: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__kernel_fi_offset72__sgpr_live_after
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__kernel_fi_offset72__sgpr_live_after
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $sgpr8, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ renamable $vgpr0 = V_ADD_U32_e32 renamable $sgpr8, %stack.1, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $sgpr8
+
+...
+
+---
+name: v_add_u32_e64__kernel_fi_offset72__sgpr_live_after
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 32, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUF-LABEL: name: v_add_u32_e64__kernel_fi_offset72__sgpr_live_after
+ ; MUBUF: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $sgpr8, killed $vgpr1, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__kernel_fi_offset72__sgpr_live_after
+ ; MUBUFW32: liveins: $sgpr8, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $sgpr8, 72, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__kernel_fi_offset72__sgpr_live_after
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $sgpr8, killed $vgpr1, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__kernel_fi_offset72__sgpr_live_after
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $sgpr8, 72, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr8
+ renamable $vgpr0 = V_ADD_U32_e64 renamable $sgpr8, %stack.1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0, implicit $sgpr8
+
+...
+
+---
+name: v_add_u32_e32__identity_vgpr__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, %stack.0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; MUBUF-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 %stack.0, $vgpr0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__identity_vgpr__fi_offset0__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset0__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 0, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, %stack.0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__fi_offset0__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__fi_offset0__identity_vgpr__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 0, $vgpr0, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 %stack.0, $vgpr0, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+ ; MUBUF-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, killed $vgpr0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, killed $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, killed $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__fi_offset0__identity_vgpr__kernel_kill
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 0, killed $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 %stack.0, killed $vgpr0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__identity_vgpr__fi_offset32__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr1 = V_MOV_B32_e32 32, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, %stack.1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+
+---
+name: v_add_u32_e32__identity_vgpr__fi_offset72__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__identity_vgpr__fi_offset72__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: $vgpr1 = V_MOV_B32_e32 72, implicit $exec
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, killed $vgpr1, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 $vgpr0, %stack.1, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__fi_offset72__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 72, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 72, $vgpr0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 72, $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 72, $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__fi_offset72__identity_vgpr__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 72, $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 %stack.1, $vgpr0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e32__fi_offset32__identity_vgpr__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e32 32, $vgpr0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 32, $vgpr0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e32 32, $vgpr0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e32__fi_offset32__identity_vgpr__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e32 32, $vgpr0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e32 %stack.1, $vgpr0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_u32_e64__identity_vgpr__fi_offset32__kernel
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+ - { id: 1, size: 64, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $vgpr0
+
+ ; MUBUF-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; MUBUF: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: {{ $}}
+ ; MUBUF-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUF-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; MUBUF-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; MUBUFW32-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; MUBUFW32: liveins: $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; MUBUFW32-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW64-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW64: liveins: $vgpr0
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $vgpr0
+ ;
+ ; FLATSCRW32-LABEL: name: v_add_u32_e64__identity_vgpr__fi_offset32__kernel
+ ; FLATSCRW32: liveins: $vgpr0
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, 32, 0, implicit $exec
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+ renamable $vgpr0 = V_ADD_U32_e64 $vgpr0, %stack.1, 0, implicit $exec
+ SI_RETURN implicit $vgpr0
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/indirect-call-set-from-other-function.ll b/llvm/test/CodeGen/AMDGPU/indirect-call-set-from-other-function.ll
new file mode 100644
index 000000000000..f419d89a7f0a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/indirect-call-set-from-other-function.ll
@@ -0,0 +1,73 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-attributor %s -o - | FileCheck %s
+
+@g_fn = addrspace(1) global ptr null
+
+;.
+; CHECK: @g_fn = addrspace(1) global ptr null
+;.
