diff --git a/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp b/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp index a98ec01d9fd4b..a3163a8969642 100644 --- a/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp +++ b/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp @@ -272,9 +272,8 @@ bool DXILFlattenArraysVisitor::visitGetElementPtrInstInGEPChainBase( ArrayType *FlattenedArrayType = GEPInfo.ParentArrayType; Value *FlatGEP = - Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand, - {Builder.getInt32(0), FlatIndex}, - GEP.getName() + ".flat", GEP.getNoWrapFlags()); + Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand, FlatIndex, + GEP.getName() + ".flat", GEP.isInBounds()); GEP.replaceAllUsesWith(FlatGEP); GEP.eraseFromParent(); diff --git a/llvm/lib/Target/DirectX/DXILPrepare.cpp b/llvm/lib/Target/DirectX/DXILPrepare.cpp index cb58f4833631d..e0068787f5e5a 100644 --- a/llvm/lib/Target/DirectX/DXILPrepare.cpp +++ b/llvm/lib/Target/DirectX/DXILPrepare.cpp @@ -148,49 +148,9 @@ class DXILPrepareModule : public ModulePass { Type *Ty) { // Omit bitcasts if the incoming value matches the instruction type. auto It = PointerTypes.find(Operand); - if (It != PointerTypes.end()) { - auto *OpTy = cast(It->second)->getElementType(); - if (OpTy == Ty) + if (It != PointerTypes.end()) + if (cast(It->second)->getElementType() == Ty) return nullptr; - } - - Type *ValTy = Operand->getType(); - // Also omit the bitcast for matching global array types - if (auto *GlobalVar = dyn_cast(Operand)) - ValTy = GlobalVar->getValueType(); - - if (auto *AI = dyn_cast(Operand)) - ValTy = AI->getAllocatedType(); - - if (auto *ArrTy = dyn_cast(ValTy)) { - Type *ElTy = ArrTy->getElementType(); - if (ElTy == Ty) - return nullptr; - } - - // finally, drill down GEP instructions until we get the array - // that is being accessed, and compare element types - if (ConstantExpr *GEPInstr = dyn_cast(Operand)) { - while (GEPInstr->getOpcode() == Instruction::GetElementPtr) { - Value *OpArg = GEPInstr->getOperand(0); - if (ConstantExpr *NewGEPInstr = dyn_cast(OpArg)) { - GEPInstr = NewGEPInstr; - continue; - } - - if (auto *GlobalVar = dyn_cast(OpArg)) - ValTy = GlobalVar->getValueType(); - if (auto *AI = dyn_cast(Operand)) - ValTy = AI->getAllocatedType(); - if (auto *ArrTy = dyn_cast(ValTy)) { - Type *ElTy = ArrTy->getElementType(); - if (ElTy == Ty) - return nullptr; - } - break; - } - } - // Insert bitcasts where we are removing the instruction. Builder.SetInsertPoint(&Inst); // This code only gets hit in opaque-pointer mode, so the type of the diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll index 47d7b50cf0186..754d5a25ca905 100644 --- a/llvm/test/CodeGen/DirectX/flatten-array.ll +++ b/llvm/test/CodeGen/DirectX/flatten-array.ll @@ -31,7 +31,7 @@ define void @alloca_4d_test () { ; CHECK-LABEL: gep_2d_test define void @gep_2d_test () { ; CHECK: [[a:%.*]] = alloca [9 x i32], align 4 - ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 0, i32 {{[0-8]}} + ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 {{[0-8]}} ; CHECK-NEXT: ret void %1 = alloca [3 x [3 x i32]], align 4 %g2d0 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* %1, i32 0, i32 0 @@ -53,7 +53,7 @@ define void @gep_2d_test () { ; CHECK-LABEL: gep_3d_test define void @gep_3d_test () { ; CHECK: [[a:%.*]] = alloca [8 x i32], align 4 - ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 0, i32 {{[0-7]}} + ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 {{[0-7]}} ; CHECK-NEXT: ret void %1 = alloca [2 x[2 x [2 x i32]]], align 4 %g3d0 = getelementptr inbounds [2 x[2 x [2 x i32]]], [2 x[2 x [2 x i32]]]* %1, i32 0, i32 0 @@ -76,7 +76,7 @@ define void @gep_3d_test () { ; CHECK-LABEL: gep_4d_test define void @gep_4d_test () { ; CHECK: [[a:%.*]] = alloca [16 x i32], align 4 - ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 0, i32 {{[0-9]|1[0-5]}} + ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 {{[0-9]|1[0-5]}} ; CHECK-NEXT: ret void %1 = alloca [2x[2 x[2 x [2 x i32]]]], align 4 %g4d0 = getelementptr inbounds [2x[2 x[2 x [2 x i32]]]], [2x[2 x[2 x [2 x i32]]]]* %1, i32 0, i32 0 @@ -123,7 +123,8 @@ define void @gep_4d_test () { @b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16 define void @global_gep_load() { - ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4 + ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 6 + ; CHECK: load i32, ptr [[GEP_PTR]], align 4 ; CHECK-NEXT: ret void %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @a, i32 0, i32 0 %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1 @@ -141,7 +142,7 @@ define void @global_gep_load_index(i32 %row, i32 %col, i32 %timeIndex) { ; CHECK-NEXT: [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]] ; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[ROW]], 12 ; CHECK-NEXT: [[TMP6:%.