; 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 -S -mtriple=amdgcn-amd-amdhsa | FileCheck %s

; Test to check if LDS accesses are lowered correctly when LDS is passed as function
; argument to non-kernel.

@lds_var = internal addrspace(3) global [1024 x i32] poison, align 4

;.
; CHECK: @llvm.amdgcn.sw.lds.my_kernel = internal addrspace(3) global ptr poison, no_sanitize_address, align 4, !absolute_symbol [[META0:![0-9]+]]
; CHECK: @llvm.amdgcn.sw.lds.my_kernel.md = internal addrspace(1) global %llvm.amdgcn.sw.lds.my_kernel.md.type { %llvm.amdgcn.sw.lds.my_kernel.md.item { i32 0, i32 8, i32 32 }, %llvm.amdgcn.sw.lds.my_kernel.md.item { i32 32, i32 4096, i32 5120 } }, 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.my_kernel], no_sanitize_address
;.
define void @my_function(ptr addrspace(3) %lds_arg) sanitize_address {
; CHECK-LABEL: define void @my_function(
; CHECK-SAME: ptr addrspace(3) [[LDS_ARG:%.*]]) #[[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:    [[TMP3:%.*]] = load ptr addrspace(3), ptr addrspace(1) [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = load ptr addrspace(1), ptr addrspace(3) [[TMP3]], align 8
; CHECK-NEXT:    [[TMP5:%.*]] = ptrtoint ptr addrspace(3) [[LDS_ARG]] to i32
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP5]]
; CHECK-NEXT:    [[TMP7:%.*]] = ptrtoint ptr addrspace(1) [[TMP6]] to i64
; CHECK-NEXT:    [[TMP8:%.*]] = lshr i64 [[TMP7]], 3
; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[TMP8]], 2147450880
; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i64 [[TMP9]] to ptr
; CHECK-NEXT:    [[TMP11:%.*]] = load i8, ptr [[TMP10]], align 1
; CHECK-NEXT:    [[TMP12:%.*]] = icmp ne i8 [[TMP11]], 0
; CHECK-NEXT:    [[TMP13:%.*]] = and i64 [[TMP7]], 7
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[TMP13]], 3
; CHECK-NEXT:    [[TMP15:%.*]] = trunc i64 [[TMP14]] to i8
; CHECK-NEXT:    [[TMP16:%.*]] = icmp sge i8 [[TMP15]], [[TMP11]]
; CHECK-NEXT:    [[TMP17:%.*]] = and i1 [[TMP12]], [[TMP16]]
; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[TMP17]])
; CHECK-NEXT:    [[TMP19:%.*]] = icmp ne i64 [[TMP18]], 0
; CHECK-NEXT:    br i1 [[TMP19]], label [[ASAN_REPORT:%.*]], label [[TMP22:%.*]], !prof [[PROF1:![0-9]+]]
; CHECK:       asan.report:
; CHECK-NEXT:    br i1 [[TMP17]], label [[TMP20:%.*]], label [[TMP21:%.*]]
; CHECK:       20:
; CHECK-NEXT:    call void @__asan_report_load4(i64 [[TMP7]]) #[[ATTR7:[0-9]+]]
; CHECK-NEXT:    call void @llvm.amdgcn.unreachable()
; CHECK-NEXT:    br label [[TMP21]]
; CHECK:       21:
; CHECK-NEXT:    br label [[TMP22]]
; CHECK:       22:
; CHECK-NEXT:    [[LDS_VAL:%.*]] = load i32, ptr addrspace(1) [[TMP6]], align 4
; CHECK-NEXT:    [[NEW_LDS_VAL:%.*]] = add i32 [[LDS_VAL]], 1
; CHECK-NEXT:    [[TMP24:%.*]] = ptrtoint ptr addrspace(3) [[LDS_ARG]] to i32
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP24]]
; CHECK-NEXT:    [[TMP26:%.*]] = ptrtoint ptr addrspace(1) [[TMP25]] to i64
; CHECK-NEXT:    [[TMP27:%.*]] = lshr i64 [[TMP26]], 3
; CHECK-NEXT:    [[TMP28:%.*]] = add i64 [[TMP27]], 2147450880
; CHECK-NEXT:    [[TMP29:%.*]] = inttoptr i64 [[TMP28]] to ptr
; CHECK-NEXT:    [[TMP30:%.*]] = load i8, ptr [[TMP29]], align 1
; CHECK-NEXT:    [[TMP31:%.*]] = icmp ne i8 [[TMP30]], 0
; CHECK-NEXT:    [[TMP32:%.*]] = and i64 [[TMP26]], 7
; CHECK-NEXT:    [[TMP33:%.*]] = add i64 [[TMP32]], 3
; CHECK-NEXT:    [[TMP34:%.*]] = trunc i64 [[TMP33]] to i8
; CHECK-NEXT:    [[TMP35:%.*]] = icmp sge i8 [[TMP34]], [[TMP30]]
; CHECK-NEXT:    [[TMP36:%.*]] = and i1 [[TMP31]], [[TMP35]]
; CHECK-NEXT:    [[TMP37:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[TMP36]])
; CHECK-NEXT:    [[TMP38:%.*]] = icmp ne i64 [[TMP37]], 0
; CHECK-NEXT:    br i1 [[TMP38]], label [[ASAN_REPORT1:%.*]], label [[TMP41:%.*]], !prof [[PROF1]]
; CHECK:       asan.report1:
; CHECK-NEXT:    br i1 [[TMP36]], label [[TMP39:%.*]], label [[TMP40:%.*]]
; CHECK:       39:
; CHECK-NEXT:    call void @__asan_report_store4(i64 [[TMP26]]) #[[ATTR7]]
; CHECK-NEXT:    call void @llvm.amdgcn.unreachable()
; CHECK-NEXT:    br label [[TMP40]]
; CHECK:       40:
; CHECK-NEXT:    br label [[TMP41]]
; CHECK:       41:
; CHECK-NEXT:    store i32 [[NEW_LDS_VAL]], ptr addrspace(1) [[TMP25]], align 4
; CHECK-NEXT:    ret void
;
  %lds_val = load i32, ptr addrspace(3) %lds_arg, align 4
  %new_lds_val = add i32 %lds_val, 1
  store i32 %new_lds_val, ptr addrspace(3) %lds_arg, align 4
  ret void
}

