diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-05-26 18:55:19 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-05-26 18:55:19 +0000 |
| commit | 51eddb87495e1fbcbcbe6bb2c6213a609d038491 (patch) | |
| tree | 8d3fac88f189703240f423fe437ef0303fdda1dd /llvm/lib/IR/AutoUpgrade.cpp | |
| parent | 02d4ff44986c03c96198aea9bbb17d4b72a4fb9f (diff) | |
| download | bcm5719-llvm-51eddb87495e1fbcbcbe6bb2c6213a609d038491.tar.gz bcm5719-llvm-51eddb87495e1fbcbcbe6bb2c6213a609d038491.zip | |
[X86] Remove masking from avx512ifma intrinsics. Use a select instead.
This allows us to avoid having mask and maskz variant. Reducing from 12 intrinsics to 6.
llvm-svn: 333346
Diffstat (limited to 'llvm/lib/IR/AutoUpgrade.cpp')
| -rw-r--r-- | llvm/lib/IR/AutoUpgrade.cpp | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp index ba2f3fa9248..bd4638f147a 100644 --- a/llvm/lib/IR/AutoUpgrade.cpp +++ b/llvm/lib/IR/AutoUpgrade.cpp @@ -265,6 +265,8 @@ static bool ShouldUpgradeX86Intrinsic(Function *F, StringRef Name) { Name.startswith("avx512.mask.lzcnt.") || // Added in 5.0 Name.startswith("avx512.mask.pternlog.") || // Added in 7.0 Name.startswith("avx512.maskz.pternlog.") || // Added in 7.0 + Name.startswith("avx512.mask.vpmadd52") || // Added in 7.0 + Name.startswith("avx512.maskz.vpmadd52") || // Added in 7.0 Name == "sse.cvtsi2ss" || // Added in 7.0 Name == "sse.cvtsi642ss" || // Added in 7.0 Name == "sse2.cvtsi2sd" || // Added in 7.0 @@ -2569,6 +2571,34 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) { Value *PassThru = ZeroMask ? ConstantAggregateZero::get(CI->getType()) : CI->getArgOperand(0); Rep = EmitX86Select(Builder, CI->getArgOperand(4), Rep, PassThru); + } else if (IsX86 && (Name.startswith("avx512.mask.vpmadd52") || + Name.startswith("avx512.maskz.vpmadd52"))) { + bool ZeroMask = Name[11] == 'z'; + bool High = Name[20] == 'h' || Name[21] == 'h'; + unsigned VecWidth = CI->getType()->getPrimitiveSizeInBits(); + Intrinsic::ID IID; + if (VecWidth == 128 && !High) + IID = Intrinsic::x86_avx512_vpmadd52l_uq_128; + else if (VecWidth == 256 && !High) + IID = Intrinsic::x86_avx512_vpmadd52l_uq_256; + else if (VecWidth == 512 && !High) + IID = Intrinsic::x86_avx512_vpmadd52l_uq_512; + else if (VecWidth == 128 && High) + IID = Intrinsic::x86_avx512_vpmadd52h_uq_128; + else if (VecWidth == 256 && High) + IID = Intrinsic::x86_avx512_vpmadd52h_uq_256; + else if (VecWidth == 512 && High) + IID = Intrinsic::x86_avx512_vpmadd52h_uq_512; + else + llvm_unreachable("Unexpected intrinsic"); + + Value *Args[] = { CI->getArgOperand(0) , CI->getArgOperand(1), + CI->getArgOperand(2) }; + Rep = Builder.CreateCall(Intrinsic::getDeclaration(CI->getModule(), IID), + Args); + Value *PassThru = ZeroMask ? ConstantAggregateZero::get(CI->getType()) + : CI->getArgOperand(0); + Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep, PassThru); } else if (IsX86 && Name.startswith("avx512.mask.") && upgradeAVX512MaskToSelect(Name, Builder, *CI, Rep)) { // Rep will be updated by the call in the condition. |
