diff --git a/llvm/lib/Target/DirectX/DXILDataScalarization.cpp b/llvm/lib/Target/DirectX/DXILDataScalarization.cpp index c97c604fdbf77..cfe270d432144 100644 --- a/llvm/lib/Target/DirectX/DXILDataScalarization.cpp +++ b/llvm/lib/Target/DirectX/DXILDataScalarization.cpp @@ -302,7 +302,7 @@ bool DataScalarizerVisitor::visitExtractElementInst(ExtractElementInst &EEI) { bool DataScalarizerVisitor::visitGetElementPtrInst(GetElementPtrInst &GEPI) { Value *PtrOperand = GEPI.getPointerOperand(); - Type *OrigGEPType = GEPI.getPointerOperandType(); + Type *OrigGEPType = GEPI.getSourceElementType(); Type *NewGEPType = OrigGEPType; bool NeedsTransform = false; @@ -319,6 +319,11 @@ bool DataScalarizerVisitor::visitGetElementPtrInst(GetElementPtrInst &GEPI) { } } + // Scalar geps should remain scalars geps. The dxil-flatten-arrays pass will + // convert these scalar geps into flattened array geps + if (!isa(OrigGEPType)) + NewGEPType = OrigGEPType; + // Note: We bail if this isn't a gep touched via alloca or global // transformations if (!NeedsTransform) diff --git a/llvm/lib/Target/DirectX/DirectXTargetMachine.cpp b/llvm/lib/Target/DirectX/DirectXTargetMachine.cpp index 40fe6c6e639e4..84751d2db2266 100644 --- a/llvm/lib/Target/DirectX/DirectXTargetMachine.cpp +++ b/llvm/lib/Target/DirectX/DirectXTargetMachine.cpp @@ -107,10 +107,10 @@ class DirectXPassConfig : public TargetPassConfig { addPass(createDXILIntrinsicExpansionLegacyPass()); addPass(createDXILCBufferAccessLegacyPass()); addPass(createDXILDataScalarizationLegacyPass()); - addPass(createDXILFlattenArraysLegacyPass()); ScalarizerPassOptions DxilScalarOptions; DxilScalarOptions.ScalarizeLoadStore = true; addPass(createScalarizerPass(DxilScalarOptions)); + addPass(createDXILFlattenArraysLegacyPass()); addPass(createDXILForwardHandleAccessesLegacyPass()); addPass(createDXILLegalizeLegacyPass()); addPass(createDXILResourceImplicitBindingLegacyPass()); diff --git a/llvm/test/CodeGen/DirectX/llc-pipeline.ll b/llvm/test/CodeGen/DirectX/llc-pipeline.ll index 36fed88fc52d6..151603a7161c5 100644 --- a/llvm/test/CodeGen/DirectX/llc-pipeline.ll +++ b/llvm/test/CodeGen/DirectX/llc-pipeline.ll @@ -19,10 +19,12 @@ ; CHECK-NEXT: DXIL Intrinsic Expansion ; CHECK-NEXT: DXIL CBuffer Access ; CHECK-NEXT: DXIL Data Scalarization -; CHECK-NEXT: DXIL Array Flattener ; CHECK-NEXT: FunctionPass Manager ; CHECK-NEXT: Dominator Tree Construction ; CHECK-NEXT: Scalarize vector operations +; CHECK-NEXT: DXIL Array Flattener +; CHECK-NEXT: FunctionPass Manager +; CHECK-NEXT: Dominator Tree Construction ; CHECK-NEXT: DXIL Forward Handle Accesses ; CHECK-NEXT: DXIL Legalizer ; CHECK-NEXT: DXIL Resource Binding Analysis diff --git a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll index 78550adbe424a..27a892591a867 100644 --- a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll +++ b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll @@ -25,13 +25,13 @@ define <4 x i32> @load_array_vec_test() #0 { ; CHECK-LABEL: define <4 x i32> @load_array_vec_test( ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] { ; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, align 4 -; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), align 4 -; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 2), align 4 -; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 3), align 4 +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), align 4 +; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 2), align 4 +; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 3), align 4 ; CHECK-NEXT: [[TMP10:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4 -; CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), i32 1), align 4 -; CHECK-NEXT: [[TMP14:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), i32 2), align 4 -; CHECK-NEXT: [[TMP16:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), i32 3), align 4 +; CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4 +; CHECK-NEXT: [[TMP14:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4 +; CHECK-NEXT: [[TMP16:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4 ; CHECK-NEXT: [[DOTI05:%.*]] = add i32 [[TMP2]], [[TMP10]] ; CHECK-NEXT: [[DOTI16:%.*]] = add i32 [[TMP4]], [[TMP12]] ; CHECK-NEXT: [[DOTI27:%.