[AMDGPU] Add pre-commit tests for PR90710. NFC.

[dstutt]

No description provided.

[llvmbot]

@llvm/pr-subscribers-backend-amdgpu

Author: David Stuttard (dstutt)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/90711.diff

1 Files Affected:

• (added) llvm/test/CodeGen/AMDGPU/image-sample-waw.mir (+23)

diff --git a/llvm/test/CodeGen/AMDGPU/image-sample-waw.mir b/llvm/test/CodeGen/AMDGPU/image-sample-waw.mir
new file mode 100644
index 00000000000000..90ba9802dc8bed
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/image-sample-waw.mir
@@ -0,0 +1,23 @@
+# 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: 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
+
+...

[dstutt]

This highlights the issue as discussed in #90201

[jayfoad]

Can you just make this the first commit in #90710? Then reviewers can see the effect that the patch has on this test by looking at the two commits individually (but when you merge it it'll all get squashed into a single commit which is OK).

[jayfoad]

Maybe call it waitcnt-sample-waw.mir by analogy with the existing waitcnt-vmem-waw.mir?

[dstutt]

Committing this as part of #90710 instead