*]] = add i32 [[TMP4]], [[TMP5]] -; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP6]] +; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP6]] ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}} ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}} ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}} @@ -162,7 +163,7 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) { ; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[ROW]], 3 ; CHECK-NEXT: [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]] -; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP4]] +; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP4]] ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}} ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}} ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}} @@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) { } define void @global_gep_store() { - ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4 + ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 13 + ; CHECK: store i32 1, ptr [[GEP_PTR]], align 4 ; CHECK-NEXT: ret void %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @b, i32 0, i32 1 %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 0 diff --git a/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll index c73e5017348d1..3ae5832ce8322 100644 --- a/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll +++ b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll @@ -8,9 +8,9 @@ define internal void @main() { ; CHECK-LABEL: define internal void @main() { ; CHECK-NEXT: [[ENTRY:.*:]] -; CHECK-NEXT: [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 0, i32 1 +; 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 0, i32 2 +; 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 ; diff --git a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll index 222fd8cab348c..7e5a92e1311f8 100644 --- a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll +++ b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll @@ -32,23 +32,23 @@ 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) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1) to ptr addrspace(3) -; CHECK-NEXT: [[TMP10:%.*]] = load i32, ptr addrspace(3) [[TMP9]], align 4 -; CHECK-NEXT: [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 1) 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) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 2) to ptr addrspace(3) -; CHECK-NEXT: [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4 -; CHECK-NEXT: [[TMP15:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 3) to ptr addrspace(3) -; CHECK-NEXT: [[TMP16:%.*]] = load i32, ptr addrspace(3) [[TMP15]], align 4 -; CHECK-NEXT: [[DOTI05:%.*]] = add i32 [[TMP2]], [[TMP10]] -; CHECK-NEXT: [[DOTI16:%.*]] = add i32 [[TMP4]], [[TMP12]] -; CHECK-NEXT: [[DOTI27:%.*]] = add i32 [[TMP6]], [[TMP14]] -; CHECK-NEXT: [[DOTI38:%.*]] = add i32 [[TMP8]], [[TMP16]] -; CHECK-NEXT: [[DOTUPTO01215:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI05]], i32 0 -; CHECK-NEXT: [[DOTUPTO11316:%.*]] = insertelement <4 x i32> [[DOTUPTO01215]], i32 [[DOTI16]], i32 1 -; CHECK-NEXT: [[DOTUPTO21417:%.*]] = insertelement <4 x i32> [[DOTUPTO11316]], i32 [[DOTI27]], i32 2 -; CHECK-NEXT: [[TMP17:%.*]] = insertelement <4 x i32> [[DOTUPTO21417]], i32 [[DOTI38]], i32 3 -; CHECK-NEXT: ret <4 x i32> [[TMP17]] +; 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: [[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: [[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]] +; CHECK-NEXT: [[DOTI210:%.*]] = add i32 [[TMP6]], [[DOTI25]] +; CHECK-NEXT: [[DOTI311:%.*]] = add i32 [[TMP8]], [[DOTI37]] +; CHECK-NEXT: [[DOTUPTO015:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI08]], i32 0 +; CHECK-NEXT: [[DOTUPTO116:%.*]] = insertelement <4 x i32> [[DOTUPTO015]], i32 [[DOTI19]], i32 1 +; CHECK-NEXT: [[DOTUPTO217:%.*]] = insertelement <4 x i32> [[DOTUPTO116]], i32 [[DOTI210]], i32 2 +; CHECK-NEXT: [[TMP16:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP16]] ; %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 @@ -60,15 +60,19 @@ define <4 x i32> @load_array_vec_test() #0 { 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: [[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 -; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> [[DOTUPTO2]], i32 [[TMP4]], i32 3 -; CHECK-NEXT: ret <4 x i32> [[TMP5]] +; CHECK-NEXT: [[TMP1:%.