10 files changed, 144 insertions, 44 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx90a.mir b/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx90a.mir
index 8be7308c8a6e..3feccff715bc 100644
--- a/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx90a.mir
+++ b/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx90a.mir
@@ -746,7 +746,7 @@ name:            smfma4x4_write_vgpr_dot_write
 body:             |
   bb.0:
     $vgpr0_vgpr1_vgpr2_vgpr3 = V_MFMA_F32_4X4X1F32_vgprcd_e64 $vgpr1, $vgpr0, $vgpr0_vgpr1_vgpr2_vgpr3, 0, 0, 0, implicit $mode, implicit $exec
-    $vgpr1 = V_DOT8_I32_I4 0, $vgpr4, 0, $vgpr4, 0, $vgpr4, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr1 = V_DOT8_I32_I4 0, $vgpr4, 0, $vgpr4, 0, $vgpr4, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: smfma4x4_read_srcc_vgpr_valu_write
 # GCN:      V_MFMA
@@ -945,7 +945,7 @@ name:            dot_write_vgpr_different_dot_read_srcc
 body:             |
   bb.0:
     $vgpr4 = V_DOT4C_I32_I8_e32 $vgpr0, $vgpr1, $vgpr4, implicit $exec
-    $vgpr1 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr4, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr1 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr4, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: dot_write_vgpr_different_dot_write
 # GCN:      V_DOT
@@ -955,7 +955,7 @@ name:            dot_write_vgpr_different_dot_write
 body:             |
   bb.0:
     $vgpr4 = V_DOT4C_I32_I8_e32 $vgpr0, $vgpr1, $vgpr4, implicit $exec
-    $vgpr4 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr0, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr4 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr0, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: dot_write_vgpr_different_valu_read
 # GCN:      V_DOT
diff --git a/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir b/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir
index d59bcfb16eec..52891989b88f 100644
--- a/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir
+++ b/llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir
@@ -1071,7 +1071,7 @@ name:            xdl_smfma4x4_write_vgpr_dot_write
 body:             |
   bb.0:
     $vgpr0_vgpr1_vgpr2_vgpr3 = V_MFMA_I32_4X4X4I8_vgprcd_e64 $vgpr1, $vgpr0, $vgpr0_vgpr1_vgpr2_vgpr3, 0, 0, 0, implicit $mode, implicit $exec
-    $vgpr1 = V_DOT8_I32_I4 0, $vgpr4, 0, $vgpr4, 0, $vgpr4, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr1 = V_DOT8_I32_I4 0, $vgpr4, 0, $vgpr4, 0, $vgpr4, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: nonxdl_smfma4x4_read_srcc_vgpr_valu_write
 # GCN:      V_MFMA
@@ -1265,7 +1265,7 @@ name:            dot_write_vgpr_different_dot_read_srcc
 body:             |
   bb.0:
     $vgpr4 = V_DOT4C_I32_I8_e32 $vgpr0, $vgpr1, $vgpr4, implicit $exec
-    $vgpr1 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr4, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr1 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr4, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: dot_write_vgpr_different_dot_write
 # GCN:      V_DOT
@@ -1275,7 +1275,7 @@ name:            dot_write_vgpr_different_dot_write
 body:             |
   bb.0:
     $vgpr4 = V_DOT4C_I32_I8_e32 $vgpr0, $vgpr1, $vgpr4, implicit $exec
-    $vgpr4 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr0, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr4 = V_DOT8_I32_I4 0, $vgpr0, 0, $vgpr0, 0, $vgpr0, 0, 0, 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: dot_write_vgpr_different_valu_read
 # GCN:      V_DOT
diff --git a/llvm/test/CodeGen/DirectX/CreateHandle.ll b/llvm/test/CodeGen/DirectX/CreateHandle.ll
index 234d4e035bf1..c9969c9c7ffd 100644
--- a/llvm/test/CodeGen/DirectX/CreateHandle.ll
+++ b/llvm/test/CodeGen/DirectX/CreateHandle.ll
@@ -1,4 +1,4 @@
-; RUN: opt -S -passes=dxil-op-lower,dxil-translate-metadata %s | FileCheck %s
+; RUN: opt -S -passes=dxil-translate-metadata,dxil-op-lower %s | FileCheck %s
 ; RUN: opt -S -passes=dxil-pretty-printer %s 2>&1 >/dev/null | FileCheck --check-prefix=CHECK-PRETTY %s
 
