derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
287 lines
10 KiB
YAML
287 lines
10 KiB
YAML
# RUN: llc -mtriple=amdgcn -run-pass peephole-opt -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
|
|
# RUN: llc -mtriple=amdgcn -passes peephole-opt -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
|
|
...
|
|
# GCN-LABEL: name: no_fold_imm_madak_mac_clamp_f32
|
|
# GCN: %23:vgpr_32 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
# GCN-NEXT: %24:vgpr_32 = nofpexcept V_MAC_F32_e64 0, killed %19, 0, killed %21, 0, %23, 1, 0, implicit $mode, implicit $exec
|
|
|
|
name: no_fold_imm_madak_mac_clamp_f32
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: sgpr_64 }
|
|
- { id: 1, class: sreg_32_xm0 }
|
|
- { id: 2, class: sgpr_32 }
|
|
- { id: 3, class: vgpr_32 }
|
|
- { id: 4, class: sreg_64_xexec }
|
|
- { id: 5, class: sreg_64_xexec }
|
|
- { id: 6, class: sreg_64_xexec }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32 }
|
|
- { id: 9, class: sreg_32_xm0 }
|
|
- { id: 10, class: sreg_64 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sreg_32_xm0 }
|
|
- { id: 13, class: sgpr_64 }
|
|
- { id: 14, class: sgpr_128 }
|
|
- { id: 15, class: sreg_32_xm0 }
|
|
- { id: 16, class: sreg_64 }
|
|
- { id: 17, class: sgpr_128 }
|
|
- { id: 18, class: sgpr_128 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: vgpr_32 }
|
|
- { id: 22, class: vreg_64 }
|
|
- { id: 23, class: vgpr_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vgpr_32 }
|
|
- { id: 26, class: vreg_64 }
|
|
- { id: 27, class: vgpr_32 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, class: vreg_64 }
|
|
liveins:
|
|
- { reg: '$sgpr0_sgpr1', virtual-reg: '%0' }
|
|
- { reg: '$vgpr0', virtual-reg: '%3' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1, $vgpr0
|
|
|
|
%3 = COPY $vgpr0
|
|
%0 = COPY $sgpr0_sgpr1
|
|
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0
|
|
%6 = S_LOAD_DWORDX2_IMM %0, 13, 0
|
|
%27 = V_ASHRREV_I32_e32 31, %3, implicit $exec
|
|
%28 = REG_SEQUENCE %3, 1, %27, 2
|
|
%11 = S_MOV_B32 61440
|
|
%12 = S_MOV_B32 0
|
|
%13 = REG_SEQUENCE killed %12, 1, killed %11, 2
|
|
%14 = REG_SEQUENCE killed %5, 17, %13, 18
|
|
%15 = S_MOV_B32 2
|
|
%29 = V_LSHL_B64_e64 killed %28, killed %15, implicit $exec
|
|
%17 = REG_SEQUENCE killed %6, 17, %13, 18
|
|
%18 = REG_SEQUENCE killed %4, 17, %13, 18
|
|
%20 = COPY %29
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %20, killed %14, 0, 0, 0, 0, implicit $exec
|
|
%22 = COPY %29
|
|
%21 = BUFFER_LOAD_DWORD_ADDR64 %22, killed %17, 0, 0, 0, 0, implicit $exec
|
|
%23 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
%24 = nofpexcept V_MAC_F32_e64 0, killed %19, 0, killed %21, 0, %23, 1, 0, implicit $mode, implicit $exec
|
|
%26 = COPY %29
|
|
BUFFER_STORE_DWORD_ADDR64 killed %24, %26, killed %18, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: no_fold_imm_madak_mac_omod_f32
|
|
# GCN: %23:vgpr_32 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
# GCN: %24:vgpr_32 = nofpexcept V_MAC_F32_e64 0, killed %19, 0, killed %21, 0, %23, 0, 2, implicit $mode, implicit $exec
|
|
|
|
name: no_fold_imm_madak_mac_omod_f32
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: sgpr_64 }
|
|
- { id: 1, class: sreg_32_xm0 }
|
|
- { id: 2, class: sgpr_32 }
|
|
- { id: 3, class: vgpr_32 }
|
|
- { id: 4, class: sreg_64_xexec }
|
|
- { id: 5, class: sreg_64_xexec }
|
|
- { id: 6, class: sreg_64_xexec }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32 }
|
|
