summaryrefslogtreecommitdiffstats
path: root/clang/lib/CodeGen/CGExpr.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'clang/lib/CodeGen/CGExpr.cpp')
-rw-r--r--clang/lib/CodeGen/CGExpr.cpp79
1 files changed, 41 insertions, 38 deletions
diff --git a/clang/lib/CodeGen/CGExpr.cpp b/clang/lib/CodeGen/CGExpr.cpp
index 1a95eb10451..38eb345d913 100644
--- a/clang/lib/CodeGen/CGExpr.cpp
+++ b/clang/lib/CodeGen/CGExpr.cpp
@@ -1369,26 +1369,28 @@ llvm::Value *CodeGenFunction::EmitLoadOfScalar(Address Addr, bool Volatile,
QualType TBAABaseType,
uint64_t TBAAOffset,
bool isNontemporal) {
- // For better performance, handle vector loads differently.
- if (Ty->isVectorType()) {
- const llvm::Type *EltTy = Addr.getElementType();
-
- const auto *VTy = cast<llvm::VectorType>(EltTy);
-
- // 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");
-
- // Shuffle vector to get vec3.
- V = Builder.CreateShuffleVector(V, llvm::UndefValue::get(vec4Ty),
- {0, 1, 2}, "extractVec");
- return EmitFromMemory(V, Ty);
+ 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);
+
+ // 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");
+
+ // 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 @@ void CodeGenFunction::EmitStoreOfScalar(llvm::Value *Value, Address Addr,
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");
+ }
}
}
OpenPOWER on IntegriCloud