File: inst-select-mad_64_32.mir

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (69 lines) | stat: -rw-r--r-- 3,582 bytes parent folder | download | duplicates (5)
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
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx1030 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX10 %s
# RUN: llc -march=amdgcn -mcpu=gfx1100 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX11 %s

---
name: mad_u64_u32_vvv
legalized: true
regBankSelected: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-LABEL: name: mad_u64_u32_vvv
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX10-NEXT: [[V_MAD_U64_U32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_e64_]], implicit [[V_MAD_U64_U32_e64_1]]
    ; GFX11-LABEL: name: mad_u64_u32_vvv
    ; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX11-NEXT: {{  $}}
    ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX11-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX11-NEXT: [[V_MAD_U64_U32_gfx11_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_gfx11_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_gfx11_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_gfx11_e64_]], implicit [[V_MAD_U64_U32_gfx11_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = COPY $vgpr3
    %4:vgpr(s64) = G_MERGE_VALUES %2, %3
    %5:vgpr(s64), %6:vcc(s1) = G_AMDGPU_MAD_U64_U32 %0, %1, %3
    S_ENDPGM 0, implicit %5, implicit %6
...

---
name: mad_i64_i32_vvv
legalized: true
regBankSelected: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-LABEL: name: mad_i64_i32_vvv
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX10-NEXT: [[V_MAD_I64_I32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_e64_]], implicit [[V_MAD_I64_I32_e64_1]]
    ; GFX11-LABEL: name: mad_i64_i32_vvv
    ; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX11-NEXT: {{  $}}
    ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX11-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX11-NEXT: [[V_MAD_I64_I32_gfx11_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_gfx11_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_gfx11_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_gfx11_e64_]], implicit [[V_MAD_I64_I32_gfx11_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = COPY $vgpr3
    %4:vgpr(s64) = G_MERGE_VALUES %2, %3
    %5:vgpr(s64), %6:vcc(s1) = G_AMDGPU_MAD_I64_I32 %0, %1, %3
    S_ENDPGM 0, implicit %5, implicit %6
...