[AMDGPU] SILoadStoreOptimizer: Precommit tests for merging across a swizzled access

diff --git a/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir b/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
index 5c8fd61..38239e0 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
+++ b/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
@@ -779,6 +779,25 @@ body:             |
 ---
 
 
+# GFX9-LABEL: name: gfx9_tbuffer_load_merge_across_swizzle
+# GFX9: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 4, 116, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+# GFX9: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 12, 116, 0, 0, 1, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+# GFX9: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 8, 116, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+name: gfx9_tbuffer_load_merge_across_swizzle
+body:             |
+  bb.0.entry:
+    %0:sgpr_32 = COPY $sgpr0
+    %1:sgpr_32 = COPY $sgpr1
+    %2:sgpr_32 = COPY $sgpr2
+    %3:sgpr_32 = COPY $sgpr3
+    %5:sgpr_128 = REG_SEQUENCE %0:sgpr_32, %subreg.sub0, %1:sgpr_32, %subreg.sub1, %2:sgpr_32, %subreg.sub2, %3:sgpr_32, %subreg.sub3
+    %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 116, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+    %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 12, 116, 0, 0, 1, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+    %9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 116, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+
 #
 # GFX10 tests
 #
@@ -1557,3 +1576,21 @@ body:             |
 ...
 ---
 
+
+# GFX10-LABEL: name: gfx10_tbuffer_load_merge_across_swizzle
+# GFX10: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 4, 22, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+# GFX10: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 12, 22, 0, 0, 1, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+# GFX10: %{{[0-9]+}}:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %4, 0, 8, 22, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+name: gfx10_tbuffer_load_merge_across_swizzle
+body:             |
+  bb.0.entry:
+    %0:sgpr_32 = COPY $sgpr0
+    %1:sgpr_32 = COPY $sgpr1
+    %2:sgpr_32 = COPY $sgpr2
+    %3:sgpr_32 = COPY $sgpr3
+    %5:sgpr_128 = REG_SEQUENCE %0:sgpr_32, %subreg.sub0, %1:sgpr_32, %subreg.sub1, %2:sgpr_32, %subreg.sub2, %3:sgpr_32, %subreg.sub3
+    %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 22, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+    %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 12, 22, 0, 0, 1, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+    %9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 22, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---