; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -passes=amdgpu-promote-alloca < %s | FileCheck %s

target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"

define amdgpu_kernel void @test_overwrite(i64 %val, i1 %cond) {
; CHECK-LABEL: define amdgpu_kernel void @test_overwrite
; CHECK-SAME: (i64 [[VAL:%.*]], i1 [[COND:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 [[COND]], label [[LOOP:%.*]], label [[END:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[PROMOTEALLOCA:%.*]] = phi <3 x i64> [ [[TMP2:%.*]], [[LOOP]] ], [ <i64 43, i64 undef, i64 undef>, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <3 x i64> [[PROMOTEALLOCA]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <3 x i64> [[PROMOTEALLOCA]], i64 68, i32 0
; CHECK-NEXT:    [[TMP2]] = insertelement <3 x i64> [[TMP1]], i64 32, i32 0
; CHECK-NEXT:    [[LOOP_CC:%.*]] = icmp ne i64 [[TMP0]], 68
; CHECK-NEXT:    br i1 [[LOOP_CC]], label [[LOOP]], label [[END]]
; CHECK:       end:
; CHECK-NEXT:    [[PROMOTEALLOCA1:%.*]] = phi <3 x i64> [ [[TMP2]], [[LOOP]] ], [ <i64 43, i64 undef, i64 undef>, [[ENTRY]] ]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <3 x i64> [[PROMOTEALLOCA1]], i32 0
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [3 x i64], align 4, addrspace(5)
  store i64 43, ptr addrspace(5) %stack
  br i1 %cond, label %loop, label %end

loop:
  %load.0 = load i64, ptr addrspace(5) %stack
  store i64 68, ptr addrspace(5) %stack
  %load.1 = load i64, ptr addrspace(5) %stack
  store i64 32, ptr addrspace(5) %stack
  %loop.cc = icmp ne i64 %load.0, %load.1
  br i1 %loop.cc, label %loop, label %end

end:
  %reload = load i64, ptr addrspace(5) %stack
  ret void
}

define <4 x i64> @test_fullvec_out_of_bounds(<4 x i64> %arg) {
; CHECK-LABEL: define <4 x i64> @test_fullvec_out_of_bounds
; CHECK-SAME: (<4 x i64> [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <4 x i64> [[ARG]], i64 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i64> undef, i64 [[TMP0]], i32 3
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i64> [[ARG]], i64 1
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i64> [[ARG]], i64 2
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x i64> [[ARG]], i64 3
; CHECK-NEXT:    ret <4 x i64> poison
;
entry:
  %stack = alloca [4 x i64], align 4, addrspace(5)
  %stack.2 = getelementptr inbounds [4 x i64], ptr addrspace(5) %stack, i32 0, i32 2
  %stack.3 = getelementptr inbounds [4 x i64], ptr addrspace(5) %stack, i32 0, i32 3
  store <4 x i64> %arg, ptr addrspace(5) %stack.3
  %reload = load <4 x i64>, ptr addrspace(5) %stack.2
  ret <4 x i64> %reload
}

define amdgpu_kernel void @test_no_overwrite(i64 %val, i1 %cond) {
; CHECK-LABEL: define amdgpu_kernel void @test_no_overwrite
; CHECK-SAME: (i64 [[VAL:%.*]], i1 [[COND:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 [[COND]], label [[LOOP:%.*]], label [[END:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[PROMOTEALLOCA:%.*]] = phi <3 x i64> [ [[TMP1:%.*]], [[LOOP]] ], [ <i64 43, i64 undef, i64 undef>, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <3 x i64> [[PROMOTEALLOCA]], i32 0
; CHECK-NEXT:    [[TMP1]] = insertelement <3 x i64> [[PROMOTEALLOCA]], i64 32, i32 1
; CHECK-NEXT:    [[LOOP_CC:%.*]] = icmp ne i64 [[TMP0]], 32
; CHECK-NEXT:    br i1 [[LOOP_CC]], label [[LOOP]], label [[END]]
; CHECK:       end:
; CHECK-NEXT:    [[PROMOTEALLOCA1:%.*]] = phi <3 x i64> [ [[TMP1]], [[LOOP]] ], [ <i64 43, i64 undef, i64 undef>, [[ENTRY]] ]
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <3 x i64> [[PROMOTEALLOCA1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <3 x i64> [[PROMOTEALLOCA1]], i32 1
; CHECK-NEXT:    ret void
;
entry:
  %stack = alloca [3 x i64], align 4, addrspace(5)
  %stack.1 = getelementptr inbounds i64, ptr addrspace(5) %stack, i32 1
  store i64 43, ptr addrspace(5) %stack
  br i1 %cond, label %loop, label %end

loop:
  %load = load i64, ptr addrspace(5) %stack
  store i64 32, ptr addrspace(5) %stack.1
  %loop.cc = icmp ne i64 %load, 32
  br i1 %loop.cc, label %loop, label %end

end:
  %reload = load i64, ptr addrspace(5) %stack
  %reload.1 = load i64, ptr addrspace(5) %stack.1
  ret void
}

define ptr @alloca_load_store_ptr64_full_ivec(ptr %arg) {
; CHECK-LABEL: define ptr @alloca_load_store_ptr64_full_ivec
; CHECK-SAME: (ptr [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = ptrtoint ptr [[ARG]] to i64
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i64 [[TMP0]] to <8 x i8>
; CHECK-NEXT:    ret ptr [[ARG]]
;
entry:
  %alloca = alloca [8 x i8], align 8, addrspace(5)
  store ptr %arg, ptr addrspace(5) %alloca, align 8
  %tmp = load ptr, ptr addrspace(5) %alloca, align 8
  ret ptr %tmp
}

define ptr addrspace(3) @alloca_load_store_ptr32_full_ivec(ptr addrspace(3) %arg) {
; CHECK-LABEL: define ptr addrspace(3) @alloca_load_store_ptr32_full_ivec
; CHECK-SAME: (ptr addrspace(3) [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = ptrtoint ptr addrspace(3) [[ARG]] to i32
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32 [[TMP0]] to <4 x i8>
; CHECK-NEXT:    ret ptr addrspace(3) [[ARG]]
;
entry:
  %alloca = alloca [4 x i8], align 8, addrspace(5)
  store ptr addrspace(3) %arg, ptr addrspace(5) %alloca, align 8
  %tmp = load ptr addrspace(3), ptr addrspace(5) %alloca, align 8
  ret ptr addrspace(3) %tmp
}

define <4 x ptr addrspace(3)> @alloca_load_store_ptr_mixed_full_ptrvec(<2 x ptr> %arg) {
; CHECK-LABEL: define <4 x ptr addrspace(3)> @alloca_load_store_ptr_mixed_full_ptrvec
; CHECK-SAME: (<2 x ptr> [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = ptrtoint <2 x ptr> [[ARG]] to <2 x i64>
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[TMP0]] to <4 x i32>
; CHECK-NEXT:    [[TMP2:%.*]] = inttoptr <4 x i32> [[TMP1]] to <4 x ptr addrspace(3)>
; CHECK-NEXT:    ret <4 x ptr addrspace(3)> [[TMP2]]
;
entry:
  %alloca = alloca [4 x i32], align 8, addrspace(5)
  store <2 x ptr> %arg, ptr addrspace(5) %alloca, align 8
  %tmp = load <4 x ptr addrspace(3)>, ptr addrspace(5) %alloca, align 8
  ret <4 x ptr addrspace(3)> %tmp
}

define <8 x i16> @ptralloca_load_store_ints_full(<2 x i64> %arg) {
; CHECK-LABEL: define <8 x i16> @ptralloca_load_store_ints_full
; CHECK-SAME: (<2 x i64> [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[ARG]] to <4 x i32>
; CHECK-NEXT:    [[TMP1:%.*]] = inttoptr <4 x i32> [[TMP0]] to <4 x ptr addrspace(5)>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i32> [[TMP0]] to <8 x i16>
; CHECK-NEXT:    ret <8 x i16> [[TMP2]]
;
entry:
  %stack = alloca [4 x ptr addrspace(5)], align 4, addrspace(5)
  store <2 x i64> %arg, ptr addrspace(5) %stack
  %reload = load <8 x i16>, ptr addrspace(5) %stack
  ret <8 x i16> %reload
}

define void @alloca_load_store_ptr_mixed_ptrvec(<2 x ptr addrspace(3)> %arg) {
; CHECK-LABEL: define void @alloca_load_store_ptr_mixed_ptrvec
; CHECK-SAME: (<2 x ptr addrspace(3)> [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = ptrtoint <2 x ptr addrspace(3)> [[ARG]] to <2 x i32>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i32> undef, i32 [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x i32> [[TMP0]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x i32> [[TMP2]], i32 [[TMP3]], i32 1
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP1]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP3]], i64 1
; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr <2 x i32> [[TMP6]] to <2 x ptr addrspace(3)>
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x i32> poison, i32 [[TMP1]], i64 0
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP3]], i64 1
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP9]], i32 undef, i64 2
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 undef, i64 3
; CHECK-NEXT:    [[TMP12:%.*]] = inttoptr <4 x i32> [[TMP11]] to <4 x ptr addrspace(3)>
; CHECK-NEXT:    ret void
;
entry:
  %alloca = alloca [8 x i32], align 8, addrspace(5)
  store <2 x ptr addrspace(3)> %arg, ptr addrspace(5) %alloca, align 8
  %tmp = load <2 x ptr addrspace(3)>, ptr addrspace(5) %alloca, align 8
  %tmp.full = load <4 x ptr addrspace(3)>, ptr addrspace(5) %alloca, align 8
  ret void
}

; Will not vectorize because we're accessing a 64 bit vector with a 32 bits pointer.
define ptr addrspace(3) @alloca_load_store_ptr_mixed_full_ivec(ptr addrspace(3) %arg) {
; CHECK-LABEL: define ptr addrspace(3) @alloca_load_store_ptr_mixed_full_ivec
; CHECK-SAME: (ptr addrspace(3) [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca [8 x i8], align 8, addrspace(5)
; CHECK-NEXT:    store ptr addrspace(3) [[ARG]], ptr addrspace(5) [[ALLOCA]], align 8
; CHECK-NEXT:    [[TMP:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[ALLOCA]], align 8
; CHECK-NEXT:    ret ptr addrspace(3) [[TMP]]
;
entry:
  %alloca = alloca [8 x i8], align 8, addrspace(5)
  store ptr addrspace(3) %arg, ptr addrspace(5) %alloca, align 8
  %tmp = load ptr addrspace(3), ptr addrspace(5) %alloca, align 8
  ret ptr addrspace(3) %tmp
}