+define void @set_fn(ptr %fn) {
+; CHECK-LABEL: define {{[^@]+}}@set_fn
+; CHECK-SAME: (ptr [[FN:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: store ptr [[FN]], ptr addrspace(1) @g_fn, align 8
+; CHECK-NEXT: ret void
+;
+entry:
+ store ptr %fn, ptr addrspace(1) @g_fn
+ ret void
+}
+
+define void @get_fn(ptr %fn) {
+; CHECK-LABEL: define {{[^@]+}}@get_fn
+; CHECK-SAME: (ptr [[FN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[LOAD:%.*]] = load ptr, ptr addrspace(1) @g_fn, align 8
+; CHECK-NEXT: store ptr [[LOAD]], ptr [[FN]], align 8
+; CHECK-NEXT: ret void
+;
+entry:
+ %load = load ptr, ptr addrspace(1) @g_fn
+ store ptr %load, ptr %fn
+ ret void
+}
+
+define void @foo() {
+; CHECK-LABEL: define {{[^@]+}}@foo
+; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[FN:%.*]] = alloca ptr, align 8, addrspace(5)
+; CHECK-NEXT: store ptr null, ptr addrspace(5) [[FN]], align 8
+; CHECK-NEXT: [[FN_CAST:%.*]] = addrspacecast ptr addrspace(5) [[FN]] to ptr
+; CHECK-NEXT: call void @get_fn(ptr [[FN_CAST]])
+; CHECK-NEXT: [[LOAD:%.*]] = load ptr, ptr addrspace(5) [[FN]], align 8
+; CHECK-NEXT: [[TOBOOL:%.*]] = icmp ne ptr [[LOAD]], null
+; CHECK-NEXT: br i1 [[TOBOOL]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
+; CHECK: if.then:
+; CHECK-NEXT: [[LOAD_1:%.*]] = load ptr, ptr addrspace(5) [[FN]], align 8
+; CHECK-NEXT: call void [[LOAD_1]]()
+; CHECK-NEXT: br label [[IF_END]]
+; CHECK: if.end:
+; CHECK-NEXT: ret void
+;
+entry:
+ %fn = alloca ptr, addrspace(5)
+ store ptr null, ptr addrspace(5) %fn
+ %fn.cast = addrspacecast ptr addrspace(5) %fn to ptr
+ call void @get_fn(ptr %fn.cast)
+ %load = load ptr, ptr addrspace(5) %fn
+ %tobool = icmp ne ptr %load, null
+ br i1 %tobool, label %if.then, label %if.end
+
+if.then:
+ %load.1 = load ptr, ptr addrspace(5) %fn
+ call void %load.1()
+ br label %if.end
+
+if.end:
+ ret void
+}
+;.
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="4,10" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-waves-per-eu"="4,10" "uniform-work-group-size"="false" }
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
index 15f23eda241b..ee7f9375bf5d 100644
--- a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
+++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
@@ -43,7 +43,6 @@
; GCN-O0-NEXT: FunctionPass Manager
; GCN-O0-NEXT: Expand Atomic instructions
; GCN-O0-NEXT: Remove unreachable blocks from the CFG
-; GCN-O0-NEXT: Expand vector predication intrinsics
; GCN-O0-NEXT: Instrument function entry/exit with calls to e.g. mcount() (post inlining)
; GCN-O0-NEXT: Scalarize Masked Memory Intrinsics
; GCN-O0-NEXT: Expand reduction intrinsics
@@ -222,7 +221,6 @@
; GCN-O1-NEXT: Constant Hoisting
; GCN-O1-NEXT: Replace intrinsics with calls to vector library
; GCN-O1-NEXT: Partially inline calls to library functions
-; GCN-O1-NEXT: Expand vector predication intrinsics
; GCN-O1-NEXT: Instrument function entry/exit with calls to e.g. mcount() (post inlining)
; GCN-O1-NEXT: Scalarize Masked Memory Intrinsics
; GCN-O1-NEXT: Expand reduction intrinsics
@@ -508,7 +506,6 @@
; GCN-O1-OPTS-NEXT: Constant Hoisting
; GCN-O1-OPTS-NEXT: Replace intrinsics with calls to vector library
; GCN-O1-OPTS-NEXT: Partially inline calls to library functions
-; GCN-O1-OPTS-NEXT: Expand vector predication intrinsics
; GCN-O1-OPTS-NEXT: Instrument function entry/exit with calls to e.g. mcount() (post inlining)
; GCN-O1-OPTS-NEXT: Scalarize Masked Memory Intrinsics
; GCN-O1-OPTS-NEXT: Expand reduction intrinsics
@@ -813,7 +810,6 @@
; GCN-O2-NEXT: Constant Hoisting
; GCN-O2-NEXT: Replace intrinsics with calls to vector library
; GCN-O2-NEXT: Partially inline calls to library functions
-; GCN-O2-NEXT: Expand vector predication intrinsics
; GCN-O2-NEXT: Instrument function entry/exit with calls to e.g. mcount() (post inlining)
; GCN-O2-NEXT: Scalarize Masked Memory Intrinsics
; GCN-O2-NEXT: Expand reduction intrinsics
@@ -1126,7 +1122,6 @@
; GCN-O3-NEXT: Constant Hoisting
; GCN-O3-NEXT: Replace intrinsics with calls to vector library
; GCN-O3-NEXT: Partially inline calls to library functions
-; GCN-O3-NEXT: Expand vector predication intrinsics
; GCN-O3-NEXT: Instrument function entry/exit with calls to e.g. mcount() (post inlining)
; GCN-O3-NEXT: Scalarize Masked Memory Intrinsics
; GCN-O3-NEXT: Expand reduction intrinsics
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll
index 074489b9ff50..d085b3c768a8 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll
@@ -523,14 +523,23 @@ define amdgpu_ps void @s_buffer_load_imm_mergex2(<4 x i32> inreg %desc) {
; GFX67-NEXT: exp mrt0 v0, v1, v0, v0 done vm
; GFX67-NEXT: s_endpgm
;
-; GFX8910-LABEL: s_buffer_load_imm_mergex2:
-; GFX8910: ; %bb.0: ; %main_body
-; GFX8910-NEXT: s_buffer_load_dwordx2 s[0:1], s[0:3], 0x4