*]] = add i32 [[TMP6]], [[TMP14]] @@ -53,9 +53,9 @@ define <4 x i32> @load_vec_test() #0 { ; CHECK-LABEL: define <4 x i32> @load_vec_test( ; CHECK-SAME: ) #[[ATTR0]] { ; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) @vecData.scalarized, align 4 -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 1), align 4 -; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 2), align 4 -; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 3), align 4 +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 1), align 4 +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 2), align 4 +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 3), align 4 ; CHECK-NEXT: [[DOTUPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP1]], i32 0 ; CHECK-NEXT: [[DOTUPTO1:%.*]] = insertelement <4 x i32> [[DOTUPTO0]], i32 [[TMP2]], i32 1 ; CHECK-NEXT: [[DOTUPTO2:%.*]] = insertelement <4 x i32> [[DOTUPTO1]], i32 [[TMP3]], i32 2 @@ -66,6 +66,42 @@ define <4 x i32> @load_vec_test() #0 { ret <4 x i32> %1 } +define <4 x i32> @load_vec_from_scalar_gep_test() #0 { +; CHECK-LABEL: define <4 x i32> @load_vec_from_scalar_gep_test( +; CHECK-SAME: ) #[[ATTR0]] { +; CHECK-NEXT: [[DOTI04:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds nuw ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4 +; CHECK-NEXT: [[DOTI116:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4 +; CHECK-NEXT: [[DOTI228:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4 +; CHECK-NEXT: [[DOTI3310:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4 +; CHECK-NEXT: [[DOTUPTO011:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI04]], i32 0 +; CHECK-NEXT: [[DOTUPTO112:%.*]] = insertelement <4 x i32> [[DOTUPTO011]], i32 [[DOTI116]], i32 1 +; CHECK-NEXT: [[DOTUPTO213:%.*]] = insertelement <4 x i32> [[DOTUPTO112]], i32 [[DOTI228]], i32 2 +; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO213]], i32 [[DOTI3310]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP1]] +; + %1 = getelementptr inbounds nuw i32, ptr addrspace(3) @"arrayofVecData", i32 4 + %2 = load <4 x i32>, ptr addrspace(3) %1, align 4 + ret <4 x i32> %2 +} + +define <4 x i32> @load_vec_from_i8_gep_test() #0 { +; CHECK-LABEL: define <4 x i32> @load_vec_from_i8_gep_test( +; CHECK-SAME: ) #[[ATTR0]] { +; CHECK-NEXT: [[DOTI04:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds nuw ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4 +; CHECK-NEXT: [[DOTI116:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4 +; CHECK-NEXT: [[DOTI228:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4 +; CHECK-NEXT: [[DOTI3310:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4 +; CHECK-NEXT: [[DOTUPTO011:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI04]], i32 0 +; CHECK-NEXT: [[DOTUPTO112:%.*]] = insertelement <4 x i32> [[DOTUPTO011]], i32 [[DOTI116]], i32 1 +; CHECK-NEXT: [[DOTUPTO213:%.*]] = insertelement <4 x i32> [[DOTUPTO112]], i32 [[DOTI228]], i32 2 +; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO213]], i32 [[DOTI3310]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP1]] +; + %1 = getelementptr inbounds nuw i8, ptr addrspace(3) @"arrayofVecData", i32 16 + %2 = load <4 x i32>, ptr addrspace(3) %1, align 4 + ret <4 x i32> %2 +} + 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]] { @@ -73,11 +109,17 @@ define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 { ; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[TMP3]] ; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[DOTFLAT]], align 4 -; CHECK-NEXT: [[DOTFLAT_I1:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 1 +; CHECK-NEXT: [[TMP4:%.*]] = mul i32 [[INDEX]], 4 +; CHECK-NEXT: [[TMP5:%.*]] = add i32 1, [[TMP4]] +; CHECK-NEXT: [[DOTFLAT_I1:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP5]] ; CHECK-NEXT: [[DOTI1:%.*]] = load i32, ptr [[DOTFLAT_I1]], align 4 -; CHECK-NEXT: [[DOTFLAT_I2:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 2 +; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[INDEX]], 4 +; CHECK-NEXT: [[TMP7:%.*]] = add i32 2, [[TMP6]] +; CHECK-NEXT: [[DOTFLAT_I2:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP7]] ; CHECK-NEXT: [[DOTI2:%.*]] = load i32, ptr [[DOTFLAT_I2]], align 4 -; CHECK-NEXT: [[DOTFLAT_I3:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 3 +; CHECK-NEXT: [[TMP8:%.