[AMDGPU][PromoteAlloca] Support memsets to ptr allocas (llvm#80678)

Fixes llvm#80366

(cherry picked from commit 4e958ab)

Author: Pierre-vh

llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp

@@ -521,10 +521,18 @@ static Value *promoteAllocaUserToVector(
       // For memset, we don't need to know the previous value because we
       // currently only allow memsets that cover the whole alloca.
       Value *Elt = MSI->getOperand(1);
-      if (DL.getTypeStoreSize(VecEltTy) > 1) {
-        Value *EltBytes =
-            Builder.CreateVectorSplat(DL.getTypeStoreSize(VecEltTy), Elt);
-        Elt = Builder.CreateBitCast(EltBytes, VecEltTy);
+      const unsigned BytesPerElt = DL.getTypeStoreSize(VecEltTy);
+      if (BytesPerElt > 1) {
+        Value *EltBytes = Builder.CreateVectorSplat(BytesPerElt, Elt);
+
+        // If the element type of the vector is a pointer, we need to first cast
+        // to an integer, then use a PtrCast.
+        if (VecEltTy->isPointerTy()) {
+          Type *PtrInt = Builder.getIntNTy(BytesPerElt * 8);
+          Elt = Builder.CreateBitCast(EltBytes, PtrInt);
+          Elt = Builder.CreateIntToPtr(Elt, VecEltTy);
+        } else
+          Elt = Builder.CreateBitCast(EltBytes, VecEltTy);
       }
 
       return Builder.CreateVectorSplat(VectorTy->getElementCount(), Elt);

llvm/test/CodeGen/AMDGPU/promote-alloca-memset.ll

@@ -84,4 +84,58 @@ entry:
   ret void
 }
 
+define amdgpu_kernel void @memset_array_ptr_alloca(ptr %out) {
+; CHECK-LABEL: @memset_array_ptr_alloca(
+; CHECK-NEXT:    store i64 0, ptr [[OUT:%.*]], align 8
+; CHECK-NEXT:    ret void
+;
+  %alloca = alloca [6 x ptr], align 16, addrspace(5)
+  call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
+  %load = load i64, ptr addrspace(5) %alloca
+  store i64 %load, ptr %out
+  ret void
+}
+
+define amdgpu_kernel void @memset_vector_ptr_alloca(ptr %out) {
+; CHECK-LABEL: @memset_vector_ptr_alloca(
+; CHECK-NEXT:    store i64 0, ptr [[OUT:%.*]], align 8
+; CHECK-NEXT:    ret void
+;
+  %alloca = alloca <6 x ptr>, align 16, addrspace(5)
+  call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
+  %load = load i64, ptr addrspace(5) %alloca
+  store i64 %load, ptr %out
+  ret void
+}
+
+define amdgpu_kernel void @memset_array_of_array_ptr_alloca(ptr %out) {
+; CHECK-LABEL: @memset_array_of_array_ptr_alloca(
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca [2 x [3 x ptr]], align 16, addrspace(5)
+; CHECK-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) [[ALLOCA]], i8 0, i64 48, i1 false)
+; CHECK-NEXT:    [[LOAD:%.*]] = load i64, ptr addrspace(5) [[ALLOCA]], align 8
+; CHECK-NEXT:    store i64 [[LOAD]], ptr [[OUT:%.*]], align 8
+; CHECK-NEXT:    ret void
+;
+  %alloca = alloca [2 x [3 x ptr]], align 16, addrspace(5)
+  call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
+  %load = load i64, ptr addrspace(5) %alloca
+  store i64 %load, ptr %out
+  ret void
+}
+
+define amdgpu_kernel void @memset_array_of_vec_ptr_alloca(ptr %out) {
+; CHECK-LABEL: @memset_array_of_vec_ptr_alloca(
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca [2 x <3 x ptr>], align 16, addrspace(5)
+; CHECK-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) [[ALLOCA]], i8 0, i64 48, i1 false)
+; CHECK-NEXT:    [[LOAD:%.*]] = load i64, ptr addrspace(5) [[ALLOCA]], align 8
+; CHECK-NEXT:    store i64 [[LOAD]], ptr [[OUT:%.*]], align 8
+; CHECK-NEXT:    ret void
+;
+  %alloca = alloca [2 x <3 x ptr>], align 16, addrspace(5)
+  call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
+  %load = load i64, ptr addrspace(5) %alloca
+  store i64 %load, ptr %out
+  ret void
+}
+
 declare void @llvm.memset.p5.i64(ptr addrspace(5) nocapture writeonly, i8, i64, i1 immarg)