-; GFX8910-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8910-NEXT: v_mov_b32_e32 v0, s0
-; GFX8910-NEXT: v_mov_b32_e32 v1, s1
-; GFX8910-NEXT: exp mrt0 v0, v1, v0, v0 done vm
-; GFX8910-NEXT: s_endpgm
+; GFX8-LABEL: s_buffer_load_imm_mergex2:
+; GFX8: ; %bb.0: ; %main_body
+; GFX8-NEXT: s_buffer_load_dwordx2 s[0:1], s[0:3], 0x4
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: v_mov_b32_e32 v0, s0
+; GFX8-NEXT: v_mov_b32_e32 v1, s1
+; GFX8-NEXT: exp mrt0 v0, v1, v0, v0 done vm
+; GFX8-NEXT: s_endpgm
+;
+; GFX910-LABEL: s_buffer_load_imm_mergex2:
+; GFX910: ; %bb.0: ; %main_body
+; GFX910-NEXT: s_buffer_load_dwordx2 s[4:5], s[0:3], 0x4
+; GFX910-NEXT: s_waitcnt lgkmcnt(0)
+; GFX910-NEXT: v_mov_b32_e32 v0, s4
+; GFX910-NEXT: v_mov_b32_e32 v1, s5
+; GFX910-NEXT: exp mrt0 v0, v1, v0, v0 done vm
+; GFX910-NEXT: s_endpgm
;
; GFX11-LABEL: s_buffer_load_imm_mergex2:
; GFX11: ; %bb.0: ; %main_body
@@ -570,16 +579,27 @@ define amdgpu_ps void @s_buffer_load_imm_mergex4(<4 x i32> inreg %desc) {
; GFX67-NEXT: exp mrt0 v0, v1, v2, v3 done vm
; GFX67-NEXT: s_endpgm
;
-; GFX8910-LABEL: s_buffer_load_imm_mergex4:
-; GFX8910: ; %bb.0: ; %main_body
-; GFX8910-NEXT: s_buffer_load_dwordx4 s[0:3], s[0:3], 0x8
-; GFX8910-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8910-NEXT: v_mov_b32_e32 v0, s0
-; GFX8910-NEXT: v_mov_b32_e32 v1, s1
-; GFX8910-NEXT: v_mov_b32_e32 v2, s2
-; GFX8910-NEXT: v_mov_b32_e32 v3, s3
-; GFX8910-NEXT: exp mrt0 v0, v1, v2, v3 done vm
-; GFX8910-NEXT: s_endpgm
+; GFX8-LABEL: s_buffer_load_imm_mergex4:
+; GFX8: ; %bb.0: ; %main_body
+; GFX8-NEXT: s_buffer_load_dwordx4 s[0:3], s[0:3], 0x8
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: v_mov_b32_e32 v0, s0
+; GFX8-NEXT: v_mov_b32_e32 v1, s1
+; GFX8-NEXT: v_mov_b32_e32 v2, s2
+; GFX8-NEXT: v_mov_b32_e32 v3, s3
+; GFX8-NEXT: exp mrt0 v0, v1, v2, v3 done vm
+; GFX8-NEXT: s_endpgm
+;
+; GFX910-LABEL: s_buffer_load_imm_mergex4:
+; GFX910: ; %bb.0: ; %main_body
+; GFX910-NEXT: s_buffer_load_dwordx4 s[4:7], s[0:3], 0x8
+; GFX910-NEXT: s_waitcnt lgkmcnt(0)
+; GFX910-NEXT: v_mov_b32_e32 v0, s4
+; GFX910-NEXT: v_mov_b32_e32 v1, s5
+; GFX910-NEXT: v_mov_b32_e32 v2, s6
+; GFX910-NEXT: v_mov_b32_e32 v3, s7
+; GFX910-NEXT: exp mrt0 v0, v1, v2, v3 done vm
+; GFX910-NEXT: s_endpgm
;
; GFX11-LABEL: s_buffer_load_imm_mergex4:
; GFX11: ; %bb.0: ; %main_body
diff --git a/llvm/test/CodeGen/AMDGPU/merge-sbuffer-load.mir b/llvm/test/CodeGen/AMDGPU/merge-sbuffer-load.mir
index 1b2f672fd57b..02c1a328f482 100644
--- a/llvm/test/CodeGen/AMDGPU/merge-sbuffer-load.mir
+++ b/llvm/test/CodeGen/AMDGPU/merge-sbuffer-load.mir
@@ -1,14 +1,31 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck %s -check-prefixes=CHECK,GFX10
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck %s -check-prefixes=CHECK,GFX12
-# CHECK-LABEL: name: merge_s_buffer_load_x2
-# CHECK: S_BUFFER_LOAD_DWORDX2_IMM %0, 0, 0 :: (dereferenceable invariant load (s64), align 4)
+---
name: merge_s_buffer_load_x2
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x2
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %3:sreg_64_xexec = S_BUFFER_LOAD_DWORDX2_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s64), align 4)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0_xexec = COPY %3.sub0
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed %3.sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x2
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_BUFFER_LOAD_DWORDX2_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s64), align 4)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[S_BUFFER_LOAD_DWORDX2_IMM]].sub0
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX2_IMM]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s32))
@@ -17,15 +34,19 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x1_x2
-# CHECK: S_BUFFER_LOAD_DWORD_IMM %0, 0, 0 :: (dereferenceable invariant load (s32))
-# CHECK: S_BUFFER_LOAD_DWORDX2_IMM %0, 4, 0 :: (dereferenceable invariant load (s64))
name: merge_s_buffer_load_x1_x2
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-LABEL: name: merge_s_buffer_load_x1_x2
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX2_IMM:%[0-9]+]]:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM [[COPY]], 4, 0 :: (dereferenceable invariant load (s64))
+ ; CHECK-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
%2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s64))
@@ -34,16 +55,28 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x2_x1
-# GFX10: S_BUFFER_LOAD_DWORDX2_IMM %0, 0, 0 :: (dereferenceable invariant load (s64))
-# GFX10: S_BUFFER_LOAD_DWORD_IMM %0, 8, 0 :: (dereferenceable invariant load (s32))
-# GFX12: S_BUFFER_LOAD_DWORDX3_IMM %0, 0, 0 :: (dereferenceable invariant load (s96), align 8)
name: merge_s_buffer_load_x2_x1
