[llvm] 21996bd - [AMDGPU] Remove amdgpu-no-heap-ptr and amdgpu-no-lds-kernel-id attributes from lowered kernels in amdgpu-sw-lower-lds pass (#120887)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Dec 22 23:12:34 PST 2024
Author: Chaitanya
Date: 2024-12-23T12:42:31+05:30
New Revision: 21996bd69c15cb1e5127f76254dfcda019ee432a
URL: https://github.com/llvm/llvm-project/commit/21996bd69c15cb1e5127f76254dfcda019ee432a
DIFF: https://github.com/llvm/llvm-project/commit/21996bd69c15cb1e5127f76254dfcda019ee432a.diff
LOG: [AMDGPU] Remove amdgpu-no-heap-ptr and amdgpu-no-lds-kernel-id attributes from lowered kernels in amdgpu-sw-lower-lds pass (#120887)
'amdgpu-sw-lower-lds' pass internally calls '__asan_malloc_impl' for
heap memory allocation.
Pass also uses 'amdgcn_lds_kernel_id' for non-kernel lds accesses
lowering.
This patch removes 'amdgpu-no-heap-ptr' and 'amdgpu-no-lds-kernel-id'
from all kernels lowered by the pass.
Added:
llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-no-heap-ptr.ll
Modified:
llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
index c3f41a4cfcf0a1..17207773b4858c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
@@ -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);
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
new file mode 100644
index 00000000000000..b9fa89dd6f0a6a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-no-kernel-lds-id.ll
@@ -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
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
+ at lds_3 = external addrspace(3) global [3 x i8], align 4
+ at 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}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-no-heap-ptr.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-no-heap-ptr.ll
new file mode 100644
index 00000000000000..73ffcdd783ded5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-no-heap-ptr.ll
@@ -0,0 +1,160 @@
+; 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
+
+; Test to check if static LDS accesses in kernel are lowered correctly. Also checks if amdgpu-no-heap-ptr attribute
+; is removed from the list of attributes
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, 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 } }, no_sanitize_address
+;.
+define amdgpu_kernel void @k0() sanitize_address #1 {
+; 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 %[[BB20:.*]]
+; 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 2, 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 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.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: br label %[[BB20]]
+; CHECK: [[BB20]]:
+; CHECK-NEXT: [[XYZCOND:%.*]] = phi i1 [ false, %[[WID]] ], [ true, %[[MALLOC]] ]
+; CHECK-NEXT: call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT: [[TMP21:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT: [[TMP22:%.*]] = 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: [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT: [[TMP24:%.*]] = 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: [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP24]]
+; CHECK-NEXT: [[TMP26:%.*]] = ptrtoint ptr addrspace(3) [[TMP23]] to i32
+; CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP21]], i32 [[TMP26]]
+; CHECK-NEXT: [[TMP28:%.*]] = ptrtoint ptr addrspace(1) [[TMP27]] to i64
+; CHECK-NEXT: [[TMP29:%.*]] = lshr i64 [[TMP28]], 3
+; CHECK-NEXT: [[TMP30:%.*]] = add i64 [[TMP29]], 2147450880
+; CHECK-NEXT: [[TMP31:%.*]] = inttoptr i64 [[TMP30]] to ptr
+; CHECK-NEXT: [[TMP32:%.*]] = load i8, ptr [[TMP31]], align 1
+; CHECK-NEXT: [[TMP33:%.*]] = icmp ne i8 [[TMP32]], 0
+; CHECK-NEXT: [[TMP34:%.*]] = and i64 [[TMP28]], 7
+; CHECK-NEXT: [[TMP35:%.*]] = trunc i64 [[TMP34]] to i8
+; CHECK-NEXT: [[TMP36:%.*]] = icmp sge i8 [[TMP35]], [[TMP32]]
+; CHECK-NEXT: [[TMP37:%.*]] = and i1 [[TMP33]], [[TMP36]]
+; CHECK-NEXT: [[TMP38:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[TMP37]])
+; CHECK-NEXT: [[TMP39:%.*]] = icmp ne i64 [[TMP38]], 0
+; CHECK-NEXT: br i1 [[TMP39]], label %[[ASAN_REPORT:.*]], label %[[BB42:.*]], !prof [[PROF2:![0-9]+]]
+; CHECK: [[ASAN_REPORT]]:
