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

[X86] Replace __builtin_ia32_vbroadcastf128_pd256 and __builtin_ia32_vbroadcastf128_ps256 with an unaligned load intrinsics and a __builtin_shufflevector call. 

llvm-svn: 333853
This commit is contained in:
Craig Topper 2018-06-03 19:42:59 +00:00
parent d6155ff002
commit 6fb26f93ef
4 changed files with 6 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clang/include/clang/Basic/BuiltinsX86.def
View File

@ -510,8 +510,6 @@ TARGET_BUILTIN(__builtin_ia32_movmskpd256, "iV4d", "nc", "avx")
TARGET_BUILTIN(__builtin_ia32_movmskps256, "iV8f", "nc", "avx")
TARGET_BUILTIN(__builtin_ia32_vzeroall, "v", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_vzeroupper, "v", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_vbroadcastf128_pd256, "V4dV2dC*", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_vbroadcastf128_ps256, "V8fV4fC*", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_lddqu256, "V32ccC*", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_maskloadpd, "V2dV2dC*V2LLi", "n", "avx")
TARGET_BUILTIN(__builtin_ia32_maskloadps, "V4fV4fC*V4i", "n", "avx")

26
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -8300,26 +8300,6 @@ static Value *EmitX86MaskLogic(CodeGenFunction &CGF, Instruction::BinaryOps Opc,
CGF.Builder.getIntNTy(std::max(NumElts, 8U)));
}
static Value *EmitX86SubVectorBroadcast(CodeGenFunction &CGF,
ArrayRef<Value *> Ops,
llvm::Type *DstTy,
unsigned SrcSizeInBits,
unsigned Align) {
// Load the subvector.
Value *SubVec = CGF.Builder.CreateAlignedLoad(Ops[0], Align);
// Create broadcast mask.
unsigned NumDstElts = DstTy->getVectorNumElements();
unsigned NumSrcElts = SrcSizeInBits / DstTy->getScalarSizeInBits();
SmallVector<uint32_t, 8> Mask;
for (unsigned i = 0; i != NumDstElts; i += NumSrcElts)
for (unsigned j = 0; j != NumSrcElts; ++j)
Mask.push_back(j);
return CGF.Builder.CreateShuffleVector(SubVec, SubVec, Mask, "subvecbcst");
}
static Value *EmitX86Select(CodeGenFunction &CGF,
Value *Mask, Value *Op0, Value *Op1) {
@ -8959,12 +8939,6 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_movdqa64load512_mask:
return EmitX86MaskedLoad(*this, Ops, 64);
case X86::BI__builtin_ia32_vbroadcastf128_pd256:
case X86::BI__builtin_ia32_vbroadcastf128_ps256: {
llvm::Type *DstTy = ConvertType(E->getType());
return EmitX86SubVectorBroadcast(*this, Ops, DstTy, 128, 1);
}
case X86::BI__builtin_ia32_storehps:
case X86::BI__builtin_ia32_storelps: {
llvm::Type *PtrTy = llvm::PointerType::getUnqual(Int64Ty);

8
clang/lib/Headers/avxintrin.h
View File

@ -3111,7 +3111,9 @@ _mm256_broadcast_ss(float const *__a)
static __inline __m256d __DEFAULT_FN_ATTRS
_mm256_broadcast_pd(__m128d const *__a)
{
return (__m256d)__builtin_ia32_vbroadcastf128_pd256((__v2df const *)__a);
__m128d __b = _mm_loadu_pd((const double *)__a);
return (__m256d)__builtin_shufflevector((__v2df)__b, (__v2df)__b,
0, 1, 0, 1);
}
/// Loads the data from a 128-bit vector of [4 x float] from the
@ -3129,7 +3131,9 @@ _mm256_broadcast_pd(__m128d const *__a)
static __inline __m256 __DEFAULT_FN_ATTRS
_mm256_broadcast_ps(__m128 const *__a)
{
return (__m256)__builtin_ia32_vbroadcastf128_ps256((__v4sf const *)__a);
__m128 __b = _mm_loadu_ps((const float *)__a);
return (__m256)__builtin_shufflevector((__v4sf)__b, (__v4sf)__b,
0, 1, 2, 3, 0, 1, 2, 3);
}
/* SIMD load ops */

2
clang/test/CodeGen/builtins-x86.c
View File

@ -466,8 +466,6 @@ void f0() {
tmp_i = __builtin_ia32_movmskps256(tmp_V8f);
__builtin_ia32_vzeroall();
__builtin_ia32_vzeroupper();
tmp_V4d = __builtin_ia32_vbroadcastf128_pd256(tmp_V2dCp);
tmp_V8f = __builtin_ia32_vbroadcastf128_ps256(tmp_V4fCp);
tmp_V32c = __builtin_ia32_lddqu256(tmp_cCp);
tmp_V2d = __builtin_ia32_maskloadpd(tmp_V2dCp, tmp_V2LLi);
tmp_V4f = __builtin_ia32_maskloadps(tmp_V4fCp, tmp_V4i);