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x2_x1
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: [[S_BUFFER_LOAD_DWORDX2_IMM:%[0-9]+]]:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s64))
+ ; GFX10-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 8, 0 :: (dereferenceable invariant load (s32))
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x2_x1
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX3_IMM:%[0-9]+]]:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s96), align 8)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_64 = COPY [[S_BUFFER_LOAD_DWORDX3_IMM]].sub0_sub1
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX3_IMM]].sub2
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s64))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s32))
@@ -52,14 +85,37 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x4
-# CHECK: S_BUFFER_LOAD_DWORDX4_IMM %0, 0, 0 :: (dereferenceable invariant load (s128), align 4)
name: merge_s_buffer_load_x4
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x4
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s128), align 4)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_64_xexec = COPY %7.sub0_sub1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_64_xexec = COPY killed %7.sub2_sub3
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY1]].sub0
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY1]].sub1
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY2]].sub0
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY2]].sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x4
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s128), align 4)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_96 = COPY [[S_BUFFER_LOAD_DWORDX4_IMM]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX4_IMM]].sub3
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY1]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY1]].sub2
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s32))
@@ -70,15 +126,19 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x1_x3
-# CHECK: S_BUFFER_LOAD_DWORD_IMM %0, 0, 0 :: (dereferenceable invariant load (s32))
-# CHECK: S_BUFFER_LOAD_DWORDX3_IMM %0, 4, 0 :: (dereferenceable invariant load (s96), align 16)
name: merge_s_buffer_load_x1_x3
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-LABEL: name: merge_s_buffer_load_x1_x3
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX3_IMM:%[0-9]+]]:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM [[COPY]], 4, 0 :: (dereferenceable invariant load (s96), align 16)
+ ; CHECK-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
%2:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s96))
@@ -87,14 +147,20 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x3_x1
-# CHECK: S_BUFFER_LOAD_DWORDX4_IMM %0, 0, 0 :: (dereferenceable invariant load (s128))
name: merge_s_buffer_load_x3_x1
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-LABEL: name: merge_s_buffer_load_x3_x1
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s128))
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_96 = COPY [[S_BUFFER_LOAD_DWORDX4_IMM]].sub0_sub1_sub2
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX4_IMM]].sub3
+ ; CHECK-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s96))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 12, 0 :: (dereferenceable invariant load (s32))
@@ -103,14 +169,53 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x8
-# CHECK: S_BUFFER_LOAD_DWORDX8_IMM %0, 0, 0 :: (dereferenceable invariant load (s256), align 4)
name: merge_s_buffer_load_x8
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %15:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 4)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %15.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %15.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_64_xexec = COPY killed [[COPY1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY4]].sub0
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY4]].sub1
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:sreg_64_xexec = COPY killed [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY9]].sub0
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY9]].sub1
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY10]].sub0
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY10]].sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 4)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_96 = COPY [[COPY1]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY1]].sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec = COPY [[COPY3]].sub0_sub1
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub2
+ ; GFX12-NEXT: [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY5]].sub0