 ; CHECK-PRETTY:       Type  Format         Dim      ID      HLSL Bind     Count
diff --git a/llvm/test/CodeGen/DirectX/CreateHandleFromBinding.ll b/llvm/test/CodeGen/DirectX/CreateHandleFromBinding.ll
index aa143dfa8211..425084e2a65a 100644
--- a/llvm/test/CodeGen/DirectX/CreateHandleFromBinding.ll
+++ b/llvm/test/CodeGen/DirectX/CreateHandleFromBinding.ll
@@ -1,4 +1,4 @@
-; RUN: opt -S -passes=dxil-op-lower,dxil-translate-metadata %s | FileCheck %s
+; RUN: opt -S -passes=dxil-translate-metadata,dxil-op-lower %s | FileCheck %s
 ; RUN: opt -S -passes=dxil-pretty-printer %s 2>&1 >/dev/null | FileCheck --check-prefix=CHECK-PRETTY %s
 
 ; CHECK-PRETTY:       Type  Format         Dim      ID      HLSL Bind     Count
diff --git a/llvm/test/CodeGen/DirectX/ShaderFlags/typed-uav-load-additional-formats.ll b/llvm/test/CodeGen/DirectX/ShaderFlags/typed-uav-load-additional-formats.ll
new file mode 100644
index 000000000000..b6947393c453
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/ShaderFlags/typed-uav-load-additional-formats.ll
@@ -0,0 +1,44 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+; RUN: llc %s --filetype=obj -o - | obj2yaml | FileCheck %s --check-prefix=CHECK-OBJ
+
+target triple = "dxil-pc-shadermodel6.7-library"
+
+; CHECK-OBJ: - Name: SFI0
+; CHECK-OBJ:   Flags:
+; CHECK-OBJ:     TypedUAVLoadAdditionalFormats: true
+
+; CHECK:      Combined Shader Flags for Module
+; CHECK-NEXT: Shader Flags Value: 0x00002000
+
+; CHECK: Note: shader requires additional functionality:
+; CHECK:       Typed UAV Load Additional Formats
+
+; CHECK: Function multicomponent : 0x00002000
+define <4 x float> @multicomponent() #0 {
+  %res = call target("dx.TypedBuffer", <4 x float>, 1, 0, 0)
+      @llvm.dx.handle.fromBinding(i32 0, i32 0, i32 1, i32 0, i1 false)
+  %val = call <4 x float> @llvm.dx.typedBufferLoad(
+      target("dx.TypedBuffer", <4 x float>, 1, 0, 0) %res, i32 0)
+  ret <4 x float> %val
+}
+
+; CHECK: Function onecomponent : 0x00000000
+define float @onecomponent() #0 {
+  %res = call target("dx.TypedBuffer", float, 1, 0, 0)
+      @llvm.dx.handle.fromBinding(i32 0, i32 0, i32 1, i32 0, i1 false)
+  %val = call float @llvm.dx.typedBufferLoad(
+      target("dx.TypedBuffer", float, 1, 0, 0) %res, i32 0)
+  ret float %val
+}
+
+; CHECK: Function noload : 0x00000000
+define void @noload(<4 x float> %val) #0 {
+  %res = call target("dx.TypedBuffer", <4 x float>, 1, 0, 0)
+      @llvm.dx.handle.fromBinding(i32 0, i32 0, i32 1, i32 0, i1 false)
+  call void @llvm.dx.typedBufferStore(
+      target("dx.TypedBuffer", <4 x float>, 1, 0, 0) %res, i32 0,
+      <4 x float> %val)
+  ret void
+}
+
+attributes #0 = { convergent norecurse nounwind "hlsl.export"}
diff --git a/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
new file mode 100644
index 000000000000..3ae5832ce832
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
@@ -0,0 +1,23 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -passes='dxil-flatten-arrays,dxil-op-lower' -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s
+
+
+@ZerroInitArr = internal constant [2 x [3 x float]] [[3 x float] zeroinitializer, [3 x float] [float 1.000000e+00, float 1.000000e+00, float 1.000000e+00]], align 16
+
+
+define internal void @main() {
+; CHECK-LABEL: define internal void @main() {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 1
+; CHECK-NEXT:    [[DOTI0:%.*]] = load float, ptr [[TMP0]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 2
+; CHECK-NEXT:    [[DOTI03:%.*]] = load float, ptr [[TMP1]], align 16
+; CHECK-NEXT:    ret void
+;
+entry:
+  %0 = getelementptr [8 x [3 x float]], ptr @ZerroInitArr, i32 0, i32 1
+  %.i0 = load float, ptr %0, align 16
+  %1 = getelementptr [8 x [3 x float]], ptr @ZerroInitArr, i32 0, i32 2
+  %.i03 = load float, ptr %1, align 16
+  ret void
+}
diff --git a/llvm/test/CodeGen/DirectX/llc-pipeline.ll b/llvm/test/CodeGen/DirectX/llc-pipeline.ll
index b3f16097f413..b07155724941 100644
--- a/llvm/test/CodeGen/DirectX/llc-pipeline.ll
+++ b/llvm/test/CodeGen/DirectX/llc-pipeline.ll
@@ -1,5 +1,5 @@
-; RUN: llc -mtriple=dxil-pc-shadermodel6.3-library -debug-pass=Structure < %s -o /dev/null 2>&1 | \
-; RUN:     grep -v "Verify generated machine code" | FileCheck %s
+; RUN: llc -filetype=asm -mtriple=dxil-pc-shadermodel6.3-library -debug-pass=Structure < %s -o /dev/null 2>&1 | grep -v "Verify generated machine code" | FileCheck %s --check-prefixes=CHECK,CHECK-ASM
+; RUN: llc -filetype=obj -mtriple=dxil-pc-shadermodel6.3-library -debug-pass=Structure < %s -o /dev/null 2>&1 | grep -v "Verify generated machine code" | FileCheck %s --check-prefixes=CHECK,CHECK-OBJ
 