- { id: 9, class: sreg_32_xm0 }
|
|
- { id: 10, class: sreg_64 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sreg_32_xm0 }
|
|
- { id: 13, class: sgpr_64 }
|
|
- { id: 14, class: sgpr_128 }
|
|
- { id: 15, class: sreg_32_xm0 }
|
|
- { id: 16, class: sreg_64 }
|
|
- { id: 17, class: sgpr_128 }
|
|
- { id: 18, class: sgpr_128 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: vgpr_32 }
|
|
- { id: 22, class: vreg_64 }
|
|
- { id: 23, class: vgpr_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vgpr_32 }
|
|
- { id: 26, class: vreg_64 }
|
|
- { id: 27, class: vgpr_32 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, class: vreg_64 }
|
|
liveins:
|
|
- { reg: '$sgpr0_sgpr1', virtual-reg: '%0' }
|
|
- { reg: '$vgpr0', virtual-reg: '%3' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1, $vgpr0
|
|
|
|
%3 = COPY $vgpr0
|
|
%0 = COPY $sgpr0_sgpr1
|
|
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0
|
|
%6 = S_LOAD_DWORDX2_IMM %0, 13, 0
|
|
%27 = V_ASHRREV_I32_e32 31, %3, implicit $exec
|
|
%28 = REG_SEQUENCE %3, 1, %27, 2
|
|
%11 = S_MOV_B32 61440
|
|
%12 = S_MOV_B32 0
|
|
%13 = REG_SEQUENCE killed %12, 1, killed %11, 2
|
|
%14 = REG_SEQUENCE killed %5, 17, %13, 18
|
|
%15 = S_MOV_B32 2
|
|
%29 = V_LSHL_B64_e64 killed %28, killed %15, implicit $exec
|
|
%17 = REG_SEQUENCE killed %6, 17, %13, 18
|
|
%18 = REG_SEQUENCE killed %4, 17, %13, 18
|
|
%20 = COPY %29
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %20, killed %14, 0, 0, 0, 0, implicit $exec
|
|
%22 = COPY %29
|
|
%21 = BUFFER_LOAD_DWORD_ADDR64 %22, killed %17, 0, 0, 0, 0, implicit $exec
|
|
%23 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
%24 = nofpexcept V_MAC_F32_e64 0, killed %19, 0, killed %21, 0, %23, 0, 2, implicit $mode, implicit $exec
|
|
%26 = COPY %29
|
|
BUFFER_STORE_DWORD_ADDR64 killed %24, %26, killed %18, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
---
|
|
# GCN: name: no_fold_imm_madak_mad_clamp_f32
|
|
# GCN: %23:vgpr_32 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
# GCN: %24:vgpr_32 = nofpexcept V_MAD_F32_e64 0, killed %19, 0, killed %21, 0, %23, 1, 0, implicit $mode, implicit $exec
|
|
|
|
name: no_fold_imm_madak_mad_clamp_f32
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: sgpr_64 }
|
|
- { id: 1, class: sreg_32_xm0 }
|
|
- { id: 2, class: sgpr_32 }
|
|
- { id: 3, class: vgpr_32 }
|
|
- { id: 4, class: sreg_64_xexec }
|
|
- { id: 5, class: sreg_64_xexec }
|
|
- { id: 6, class: sreg_64_xexec }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32 }
|
|
- { id: 9, class: sreg_32_xm0 }
|
|
- { id: 10, class: sreg_64 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sreg_32_xm0 }
|
|
- { id: 13, class: sgpr_64 }
|
|
- { id: 14, class: sgpr_128 }
|
|
- { id: 15, class: sreg_32_xm0 }
|
|
- { id: 16, class: sreg_64 }
|
|
- { id: 17, class: sgpr_128 }
|
|
- { id: 18, class: sgpr_128 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: vgpr_32 }
|
|
- { id: 22, class: vreg_64 }
|
|
- { id: 23, class: vgpr_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vgpr_32 }
|
|
- { id: 26, class: vreg_64 }
|
|
- { id: 27, class: vgpr_32 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, class: vreg_64 }
|
|
liveins:
|
|
- { reg: '$sgpr0_sgpr1', virtual-reg: '%0' }
|
|
- { reg: '$vgpr0', virtual-reg: '%3' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1, $vgpr0
|
|
|
|
%3 = COPY $vgpr0
|
|
%0 = COPY $sgpr0_sgpr1
|
|
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0
|
|
