File: AMDGPUCombine.td

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-11
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,418,840 kB
  • sloc: cpp: 5,290,826; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,898; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,913; xml: 953; cs: 573; fortran: 539
file content (90 lines) | stat: -rw-r--r-- 4,316 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
//=- 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]> {
  let DisableRuleOption = "amdgpuregbankcombiner-disable-rule";
  let StateClass = "AMDGPURegBankCombinerHelperState";
  let AdditionalArguments = [];
}