define amdgpu_kernel void @my_kernel() sanitize_address {
; CHECK-LABEL: define amdgpu_kernel void @my_kernel(
; CHECK-SAME: ) #[[ATTR1:[0-9]+]] !llvm.amdgcn.lds.kernel.id [[META2:![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:    [[TMP11:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_MY_KERNEL_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, i32 0, i32 1, i32 0), align 4
; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_MY_KERNEL_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, i32 0, i32 1, i32 2), align 4
; CHECK-NEXT:    [[TMP14:%.*]] = add i32 [[TMP11]], [[TMP12]]
; CHECK-NEXT:    [[TMP13:%.*]] = zext i32 [[TMP14]] to i64
; CHECK-NEXT:    [[TMP10:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr [[TMP10]] to i64
; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @__asan_malloc_impl(i64 [[TMP13]], i64 [[TMP15]])
; CHECK-NEXT:    [[TMP6:%.*]] = inttoptr i64 [[TMP16]] to ptr addrspace(1)
; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, align 8
; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 8
; CHECK-NEXT:    [[TMP22:%.*]] = ptrtoint ptr addrspace(1) [[TMP21]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP22]], i64 24)
; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP6]], i64 4128
; CHECK-NEXT:    [[TMP24:%.*]] = ptrtoint ptr addrspace(1) [[TMP23]] to i64
; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP24]], i64 1024)
; CHECK-NEXT:    br label [[TMP7]]
; CHECK:       18:
; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT:    [[TMP17:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, align 8
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_MY_KERNEL_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, i32 0, i32 1, i32 0), align 4
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, i32 [[TMP8]]
; CHECK-NEXT:    [[LDS_PTR:%.*]] = getelementptr [1024 x i32], ptr addrspace(3) [[TMP9]], i32 0, i32 0
; CHECK-NEXT:    call void @my_function(ptr addrspace(3) [[LDS_PTR]])
; 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:    [[TMP18:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT:    [[TMP19:%.*]] = ptrtoint ptr [[TMP18]] to i64
; CHECK-NEXT:    [[TMP20:%.*]] = ptrtoint ptr addrspace(1) [[TMP17]] to i64
; CHECK-NEXT:    call void @__asan_free_impl(i64 [[TMP20]], i64 [[TMP19]])
; CHECK-NEXT:    br label [[END]]
; CHECK:       End:
; CHECK-NEXT:    ret void
;
  %lds_ptr = getelementptr [1024 x i32], ptr addrspace(3) @lds_var, i32 0, i32 0
  call void @my_function(ptr addrspace(3) %lds_ptr)
  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: attributes #[[ATTR5:[0-9]+]] = { convergent nocallback nofree nounwind willreturn memory(none) }
; CHECK: attributes #[[ATTR6:[0-9]+]] = { convergent nocallback nofree nounwind }
; CHECK: attributes #[[ATTR7]] = { nomerge }
;.
; CHECK: [[META0]] = !{i32 0, i32 1}
; CHECK: [[PROF1]] = !{!"branch_weights", i32 1, i32 1048575}
; CHECK: [[META2]] = !{i32 0}
;.