[AMDGPU] Handle lowering addrspace casts from LDS to FLAT address in amdgpu-sw-lower-lds. (#121214)
"infer-address-spaces" pass replaces all refinable generic pointers with
equivalent specific pointers.
At -O0 optimisation level, infer-address-spaces pass doesn't run in the
pipeline.
"amdgpu-sw-lower-lds" pass instruments memory operations on addrspace(3)
ptrs. Since, extra addrspacecasts are present from lds to flat
addrspaces at -O0 and the actual store/load memory instructions are now
on flat addrspace, these addrspacecast need to be handled in the
amdgpu-sw-lower-lds pass itself. This patch lowers the lds ptr first to
the corresponding ptr in the global memory from the asan_malloc. Then
replaces the original cast with addrspacecast from global ptr to flat
ptr.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
index b9fa89d..704bc9e 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
@@ -29,8 +29,12 @@
; CHECK-NEXT: [[TMP10:%.*]] = load ptr addrspace(1), ptr addrspace(1) [[TMP9]], align 8
; CHECK-NEXT: [[TMP11:%.*]] = load i32, ptr addrspace(1) [[TMP10]], align 4
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP3]], i32 [[TMP11]]
-; CHECK-NEXT: [[X:%.*]] = addrspacecast ptr addrspace(3) [[TMP8]] to ptr
-; CHECK-NEXT: [[TMP13:%.*]] = addrspacecast ptr addrspace(3) [[TMP8]] to ptr
+; CHECK-NEXT: [[TMP18:%.*]] = ptrtoint ptr addrspace(3) [[TMP8]] to i32
+; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = addrspacecast ptr addrspace(1) [[TMP19]] to ptr
+; CHECK-NEXT: [[TMP16:%.*]] = ptrtoint ptr addrspace(3) [[TMP8]] to i32
+; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP16]]
+; CHECK-NEXT: [[TMP13:%.*]] = addrspacecast ptr addrspace(1) [[TMP17]] to ptr
; CHECK-NEXT: store i8 3, ptr [[TMP13]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = ptrtoint ptr addrspace(3) [[TMP12]] to i32
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP14]]