%6 = S_LOAD_DWORDX2_IMM %0, 13, 0
|
|
%27 = V_ASHRREV_I32_e32 31, %3, implicit $exec
|
|
%28 = REG_SEQUENCE %3, 1, %27, 2
|
|
%11 = S_MOV_B32 61440
|
|
%12 = S_MOV_B32 0
|
|
%13 = REG_SEQUENCE killed %12, 1, killed %11, 2
|
|
%14 = REG_SEQUENCE killed %5, 17, %13, 18
|
|
%15 = S_MOV_B32 2
|
|
%29 = V_LSHL_B64_e64 killed %28, killed %15, implicit $exec
|
|
%17 = REG_SEQUENCE killed %6, 17, %13, 18
|
|
%18 = REG_SEQUENCE killed %4, 17, %13, 18
|
|
%20 = COPY %29
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %20, killed %14, 0, 0, 0, 0, implicit $exec
|
|
%22 = COPY %29
|
|
%21 = BUFFER_LOAD_DWORD_ADDR64 %22, killed %17, 0, 0, 0, 0, implicit $exec
|
|
%23 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
%24 = nofpexcept V_MAD_F32_e64 0, killed %19, 0, killed %21, 0, %23, 1, 0, implicit $mode, implicit $exec
|
|
%26 = COPY %29
|
|
BUFFER_STORE_DWORD_ADDR64 killed %24, %26, killed %18, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
---
|
|
# GCN: name: no_fold_imm_madak_mad_omod_f32
|
|
# GCN: %23:vgpr_32 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
# GCN: %24:vgpr_32 = nofpexcept V_MAD_F32_e64 0, killed %19, 0, killed %21, 0, %23, 0, 1, implicit $mode, implicit $exec
|
|
|
|
name: no_fold_imm_madak_mad_omod_f32
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: sgpr_64 }
|
|
- { id: 1, class: sreg_32_xm0 }
|
|
- { id: 2, class: sgpr_32 }
|
|
- { id: 3, class: vgpr_32 }
|
|
- { id: 4, class: sreg_64_xexec }
|
|
- { id: 5, class: sreg_64_xexec }
|
|
- { id: 6, class: sreg_64_xexec }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32 }
|
|
- { id: 9, class: sreg_32_xm0 }
|
|
- { id: 10, class: sreg_64 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sreg_32_xm0 }
|
|
- { id: 13, class: sgpr_64 }
|
|
- { id: 14, class: sgpr_128 }
|
|
- { id: 15, class: sreg_32_xm0 }
|
|
- { id: 16, class: sreg_64 }
|
|
- { id: 17, class: sgpr_128 }
|
|
- { id: 18, class: sgpr_128 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: vgpr_32 }
|
|
- { id: 22, class: vreg_64 }
|
|
- { id: 23, class: vgpr_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vgpr_32 }
|
|
- { id: 26, class: vreg_64 }
|
|
- { id: 27, class: vgpr_32 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, class: vreg_64 }
|
|
liveins:
|
|
- { reg: '$sgpr0_sgpr1', virtual-reg: '%0' }
|
|
- { reg: '$vgpr0', virtual-reg: '%3' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1, $vgpr0
|
|
|
|
%3 = COPY $vgpr0
|
|
%0 = COPY $sgpr0_sgpr1
|
|
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0
|
|
%6 = S_LOAD_DWORDX2_IMM %0, 13, 0
|
|
%27 = V_ASHRREV_I32_e32 31, %3, implicit $exec
|
|
%28 = REG_SEQUENCE %3, 1, %27, 2
|
|
%11 = S_MOV_B32 61440
|
|
%12 = S_MOV_B32 0
|
|
%13 = REG_SEQUENCE killed %12, 1, killed %11, 2
|
|
%14 = REG_SEQUENCE killed %5, 17, %13, 18
|
|
%15 = S_MOV_B32 2
|
|
%29 = V_LSHL_B64_e64 killed %28, killed %15, implicit $exec
|
|
%17 = REG_SEQUENCE killed %6, 17, %13, 18
|
|
%18 = REG_SEQUENCE killed %4, 17, %13, 18
|
|
%20 = COPY %29
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %20, killed %14, 0, 0, 0, 0, implicit $exec
|
|
%22 = COPY %29
|
|
%21 = BUFFER_LOAD_DWORD_ADDR64 %22, killed %17, 0, 0, 0, 0, implicit $exec
|
|
%23 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
%24 = nofpexcept V_MAD_F32_e64 0, killed %19, 0, killed %21, 0, %23, 0, 1, implicit $mode, implicit $exec
|
|
%26 = COPY %29
|
|
BUFFER_STORE_DWORD_ADDR64 killed %24, %26, killed %18, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
|
|
...
|