[llvm] 939d62c - [AMDGPU] Pre-commit load/store combine tests. NFC.

[Stanislav Mekhanoshin via llvm-commits]

Author: Stanislav Mekhanoshin
Date: 2022-02-22T16:28:44-08:00
New Revision: 939d62c18530fce6544aae7bcdec7f1e3a600044

URL: https://github.com/llvm/llvm-project/commit/939d62c18530fce6544aae7bcdec7f1e3a600044
DIFF: https://github.com/llvm/llvm-project/commit/939d62c18530fce6544aae7bcdec7f1e3a600044.diff

LOG: [AMDGPU] Pre-commit load/store combine tests. NFC.

Added: 
    

Modified: 
    llvm/test/CodeGen/AMDGPU/merge-global-load-store.mir

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/AMDGPU/merge-global-load-store.mir b/llvm/test/CodeGen/AMDGPU/merge-global-load-store.mir
index d2404fca19b50..8d4fcca8f741d 100644
--- a/llvm/test/CodeGen/AMDGPU/merge-global-load-store.mir
+++ b/llvm/test/CodeGen/AMDGPU/merge-global-load-store.mir
@@ -8,13 +8,13 @@ body:             |
 
     ; GCN-LABEL: name: merge_global_load_dword_2
     ; GCN: [[DEF:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
-    ; GCN-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 [[DEF]], 0, 0, implicit $exec :: (load (s64) from `i32 addrspace(1)* undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 [[DEF]], 0, 0, implicit $exec :: (load (s64) from `float addrspace(1)* undef` + 4, align 4, addrspace 1)
     ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[GLOBAL_LOAD_DWORDX2_]].sub0
     ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[GLOBAL_LOAD_DWORDX2_]].sub1
     ; GCN-NEXT: S_NOP 0, implicit [[COPY]], implicit [[COPY1]]
     %0:vreg_64_align2 = IMPLICIT_DEF
-    %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef`, align 4, addrspace 1)
-    %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef`, align 4, addrspace 1)
+    %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec :: (load (s32) from `float addrspace(1)* undef` + 4, basealign 4, addrspace 1)
+    %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef` + 8, basealign 4, addrspace 1)
     S_NOP 0, implicit %1, implicit %2
 ...
 
@@ -397,3 +397,40 @@ body:             |
     %3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1.sub1, 4, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef`, align 4, addrspace 1)
     S_NOP 0, implicit %2, implicit %3
 ...
+
+---
+name:            merge_global_load_dword_2_out_of_order
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_global_load_dword_2_out_of_order
+    ; GCN: [[DEF:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 [[DEF]], 0, 0, implicit $exec :: (load (s64) from `i32 addrspace(1)* undef`, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[GLOBAL_LOAD_DWORDX2_]].sub1
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[GLOBAL_LOAD_DWORDX2_]].sub0
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY]], implicit [[COPY1]]
+    %0:vreg_64_align2 = IMPLICIT_DEF
+    %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef` + 4, align 8, addrspace 1)
+    %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec :: (load (s32) from `float addrspace(1)* undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %1, implicit %2
+...
+
+---
+name:            merge_global_load_dword_3_out_of_order
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_global_load_dword_3_out_of_order
+    ; GCN: [[DEF:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[GLOBAL_LOAD_DWORDX3_:%[0-9]+]]:vreg_96_align2 = GLOBAL_LOAD_DWORDX3 [[DEF]], 0, 0, implicit $exec :: (load (s96) from `i32 addrspace(1)* undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY [[GLOBAL_LOAD_DWORDX3_]].sub0_sub1
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[GLOBAL_LOAD_DWORDX3_]].sub2
+    ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
+    ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY killed [[COPY]].sub0
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY2]], implicit [[COPY3]]
+    %0:vreg_64_align2 = IMPLICIT_DEF
+    %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef` + 4, align 4, addrspace 1)
+    %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec :: (load (s32) from `float addrspace(1)* undef`, align 16, addrspace 1)
+    %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, implicit $exec :: (load (s32) from `i32 addrspace(1)* undef` + 8, align 8, addrspace 1)
+    S_NOP 0, implicit %1, implicit %2
+...