https://github.com/llvm/llvm-project/pull/90201 made some fixes for gfx12 image_msaa_load waitcnt insertion. That fix might break in some situations for pre-gfx12 - this fixes that by explitly checking for VSAMPLE which always requires a s_wait_samplecnt and leaves the previous logic intact for non-gfx12.
25 lines
2.0 KiB
YAML
25 lines
2.0 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX11 %s
|
|
|
|
---
|
|
name: sample_load_msaa
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
|
|
|
|
; GFX11-LABEL: name: sample_load_msaa
|
|
; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: S_WAITCNT 0
|
|
; GFX11-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V1_gfx11 killed renamable $vgpr0, renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, killed renamable $sgpr8_sgpr9_sgpr10_sgpr11, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
|
|
; GFX11-NEXT: S_WAITCNT 1015
|
|
; GFX11-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_MSAA_LOAD_V4_V2_gfx11 killed renamable $vgpr4_vgpr5, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 4, 7, -1, 0, 0, -1, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
|
|
; GFX11-NEXT: S_WAITCNT 1015
|
|
; GFX11-NEXT: SI_RETURN_TO_EPILOG killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3
|
|
renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V1_gfx11 killed renamable $vgpr0, renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, killed renamable $sgpr8_sgpr9_sgpr10_sgpr11, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
|
|
renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_MSAA_LOAD_V4_V2_gfx11 killed renamable $vgpr4_vgpr5, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 4, 7, -1, 0, 0, -1, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
|
|
SI_RETURN_TO_EPILOG killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3
|
|
|
|
...
|