llvm/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 4
; RUN: opt < %s -passes=amdgpu-sw-lower-lds -amdgpu-asan-instrument-lds=false -S -mtriple=amdgcn-amd-amdhsa | FileCheck %s

; Test to check if static LDS is lowered correctly when a non-kernel with LDS accesses is called from kernel.
@lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
@lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
@lds_3 = external addrspace(3) global [3 x i8], align 4
@lds_4 = external addrspace(3) global [4 x i8], align 8

;.
; CHECK: @llvm.amdgcn.sw.lds.k0 = internal addrspace(3) global ptr poison, no_sanitize_address, align 8, !absolute_symbol [[META0:![0-9]+]]
; CHECK: @llvm.amdgcn.sw.lds.k0.md = internal addrspace(1) global %llvm.amdgcn.sw.lds.k0.md.type { %llvm.amdgcn.sw.lds.k0.md.item { i32 0, i32 8, i32 32 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 32, i32 1, i32 32 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 64, i32 4, i32 32 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 96, i32 3, i32 32 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 128, i32 4, i32 32 } }, no_sanitize_address
; @llvm.amdgcn.sw.lds.base.table = internal addrspace(1) constant [1 x ptr addrspace(3)] [ptr addrspace(3) @llvm.amdgcn.sw.lds.k0], no_sanitize_address
; @llvm.amdgcn.sw.lds.offset.table = internal addrspace(1) constant [1 x [2 x ptr addrspace(1)]] [[2 x ptr addrspace(1)] [ptr addrspace(1) getelementptr inbounds (%llvm.amdgcn.sw.lds.k0.md.type, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), ptr addrspace(1) getelementptr inbounds (%llvm.amdgcn.sw.lds.k0.md.type, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 4, i32 0)]], no_sanitize_address
;.
define void @use_variables() sanitize_address {
; CHECK-LABEL: define void @use_variables(
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [1 x ptr addrspace(3)], ptr addrspace(1) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
; CHECK-NEXT:    [[TMP4:%.*]] = load ptr addrspace(3), ptr addrspace(1) [[TMP2]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = load ptr addrspace(1), ptr addrspace(3) [[TMP4]], align 8
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [1 x [2 x ptr addrspace(1)]], ptr addrspace(1) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = load ptr addrspace(1), ptr addrspace(1) [[TMP6]], align 8
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) [[TMP5]], align 4
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [1 x [2 x ptr addrspace(1)]], ptr addrspace(1) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
; CHECK-NEXT:    [[TMP12:%.*]] = load ptr addrspace(1), ptr addrspace(1) [[TMP11]], align 8
; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) [[TMP12]], align 4
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP10]]
; CHECK-NEXT:    [[X:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
; CHECK-NEXT:    [[TMP16:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
; CHECK-NEXT:    store i8 3, ptr [[TMP16]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = ptrtoint ptr addrspace(3) [[TMP15]] to i32
; CHECK-NEXT:    [[TMP31:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP7]], i32 [[TMP14]]
; CHECK-NEXT:    store i8 3, ptr addrspace(1) [[TMP31]], align 8
; CHECK-NEXT:    ret void
;
  %X = addrspacecast ptr addrspace(3) @lds_3 to ptr
  store i8 3, ptr addrspacecast( ptr addrspace(3) @lds_3 to ptr), align 4
  store i8 3, ptr addrspace(3) @lds_4, align 8
  ret void
}

define amdgpu_kernel void @k0() sanitize_address {
; CHECK-LABEL: define amdgpu_kernel void @k0(
; CHECK-SAME: ) #[[ATTR1:[0-9]+]] !llvm.amdgcn.lds.kernel.id [[META1:![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 [[TMP7:%.*]]
; CHECK:       Malloc:
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 4, i32 0), align 4
; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 4, i32 2), align 4
; CHECK-NEXT:    [[TMP16:%.*]] = add i32 [[TMP13]], [[TMP14]]
; CHECK-NEXT:    [[TMP15:%.*]] = zext i32 [[TMP16]] to i64
; CHECK-NEXT:    [[TMP23:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP24:%.*]] = ptrtoint ptr [[TMP23]] to i64
; CHECK-NEXT:    [[TMP12:%.*]] = call i64 @__asan_malloc_impl(i64 [[TMP15]], i64 [[TMP24]])
; CHECK-NEXT:    [[TMP6:%.*]] = inttoptr i64 [[TMP12]] to ptr addrspace(1)
; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 8
; CHECK-NEXT:    [[TMP26:%.*]] = ptrtoint ptr addrspace(1) [[TMP25]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP26]], i64 24)
; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 33
; CHECK-NEXT:    [[TMP28:%.*]] = ptrtoint ptr addrspace(1) [[TMP27]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP28]], i64 31)
; CHECK-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 68
; CHECK-NEXT:    [[TMP45:%.*]] = ptrtoint ptr addrspace(1) [[TMP29]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP45]], i64 28)
; CHECK-NEXT:    [[TMP65:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 99
; CHECK-NEXT:    [[TMP66:%.*]] = ptrtoint ptr addrspace(1) [[TMP65]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP66]], i64 29)
; CHECK-NEXT:    [[TMP67:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 132
; CHECK-NEXT:    [[TMP68:%.*]] = ptrtoint ptr addrspace(1) [[TMP67]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP68]], i64 28)
; CHECK-NEXT:    br label [[TMP7]]
; CHECK:       24:
; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT:    [[TMP19:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP10]]
; CHECK-NEXT:    [[TMP17:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 4
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP17]]
; CHECK-NEXT:    call void @use_variables()
; CHECK-NEXT:    [[TMP30:%.*]] = ptrtoint ptr addrspace(3) [[TMP11]] to i32
; CHECK-NEXT:    [[TMP31:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP19]], i32 [[TMP30]]
; CHECK-NEXT:    store i8 7, ptr addrspace(1) [[TMP31]], align 1
; CHECK-NEXT:    [[TMP47:%.*]] = ptrtoint ptr addrspace(3) [[TMP18]] to i32
; CHECK-NEXT:    [[TMP48:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP19]], i32 [[TMP47]]
; CHECK-NEXT:    store i32 8, ptr addrspace(1) [[TMP48]], align 2
; CHECK-NEXT:    br label [[CONDFREE1:%.*]]
; CHECK:       CondFree:
; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
; CHECK:       Free:
; CHECK-NEXT:    [[TMP20:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP21:%.*]] = ptrtoint ptr [[TMP20]] to i64
; CHECK-NEXT:    [[TMP22:%.*]] = ptrtoint ptr addrspace(1) [[TMP19]] to i64
; CHECK-NEXT:    call void @__asan_free_impl(i64 [[TMP22]], i64 [[TMP21]])
; CHECK-NEXT:    br label [[END]]
; CHECK:       End:
; CHECK-NEXT:    ret void
;
  call void @use_variables()
  store i8 7, ptr addrspace(3) @lds_1, align 1
  store i32 8, ptr addrspace(3) @lds_2, align 2
  ret void
}

!llvm.module.flags = !{!0}
!0 = !{i32 4, !"nosanitize_address", i32 1}

;.
; CHECK: attributes #[[ATTR0]] = { sanitize_address }
; CHECK: attributes #[[ATTR1]] = { sanitize_address "amdgpu-lds-size"="8" }
; CHECK: attributes #[[ATTR2:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
; CHECK: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(none) }
; CHECK: attributes #[[ATTR4:[0-9]+]] = { convergent nocallback nofree nounwind willreturn }
;.
; CHECK: [[META0]] = !{i32 0, i32 1}
; CHECK: [[META1]] = !{i32 0}
;.