Author: lattner
Date: Thu Jul 29 00:02:29 2010
New Revision: 109732
URL: http://llvm.org/viewvc/llvm-project?rev=109732&view=rev
Log:
ignore structs that wrap vectors in IR, the abstraction shouldn't add penalty.
Before we'd compile the example into something like:
%coerce.dive2 = getelementptr %struct.v4f32wrapper* %retval, i32 0, i32 0 ;
<<4 x float>*> [#uses=1]
%1 = bitcast <4 x float>* %coerce.dive2 to <2 x double>* ; <<2 x double>*>
[#uses=1]
%2 = load <2 x double>* %1, align 1 ; <<2 x double>> [#uses=1]
ret <2 x double> %2
Now we produce:
%coerce.dive2 = getelementptr %struct.v4f32wrapper* %retval, i32 0, i32 0 ;
<<4 x float>*> [#uses=1]
%0 = load <4 x float>* %coerce.dive2, align 1 ; <<4 x float>> [#uses=1]
ret <4 x float> %0
Modified:
cfe/trunk/lib/CodeGen/TargetInfo.cpp
cfe/trunk/test/CodeGen/x86_64-arguments.c
Modified: cfe/trunk/lib/CodeGen/TargetInfo.cpp
URL:
http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/CodeGen/TargetInfo.cpp?rev=109732&r1=109731&r2=109732&view=diff
==============================================================================
--- cfe/trunk/lib/CodeGen/TargetInfo.cpp (original)
+++ cfe/trunk/lib/CodeGen/TargetInfo.cpp Thu Jul 29 00:02:29 2010
@@ -1185,9 +1185,20 @@
/// full vector XMM register. Pick an LLVM IR type that will be passed as a
/// vector register.
const llvm::Type *X86_64ABIInfo::Get16ByteVectorType(QualType Ty) const {
+ const llvm::Type *IRType = CGT.ConvertTypeRecursive(Ty);
+
+ // Wrapper structs that just contain vectors are passed just like vectors,
+ // strip them off if present.
+ const llvm::StructType *STy = dyn_cast<llvm::StructType>(IRType);
+ while (STy && STy->getNumElements() == 1) {
+ IRType = STy->getElementType(0);
+ STy = dyn_cast<llvm::StructType>(IRType);
+ }
+
+
+
// If the preferred type is a 16-byte vector, prefer to pass it.
- if (const llvm::VectorType *VT =
- dyn_cast<llvm::VectorType>(CGT.ConvertTypeRecursive(Ty))){
+ if (const llvm::VectorType *VT = dyn_cast<llvm::VectorType>(IRType)){
const llvm::Type *EltTy = VT->getElementType();
if (VT->getBitWidth() == 128 &&
(EltTy->isFloatTy() || EltTy->isDoubleTy() ||
Modified: cfe/trunk/test/CodeGen/x86_64-arguments.c
URL:
http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGen/x86_64-arguments.c?rev=109732&r1=109731&r2=109732&view=diff
==============================================================================
--- cfe/trunk/test/CodeGen/x86_64-arguments.c (original)
+++ cfe/trunk/test/CodeGen/x86_64-arguments.c Thu Jul 29 00:02:29 2010
@@ -168,3 +168,13 @@
// CHECK: define %struct.foo26 @f26(%struct.foo26* %P)
return *P;
}
+
+
+struct v4f32wrapper {
+ v4f32 v;
+};
+
+struct v4f32wrapper f27(struct v4f32wrapper X) {
+ // CHECK: define <4 x float> @f27(<4 x float> %X.coerce)
+ return X;
+}
\ No newline at end of file
_______________________________________________
cfe-commits mailing list
cfe-commits@cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits
