Skip to content

[AMDGPU] Remove amdgpu-no-heap-ptr and amdgpu-no-lds-kernel-id attributes from lowered kernels in amdgpu-sw-lower-lds pass #120887

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 23, 2024
Merged

[AMDGPU] Remove amdgpu-no-heap-ptr and amdgpu-no-lds-kernel-id attributes from lowered kernels in amdgpu-sw-lower-lds pass #120887

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1176,10 +1176,13 @@ bool AMDGPUSwLowerLDS::run() {
LDSParams.IndirectAccess.DynamicLDSGlobals.empty()) {
Changed = false;
} else {
removeFnAttrFromReachable(CG, Func,
{"amdgpu-no-workitem-id-x",
"amdgpu-no-workitem-id-y",
"amdgpu-no-workitem-id-z"});
removeFnAttrFromReachable(
CG, Func,
{"amdgpu-no-workitem-id-x", "amdgpu-no-workitem-id-y",
"amdgpu-no-workitem-id-z", "amdgpu-no-heap-ptr"});
if (!LDSParams.IndirectAccess.StaticLDSGlobals.empty() ||
!LDSParams.IndirectAccess.DynamicLDSGlobals.empty())
removeFnAttrFromReachable(CG, Func, {"amdgpu-no-lds-kernel-id"});
reorderStaticDynamicIndirectLDSSet(LDSParams);
buildSwLDSGlobal(Func);
buildSwDynLDSGlobal(Func);
Expand Down
130 changes: 130 additions & 0 deletions llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,130 @@
; 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 -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.
; Also checks if amdgpu-no-lds-kernel-id attribute is removed from the list of attributes
@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: [[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:%.*]] = 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: [[TMP6:%.*]] = load ptr addrspace(1), ptr addrspace(1) [[TMP5]], align 8
; CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr addrspace(1) [[TMP6]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP3]], i32 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = 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: [[TMP10:%.*]] = load ptr addrspace(1), ptr addrspace(1) [[TMP9]], align 8
; CHECK-NEXT: [[TMP11:%.*]] = load i32, ptr addrspace(1) [[TMP10]], align 4
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP3]], i32 [[TMP11]]
; CHECK-NEXT: [[X:%.*]] = addrspacecast ptr addrspace(3) [[TMP8]] to ptr
; CHECK-NEXT: [[TMP13:%.*]] = addrspacecast ptr addrspace(3) [[TMP8]] to ptr
; CHECK-NEXT: store i8 3, ptr [[TMP13]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = ptrtoint ptr addrspace(3) [[TMP12]] to i32
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP4]], i32 [[TMP14]]
; CHECK-NEXT: store i8 3, ptr addrspace(1) [[TMP15]], 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 #1 {
; CHECK-LABEL: define amdgpu_kernel void @k0(
; 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 %[[BB24:.*]]
; 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 4, 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 4, 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 33
; CHECK-NEXT: [[TMP17:%.*]] = ptrtoint ptr addrspace(1) [[TMP16]] to i64
; CHECK-NEXT: call void @__asan_poison_region(i64 [[TMP17]], i64 31)
; 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: [[TMP20:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 99
; CHECK-NEXT: [[TMP21:%.*]] = ptrtoint ptr addrspace(1) [[TMP20]] to i64
; CHECK-NEXT: call void @__asan_poison_region(i64 [[TMP21]], i64 29)
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 132
; CHECK-NEXT: [[TMP23:%.*]] = ptrtoint ptr addrspace(1) [[TMP22]] to i64
; CHECK-NEXT: call void @__asan_poison_region(i64 [[TMP23]], i64 28)
; CHECK-NEXT: br label %[[BB24]]
; CHECK: [[BB24]]:
; CHECK-NEXT: [[XYZCOND:%.*]] = phi i1 [ false, %[[WID]] ], [ true, %[[MALLOC]] ]
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier()
; CHECK-NEXT: [[TMP25:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
; CHECK-NEXT: [[TMP26:%.*]] = 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: [[TMP27:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP26]]
; CHECK-NEXT: [[TMP28:%.*]] = 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: [[TMP29:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP28]]
; CHECK-NEXT: call void @use_variables()
; CHECK-NEXT: [[TMP30:%.*]] = ptrtoint ptr addrspace(3) [[TMP27]] to i32
; CHECK-NEXT: [[TMP31:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP25]], i32 [[TMP30]]
; CHECK-NEXT: store i8 7, ptr addrspace(1) [[TMP31]], align 1
; CHECK-NEXT: [[TMP32:%.*]] = ptrtoint ptr addrspace(3) [[TMP29]] to i32
; CHECK-NEXT: [[TMP33:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP25]], i32 [[TMP32]]
; CHECK-NEXT: store i32 8, ptr addrspace(1) [[TMP33]], align 2
; 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: [[TMP34:%.*]] = call ptr @llvm.returnaddress(i32 0)
; CHECK-NEXT: [[TMP35:%.*]] = ptrtoint ptr [[TMP34]] to i64
; CHECK-NEXT: [[TMP36:%.*]] = ptrtoint ptr addrspace(1) [[TMP25]] to i64
; CHECK-NEXT: call void @__asan_free_impl(i64 [[TMP36]], i64 [[TMP35]])
; 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}
attributes #1 = { "amdgpu-no-lds-kernel-id" }
;.
; 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:![0-9]+]] = !{i32 4, !"nosanitize_address", i32 1}
; CHECK: [[META2]] = !{i32 0}
;.
Loading
Loading