+ ; GFX12-NEXT: [[COPY8:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY5]].sub1
+ ; GFX12-NEXT: [[COPY9:%[0-9]+]]:sgpr_96 = COPY [[COPY2]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY10:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY2]].sub3
+ ; GFX12-NEXT: [[COPY11:%[0-9]+]]:sreg_64_xexec = COPY [[COPY9]].sub0_sub1
+ ; GFX12-NEXT: [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY9]].sub2
+ ; GFX12-NEXT: [[COPY13:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY11]].sub0
+ ; GFX12-NEXT: [[COPY14:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY11]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s32))
@@ -125,14 +230,53 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x8_reordered
-# CHECK: S_BUFFER_LOAD_DWORDX8_IMM %0, 0, 0 :: (dereferenceable invariant load (s256), align 4)
name: merge_s_buffer_load_x8_reordered
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_reordered
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %15:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 4)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %15.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %15.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_64_xexec = COPY killed [[COPY1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub1
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub0
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:sreg_64_xexec = COPY killed [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY7]].sub1
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY7]].sub0
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY4]].sub1
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY4]].sub0
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY8]].sub1
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY8]].sub0
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_reordered
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 4)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_96 = COPY [[COPY1]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY1]].sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec = COPY [[COPY3]].sub0_sub1
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub2
+ ; GFX12-NEXT: [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY5]].sub1
+ ; GFX12-NEXT: [[COPY8:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY5]].sub0
+ ; GFX12-NEXT: [[COPY9:%[0-9]+]]:sgpr_96 = COPY [[COPY2]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY10:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY2]].sub3
+ ; GFX12-NEXT: [[COPY11:%[0-9]+]]:sreg_64_xexec = COPY [[COPY9]].sub0_sub1
+ ; GFX12-NEXT: [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY9]].sub2
+ ; GFX12-NEXT: [[COPY13:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY11]].sub1
+ ; GFX12-NEXT: [[COPY14:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY11]].sub0
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 20, 0 :: (dereferenceable invariant load (s32))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s32))
@@ -147,14 +291,37 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x8_out_of_x2
-# CHECK: S_BUFFER_LOAD_DWORDX8_IMM %0, 0, 0 :: (dereferenceable invariant load (s256), align 8)
name: merge_s_buffer_load_x8_out_of_x2
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x2
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %7.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %7.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x2
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s64))
%2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s64))
@@ -165,14 +332,29 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x8_out_of_x4
-# CHECK: S_BUFFER_LOAD_DWORDX8_IMM %0, 0, 0 :: (dereferenceable invariant load (s256), align 16)
name: merge_s_buffer_load_x8_out_of_x4
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x4
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %3:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %3.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %3.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x4
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
%2:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s128))
@@ -181,14 +363,37 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_x8_mixed
-# CHECK: S_BUFFER_LOAD_DWORDX8_IMM %0, 0, 0 :: (dereferenceable invariant load (s256), align 16)
name: merge_s_buffer_load_x8_mixed
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_mixed
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %7.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %7.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_mixed
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub2_sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s32))
@@ -199,14 +404,39 @@ body: |
...
