diff options
| author | Craig Topper <craig.topper@gmail.com> | 2016-06-15 14:06:34 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@gmail.com> | 2016-06-15 14:06:34 +0000 |
| commit | a54c21e742ac9fffe83c0cfec4fa164f28599880 (patch) | |
| tree | 6e41a90ea308397c89bdeb12d50cfb98e7ed4dac /clang/lib/CodeGen/CGBuiltin.cpp | |
| parent | 48b54c95ec752e29d71d1dc7c07082b7bb390bc3 (diff) | |
| download | bcm5719-llvm-a54c21e742ac9fffe83c0cfec4fa164f28599880.tar.gz bcm5719-llvm-a54c21e742ac9fffe83c0cfec4fa164f28599880.zip | |
[AVX512] Use native IR for mask pcmpeq/pcmpgt intrinsics.
llvm-svn: 272787
Diffstat (limited to 'clang/lib/CodeGen/CGBuiltin.cpp')
| -rw-r--r-- | clang/lib/CodeGen/CGBuiltin.cpp | 49 |
1 files changed, 49 insertions, 0 deletions
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index 298707874f3..462f1a7d6c5 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -6414,6 +6414,29 @@ static Value *EmitX86Select(CodeGenFunction &CGF, return CGF.Builder.CreateSelect(Mask, Op0, Op1); } +static Value *EmitX86MaskedCompare(CodeGenFunction &CGF, CmpInst::Predicate P, + SmallVectorImpl<Value *> &Ops) { + unsigned NumElts = Ops[0]->getType()->getVectorNumElements(); + Value *Cmp = CGF.Builder.CreateICmp(P, Ops[0], Ops[1]); + + const auto *C = dyn_cast<Constant>(Ops[2]); + if (!C || !C->isAllOnesValue()) + Cmp = CGF.Builder.CreateAnd(Cmp, getMaskVecValue(CGF, Ops[2], NumElts)); + + if (NumElts < 8) { + uint32_t Indices[8]; + for (unsigned i = 0; i != NumElts; ++i) + Indices[i] = i; + for (unsigned i = NumElts; i != 8; ++i) + Indices[i] = NumElts; + Cmp = CGF.Builder.CreateShuffleVector(Cmp, UndefValue::get(Cmp->getType()), + Indices); + } + return CGF.Builder.CreateBitCast(Cmp, + IntegerType::get(CGF.getLLVMContext(), + std::max(NumElts, 8U))); +} + Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID, const CallExpr *E) { if (BuiltinID == X86::BI__builtin_ms_va_start || @@ -6807,6 +6830,32 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID, case X86::BI__builtin_ia32_selectpd_256: case X86::BI__builtin_ia32_selectpd_512: return EmitX86Select(*this, Ops[0], Ops[1], Ops[2]); + case X86::BI__builtin_ia32_pcmpeqb128_mask: + case X86::BI__builtin_ia32_pcmpeqb256_mask: + case X86::BI__builtin_ia32_pcmpeqb512_mask: + case X86::BI__builtin_ia32_pcmpeqw128_mask: + case X86::BI__builtin_ia32_pcmpeqw256_mask: + case X86::BI__builtin_ia32_pcmpeqw512_mask: + case X86::BI__builtin_ia32_pcmpeqd128_mask: + case X86::BI__builtin_ia32_pcmpeqd256_mask: + case X86::BI__builtin_ia32_pcmpeqd512_mask: + case X86::BI__builtin_ia32_pcmpeqq128_mask: + case X86::BI__builtin_ia32_pcmpeqq256_mask: + case X86::BI__builtin_ia32_pcmpeqq512_mask: + return EmitX86MaskedCompare(*this, ICmpInst::ICMP_EQ, Ops); + case X86::BI__builtin_ia32_pcmpgtb128_mask: + case X86::BI__builtin_ia32_pcmpgtb256_mask: + case X86::BI__builtin_ia32_pcmpgtb512_mask: + case X86::BI__builtin_ia32_pcmpgtw128_mask: + case X86::BI__builtin_ia32_pcmpgtw256_mask: + case X86::BI__builtin_ia32_pcmpgtw512_mask: + case X86::BI__builtin_ia32_pcmpgtd128_mask: + case X86::BI__builtin_ia32_pcmpgtd256_mask: + case X86::BI__builtin_ia32_pcmpgtd512_mask: + case X86::BI__builtin_ia32_pcmpgtq128_mask: + case X86::BI__builtin_ia32_pcmpgtq256_mask: + case X86::BI__builtin_ia32_pcmpgtq512_mask: + return EmitX86MaskedCompare(*this, ICmpInst::ICMP_SGT, Ops); // 3DNow! case X86::BI__builtin_ia32_pswapdsf: case X86::BI__builtin_ia32_pswapdsi: { |
