llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-vector-ptrs.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 5
; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -amdgpu-asan-instrument-lds=false -mtriple=amdgcn-amd-amdhsa | FileCheck %s

; Test to check if vector of static LDS ptrs accesses in kernel are lowered correctly.
@lds_var1 = internal addrspace(3) global i32 poison
@lds_var2 = internal addrspace(3) global i32 poison

;.
; CHECK: @llvm.amdgcn.sw.lds.example = internal addrspace(3) global ptr poison, no_sanitize_address, align 4, !absolute_symbol [[META0:![0-9]+]]
; CHECK: @llvm.amdgcn.sw.lds.example.md = internal addrspace(1) global %llvm.amdgcn.sw.lds.example.md.type { %llvm.amdgcn.sw.lds.example.md.item { i32 0, i32 8, i32 32 }, %llvm.amdgcn.sw.lds.example.md.item { i32 32, i32 4, i32 32 }, %llvm.amdgcn.sw.lds.example.md.item { i32 64, i32 4, i32 32 } }, no_sanitize_address
;.
define amdgpu_kernel void @example() sanitize_address {
; CHECK-LABEL: define amdgpu_kernel void @example(
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[WID:.*]]:
; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
; CHECK-NEXT:    br i1 [[TMP5]], label %[[MALLOC:.*]], label %[[ENTRY:.*]]
; CHECK:       [[MALLOC]]:
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_EXAMPLE_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.example.md, i32 0, i32 2, i32 0), align 4
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_EXAMPLE_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.example.md, i32 0, i32 2, i32 2), align 4
; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP6]], [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[TMP8]] to i64
; CHECK-NEXT:    [[TMP10:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP11:%.*]] = ptrtoint ptr [[TMP10]] to i64
; CHECK-NEXT:    [[TMP12:%.*]] = call i64 @__asan_malloc_impl(i64 [[TMP9]], i64 [[TMP11]])
; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i64 [[TMP12]] to ptr addrspace(1)
; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.example, align 8
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 8
; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr addrspace(1) [[TMP14]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP15]], i64 24)
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 36
; CHECK-NEXT:    [[TMP17:%.*]] = ptrtoint ptr addrspace(1) [[TMP16]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP17]], i64 28)
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 68
; CHECK-NEXT:    [[TMP19:%.*]] = ptrtoint ptr addrspace(1) [[TMP18]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP19]], i64 28)
; CHECK-NEXT:    br label %[[ENTRY]]
; CHECK:       [[ENTRY]]:
; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, %[[WID]] ], [ true, %[[MALLOC]] ]
; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT:    [[TMP20:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.example, align 8
; CHECK-NEXT:    [[TMP21:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_EXAMPLE_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.example.md, i32 0, i32 1, i32 0), align 4
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.example, i32 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_EXAMPLE_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.example.md, i32 0, i32 2, i32 0), align 4
; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.example, i32 [[TMP23]]
; CHECK-NEXT:    [[VEC_LDS_PTRS:%.*]] = insertelement <2 x ptr addrspace(3)> poison, ptr addrspace(3) [[TMP22]], i32 0
; CHECK-NEXT:    [[VEC_LDS_PTRS1:%.*]] = insertelement <2 x ptr addrspace(3)> [[VEC_LDS_PTRS]], ptr addrspace(3) [[TMP24]], i32 1
; CHECK-NEXT:    [[TMP25:%.*]] = ptrtoint <2 x ptr addrspace(3)> [[VEC_LDS_PTRS1]] to <2 x i32>
; CHECK-NEXT:    [[TMP31:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP20]], <2 x i32> [[TMP25]]
; CHECK-NEXT:    [[TMP32:%.*]] = addrspacecast <2 x ptr addrspace(1)> [[TMP31]] to <2 x ptr>
; CHECK-NEXT:    [[ELEM0:%.*]] = extractelement <2 x ptr> [[TMP32]], i32 0
; CHECK-NEXT:    store i32 42, ptr [[ELEM0]], align 4
; CHECK-NEXT:    [[ELEM1:%.*]] = extractelement <2 x ptr> [[TMP32]], i32 1
; CHECK-NEXT:    store i32 43, ptr [[ELEM1]], align 4
; CHECK-NEXT:    br label %[[CONDFREE:.*]]
; CHECK:       [[CONDFREE]]:
; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT:    br i1 [[XYZCOND]], label %[[FREE:.*]], label %[[END:.*]]
; CHECK:       [[FREE]]:
; CHECK-NEXT:    [[TMP33:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP34:%.*]] = ptrtoint ptr [[TMP33]] to i64
; CHECK-NEXT:    [[TMP35:%.*]] = ptrtoint ptr addrspace(1) [[TMP20]] to i64
; CHECK-NEXT:    call void @__asan_free_impl(i64 [[TMP35]], i64 [[TMP34]])
; CHECK-NEXT:    br label %[[END]]
; CHECK:       [[END]]:
; CHECK-NEXT:    ret void
;
entry:
  ; Create a vector of flat pointers
  %vec_lds_ptrs = insertelement <2 x ptr addrspace(3)> poison, ptr addrspace(3) @lds_var1, i32 0
  %vec_lds_ptrs1 = insertelement <2 x ptr addrspace(3)> %vec_lds_ptrs, ptr addrspace(3) @lds_var2, i32 1
  %vec_flat_ptrs = addrspacecast <2 x ptr addrspace(3)> %vec_lds_ptrs1 to <2 x ptr>
  %elem0 = extractelement <2 x ptr> %vec_flat_ptrs, i32 0
  store i32 42, ptr %elem0, align 4
  %elem1 = extractelement <2 x ptr> %vec_flat_ptrs, i32 1
  store i32 43, ptr %elem1, align 4
  ret void
}

!llvm.module.flags = !{!0}
!0 = !{i32 4, !"nosanitize_address", i32 1}
;.
; CHECK: attributes #[[ATTR0]] = { sanitize_address "amdgpu-lds-size"="8" }
; CHECK: attributes #[[ATTR1:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
; CHECK: attributes #[[ATTR2:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(none) }
; CHECK: attributes #[[ATTR3:[0-9]+]] = { convergent nocallback nofree nounwind willreturn }
;.
; CHECK: [[META0]] = !{i32 0, i32 1}
; CHECK: [[META1:![0-9]+]] = !{i32 4, !"nosanitize_address", i32 1}
;.