*]] = bitcast ptr addrspace(3) @vecData.scalarized to ptr addrspace(3) +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) [[TMP1]], align 4 +; CHECK-NEXT: [[TMP3:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 1) to ptr addrspace(3) +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) [[TMP3]], align 4 +; CHECK-NEXT: [[TMP5:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 2) to ptr addrspace(3) +; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr addrspace(3) [[TMP5]], align 4 +; CHECK-NEXT: [[TMP7:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @vecData.scalarized, i32 3) to ptr addrspace(3) +; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4 +; CHECK-NEXT: [[DOTUPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2]], i32 0 +; CHECK-NEXT: [[DOTUPTO1:%.*]] = insertelement <4 x i32> [[DOTUPTO0]], i32 [[TMP4]], i32 1 +; CHECK-NEXT: [[DOTUPTO2:%.*]] = insertelement <4 x i32> [[DOTUPTO1]], i32 [[TMP6]], i32 2 +; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x i32> [[DOTUPTO2]], i32 [[TMP8]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP9]] ; %1 = load <4 x i32>, <4 x i32> addrspace(3)* @"vecData", align 4 ret <4 x i32> %1 @@ -77,19 +81,23 @@ 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 inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[INDEX]] -; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[DOTFLAT]], align 4 -; CHECK-NEXT: [[DOTFLAT_I1:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 1 +; 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 +; CHECK-NEXT: [[DOTFLAT_I1:%.*]] = getelementptr i32, ptr [[TMP3]], i32 1 ; CHECK-NEXT: [[DOTI1:%.*]] = load i32, ptr [[DOTFLAT_I1]], align 4 -; CHECK-NEXT: [[DOTFLAT_I2:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 2 +; CHECK-NEXT: [[TMP4:%.*]] = bitcast ptr [[DOTFLAT]] to ptr +; CHECK-NEXT: [[DOTFLAT_I2:%.*]] = getelementptr i32, ptr [[TMP4]], i32 2 ; CHECK-NEXT: [[DOTI2:%.*]] = load i32, ptr [[DOTFLAT_I2]], align 4 -; CHECK-NEXT: [[DOTFLAT_I3:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 3 +; CHECK-NEXT: [[TMP5:%.*]] = bitcast ptr [[DOTFLAT]] to ptr +; CHECK-NEXT: [[DOTFLAT_I3:%.*]] = getelementptr i32, ptr [[TMP5]], i32 3 ; 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 -; CHECK-NEXT: [[DOTUPTO23:%.*]] = insertelement <4 x i32> [[DOTUPTO12]], i32 [[DOTI2]], i32 2 -; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO23]], i32 [[DOTI3]], i32 3 -; CHECK-NEXT: ret <4 x i32> [[TMP1]] +; CHECK-NEXT: [[DOTUPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2]], i32 0 +; CHECK-NEXT: [[DOTUPTO1:%.*]] = insertelement <4 x i32> [[DOTUPTO0]], i32 [[DOTI1]], i32 1 +; CHECK-NEXT: [[DOTUPTO2:%.*]] = insertelement <4 x i32> [[DOTUPTO1]], i32 [[DOTI2]], i32 2 +; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[DOTUPTO2]], i32 [[DOTI3]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP6]] ; %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 @@ -99,23 +107,31 @@ define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 { 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) @groushared2dArrayofVectors.scalarized.1dim, align 4 -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), align 4 -; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 2), align 4 -; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 3), align 4 -; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), align 4 -; CHECK-NEXT: [[DOTI13:%.*]] = load i32, ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), 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) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), 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) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), i32 3), align 4 -; CHECK-NEXT: [[DOTI08:%.*]] = add i32 [[TMP1]], [[TMP5]] -; CHECK-NEXT: [[DOTI19:%.*]] = add i32 [[TMP2]], [[DOTI13]] -; CHECK-NEXT: [[DOTI210:%.*]] = add i32 [[TMP3]], [[DOTI25]] -; CHECK-NEXT: [[DOTI311:%.*]] = add i32 [[TMP4]], [[DOTI37]] +; CHECK-NEXT: [[TMP1:%.*]] = bitcast ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim to ptr addrspace(3) +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) [[TMP1]], align 4 +; CHECK-NEXT: [[TMP3:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1) to ptr addrspace(3) +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) [[TMP3]], align 4 +; CHECK-NEXT: [[TMP5:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 2) to ptr addrspace(3) +; 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: [[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: [[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: [[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: [[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]] +; CHECK-NEXT: [[DOTI210:%.