Skip to content

Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" #143043

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 6, 2025
Merged

Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" #143043

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ae8008
Revert "Adjust bit cast instruction filter for DXIL Prepare pass (#14…
farzonl Jun 6, 2025
babc67e
Revert "[DirectX] Array GEPs need two indices (#142853)"
farzonl Jun 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions llvm/lib/Target/DirectX/DXILFlattenArrays.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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();
Expand Down
44 changes: 2 additions & 42 deletions llvm/lib/Target/DirectX/DXILPrepare.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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<TypedPointerType>(It->second)->getElementType();
if (OpTy == Ty)
if (It != PointerTypes.end())
if (cast<TypedPointerType>(It->second)->getElementType() == Ty)
return nullptr;
}

Type *ValTy = Operand->getType();
// Also omit the bitcast for matching global array types
if (auto *GlobalVar = dyn_cast<GlobalVariable>(Operand))
ValTy = GlobalVar->getValueType();

if (auto *AI = dyn_cast<AllocaInst>(Operand))
ValTy = AI->getAllocatedType();

if (auto *ArrTy = dyn_cast<ArrayType>(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<ConstantExpr>(Operand)) {
while (GEPInstr->getOpcode() == Instruction::GetElementPtr) {
Value *OpArg = GEPInstr->getOperand(0);
if (ConstantExpr *NewGEPInstr = dyn_cast<ConstantExpr>(OpArg)) {
GEPInstr = NewGEPInstr;
continue;
}

if (auto *GlobalVar = dyn_cast<GlobalVariable>(OpArg))
ValTy = GlobalVar->getValueType();
if (auto *AI = dyn_cast<AllocaInst>(Operand))
ValTy = AI->getAllocatedType();
if (auto *ArrTy = dyn_cast<ArrayType>(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
Expand Down
16 changes: 9 additions & 7 deletions llvm/test/CodeGen/DirectX/flatten-array.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand All @@ -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
Expand All @@ -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
Expand Down Expand Up @@ -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
Expand All @@ -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]{{.*}}
Expand All @@ -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]{{.*}}
Expand All @@ -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
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
;
Expand Down
Loading
Loading