Preserve vec3 type.
Summary: Preserve vec3 type with CodeGen option.
Reviewers: Anastasia, bruno
Reviewed By: Anastasia
Subscribers: bruno, ahatanak, cfe-commits
Differential Revision: https://reviews.llvm.org/D30810
llvm-svn: 299445
diff --git a/clang/lib/CodeGen/CGExpr.cpp b/clang/lib/CodeGen/CGExpr.cpp
index 1a95eb1..38eb345 100644
--- a/clang/lib/CodeGen/CGExpr.cpp
+++ b/clang/lib/CodeGen/CGExpr.cpp
@@ -1369,26 +1369,28 @@
QualType TBAABaseType,
uint64_t TBAAOffset,
bool isNontemporal) {
- // For better performance, handle vector loads differently.
- if (Ty->isVectorType()) {
- const llvm::Type *EltTy = Addr.getElementType();
+ if (!CGM.getCodeGenOpts().PreserveVec3Type) {
+ // For better performance, handle vector loads differently.
+ if (Ty->isVectorType()) {
+ const llvm::Type *EltTy = Addr.getElementType();
- const auto *VTy = cast<llvm::VectorType>(EltTy);
+ const auto *VTy = cast<llvm::VectorType>(EltTy);
- // Handle vectors of size 3 like size 4 for better performance.
- if (VTy->getNumElements() == 3) {
+ // Handle vectors of size 3 like size 4 for better performance.
+ if (VTy->getNumElements() == 3) {
- // Bitcast to vec4 type.
- llvm::VectorType *vec4Ty = llvm::VectorType::get(VTy->getElementType(),
- 4);
- Address Cast = Builder.CreateElementBitCast(Addr, vec4Ty, "castToVec4");
- // Now load value.
- llvm::Value *V = Builder.CreateLoad(Cast, Volatile, "loadVec4");
+ // Bitcast to vec4 type.
+ llvm::VectorType *vec4Ty =
+ llvm::VectorType::get(VTy->getElementType(), 4);
+ Address Cast = Builder.CreateElementBitCast(Addr, vec4Ty, "castToVec4");
+ // Now load value.
+ llvm::Value *V = Builder.CreateLoad(Cast, Volatile, "loadVec4");
- // Shuffle vector to get vec3.
- V = Builder.CreateShuffleVector(V, llvm::UndefValue::get(vec4Ty),
- {0, 1, 2}, "extractVec");
- return EmitFromMemory(V, Ty);
+ // Shuffle vector to get vec3.
+ V = Builder.CreateShuffleVector(V, llvm::UndefValue::get(vec4Ty),
+ {0, 1, 2}, "extractVec");
+ return EmitFromMemory(V, Ty);
+ }
}
}
@@ -1456,24 +1458,25 @@
uint64_t TBAAOffset,
bool isNontemporal) {
- // Handle vectors differently to get better performance.
- if (Ty->isVectorType()) {
- llvm::Type *SrcTy = Value->getType();
- auto *VecTy = cast<llvm::VectorType>(SrcTy);
- // Handle vec3 special.
- if (VecTy->getNumElements() == 3) {
- // Our source is a vec3, do a shuffle vector to make it a vec4.
- llvm::Constant *Mask[] = {Builder.getInt32(0), Builder.getInt32(1),
- Builder.getInt32(2),
- llvm::UndefValue::get(Builder.getInt32Ty())};
- llvm::Value *MaskV = llvm::ConstantVector::get(Mask);
- Value = Builder.CreateShuffleVector(Value,
- llvm::UndefValue::get(VecTy),
- MaskV, "extractVec");
- SrcTy = llvm::VectorType::get(VecTy->getElementType(), 4);
- }
- if (Addr.getElementType() != SrcTy) {
- Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
+ if (!CGM.getCodeGenOpts().PreserveVec3Type) {
+ // Handle vectors differently to get better performance.
+ if (Ty->isVectorType()) {
+ llvm::Type *SrcTy = Value->getType();
+ auto *VecTy = cast<llvm::VectorType>(SrcTy);
+ // Handle vec3 special.
+ if (VecTy->getNumElements() == 3) {
+ // Our source is a vec3, do a shuffle vector to make it a vec4.
+ llvm::Constant *Mask[] = {Builder.getInt32(0), Builder.getInt32(1),
+ Builder.getInt32(2),
+ llvm::UndefValue::get(Builder.getInt32Ty())};
+ llvm::Value *MaskV = llvm::ConstantVector::get(Mask);
+ Value = Builder.CreateShuffleVector(Value, llvm::UndefValue::get(VecTy),
+ MaskV, "extractVec");
+ SrcTy = llvm::VectorType::get(VecTy->getElementType(), 4);
+ }
+ if (Addr.getElementType() != SrcTy) {
+ Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
+ }
}
}
diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index e9041b2..8ee4d3f 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -3593,8 +3593,12 @@
// vector to get a vec4, then a bitcast if the target type is different.
if (NumElementsSrc == 3 && NumElementsDst != 3) {
Src = ConvertVec3AndVec4(Builder, CGF, Src, 4);
- Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
- DstTy);
+
+ if (!CGF.CGM.getCodeGenOpts().PreserveVec3Type) {
+ Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
+ DstTy);
+ }
+
Src->setName("astype");
return Src;
}
@@ -3603,9 +3607,12 @@
// to vec4 if the original type is not vec4, then a shuffle vector to
// get a vec3.
if (NumElementsSrc != 3 && NumElementsDst == 3) {
- auto Vec4Ty = llvm::VectorType::get(DstTy->getVectorElementType(), 4);
- Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
- Vec4Ty);
+ if (!CGF.CGM.getCodeGenOpts().PreserveVec3Type) {
+ auto Vec4Ty = llvm::VectorType::get(DstTy->getVectorElementType(), 4);
+ Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
+ Vec4Ty);
+ }
+
Src = ConvertVec3AndVec4(Builder, CGF, Src, 3);
Src->setName("astype");
return Src;
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 9138450..271d1ca 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -729,6 +729,7 @@
}
}
+ Opts.PreserveVec3Type = Args.hasArg(OPT_fpreserve_vec3_type);
Opts.InstrumentFunctions = Args.hasArg(OPT_finstrument_functions);
Opts.XRayInstrumentFunctions = Args.hasArg(OPT_fxray_instrument);
Opts.XRayInstructionThreshold =