maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Vector codegen improvements 

llvm-svn: 62458
This commit is contained in:
Nate Begeman 2009-01-18 06:42:49 +00:00
parent e5be1cd635
commit b699c9bf57
6 changed files with 102 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
clang/lib/AST/ASTContext.cpp
View File

@ -20,6 +20,7 @@
#include "llvm/ADT/StringExtras.h"
#include "llvm/Bitcode/Serialize.h"
#include "llvm/Bitcode/Deserialize.h"
#include "llvm/Support/MathExtras.h"
using namespace clang;
@ -284,8 +285,11 @@ ASTContext::getTypeInfo(const Type *T) {
std::pair<uint64_t, unsigned> EltInfo =
getTypeInfo(cast<VectorType>(T)->getElementType());
Width = EltInfo.first*cast<VectorType>(T)->getNumElements();
// FIXME: This isn't right for unusual vectors
Align = Width;
// If the alignment is not a power of 2, round up to the next power of 2.
// This happens for non-power-of-2 length vectors.
// FIXME: this should probably be a target property.
Align = 1 << llvm::Log2_32_Ceil(Align);
break;
}

2
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -631,6 +631,8 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_vec_ext_v2di:
case X86::BI__builtin_ia32_vec_ext_v4sf:
case X86::BI__builtin_ia32_vec_ext_v4si:
case X86::BI__builtin_ia32_vec_ext_v8hi:
case X86::BI__builtin_ia32_vec_ext_v4hi:
case X86::BI__builtin_ia32_vec_ext_v2df:
return Builder.CreateExtractElement(Ops[0], Ops[1], "result");
case X86::BI__builtin_ia32_cmpordss:

77
clang/lib/CodeGen/CGExpr.cpp
View File

@ -309,8 +309,8 @@ RValue CodeGenFunction::EmitLoadOfKVCRefLValue(LValue LV,
return EmitObjCPropertyGet(LV.getKVCRefExpr());
}
// If this is a reference to a subset of the elements of a vector, either
// shuffle the input or extract/insert them as appropriate.
// If this is a reference to a subset of the elements of a vector, create an
// appropriate shufflevector.
RValue CodeGenFunction::EmitLoadOfExtVectorElementLValue(LValue LV,
QualType ExprType) {
llvm::Value *Vec = Builder.CreateLoad(LV.getExtVectorAddr(),
@ -327,13 +327,9 @@ RValue CodeGenFunction::EmitLoadOfExtVectorElementLValue(LValue LV,
return RValue::get(Builder.CreateExtractElement(Vec, Elt, "tmp"));
}
// If the source and destination have the same number of elements, use a
// vector shuffle instead of insert/extracts.
// Always use shuffle vector to try to retain the original program structure
unsigned NumResultElts = ExprVT->getNumElements();
unsigned NumSourceElts =
cast<llvm::VectorType>(Vec->getType())->getNumElements();
if (NumResultElts == NumSourceElts) {
llvm::SmallVector<llvm::Constant*, 4> Mask;
for (unsigned i = 0; i != NumResultElts; ++i) {
unsigned InIdx = getAccessedFieldNo(i, Elts);
@ -347,22 +343,6 @@ RValue CodeGenFunction::EmitLoadOfExtVectorElementLValue(LValue LV,
return RValue::get(Vec);
}
// Start out with an undef of the result type.
llvm::Value *Result = llvm::UndefValue::get(ConvertType(ExprType));
// Extract/Insert each element of the result.
for (unsigned i = 0; i != NumResultElts; ++i) {
unsigned InIdx = getAccessedFieldNo(i, Elts);
llvm::Value *Elt = llvm::ConstantInt::get(llvm::Type::Int32Ty, InIdx);
Elt = Builder.CreateExtractElement(Vec, Elt, "tmp");
llvm::Value *OutIdx = llvm::ConstantInt::get(llvm::Type::Int32Ty, i);
Result = Builder.CreateInsertElement(Result, Elt, OutIdx, "tmp");
}
return RValue::get(Result);
}
/// EmitStoreThroughLValue - Store the specified rvalue into the specified
@ -548,15 +528,54 @@ void CodeGenFunction::EmitStoreThroughExtVectorComponentLValue(RValue Src,
if (const VectorType *VTy = Ty->getAsVectorType()) {
unsigned NumSrcElts = VTy->getNumElements();
// Extract/Insert each element.
unsigned NumDstElts =
cast<llvm::VectorType>(Vec->getType())->getNumElements();
if (NumDstElts == NumSrcElts) {
// Use shuffle vector is the src and destination are the same number
// of elements
llvm::SmallVector<llvm::Constant*, 4> Mask;
for (unsigned i = 0; i != NumSrcElts; ++i) {
llvm::Value *Elt = llvm::ConstantInt::get(llvm::Type::Int32Ty, i);
Elt = Builder.CreateExtractElement(SrcVal, Elt, "tmp");
unsigned InIdx = getAccessedFieldNo(i, Elts);
Mask.push_back(llvm::ConstantInt::get(llvm::Type::Int32Ty, InIdx));
}
llvm::Value *MaskV = llvm::ConstantVector::get(&Mask[0], Mask.size());
Vec = Builder.CreateShuffleVector(SrcVal,
llvm::UndefValue::get(Vec->getType()),
MaskV, "tmp");
}
else if (NumDstElts > NumSrcElts) {
// Extended the source vector to the same length and then shuffle it
// into the destination.
// FIXME: since we're shuffling with undef, can we just use the indices
// into that? This could be simpler.
llvm::SmallVector<llvm::Constant*, 4> ExtMask;
unsigned i;
for (i = 0; i != NumSrcElts; ++i)
ExtMask.push_back(llvm::ConstantInt::get(llvm::Type::Int32Ty, i));
for (; i != NumDstElts; ++i)
ExtMask.push_back(llvm::UndefValue::get(llvm::Type::Int32Ty));
llvm::Value *ExtMaskV = llvm::ConstantVector::get(&ExtMask[0],
ExtMask.size());
llvm::Value *ExtSrcVal = Builder.CreateShuffleVector(SrcVal,
llvm::UndefValue::get(SrcVal->getType()),
ExtMaskV, "tmp");
// build identity
llvm::SmallVector<llvm::Constant*, 4> Mask;
for (unsigned i = 0; i != NumDstElts; ++i) {
Mask.push_back(llvm::ConstantInt::get(llvm::Type::Int32Ty, i));
}
// modify when what gets shuffled in
for (unsigned i = 0; i != NumSrcElts; ++i) {
unsigned Idx = getAccessedFieldNo(i, Elts);
llvm::Value *OutIdx = llvm::ConstantInt::get(llvm::Type::Int32Ty, Idx);
Vec = Builder.CreateInsertElement(Vec, Elt, OutIdx, "tmp");
Mask[Idx] =llvm::ConstantInt::get(llvm::Type::Int32Ty, i+NumDstElts);
}
llvm::Value *MaskV = llvm::ConstantVector::get(&Mask[0], Mask.size());
Vec = Builder.CreateShuffleVector(Vec, ExtSrcVal, MaskV, "tmp");
}
else {
// We should never shorten the vector
assert(0 && "unexpected shorten vector length");
}
} else {
// If the Src is a scalar (not a vector) it must be updating one element.