+; CHECK-NEXT: br i1 [[TMP37]], label %[[BB40:.*]], label %[[BB41:.*]]
+; CHECK: [[BB40]]:
+; CHECK-NEXT: call void @__asan_report_store1(i64 [[TMP28]]) #[[ATTR6:[0-9]+]]
+; CHECK-NEXT: call void @llvm.amdgcn.unreachable()
+; CHECK-NEXT: br label %[[BB41]]
+; CHECK: [[BB41]]:
+; CHECK-NEXT: br label %[[BB42]]
+; CHECK: [[BB42]]:
+; CHECK-NEXT: store i8 7, ptr addrspace(1) [[TMP27]], align 4
+; CHECK-NEXT: [[TMP43:%.*]] = ptrtoint ptr addrspace(3) [[TMP25]] to i32
+; CHECK-NEXT: [[TMP44:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP21]], i32 [[TMP43]]
+; CHECK-NEXT: [[TMP45:%.*]] = ptrtoint ptr addrspace(1) [[TMP44]] to i64
+; CHECK-NEXT: [[TMP46:%.*]] = add i64 [[TMP45]], 3
+; CHECK-NEXT: [[TMP47:%.*]] = inttoptr i64 [[TMP46]] to ptr addrspace(1)
+; CHECK-NEXT: [[TMP48:%.*]] = ptrtoint ptr addrspace(1) [[TMP44]] to i64
+; CHECK-NEXT: [[TMP49:%.*]] = lshr i64 [[TMP48]], 3
+; CHECK-NEXT: [[TMP50:%.*]] = add i64 [[TMP49]], 2147450880
+; CHECK-NEXT: [[TMP51:%.*]] = inttoptr i64 [[TMP50]] to ptr
+; CHECK-NEXT: [[TMP52:%.*]] = load i8, ptr [[TMP51]], align 1
+; CHECK-NEXT: [[TMP53:%.*]] = icmp ne i8 [[TMP52]], 0
+; CHECK-NEXT: [[TMP54:%.*]] = and i64 [[TMP48]], 7
+; CHECK-NEXT: [[TMP55:%.*]] = trunc i64 [[TMP54]] to i8
+; CHECK-NEXT: [[TMP56:%.*]] = icmp sge i8 [[TMP55]], [[TMP52]]
+; CHECK-NEXT: [[TMP57:%.*]] = and i1 [[TMP53]], [[TMP56]]
+; CHECK-NEXT: [[TMP58:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[TMP57]])
+; CHECK-NEXT: [[TMP59:%.*]] = icmp ne i64 [[TMP58]], 0
+; CHECK-NEXT: br i1 [[TMP59]], label %[[ASAN_REPORT1:.*]], label %[[BB62:.*]], !prof [[PROF2]]
+; CHECK: [[ASAN_REPORT1]]:
+; CHECK-NEXT: br i1 [[TMP57]], label %[[BB60:.*]], label %[[BB61:.*]]
+; CHECK: [[BB60]]:
+; CHECK-NEXT: call void @__asan_report_store1(i64 [[TMP48]]) #[[ATTR6]]
+; CHECK-NEXT: call void @llvm.amdgcn.unreachable()
+; CHECK-NEXT: br label %[[BB61]]
+; CHECK: [[BB61]]:
+; CHECK-NEXT: br label %[[BB62]]
+; CHECK: [[BB62]]:
+; CHECK-NEXT: [[TMP63:%.*]] = ptrtoint ptr addrspace(1) [[TMP47]] to i64
+; CHECK-NEXT: [[TMP64:%.*]] = lshr i64 [[TMP63]], 3
+; CHECK-NEXT: [[TMP65:%.*]] = add i64 [[TMP64]], 2147450880
+; CHECK-NEXT: [[TMP66:%.*]] = inttoptr i64 [[TMP65]] to ptr
+; CHECK-NEXT: [[TMP67:%.*]] = load i8, ptr [[TMP66]], align 1
+; CHECK-NEXT: [[TMP68:%.*]] = icmp ne i8 [[TMP67]], 0
+; CHECK-NEXT: [[TMP69:%.*]] = and i64 [[TMP63]], 7
+; CHECK-NEXT: [[TMP70:%.*]] = trunc i64 [[TMP69]] to i8
+; CHECK-NEXT: [[TMP71:%.*]] = icmp sge i8 [[TMP70]], [[TMP67]]
+; CHECK-NEXT: [[TMP72:%.*]] = and i1 [[TMP68]], [[TMP71]]
+; CHECK-NEXT: [[TMP73:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[TMP72]])
+; CHECK-NEXT: [[TMP74:%.*]] = icmp ne i64 [[TMP73]], 0
+; CHECK-NEXT: br i1 [[TMP74]], label %[[ASAN_REPORT2:.*]], label %[[BB77:.*]], !prof [[PROF2]]
+; CHECK: [[ASAN_REPORT2]]:
+; CHECK-NEXT: br i1 [[TMP72]], label %[[BB75:.*]], label %[[BB76:.*]]
+; CHECK: [[BB75]]:
+; CHECK-NEXT: call void @__asan_report_store1(i64 [[TMP63]]) #[[ATTR6]]
+; CHECK-NEXT: call void @llvm.amdgcn.unreachable()
+; CHECK-NEXT: br label %[[BB76]]
+; CHECK: [[BB76]]:
+; CHECK-NEXT: br label %[[BB77]]
+; CHECK: [[BB77]]:
+; CHECK-NEXT: store i32 8, ptr addrspace(1) [[TMP44]], 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: [[TMP78:%.*]] = call ptr @llvm.returnaddress(i32 0)
+; CHECK-NEXT: [[TMP79:%.*]] = ptrtoint ptr [[TMP78]] to i64
+; CHECK-NEXT: [[TMP80:%.*]] = ptrtoint ptr addrspace(1) [[TMP21]] to i64
+; CHECK-NEXT: call void @__asan_free_impl(i64 [[TMP80]], i64 [[TMP79]])
+; CHECK-NEXT: br label %[[END]]
+; CHECK: [[END]]:
+; CHECK-NEXT: ret void
+;
+ store i8 7, ptr addrspace(3) @lds_1, align 4
+ 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-heap-ptr" }
+;.
+; 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: attributes #[[ATTR4:[0-9]+]] = { convergent nocallback nofree nounwind willreturn memory(none) }
+; CHECK: attributes #[[ATTR5:[0-9]+]] = { convergent nocallback nofree nounwind }
+; CHECK: attributes #[[ATTR6]] = { nomerge }
+;.
+; CHECK: [[META0]] = !{i32 0, i32 1}
+; CHECK: [[META1:![0-9]+]] = !{i32 4, !"nosanitize_address", i32 1}
+; CHECK: [[PROF2]] = !{!"branch_weights", i32 1, i32 1048575}
+;.
More information about the llvm-commits
mailing list