 ; REQUIRES: asserts
 
@@ -7,6 +7,11 @@
 ; CHECK-NEXT: Target Library Information
 ; CHECK-NEXT: DXIL Resource Type Analysis
 ; CHECK-NEXT: Target Transform Information
+
+; CHECK-OBJ-NEXT: Machine Module Information
+; CHECK-OBJ-NEXT: Machine Branch Probability Analysis
+; CHECK-OBJ-NEXT: Create Garbage Collector Module Metadata
+
 ; CHECK-NEXT: ModulePass Manager
 ; CHECK-NEXT:   DXIL Finalize Linkage
 ; CHECK-NEXT:   DXIL Intrinsic Expansion
@@ -17,11 +22,19 @@
 ; CHECK-NEXT:     Dominator Tree Construction
 ; CHECK-NEXT:     Scalarize vector operations
 ; CHECK-NEXT:   DXIL Resource Binding Analysis
-; CHECK-NEXT:   DXIL Op Lowering
 ; CHECK-NEXT:   DXIL resource Information
 ; CHECK-NEXT:   DXIL Shader Flag Analysis
 ; CHECK-NEXT:   DXIL Module Metadata analysis
 ; CHECK-NEXT:   DXIL Translate Metadata
+; CHECK-NEXT:   DXIL Op Lowering
 ; CHECK-NEXT:   DXIL Prepare Module
-; CHECK-NEXT:   DXIL Metadata Pretty Printer
-; CHECK-NEXT:   Print Module IR
+
+; CHECK-ASM-NEXT: DXIL Metadata Pretty Printer
+; CHECK-ASM-NEXT: Print Module IR
+
+; CHECK-OBJ-NEXT: DXIL Embedder
+; CHECK-OBJ-NEXT: DXContainer Global Emitter
+; CHECK-OBJ-NEXT: FunctionPass Manager
+; CHECK-OBJ-NEXT:   Lazy Machine Block Frequency Analysis
+; CHECK-OBJ-NEXT:   Machine Optimization Remark Emitter
+; CHECK-OBJ-NEXT:   DXIL Assembly Printer
diff --git a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
index 597252038365..4e522c6ef5da 100644
--- a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
+++ b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
@@ -21,7 +21,6 @@
 ; CHECK-NOT: @groushared2dArrayofVectors
 ; CHECK-NOT: @groushared2dArrayofVectors.scalarized
 
