Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fmad.s32.mir
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

214 lines
8.0 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX6 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX10 %s
---
name: fmad_f32
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAC_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAC_F32_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAC_F32_e64_]]
; GFX10-LABEL: name: fmad_f32
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAC_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAC_F32_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAC_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FMAD %0, %1, %2
S_ENDPGM 0, implicit %3
...
---
name: fmad_f32_fneg_src0
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32_fneg_src0
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 1, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
; GFX10-LABEL: name: fmad_f32_fneg_src0
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 1, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FNEG %0
%4:vgpr(s32) = G_FMAD %3, %1, %2
S_ENDPGM 0, implicit %4
...
---
name: fmad_f32_fneg_src1
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32_fneg_src1
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 1, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
; GFX10-LABEL: name: fmad_f32_fneg_src1
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 1, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FNEG %1
%4:vgpr(s32) = G_FMAD %0, %3, %2
S_ENDPGM 0, implicit %4
...
---
name: fmad_f32_fneg_src2
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32_fneg_src2
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 1, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
; GFX10-LABEL: name: fmad_f32_fneg_src2
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 1, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FNEG %2
%4:vgpr(s32) = G_FMAD %0, %1, %3
S_ENDPGM 0, implicit %4
...
---
name: fmad_f32_fabs_src2
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32_fabs_src2
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 2, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
; GFX10-LABEL: name: fmad_f32_fabs_src2
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 2, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FABS %2
%4:vgpr(s32) = G_FMAD %0, %1, %3
S_ENDPGM 0, implicit %4
...
---
name: fmad_f32_copy_fneg_src2
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: fmad_f32_copy_fneg_src2
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-NEXT: {{ $}}
; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 1, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX6-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
; GFX10-LABEL: name: fmad_f32_copy_fneg_src2
; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
; 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]+]]:vgpr_32 = COPY $vgpr2
; GFX10-NEXT: [[V_MAD_F32_e64_:%[0-9]+]]:vgpr_32 = V_MAD_F32_e64 0, [[COPY]], 0, [[COPY1]], 1, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_F32_e64_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FNEG %2
%4:vgpr(s32) = COPY %3
%5:vgpr(s32) = G_FMAD %0, %1, %4
S_ENDPGM 0, implicit %5
...