forked from OSchip/llvm-project
91 lines
4.2 KiB
TableGen
91 lines
4.2 KiB
TableGen
//=- AMDGPUCombine.td - Define AMDGPU Combine Rules ----------*- tablegen -*-=//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "llvm/Target/GlobalISel/Combine.td"
|
|
|
|
// TODO: This really belongs after legalization after scalarization.
|
|
// TODO: GICombineRules should accept subtarget predicates
|
|
|
|
def fmin_fmax_legacy_matchdata : GIDefMatchData<"AMDGPUPostLegalizerCombinerHelper::FMinFMaxLegacyInfo">;
|
|
|
|
def fcmp_select_to_fmin_fmax_legacy : GICombineRule<
|
|
(defs root:$select, fmin_fmax_legacy_matchdata:$matchinfo),
|
|
(match (wip_match_opcode G_SELECT):$select,
|
|
[{ return PostLegalizerHelper.matchFMinFMaxLegacy(*${select}, ${matchinfo}); }]),
|
|
(apply [{ PostLegalizerHelper.applySelectFCmpToFMinToFMaxLegacy(*${select}, ${matchinfo}); }])>;
|
|
|
|
|
|
def uchar_to_float : GICombineRule<
|
|
(defs root:$itofp),
|
|
(match (wip_match_opcode G_UITOFP, G_SITOFP):$itofp,
|
|
[{ return PostLegalizerHelper.matchUCharToFloat(*${itofp}); }]),
|
|
(apply [{ PostLegalizerHelper.applyUCharToFloat(*${itofp}); }])>;
|
|
|
|
def cvt_f32_ubyteN_matchdata : GIDefMatchData<"AMDGPUPostLegalizerCombinerHelper::CvtF32UByteMatchInfo">;
|
|
|
|
def cvt_f32_ubyteN : GICombineRule<
|
|
(defs root:$cvt_f32_ubyteN, cvt_f32_ubyteN_matchdata:$matchinfo),
|
|
(match (wip_match_opcode G_AMDGPU_CVT_F32_UBYTE0,
|
|
G_AMDGPU_CVT_F32_UBYTE1,
|
|
G_AMDGPU_CVT_F32_UBYTE2,
|
|
G_AMDGPU_CVT_F32_UBYTE3):$cvt_f32_ubyteN,
|
|
[{ return PostLegalizerHelper.matchCvtF32UByteN(*${cvt_f32_ubyteN}, ${matchinfo}); }]),
|
|
(apply [{ PostLegalizerHelper.applyCvtF32UByteN(*${cvt_f32_ubyteN}, ${matchinfo}); }])>;
|
|
|
|
def clamp_i64_to_i16_matchdata : GIDefMatchData<"AMDGPUPreLegalizerCombinerHelper::ClampI64ToI16MatchInfo">;
|
|
|
|
def clamp_i64_to_i16 : GICombineRule<
|
|
(defs root:$clamp_i64_to_i16, clamp_i64_to_i16_matchdata:$matchinfo),
|
|
(match (wip_match_opcode G_TRUNC):$clamp_i64_to_i16,
|
|
[{ return PreLegalizerHelper.matchClampI64ToI16(*${clamp_i64_to_i16}, MRI, *MF, ${matchinfo}); }]),
|
|
(apply [{ PreLegalizerHelper.applyClampI64ToI16(*${clamp_i64_to_i16}, ${matchinfo}); }])>;
|
|
|
|
def med3_matchdata : GIDefMatchData<"AMDGPURegBankCombinerHelper::Med3MatchInfo">;
|
|
|
|
def int_minmax_to_med3 : GICombineRule<
|
|
(defs root:$min_or_max, med3_matchdata:$matchinfo),
|
|
(match (wip_match_opcode G_SMAX,
|
|
G_SMIN,
|
|
G_UMAX,
|
|
G_UMIN):$min_or_max,
|
|
[{ return RegBankHelper.matchIntMinMaxToMed3(*${min_or_max}, ${matchinfo}); }]),
|
|
(apply [{ RegBankHelper.applyMed3(*${min_or_max}, ${matchinfo}); }])>;
|
|
|
|
def remove_fcanonicalize_matchinfo : GIDefMatchData<"Register">;
|
|
|
|
def remove_fcanonicalize : GICombineRule<
|
|
(defs root:$fcanonicalize, remove_fcanonicalize_matchinfo:$matchinfo),
|
|
(match (wip_match_opcode G_FCANONICALIZE):$fcanonicalize,
|
|
[{ return PostLegalizerHelper.matchRemoveFcanonicalize(*${fcanonicalize}, ${matchinfo}); }]),
|
|
(apply [{ Helper.replaceSingleDefInstWithReg(*${fcanonicalize}, ${matchinfo}); }])>;
|
|
|
|
// Combines which should only apply on SI/VI
|
|
def gfx6gfx7_combines : GICombineGroup<[fcmp_select_to_fmin_fmax_legacy]>;
|
|
|
|
def AMDGPUPreLegalizerCombinerHelper: GICombinerHelper<
|
|
"AMDGPUGenPreLegalizerCombinerHelper", [all_combines, clamp_i64_to_i16]> {
|
|
let DisableRuleOption = "amdgpuprelegalizercombiner-disable-rule";
|
|
let StateClass = "AMDGPUPreLegalizerCombinerHelperState";
|
|
}
|
|
|
|
def AMDGPUPostLegalizerCombinerHelper: GICombinerHelper<
|
|
"AMDGPUGenPostLegalizerCombinerHelper",
|
|
[all_combines, gfx6gfx7_combines,
|
|
uchar_to_float, cvt_f32_ubyteN, remove_fcanonicalize]> {
|
|
let DisableRuleOption = "amdgpupostlegalizercombiner-disable-rule";
|
|
let StateClass = "AMDGPUPostLegalizerCombinerHelperState";
|
|
let AdditionalArguments = [];
|
|
}
|
|
|
|
def AMDGPURegBankCombinerHelper : GICombinerHelper<
|
|
"AMDGPUGenRegBankCombinerHelper", [zext_trunc_fold, int_minmax_to_med3, ptr_add_immed_chain]> {
|
|
let DisableRuleOption = "amdgpuregbankcombiner-disable-rule";
|
|
let StateClass = "AMDGPURegBankCombinerHelperState";
|
|
let AdditionalArguments = [];
|
|
}
|