[llvm] 2e2f3e3 - [AMDGPU] Add test for no waitcnt before issuing LDS DMA. NFC.

[Stanislav Mekhanoshin via llvm-commits]

Author: Stanislav Mekhanoshin
Date: 2022-05-17T10:45:55-07:00
New Revision: 2e2f3e33dff4917df055b7dba2860a64f8060db2

URL: https://github.com/llvm/llvm-project/commit/2e2f3e33dff4917df055b7dba2860a64f8060db2
DIFF: https://github.com/llvm/llvm-project/commit/2e2f3e33dff4917df055b7dba2860a64f8060db2.diff

LOG: [AMDGPU] Add test for no waitcnt before issuing LDS DMA. NFC.

A wait is only needed after the DMA before LDS can be read.

Added: 
    

Modified: 
    llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir b/llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir
index 83f7fdf86ac4..499bd6ada3ce 100644
--- a/llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir
+++ b/llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir
@@ -96,3 +96,24 @@ body:             |
     S_ENDPGM 0
 
 ...
+
+# No need to wait before load from VMEM to LDS.
+# GCN-LABEL: name: series_of_buffer_load_dword_lds_ds_read
+# GCN:      BUFFER_LOAD_DWORD_LDS_IDXEN
+# GCN-NEXT: BUFFER_LOAD_DWORD_LDS_IDXEN
+# GCN-NEXT: BUFFER_LOAD_DWORD_LDS_IDXEN
+# GCN-NEXT: S_WAITCNT 3952
+#                     vmcnt(0)
+# GCN-NEXT: DS_READ_B32_gfx9
+---
+name: series_of_buffer_load_dword_lds_ds_read
+body:             |
+  bb.0:
+    $m0 = S_MOV_B32 0
+    BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 0, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `i32 addrspace(1)* undef`), (store (s32) into `i32 addrspace(3)* undef`)
+    BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `i32 addrspace(1)* undef` + 4), (store (s32) into `i32 addrspace(3)* undef` + 4)
+    BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 8, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `i32 addrspace(1)* undef` + 8), (store (s32) into `i32 addrspace(3)* undef` + 8)
+    $vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `i32 addrspace(3)* undef`)
+    S_ENDPGM 0
+
+...