*]] = mul i32 [[INDEX]], 4 +; CHECK-NEXT: [[TMP9:%.*]] = add i32 3, [[TMP8]] +; CHECK-NEXT: [[DOTFLAT_I3:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP9]] ; CHECK-NEXT: [[DOTI3:%.*]] = load i32, ptr [[DOTFLAT_I3]], align 4 ; CHECK-NEXT: [[DOTUPTO01:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0 ; CHECK-NEXT: [[DOTUPTO12:%.*]] = insertelement <4 x i32> [[DOTUPTO01]], i32 [[DOTI1]], i32 1 @@ -90,17 +132,85 @@ define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 { ret <4 x i32> %4 } +define <4 x i32> @load_static_array_of_vec_from_scalar_gep_test(i32 %index) #0 { +; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_from_scalar_gep_test( +; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] { +; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[INDEX]], 4 +; CHECK-NEXT: [[TMP2:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP3:%.*]] = add i32 0, [[TMP2]] +; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP3]] +; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[TMP4]], align 4 +; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP6:%.*]] = add i32 1, [[TMP5]] +; CHECK-NEXT: [[DOTI14:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP6]] +; CHECK-NEXT: [[DOTI11:%.*]] = load i32, ptr [[DOTI14]], align 4 +; CHECK-NEXT: [[TMP7:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP8:%.*]] = add i32 2, [[TMP7]] +; CHECK-NEXT: [[DOTI25:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP8]] +; CHECK-NEXT: [[DOTI22:%.*]] = load i32, ptr [[DOTI25]], align 4 +; CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP10:%.*]] = add i32 3, [[TMP9]] +; CHECK-NEXT: [[DOTI36:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP10]] +; CHECK-NEXT: [[DOTI33:%.*]] = load i32, ptr [[DOTI36]], align 4 +; CHECK-NEXT: [[DOTUPTO07:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0 +; CHECK-NEXT: [[DOTUPTO18:%.*]] = insertelement <4 x i32> [[DOTUPTO07]], i32 [[DOTI11]], i32 1 +; CHECK-NEXT: [[DOTUPTO29:%.*]] = insertelement <4 x i32> [[DOTUPTO18]], i32 [[DOTI22]], i32 2 +; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[DOTUPTO29]], i32 [[DOTI33]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP11]] +; + %2 = mul i32 %index, 4 + %3 = getelementptr inbounds i32, ptr @staticArrayOfVecData, i32 %2 + %4 = load <4 x i32>, <4 x i32>* %3, align 4 + ret <4 x i32> %4 +} + +define <4 x i32> @load_static_array_of_vec_from_i8_gep_test(i32 %index) #0 { +; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_from_i8_gep_test( +; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] { +; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[INDEX]], 12 +; CHECK-NEXT: [[TMP2:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP12:%.*]] = lshr i32 [[TMP2]], 2 +; CHECK-NEXT: [[TMP3:%.*]] = add i32 0, [[TMP12]] +; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP3]] +; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[TMP4]], align 4 +; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP14:%.*]] = lshr i32 [[TMP5]], 2 +; CHECK-NEXT: [[TMP6:%.*]] = add i32 1, [[TMP14]] +; CHECK-NEXT: [[DOTI14:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP6]] +; CHECK-NEXT: [[DOTI11:%.*]] = load i32, ptr [[DOTI14]], align 4 +; CHECK-NEXT: [[TMP7:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP15:%.*]] = lshr i32 [[TMP7]], 2 +; CHECK-NEXT: [[TMP8:%.*]] = add i32 2, [[TMP15]] +; CHECK-NEXT: [[DOTI25:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP8]] +; CHECK-NEXT: [[DOTI22:%.*]] = load i32, ptr [[DOTI25]], align 4 +; CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[TMP1]], 1 +; CHECK-NEXT: [[TMP13:%.*]] = lshr i32 [[TMP9]], 2 +; CHECK-NEXT: [[TMP10:%.*]] = add i32 3, [[TMP13]] +; CHECK-NEXT: [[DOTI36:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP10]] +; CHECK-NEXT: [[DOTI33:%.*]] = load i32, ptr [[DOTI36]], align 4 +; CHECK-NEXT: [[DOTUPTO07:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0 +; CHECK-NEXT: [[DOTUPTO18:%.*]] = insertelement <4 x i32> [[DOTUPTO07]], i32 [[DOTI11]], i32 1 +; CHECK-NEXT: [[DOTUPTO29:%.