Merge branch 'main' into users/mingmingl-llvm/samplefdo-profile-formatusers/mingmingl-llvm/samplefdo-profile-format

1 files changed, 146 insertions, 76 deletions

diff --git a/llvm/test/CodeGen/LoongArch/lsx/fpowi.ll b/llvm/test/CodeGen/LoongArch/lsx/fpowi.ll
index 735dad453660..8005318f4f62 100644
--- a/llvm/test/CodeGen/LoongArch/lsx/fpowi.ll
+++ b/llvm/test/CodeGen/LoongArch/lsx/fpowi.ll
@@ -1,57 +1,102 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s
+; RUN: llc --mtriple=loongarch32 -mattr=+32s,+lsx < %s | FileCheck %s --check-prefix=LA32
+; RUN: llc --mtriple=loongarch64 -mattr=+lsx < %s | FileCheck %s --check-prefix=LA64
 
 declare <4 x float> @llvm.powi.v4f32.i32(<4 x float>, i32)
 
 define <4 x float> @powi_v4f32(<4 x float> %va, i32 %b) nounwind {
-; CHECK-LABEL: powi_v4f32:
-; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    addi.d $sp, $sp, -48
-; CHECK-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
-; CHECK-NEXT:    st.d $fp, $sp, 32 # 8-byte Folded Spill
-; CHECK-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
-; CHECK-NEXT:    addi.w $fp, $a0, 0
-; CHECK-NEXT:    vreplvei.w $vr0, $vr0, 1
-; CHECK-NEXT:    # kill: def $f0 killed $f0 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powisf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0 killed $f0 def $vr0
-; CHECK-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
-; CHECK-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
-; CHECK-NEXT:    vreplvei.w $vr0, $vr0, 0
-; CHECK-NEXT:    # kill: def $f0 killed $f0 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powisf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0 killed $f0 def $vr0
-; CHECK-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
-; CHECK-NEXT:    vextrins.w $vr0, $vr1, 16
-; CHECK-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
-; CHECK-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
-; CHECK-NEXT:    vreplvei.w $vr0, $vr0, 2
-; CHECK-NEXT:    # kill: def $f0 killed $f0 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powisf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0 killed $f0 def $vr0
-; CHECK-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
-; CHECK-NEXT:    vextrins.w $vr1, $vr0, 32
-; CHECK-NEXT:    vst $vr1, $sp, 0 # 16-byte Folded Spill
-; CHECK-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
-; CHECK-NEXT:    vreplvei.w $vr0, $vr0, 3
-; CHECK-NEXT:    # kill: def $f0 killed $f0 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powisf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0 killed $f0 def $vr0
-; CHECK-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
-; CHECK-NEXT:    vextrins.w $vr1, $vr0, 48
-; CHECK-NEXT:    vori.b $vr0, $vr1, 0
-; CHECK-NEXT:    ld.d $fp, $sp, 32 # 8-byte Folded Reload
-; CHECK-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
-; CHECK-NEXT:    addi.d $sp, $sp, 48
-; CHECK-NEXT:    ret
+; LA32-LABEL: powi_v4f32:
+; LA32:       # %bb.0: # %entry
+; LA32-NEXT:    addi.w $sp, $sp, -48
+; LA32-NEXT:    st.w $ra, $sp, 44 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 40 # 4-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    bl __powisf2
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    move $a0, $fp
+; LA32-NEXT:    bl __powisf2
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 2
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    move $a0, $fp
+; LA32-NEXT:    bl __powisf2
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA32-NEXT:    vst $vr1, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 3
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    move $a0, $fp
+; LA32-NEXT:    bl __powisf2
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA32-NEXT:    vori.b $vr0, $vr1, 0
+; LA32-NEXT:    ld.w $fp, $sp, 40 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 44 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 48
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: powi_v4f32:
+; LA64:       # %bb.0: # %entry
+; LA64-NEXT:    addi.d $sp, $sp, -48
+; LA64-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 32 # 8-byte Folded Spill
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    addi.w $fp, $a0, 0
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powisf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powisf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 2
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powisf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA64-NEXT:    vst $vr1, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 3
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powisf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA64-NEXT:    vori.b $vr0, $vr1, 0
+; LA64-NEXT:    ld.d $fp, $sp, 32 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 48
+; LA64-NEXT:    ret
 entry:
   %res = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> %va, i32 %b)
   ret <4 x float> %res
@@ -60,33 +105,58 @@ entry:
 declare <2 x double> @llvm.powi.v2f64.i32(<2 x double>, i32)
 
 define <2 x double> @powi_v2f64(<2 x double> %va, i32 %b) nounwind {
-; CHECK-LABEL: powi_v2f64:
-; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    addi.d $sp, $sp, -48
-; CHECK-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
-; CHECK-NEXT:    st.d $fp, $sp, 32 # 8-byte Folded Spill
-; CHECK-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
-; CHECK-NEXT:    addi.w $fp, $a0, 0
-; CHECK-NEXT:    vreplvei.d $vr0, $vr0, 1
-; CHECK-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powidf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
-; CHECK-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
-; CHECK-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
-; CHECK-NEXT:    vreplvei.d $vr0, $vr0, 0
-; CHECK-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
-; CHECK-NEXT:    move $a0, $fp
-; CHECK-NEXT:    pcaddu18i $ra, %call36(__powidf2)
-; CHECK-NEXT:    jirl $ra, $ra, 0
-; CHECK-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
-; CHECK-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
-; CHECK-NEXT:    vextrins.d $vr0, $vr1, 16
-; CHECK-NEXT:    ld.d $fp, $sp, 32 # 8-byte Folded Reload
-; CHECK-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
-; CHECK-NEXT:    addi.d $sp, $sp, 48
-; CHECK-NEXT:    ret
+; LA32-LABEL: powi_v2f64:
+; LA32:       # %bb.0: # %entry
+; LA32-NEXT:    addi.w $sp, $sp, -48
+; LA32-NEXT:    st.w $ra, $sp, 44 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 40 # 4-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vreplvei.d $vr0, $vr0, 1
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA32-NEXT:    bl __powidf2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.d $vr0, $vr0, 0
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA32-NEXT:    move $a0, $fp
+; LA32-NEXT:    bl __powidf2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA32-NEXT:    ld.w $fp, $sp, 40 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 44 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 48
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: powi_v2f64:
+; LA64:       # %bb.0: # %entry
+; LA64-NEXT:    addi.d $sp, $sp, -48
+; LA64-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 32 # 8-byte Folded Spill
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    addi.w $fp, $a0, 0
+; LA64-NEXT:    vreplvei.d $vr0, $vr0, 1
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powidf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.d $vr0, $vr0, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(__powidf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA64-NEXT:    ld.d $fp, $sp, 32 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 48
+; LA64-NEXT:    ret
 entry:
   %res = call <2 x double> @llvm.powi.v2f64.i32(<2 x double> %va, i32 %b)
   ret <2 x double> %res