Files
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

196 lines
8.9 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX10 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX11 %s
---
name: test_waitcnt_preexisting_vscnt_unmodified
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-LABEL: name: test_waitcnt_preexisting_vscnt_unmodified
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX10-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX10-NEXT: S_BARRIER
; GFX10-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX10-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: test_waitcnt_preexisting_vscnt_unmodified
; GFX11: liveins: $vgpr0_vgpr1, $vgpr2
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX11-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX11-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX11-NEXT: S_BARRIER
; GFX11-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX11-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0
GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
S_WAITCNT_VSCNT_soft undef $sgpr_null, 0
S_BARRIER
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
---
name: test_waitcnt_preexisting_vscnt_needs_vscnt
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-LABEL: name: test_waitcnt_preexisting_vscnt_needs_vscnt
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX10-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 1
; GFX10-NEXT: S_BARRIER
; GFX10-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX10-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: test_waitcnt_preexisting_vscnt_needs_vscnt
; GFX11: liveins: $vgpr0_vgpr1, $vgpr2
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX11-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX11-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 1
; GFX11-NEXT: S_BARRIER
; GFX11-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX11-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0
GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
S_WAITCNT_VSCNT_soft undef $sgpr_null, 1
S_BARRIER
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
---
name: test_waitcnt_preexisting_vscnt_with_other_waitcnt
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-LABEL: name: test_waitcnt_preexisting_vscnt_with_other_waitcnt
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX10-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX10-NEXT: S_BARRIER
; GFX10-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX10-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: test_waitcnt_preexisting_vscnt_with_other_waitcnt
; GFX11: liveins: $vgpr0_vgpr1, $vgpr2
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX11-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX11-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX11-NEXT: S_BARRIER
; GFX11-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX11-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0
GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
S_WAITCNT_soft 112
S_WAITCNT_VSCNT_soft undef $sgpr_null, 0
S_BARRIER
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
---
name: test_waitcnt_preexisting_vscnt_combined
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-LABEL: name: test_waitcnt_preexisting_vscnt_combined
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX10-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX10-NEXT: S_BARRIER
; GFX10-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX10-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: test_waitcnt_preexisting_vscnt_combined
; GFX11: liveins: $vgpr0_vgpr1, $vgpr2
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX11-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX11-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
; GFX11-NEXT: S_BARRIER
; GFX11-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX11-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0
GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
S_WAITCNT_VSCNT_soft undef $sgpr_null, 0
S_WAITCNT_VSCNT_soft undef $sgpr_null, 1
S_WAITCNT_VSCNT_soft undef $sgpr_null, 2
S_BARRIER
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
---
name: test_waitcnt_preexisting_vscnt_combined_both_types
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-LABEL: name: test_waitcnt_preexisting_vscnt_combined_both_types
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX10-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 1
; GFX10-NEXT: S_BARRIER
; GFX10-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX10-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX10-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: test_waitcnt_preexisting_vscnt_combined_both_types
; GFX11: liveins: $vgpr0_vgpr1, $vgpr2
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
; GFX11-NEXT: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
; GFX11-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 1
; GFX11-NEXT: S_BARRIER
; GFX11-NEXT: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_WAITCNT .Vmcnt_0_Lgkmcnt_0
; GFX11-NEXT: FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0
GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
S_WAITCNT_soft 0
S_WAITCNT_VSCNT_soft undef $sgpr_null, 1
S_WAITCNT_soft 0
S_WAITCNT_VSCNT_soft undef $sgpr_null, 2
S_WAITCNT_soft 0
S_BARRIER
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_STORE_DWORD $vgpr0_vgpr1, $vgpr0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...