---
-# CHECK-LABEL: name: merge_s_buffer_load_sgpr_imm
-# CHECK: S_BUFFER_LOAD_DWORDX4_SGPR_IMM %0, %1, 0, 0 :: (dereferenceable invariant load (s128), align 4)
name: merge_s_buffer_load_sgpr_imm
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; GFX10-LABEL: name: merge_s_buffer_load_sgpr_imm
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GFX10-NEXT: early-clobber %8:sgpr_128 = S_BUFFER_LOAD_DWORDX4_SGPR_IMM_ec [[COPY]], [[COPY1]], 0, 0 :: (dereferenceable invariant load (s128), align 4)
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_64_xexec = COPY %8.sub0_sub1
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY killed %8.sub2_sub3
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY2]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY2]].sub1
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_sgpr_imm
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_SGPR_IMM [[COPY]], [[COPY1]], 0, 0 :: (dereferenceable invariant load (s128), align 4)
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_96 = COPY [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub0_sub1_sub2
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub3
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY2]].sub2
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY4]].sub0
+ ; GFX12-NEXT: [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY4]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32 = COPY $sgpr4
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM %0:sgpr_128, %1:sreg_32, 0, 0 :: (dereferenceable invariant load (s32))
@@ -218,15 +448,21 @@ body: |
...
---
-# CHECK-LABEL: name: no_merge_for_different_soffsets
-# CHECK: S_BUFFER_LOAD_DWORD_SGPR_IMM %0, %1, 4, 0 :: (dereferenceable invariant load (s32))
-# CHECK: S_BUFFER_LOAD_DWORD_SGPR_IMM %0, %2, 8, 0 :: (dereferenceable invariant load (s32))
name: no_merge_for_different_soffsets
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, $sgpr5
+ ; CHECK-LABEL: name: no_merge_for_different_soffsets
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, $sgpr5
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr5
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_SGPR_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM [[COPY]], [[COPY1]], 4, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_SGPR_IMM1:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM [[COPY]], [[COPY2]], 8, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32 = COPY $sgpr4
%2:sreg_32 = COPY $sgpr5
@@ -237,15 +473,20 @@ body: |
...
---
-# CHECK-LABEL: name: no_merge_for_non_adjacent_offsets
-# CHECK: S_BUFFER_LOAD_DWORD_SGPR_IMM %0, %1, 4, 0 :: (dereferenceable invariant load (s32))
-# CHECK: S_BUFFER_LOAD_DWORD_SGPR_IMM %0, %1, 12, 0 :: (dereferenceable invariant load (s32))
name: no_merge_for_non_adjacent_offsets
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; CHECK-LABEL: name: no_merge_for_non_adjacent_offsets
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_SGPR_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM [[COPY]], [[COPY1]], 4, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_SGPR_IMM1:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM [[COPY]], [[COPY1]], 12, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: S_ENDPGM 0
%0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
%1:sreg_32 = COPY $sgpr4
%2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_SGPR_IMM %0:sgpr_128, %1:sreg_32, 4, 0 :: (dereferenceable invariant load (s32))
@@ -253,4 +494,420 @@ body: |
S_ENDPGM 0
...
+
+# The constrained multi-dword buffer load merge tests.