*]] = add i32 [[TMP6]], [[DOTI25]] +; CHECK-NEXT: [[DOTI311:%.*]] = add i32 [[TMP8]], [[DOTI37]] ; CHECK-NEXT: [[DOTUPTO015:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI08]], i32 0 ; CHECK-NEXT: [[DOTUPTO116:%.*]] = insertelement <4 x i32> [[DOTUPTO015]], i32 [[DOTI19]], i32 1 ; CHECK-NEXT: [[DOTUPTO217:%.*]] = insertelement <4 x i32> [[DOTUPTO116]], i32 [[DOTI210]], i32 2 -; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3 -; CHECK-NEXT: ret <4 x i32> [[TMP6]] +; CHECK-NEXT: [[TMP16:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3 +; CHECK-NEXT: ret <4 x i32> [[TMP16]] ; %1 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([3 x [3 x <4 x i32>]], [3 x [3 x <4 x i32>]] addrspace(3)* @"groushared2dArrayofVectors", i32 0, i32 0, i32 0), align 4 %2 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([3 x [3 x <4 x i32>]], [3 x [3 x <4 x i32>]] addrspace(3)* @"groushared2dArrayofVectors", i32 0, i32 1, i32 1), align 4 diff --git a/llvm/test/CodeGen/DirectX/noop_bitcast_global_array_type.ll b/llvm/test/CodeGen/DirectX/noop_bitcast_global_array_type.ll deleted file mode 100644 index 1f33700e014c7..0000000000000 --- a/llvm/test/CodeGen/DirectX/noop_bitcast_global_array_type.ll +++ /dev/null @@ -1,53 +0,0 @@ -; RUN: opt -S --dxil-prepare %s | FileCheck %s - -; Test that global arrays do not get a bitcast instruction -; after the dxil-prepare pass. - -target triple = "dxilv1.2-unknown-shadermodel6.2-compute" - -@inputTile.1dim = local_unnamed_addr addrspace(3) global [3 x float] zeroinitializer, align 2 - -; CHECK-LABEL: testload -define float @testload() local_unnamed_addr { - ; NOTE: this would be "bitcast ptr addrspace(3)..." before the change that introduced this test, - ; after the dxil-prepare pass is run - ; CHECK-NEXT: load float, ptr addrspace(3) @inputTile.1dim, align 2 - %v = load float, ptr addrspace(3) @inputTile.1dim, align 2 - - ret float %v -} - -; CHECK-LABEL: teststore -define void @teststore() local_unnamed_addr { - ; CHECK-next: store float 2.000000e+00, ptr addrspace(3) @inputTile.1dim, align 2 - store float 2.000000e+00, ptr addrspace(3) @inputTile.1dim, align 2 - - ret void -} - -; CHECK-LABEL: testGEPConst -define float @testGEPConst() local_unnamed_addr { - ; CHECK-NEXT: load float, ptr addrspace(3) getelementptr (float, ptr addrspace(3) @inputTile.1dim, i32 1), align 4 - %v = load float, ptr addrspace(3) getelementptr (float, ptr addrspace(3) @inputTile.1dim, i32 1), align 4 - - ret float %v -} - -; CHECK-LABEL: testGEPNonConst -define float @testGEPNonConst(i32 %i) local_unnamed_addr { - ; CHECK-NEXT: getelementptr float, ptr addrspace(3) @inputTile.1dim, i32 %i - %gep = getelementptr float, ptr addrspace(3) @inputTile.1dim, i32 %i - %v = load float, ptr addrspace(3) %gep - - ret float %v -} - -; CHECK-LABEL: testAlloca -define float @testAlloca(i32 %i) local_unnamed_addr { - ; CHECK-NEXT: alloca [3 x float], align 4 - %arr = alloca [3 x float], align 4 - ; CHECK-NEXT: getelementptr [3 x float], ptr %arr, i32 1 - %gep = getelementptr [3 x float], ptr %arr, i32 1 - %v = load float, ptr %gep - ret float %v -} diff --git a/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll index a07ce2c24f7ac..2676abec1d8ae 100644 --- a/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll +++ b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll @@ -8,13 +8,13 @@ define internal void @main() #1 { ; CHECK-LABEL: define internal void @main() { ; CHECK-NEXT: [[ENTRY:.*:]] -; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 0, i32 1 +; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 1 ; CHECK-NEXT: [[DOTI0:%.*]] = load float, ptr [[TMP0]], align 16 ; CHECK-NEXT: [[DOTI1:%.*]] = getelementptr float, ptr [[TMP0]], i32 1 ; CHECK-NEXT: [[DOTI11:%.*]] = load float, ptr [[DOTI1]], align 4 ; CHECK-NEXT: [[DOTI2:%.*]] = getelementptr float, ptr [[TMP0]], i32 2 ; CHECK-NEXT: [[DOTI22:%.*]] = load float, ptr [[DOTI2]], align 8 -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 0, i32 2 +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 2 ; CHECK-NEXT: [[DOTI03:%.*]] = load float, ptr [[TMP1]], align 16 ; CHECK-NEXT: [[DOTI14:%.*]] = getelementptr float, ptr [[TMP1]], i32 1 ; CHECK-NEXT: [[DOTI15:%.*]] = load float, ptr [[DOTI14]], align 4