aed9f11965
"infer-address-spaces" pass replaces all refinable generic pointers with equivalent specific pointers. At -O0 optimisation level, infer-address-spaces pass doesn't run in the pipeline. "amdgpu-sw-lower-lds" pass instruments memory operations on addrspace(3) ptrs. Since, extra addrspacecasts are present from lds to flat addrspaces at -O0 and the actual store/load memory instructions are now on flat addrspace, these addrspacecast need to be handled in the amdgpu-sw-lower-lds pass itself. This patch lowers the lds ptr first to the corresponding ptr in the global memory from the asan_malloc. Then replaces the original cast with addrspacecast from global ptr to flat ptr.
77 lines
4.9 KiB
LLVM
77 lines
4.9 KiB
LLVM
; 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 -mtriple=amdgcn-amd-amdhsa | FileCheck %s
|
|
@lds = internal addrspace(3) global [5 x i32] poison, align 16
|
|
|
|
;.
|
|
; CHECK: @llvm.amdgcn.sw.lds.k0 = internal addrspace(3) global ptr poison, no_sanitize_address, align 16, !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 20, i32 64 } }, no_sanitize_address
|
|
;.
|
|
define amdgpu_kernel void @k0() sanitize_address {
|
|
; CHECK-LABEL: define amdgpu_kernel void @k0(
|
|
; 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 %[[BB18:.*]]
|
|
; CHECK: [[MALLOC]]:
|
|
; CHECK-NEXT: [[TMP6:%.*]] = 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: [[TMP7:%.*]] = 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 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.k0, 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 52
|
|
; CHECK-NEXT: [[TMP17:%.*]] = ptrtoint ptr addrspace(1) [[TMP16]] to i64
|
|
; CHECK-NEXT: call void @__asan_poison_region(i64 [[TMP17]], i64 44)
|
|
; CHECK-NEXT: br label %[[BB18]]
|
|
; CHECK: [[BB18]]:
|
|
; 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: [[TMP20:%.*]] = 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: [[TMP21:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP20]]
|
|
; CHECK-NEXT: [[TMP22:%.*]] = ptrtoint ptr addrspace(3) [[TMP21]] to i32
|
|
; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP19]], i32 [[TMP22]]
|
|
; CHECK-NEXT: [[TMP24:%.*]] = addrspacecast ptr addrspace(1) [[TMP23]] to ptr
|
|
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds [5 x i32], ptr [[TMP24]], i64 0, i64 0
|
|
; CHECK-NEXT: store i32 1, ptr [[GEP]], 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: [[TMP25:%.*]] = call ptr @llvm.returnaddress(i32 0)
|
|
; CHECK-NEXT: [[TMP26:%.*]] = ptrtoint ptr [[TMP25]] to i64
|
|
; CHECK-NEXT: [[TMP27:%.*]] = ptrtoint ptr addrspace(1) [[TMP19]] to i64
|
|
; CHECK-NEXT: call void @__asan_free_impl(i64 [[TMP27]], i64 [[TMP26]])
|
|
; CHECK-NEXT: br label %[[END]]
|
|
; CHECK: [[END]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%gep = getelementptr inbounds [5 x i32], ptr addrspacecast (ptr addrspace(3) @lds to ptr), i64 0, i64 0
|
|
store i32 1, ptr %gep, align 4
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 4, !"nosanitize_address", i32 1}
|
|
;.
|
|
; CHECK: attributes #[[ATTR0]] = { sanitize_address "amdgpu-lds-size"="16" }
|
|
; 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}
|
|
;.
|