-
 define <4 x i32> @load_array_vec_test() #0 {
 ; CHECK-LABEL: define <4 x i32> @load_array_vec_test(
 ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
@@ -33,18 +32,13 @@ define <4 x i32> @load_array_vec_test() #0 {
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(3) [[TMP5]], align 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = bitcast ptr addrspace(3) @arrayofVecData.scalarized.1dim to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr [2 x [3 x float]], ptr addrspace(3) [[TMP9]], i32 0, i32 1
-; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(3) [[TMP11]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI12:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP13]], i32 1
+; CHECK-NEXT:    [[DOTI12:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI13:%.*]] = load i32, ptr addrspace(3) [[DOTI12]], align 4
-; CHECK-NEXT:    [[TMP14:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI24:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP14]], i32 2
+; CHECK-NEXT:    [[DOTI24:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 2) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI25:%.*]] = load i32, ptr addrspace(3) [[DOTI24]], align 4
-; CHECK-NEXT:    [[TMP15:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI36:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP15]], i32 3
+; CHECK-NEXT:    [[DOTI36:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI37:%.*]] = load i32, ptr addrspace(3) [[DOTI36]], align 4
 ; CHECK-NEXT:    [[DOTI08:%.*]] = add i32 [[TMP2]], [[TMP12]]
 ; CHECK-NEXT:    [[DOTI19:%.*]] = add i32 [[TMP4]], [[DOTI13]]
@@ -87,7 +81,7 @@ define <4 x i32> @load_vec_test() #0 {
 define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 {
 ; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_test(
 ; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] {
-; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 [[INDEX]]
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 [[INDEX]]
 ; CHECK-NEXT:    [[TMP1:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
@@ -121,18 +115,13 @@ define <4 x i32> @multid_load_test() #0 {
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(3) [[TMP5]], align 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = bitcast ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr [3 x [3 x [4 x i32]]], ptr addrspace(3) [[TMP9]], i32 0, i32 1, i32 1
-; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(3) [[TMP11]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI12:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP13]], i32 1
+; CHECK-NEXT:    [[DOTI12:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI13:%.*]] = load i32, ptr addrspace(3) [[DOTI12]], align 4
-; CHECK-NEXT:    [[TMP14:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI24:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP14]], i32 2
+; CHECK-NEXT:    [[DOTI24:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 2) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI25:%.*]] = load i32, ptr addrspace(3) [[DOTI24]], align 4
-; CHECK-NEXT:    [[TMP15:%.*]] = bitcast ptr addrspace(3) [[TMP10]] to ptr addrspace(3)
-; CHECK-NEXT:    [[DOTI36:%.*]] = getelementptr i32, ptr addrspace(3) [[TMP15]], i32 3
+; CHECK-NEXT:    [[DOTI36:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[DOTI37:%.*]] = load i32, ptr addrspace(3) [[DOTI36]], align 4
 ; CHECK-NEXT:    [[DOTI08:%.*]] = add i32 [[TMP2]], [[TMP12]]
 ; CHECK-NEXT:    [[DOTI19:%.*]] = add i32 [[TMP4]], [[DOTI13]]
diff --git a/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll
new file mode 100644
index 000000000000..25dc2c36b4e1
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll
@@ -0,0 +1,25 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -passes='dxil-data-scalarization,dxil-flatten-arrays,function(scalarizer<load-store>),dxil-op-lower' -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s
+
+
+@StaticArr = internal constant [8 x <3 x float>] [<3 x float> zeroinitializer, <3 x float> splat (float 5.000000e-01), <3 x float> <float 1.000000e+00, float 5.000000e-01, float 5.000000e-01>, <3 x float> <float 5.000000e-01, float 1.000000e+00, float 5.000000e-01>, <3 x float> <float 5.000000e-01, float 5.000000e-01, float 1.000000e+00>, <3 x float> <float 5.000000e-01, float 1.000000e+00, float 1.000000e+00>, <3 x float> <float 1.000000e+00, float 5.000000e-01, float 1.000000e+00>, <3 x float> <float 1.000000e+00, float 1.000000e+00, float 5.000000e-01>], align 16
+
+; Function Attrs: alwaysinline convergent mustprogress norecurse nounwind
+define internal void @main() #1 {
+; CHECK-LABEL: define internal void @main() {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[DOTI0:%.*]] = load float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 1), align 16
+; CHECK-NEXT:    [[DOTI1:%.*]] = load float, ptr getelementptr (float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 1), i32 1), align 4
+; CHECK-NEXT:    [[DOTI2:%.*]] = load float, ptr getelementptr (float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 1), i32 2), align 8
+; CHECK-NEXT:    [[DOTI01:%.*]] = load float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 2), align 16
+; CHECK-NEXT:    [[DOTI12:%.*]] = load float, ptr getelementptr (float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 2), i32 1), align 4
+; CHECK-NEXT:    [[DOTI23:%.*]] = load float, ptr getelementptr (float, ptr getelementptr inbounds ([24 x float], ptr @StaticArr.scalarized.1dim, i32 2), i32 2), align 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  %arrayidx = getelementptr inbounds [8 x <3 x float>], ptr @StaticArr, i32 0, i32 1
+  %2 = load <3 x float>, ptr %arrayidx, align 16
+  %arrayidx2 = getelementptr inbounds [8 x <3 x float>], ptr @StaticArr, i32 0, i32 2
+  %3 = load <3 x float>, ptr %arrayidx2, align 16
+  ret void
+}
diff --git a/llvm/test/CodeGen/DirectX/scalar-load.ll b/llvm/test/CodeGen/DirectX/scalar-load.ll
index a32db8b8e399..ed1e9109b7b1 100644
--- a/llvm/test/CodeGen/DirectX/scalar-load.ll
+++ b/llvm/test/CodeGen/DirectX/scalar-load.ll
@@ -2,10 +2,10 @@
 