24
clang/lib/CodeGen/CGExprScalar.cpp
View File

@ -409,10 +409,26 @@ Value *ScalarExprEmitter::EmitScalarConversion(Value *Src, QualType SrcType,
}
// A scalar can be splatted to an extended vector of the same element type
if (DstType->isExtVectorType() && !isa<VectorType>(SrcType) &&
cast<llvm::VectorType>(DstTy)->getElementType() == Src->getType())
return CGF.EmitVector(&Src, DstType->getAsVectorType()->getNumElements(),
true);
if (DstType->isExtVectorType() && !isa<VectorType>(SrcType)) {
// Cast the scalar to element type
QualType EltTy = DstType->getAsExtVectorType()->getElementType();
llvm::Value *Elt = EmitScalarConversion(Src, SrcType, EltTy);
// Insert the element in element zero of an undef vector
llvm::Value *UnV = llvm::UndefValue::get(DstTy);
llvm::Value *Idx = llvm::ConstantInt::get(llvm::Type::Int32Ty, 0);
UnV = Builder.CreateInsertElement(UnV, Elt, Idx, "tmp");
// Splat the element across to all elements
llvm::SmallVector<llvm::Constant*, 16> Args;
unsigned NumElements = cast<llvm::VectorType>(DstTy)->getNumElements();
for (unsigned i = 0; i < NumElements; i++)
Args.push_back(llvm::ConstantInt::get(llvm::Type::Int32Ty, 0));
llvm::Constant *Mask = llvm::ConstantVector::get(&Args[0], NumElements);
llvm::Value *Yay = Builder.CreateShuffleVector(UnV, UnV, Mask, "splat");
return Yay;
}
// Allow bitcast from vector to integer/fp of the same size.
if (isa<llvm::VectorType>(Src->getType()) ||

15
clang/test/CodeGen/ext-vector-shuffle.c Normal file
View File

@ -0,0 +1,15 @@
// RUN: clang %s -emit-llvm -o - | not grep 'extractelement'
// RUN: clang %s -emit-llvm -o - | not grep 'insertelement'
// RUN: clang %s -emit-llvm -o - | grep 'shufflevector'
typedef __attribute__(( ext_vector_type(2) )) float float2;
typedef __attribute__(( ext_vector_type(4) )) float float4;
float2 test1(float4 V) {
return V.xy + V.wz;
}
float4 test2(float4 V) {
float2 W = V.ww;
return W.xyxy + W.yxyx;
}