+
+---
+name: merge_s_buffer_load_x1_x2ec
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_x1_x2ec
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: early-clobber %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec [[COPY]], 4, 0 :: (dereferenceable invariant load (s64))
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
+ early-clobber %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x2ec_x1
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x2ec_x1
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s64))
+ ; GFX10-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 8, 0 :: (dereferenceable invariant load (s32))
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x2ec_x1
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX3_IMM:%[0-9]+]]:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s96), align 8)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_64 = COPY [[S_BUFFER_LOAD_DWORDX3_IMM]].sub0_sub1
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX3_IMM]].sub2
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s64))
+ %2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s32))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x1_x3ec
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_x1_x3ec
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s32))
+ ; CHECK-NEXT: early-clobber %2:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM_ec [[COPY]], 4, 0 :: (dereferenceable invariant load (s96), align 16)
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s32))
+ early-clobber %2:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM_ec %0:sgpr_128, 4, 0 :: (dereferenceable invariant load (s96))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x3ec_x1
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_x3ec_x1
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s128))
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_96 = COPY [[S_BUFFER_LOAD_DWORDX4_IMM]].sub0_sub1_sub2
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[S_BUFFER_LOAD_DWORDX4_IMM]].sub3
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_96 = S_BUFFER_LOAD_DWORDX3_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s96))
+ %2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 12, 0 :: (dereferenceable invariant load (s32))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x8_out_of_x2ec_reordered
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x2ec_reordered
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %7.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %7.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x2ec_reordered
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s64))
+ early-clobber %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s64))
+ early-clobber %3:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s64))
+ early-clobber %4:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 24, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
---
+
+name: merge_s_buffer_load_x8_out_of_x2ec_x2
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x2ec_x2
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %7.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %7.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x2ec_x2
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 8)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY [[COPY1]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY1]].sub2_sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY [[COPY2]].sub2_sub3
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s64))
+ early-clobber %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s64))
+ %3:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s64))
+ %4:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 24, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x8_out_of_x4ec
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x4ec
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %3:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %3.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %3.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x4ec
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
+ early-clobber %2:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s128))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x8_out_of_x4ec_x4
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x4ec_x4
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %3:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %3.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %3.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x4ec_x4
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
+ %2:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s128))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x8_out_of_x4_x4ec
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_out_of_x4_x4ec
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %3:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %3.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %3.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_out_of_x4_x4ec
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
+ early-clobber %2:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s128))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x8_mixed_including_ec_opcodes
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_x8_mixed_including_ec_opcodes
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: early-clobber %7:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM_ec [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY %7.sub0_sub1_sub2_sub3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed %7.sub4_sub5_sub6_sub7
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub2_sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_x8_mixed_including_ec_opcodes
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256), align 16)
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY [[COPY2]].sub0_sub1
+ ; GFX12-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY killed [[COPY2]].sub2_sub3
+ ; GFX12-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec = COPY [[COPY3]].sub0
+ ; GFX12-NEXT: [[COPY6:%[0-9]+]]:sreg_32_xm0_xexec = COPY killed [[COPY3]].sub1
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ early-clobber %1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM_ec %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128))
+ %2:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s32))
+ early-clobber %3:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM_ec %0:sgpr_128, 24, 0 :: (dereferenceable invariant load (s64))
+ %4:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %0:sgpr_128, 20, 0 :: (dereferenceable invariant load (s32))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_sgpr_imm_x2ec_x2ec
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+
+ ; GFX10-LABEL: name: merge_s_buffer_load_sgpr_imm_x2ec_x2ec
+ ; GFX10: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GFX10-NEXT: early-clobber %4:sgpr_128 = S_BUFFER_LOAD_DWORDX4_SGPR_IMM_ec [[COPY]], [[COPY1]], 0, 0 :: (dereferenceable invariant load (s128), align 8)
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_64 = COPY %4.sub0_sub1
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY killed %4.sub2_sub3
+ ; GFX10-NEXT: S_ENDPGM 0
+ ;
+ ; GFX12-LABEL: name: merge_s_buffer_load_sgpr_imm_x2ec_x2ec
+ ; GFX12: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; GFX12-NEXT: {{ $}}
+ ; GFX12-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GFX12-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GFX12-NEXT: [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_SGPR_IMM [[COPY]], [[COPY1]], 0, 0 :: (dereferenceable invariant load (s128), align 8)
+ ; GFX12-NEXT: [[COPY2:%[0-9]+]]:sgpr_64 = COPY [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub0_sub1
+ ; GFX12-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY killed [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub2_sub3
+ ; GFX12-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sreg_32 = COPY $sgpr4
+ early-clobber %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_SGPR_IMM_ec %0:sgpr_128, %1:sreg_32, 0, 0 :: (dereferenceable invariant load (s64))
+ early-clobber %3:sgpr_64 = S_BUFFER_LOAD_DWORDX2_SGPR_IMM_ec %0:sgpr_128, %1:sreg_32, 8, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
+
+# No constrained opcode required when the MEM operand has met the required alignment.
