; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck %s

; CHECK: @promote_alloca_size_63.stack = internal unnamed_addr addrspace(3) global [63 x [5 x i32]] undef, align 4

define void @promote_alloca_size_63(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
entry:
  %stack = alloca [5 x i32], align 4
  %0 = load i32, i32 addrspace(1)* %in, align 4
  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
  store i32 4, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
  store i32 5, i32* %arrayidx3, align 4
  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
  %2 = load i32, i32* %arrayidx10, align 4
  store i32 %2, i32 addrspace(1)* %out, align 4
  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
  %3 = load i32, i32* %arrayidx12
  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
  store i32 %3, i32 addrspace(1)* %arrayidx13
  ret void
}

; CHECK: @promote_alloca_size_256.stack = internal unnamed_addr addrspace(3) global [256 x [5 x i32]] undef, align 4

define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #1 {
entry:
  %stack = alloca [5 x i32], align 4
  %0 = load i32, i32 addrspace(1)* %in, align 4
  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
  store i32 4, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
  store i32 5, i32* %arrayidx3, align 4
  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
  %2 = load i32, i32* %arrayidx10, align 4
  store i32 %2, i32 addrspace(1)* %out, align 4
  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
  %3 = load i32, i32* %arrayidx12
  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
  store i32 %3, i32 addrspace(1)* %arrayidx13
  ret void
}

; CHECK: @promote_alloca_size_1600.stack = internal unnamed_addr addrspace(3) global [1600 x [5 x i32]] undef, align 4

define void @promote_alloca_size_1600(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #2 {
entry:
  %stack = alloca [5 x i32], align 4
  %0 = load i32, i32 addrspace(1)* %in, align 4
  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
  store i32 4, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
  store i32 5, i32* %arrayidx3, align 4
  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
  %2 = load i32, i32* %arrayidx10, align 4
  store i32 %2, i32 addrspace(1)* %out, align 4
  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
  %3 = load i32, i32* %arrayidx12
  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
  store i32 %3, i32 addrspace(1)* %arrayidx13
  ret void
}

; CHECK: @occupancy_0(
; CHECK: alloca [5 x i32]
define void @occupancy_0(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #3 {
entry:
  %stack = alloca [5 x i32], align 4
  %0 = load i32, i32 addrspace(1)* %in, align 4
  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
  store i32 4, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
  store i32 5, i32* %arrayidx3, align 4
  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
  %2 = load i32, i32* %arrayidx10, align 4
  store i32 %2, i32 addrspace(1)* %out, align 4
  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
  %3 = load i32, i32* %arrayidx12
  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
  store i32 %3, i32 addrspace(1)* %arrayidx13
  ret void
}

; CHECK: @occupancy_max(
; CHECK: alloca [5 x i32]
define void @occupancy_max(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #4 {
entry:
  %stack = alloca [5 x i32], align 4
  %0 = load i32, i32 addrspace(1)* %in, align 4
  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
  store i32 4, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
  store i32 5, i32* %arrayidx3, align 4
  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
  %2 = load i32, i32* %arrayidx10, align 4
  store i32 %2, i32 addrspace(1)* %out, align 4
  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
  %3 = load i32, i32* %arrayidx12
  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
  store i32 %3, i32 addrspace(1)* %arrayidx13
  ret void
}

attributes #0 = { nounwind "amdgpu-max-work-group-size"="63" }
attributes #1 = { nounwind "amdgpu-max-waves-per-eu"="3" "amdgpu-max-work-group-size"="256" }
attributes #2 = { nounwind "amdgpu-max-waves-per-eu"="1" "amdgpu-max-work-group-size"="1600" }
attributes #3 = { nounwind "amdgpu-max-waves-per-eu"="0" }
attributes #4 = { nounwind "amdgpu-max-waves-per-eu"="-1" }