; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -passes=amdgpu-promote-alloca < %s | FileCheck %s

; Checks that memsets don't block PromoteAlloca.

define amdgpu_kernel void @memset_all_zero(i64 %val) {
; CHECK-LABEL: @memset_all_zero(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <6 x i64> zeroinitializer, i64 [[VAL:%.*]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <6 x i64> [[TMP0]], i64 [[VAL]], i32 1
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [6 x i64], align 4, addrspace(5)
  call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 48, i1 false)
  store i64 %val, ptr addrspace(5) %stack
  %reload = load i64, ptr addrspace(5) %stack
  %stack.1 = getelementptr [6 x i64], ptr addrspace(5) %stack, i64 0, i64 1
  store i64 %val, ptr addrspace(5) %stack.1
  ret void
}

define amdgpu_kernel void @memset_all_5(i64 %val) {
; CHECK-LABEL: @memset_all_5(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i64> <i64 361700864190383365, i64 361700864190383365, i64 361700864190383365, i64 361700864190383365>, i64 [[VAL:%.*]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i64> [[TMP0]], i64 [[VAL]], i32 1
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [4 x i64], align 4, addrspace(5)
  call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 5, i64 32, i1 false)
  store i64 %val, ptr addrspace(5) %stack
  %reload = load i64, ptr addrspace(5) %stack
  %stack.1 = getelementptr [6 x i64], ptr addrspace(5) %stack, i64 0, i64 1
  store i64 %val, ptr addrspace(5) %stack.1
  ret void
}

define amdgpu_kernel void @memset_volatile_nopromote(i64 %val) {
; CHECK-LABEL: @memset_volatile_nopromote(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) [[STACK]], i8 0, i64 32, i1 true)
; CHECK-NEXT:    store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [4 x i64], align 4, addrspace(5)
  call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 32, i1 true)
  store i64 %val, ptr addrspace(5) %stack
  ret void
}

define amdgpu_kernel void @memset_badsize_nopromote(i64 %val) {
; CHECK-LABEL: @memset_badsize_nopromote(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) [[STACK]], i8 0, i64 31, i1 true)
; CHECK-NEXT:    store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [4 x i64], align 4, addrspace(5)
  call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 31, i1 true)
  store i64 %val, ptr addrspace(5) %stack
  ret void
}

define amdgpu_kernel void @memset_offset_ptr_nopromote(i64 %val) {
; CHECK-LABEL: @memset_offset_ptr_nopromote(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr [4 x i64], ptr addrspace(5) [[STACK]], i64 0, i64 1
; CHECK-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) [[GEP]], i8 0, i64 24, i1 true)
; CHECK-NEXT:    store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [4 x i64], align 4, addrspace(5)
  %gep = getelementptr [4 x i64], ptr addrspace(5) %stack, i64 0, i64 1
  call void @llvm.memset.p5.i64(ptr addrspace(5) %gep, i8 0, i64 24, i1 true)
  store i64 %val, ptr addrspace(5) %stack
  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)