+
+---
+
+name: merge_s_buffer_load_x2_x2_no_constrained_opc_needed
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_x2_x2_no_constrained_opc_needed
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s128))
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_64 = COPY [[S_BUFFER_LOAD_DWORDX4_IMM]].sub0_sub1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_64 = COPY killed [[S_BUFFER_LOAD_DWORDX4_IMM]].sub2_sub3
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s64), align 16)
+ %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_IMM %0:sgpr_128, 8, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_x4_x4_no_constrained_opc_needed
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_x4_x4_no_constrained_opc_needed
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX8_IMM:%[0-9]+]]:sgpr_256 = S_BUFFER_LOAD_DWORDX8_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s256))
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_128 = COPY [[S_BUFFER_LOAD_DWORDX8_IMM]].sub0_sub1_sub2_sub3
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_128 = COPY killed [[S_BUFFER_LOAD_DWORDX8_IMM]].sub4_sub5_sub6_sub7
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 0, 0 :: (dereferenceable invariant load (s128), align 32)
+ %2:sgpr_128 = S_BUFFER_LOAD_DWORDX4_IMM %0:sgpr_128, 16, 0 :: (dereferenceable invariant load (s128))
+
+ S_ENDPGM 0
+...
+---
+
+name: merge_s_buffer_load_sgpr_imm_x2ec_x2ec_no_constrained_opc_needed
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+
+ ; CHECK-LABEL: name: merge_s_buffer_load_sgpr_imm_x2ec_x2ec_no_constrained_opc_needed
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; CHECK-NEXT: [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM:%[0-9]+]]:sgpr_128 = S_BUFFER_LOAD_DWORDX4_SGPR_IMM [[COPY]], [[COPY1]], 0, 0 :: (dereferenceable invariant load (s128))
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_64 = COPY [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub0_sub1
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY killed [[S_BUFFER_LOAD_DWORDX4_SGPR_IMM]].sub2_sub3
+ ; CHECK-NEXT: S_ENDPGM 0
+ %0:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ %1:sreg_32 = COPY $sgpr4
+ %2:sgpr_64 = S_BUFFER_LOAD_DWORDX2_SGPR_IMM %0:sgpr_128, %1:sreg_32, 0, 0 :: (dereferenceable invariant load (s64), align 16)
+ %3:sgpr_64 = S_BUFFER_LOAD_DWORDX2_SGPR_IMM %0:sgpr_128, %1:sreg_32, 8, 0 :: (dereferenceable invariant load (s64))
+
+ S_ENDPGM 0
+...
diff --git a/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll b/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll
index e86ee1adef3d..3a6b0485d241 100644
--- a/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll
+++ b/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll
@@ -34,9 +34,8 @@ define amdgpu_kernel void @test_simple_indirect_call() {
; ATTRIBUTOR_GCN-LABEL: define {{[^@]+}}@test_simple_indirect_call
; ATTRIBUTOR_GCN-SAME: () #[[ATTR1:[0-9]+]] {
; ATTRIBUTOR_GCN-NEXT: [[FPTR:%.*]] = alloca ptr, align 8, addrspace(5)
-; ATTRIBUTOR_GCN-NEXT: [[FPTR_CAST:%.*]] = addrspacecast ptr addrspace(5) [[FPTR]] to ptr
-; ATTRIBUTOR_GCN-NEXT: store ptr @indirect, ptr [[FPTR_CAST]], align 8
-; ATTRIBUTOR_GCN-NEXT: [[FP:%.*]] = load ptr, ptr [[FPTR_CAST]], align 8
+; ATTRIBUTOR_GCN-NEXT: store ptr @indirect, ptr addrspace(5) [[FPTR]], align 8
+; ATTRIBUTOR_GCN-NEXT: [[FP:%.*]] = load ptr, ptr addrspace(5) [[FPTR]], align 8
; ATTRIBUTOR_GCN-NEXT: call void [[FP]]()
; ATTRIBUTOR_GCN-NEXT: ret void
;
@@ -75,12 +74,16 @@ define amdgpu_kernel void @test_simple_indirect_call() {
ret void
}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"amdhsa_code_object_version", i32 500}
;.
; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-stack-objects" }
;.
; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="4,10" "uniform-work-group-size"="false" }
; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "uniform-work-group-size"="false" }
;.
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdhsa_code_object_version", i32 500}
+; AKF_GCN: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 500}
+;.
+; ATTRIBUTOR_GCN: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 500}
+;.