 ; Make sure we can load groupshared, static vectors and arrays of vectors
 
-@"arrayofVecData" = local_unnamed_addr addrspace(3) global [2 x <3 x float>] zeroinitializer, align 16
-@"vecData" = external addrspace(3) global <4 x i32>, align 4
+@arrayofVecData = local_unnamed_addr addrspace(3) global [2 x <3 x float>] zeroinitializer, align 16
+@vecData = external addrspace(3) global <4 x i32>, align 4
 @staticArrayOfVecData = internal global [3 x <4 x i32>] [<4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32> <i32 5, i32 6, i32 7, i32 8>, <4 x i32> <i32 9, i32 10, i32 11, i32 12>], align 4
-@"groushared2dArrayofVectors" = local_unnamed_addr addrspace(3) global [3 x [ 3 x <4 x i32>]] zeroinitializer, align 16
+@groushared2dArrayofVectors = local_unnamed_addr addrspace(3) global [3 x [ 3 x <4 x i32>]] zeroinitializer, align 16
 
 ; CHECK: @arrayofVecData.scalarized = local_unnamed_addr addrspace(3) global [2 x [3 x float]] zeroinitializer, align 16
 ; CHECK: @vecData.scalarized = external addrspace(3) global [4 x i32], align 4
@@ -19,12 +19,12 @@
 
 
 ; CHECK-LABEL: load_array_vec_test
-define <4 x i32> @load_array_vec_test() #0 {
-  ; CHECK-COUNT-8: load i32, ptr addrspace(3) {{(.*@arrayofVecData.scalarized.*|%.*)}}, align 4
-  %1 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([2 x <4 x i32>], [2 x <4 x i32>] addrspace(3)* @"arrayofVecData", i32 0, i32 0), align 4
-  %2 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([2 x <4 x i32>], [2 x <4 x i32>] addrspace(3)* @"arrayofVecData", i32 0, i32 1), align 4
-  %3 = add <4 x i32> %1, %2
-  ret <4 x i32> %3
+define <3 x float> @load_array_vec_test() #0 {
+  ; CHECK-COUNT-6: load float, ptr addrspace(3) {{(.*@arrayofVecData.scalarized.*|%.*)}}, align 4
+  %1 = load <3 x float>, <3 x float> addrspace(3)* getelementptr inbounds ([2 x <3 x float>], [2 x <3 x float>] addrspace(3)* @"arrayofVecData", i32 0, i32 0), align 4
+  %2 = load <3 x float>, <3 x float> addrspace(3)* getelementptr inbounds ([2 x <3 x float>], [2 x <3 x float>] addrspace(3)* @"arrayofVecData", i32 0, i32 1), align 4
+  %3 = fadd <3 x float> %1, %2
+  ret <3 x float> %3
 }
 
 ; CHECK-LABEL: load_vec_test
@@ -36,8 +36,14 @@ define <4 x i32> @load_vec_test() #0 {
 
 ; CHECK-LABEL: load_static_array_of_vec_test
 define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 {
-  ; CHECK: getelementptr [3 x [4 x i32]], ptr @staticArrayOfVecData.scalarized, i32 0, i32 %index
-  ; CHECK-COUNT-4: load i32, ptr {{.*}}, align 4
+  ; CHECK: getelementptr inbounds [3 x [4 x i32]], ptr @staticArrayOfVecData.scalarized, i32 0, i32 %index
+  ; CHECK: load i32, ptr {{.*}}, align 4
+  ; CHECK: getelementptr i32, ptr {{.*}}, i32 1
+  ; CHECK: load i32, ptr {{.*}}, align 4
+  ; CHECK: getelementptr i32, ptr {{.*}}, i32 2
+  ; CHECK: load i32, ptr {{.*}}, align 4
+  ; CHECK: getelementptr i32, ptr {{.*}}, i32 3
+  ; CHECK: load i32, ptr {{.*}}, align 4
   %3 = getelementptr inbounds [3 x <4 x i32>], [3 x <4 x i32>]* @staticArrayOfVecData, i32 0, i32 %index
   %4 = load <4 x i32>, <4 x i32>* %3, align 4
   ret <4 x i32> %4