*]] = insertelement <4 x i32> [[DOTUPTO18]], i32 [[DOTI22]], i32 2 +; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[DOTUPTO29]], i32 [[DOTI33]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP11]] +; + %2 = mul i32 %index, 12 + %3 = getelementptr inbounds i8, ptr @staticArrayOfVecData, i32 %2 + %4 = load <4 x i32>, <4 x i32>* %3, align 4 + ret <4 x i32> %4 +} + define <4 x i32> @multid_load_test() #0 { ; CHECK-LABEL: define <4 x i32> @multid_load_test( ; CHECK-SAME: ) #[[ATTR0]] { ; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, align 4 -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 1), align 4 -; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 2), align 4 -; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 3), align 4 +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), align 4 +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 2), align 4 +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 3), align 4 ; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 16), align 4 -; CHECK-NEXT: [[DOTI13:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 16), i32 1), align 4 -; CHECK-NEXT: [[DOTI25:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 16), i32 2), align 4 -; CHECK-NEXT: [[DOTI37:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 16), i32 3), align 4 +; CHECK-NEXT: [[DOTI13:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 17), align 4 +; CHECK-NEXT: [[DOTI25:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 18), align 4 +; CHECK-NEXT: [[DOTI37:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 19), align 4 ; CHECK-NEXT: [[DOTI08:%.*]] = add i32 [[TMP1]], [[TMP5]] ; CHECK-NEXT: [[DOTI19:%.*]] = add i32 [[TMP2]], [[DOTI13]] ; CHECK-NEXT: [[DOTI210:%.*]] = add i32 [[TMP3]], [[DOTI25]] diff --git a/llvm/test/CodeGen/DirectX/scalar-store.ll b/llvm/test/CodeGen/DirectX/scalar-store.ll index 7e9fe0e330661..a124c665ad15e 100644 --- a/llvm/test/CodeGen/DirectX/scalar-store.ll +++ b/llvm/test/CodeGen/DirectX/scalar-store.ll @@ -14,17 +14,31 @@ ; CHECK-LABEL: store_array_vec_test define void @store_array_vec_test () local_unnamed_addr #0 { - ; CHECK-COUNT-6: store float {{1|2|3|4|6}}.000000e+00, ptr addrspace(3) {{(.*@arrayofVecData.scalarized.1dim.*|%.*)}}, align {{4|8|16}} - ; CHECK-NEXT: ret void - store <3 x float> , ptr addrspace(3) @"arrayofVecData", align 16 - store <3 x float> , ptr addrspace(3) getelementptr inbounds (i8, ptr addrspace(3) @"arrayofVecData", i32 16), align 16 - ret void - } +; CHECK-NEXT: store float 1.000000e+00, ptr addrspace(3) @arrayofVecData.scalarized.1dim, align 16 +; CHECK-NEXT: store float 2.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), align 4 +; CHECK-NEXT: store float 3.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 2), align 8 +; CHECK-NEXT: store float 2.000000e+00, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 3), align 16 +; CHECK-NEXT: store float 4.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4 +; CHECK-NEXT: store float 6.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 8 +; CHECK-NEXT: ret void +; + store <3 x float> , ptr addrspace(3) @"arrayofVecData", align 16 + store <3 x float> , ptr addrspace(3) getelementptr inbounds (i8, ptr addrspace(3) @"arrayofVecData", i32 12), align 16 + ret void +} ; CHECK-LABEL: store_vec_test define void @store_vec_test(<4 x i32> %inputVec) #0 { - ; CHECK-COUNT-4: store i32 %inputVec.{{.*}}, ptr addrspace(3) {{(@vecData.scalarized|getelementptr \(i32, ptr addrspace\(3\) @vecData.scalarized, i32 .*\)|%.*)}}, align 4 - ; CHECK-NEXT: ret void +; CHECK-NEXT: [[INPUTVEC_I01:%.*]] = extractelement <4 x i32> %inputVec, i32 0 +; CHECK-NEXT: store i32 [[INPUTVEC_I01]], ptr addrspace(3) @vecData.scalarized, align 4 +; CHECK-NEXT: [[INPUTVEC_I12:%.*]] = extractelement <4 x i32> %inputVec, i32 1 +; CHECK-NEXT: store i32 [[INPUTVEC_I12]], ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 1), align 4 +; CHECK-NEXT: [[INPUTVEC_I23:%.*]] = extractelement <4 x i32> %inputVec, i32 2 +; CHECK-NEXT: store i32 [[INPUTVEC_I23]], ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 2), align 4 +; CHECK-NEXT: [[INPUTVEC_I34:%.*]] = extractelement <4 x i32> %inputVec, i32 3 +; CHECK-NEXT: store i32 [[INPUTVEC_I34]], ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 3), align 4 +; CHECK-NEXT: ret void +; store <4 x i32> %inputVec, <4 x i32> addrspace(3)* @"vecData", align 4 ret void }