llvm-project/llvm/lib/Target/AMDGPU/AMDGPUFeatures.td

61 lines
1.8 KiB
TableGen

//===-- AMDGPUFeatures.td - AMDGPU Feature Definitions -----*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
def FeatureFP64 : SubtargetFeature<"fp64",
"FP64",
"true",
"Enable double precision operations"
>;
def FeatureFMA : SubtargetFeature<"fmaf",
"FMA",
"true",
"Enable single precision FMA (not as fast as mul+add, but fused)"
>;
class SubtargetFeatureLocalMemorySize <int Value> : SubtargetFeature<
"localmemorysize"#Value,
"LocalMemorySize",
!cast<string>(Value),
"The size of local memory in bytes"
>;
def FeatureLocalMemorySize0 : SubtargetFeatureLocalMemorySize<0>;
def FeatureLocalMemorySize32768 : SubtargetFeatureLocalMemorySize<32768>;
def FeatureLocalMemorySize65536 : SubtargetFeatureLocalMemorySize<65536>;
class SubtargetFeatureWavefrontSize <int Value> : SubtargetFeature<
"wavefrontsize"#Value,
"WavefrontSize",
!cast<string>(Value),
"The number of threads per wavefront"
>;
def FeatureWavefrontSize16 : SubtargetFeatureWavefrontSize<16>;
def FeatureWavefrontSize32 : SubtargetFeatureWavefrontSize<32>;
def FeatureWavefrontSize64 : SubtargetFeatureWavefrontSize<64>;
class SubtargetFeatureGeneration <string Value, string Subtarget,
list<SubtargetFeature> Implies> :
SubtargetFeature <Value, "Gen", Subtarget#"::"#Value,
Value#" GPU generation", Implies>;
def FeatureDX10Clamp : SubtargetFeature<"dx10-clamp",
"DX10Clamp",
"true",
"clamp modifier clamps NaNs to 0.0"
>;
def FeaturePromoteAlloca : SubtargetFeature <"promote-alloca",
"EnablePromoteAlloca",
"true",
"Enable promote alloca pass"
>;