[clang] b8e3077 - [Clang][OpenMP] Fix the issue that list items in `has_device_addr` are still mapped to the target device
Shilei Tian via cfe-commits
cfe-commits at lists.llvm.org
Thu May 25 17:19:12 PDT 2023
Author: Shilei Tian
Date: 2023-05-25T20:19:07-04:00
New Revision: b8e3077d60de73ddcb1511a68af3fdd37fe81cf7
URL: https://github.com/llvm/llvm-project/commit/b8e3077d60de73ddcb1511a68af3fdd37fe81cf7
DIFF: https://github.com/llvm/llvm-project/commit/b8e3077d60de73ddcb1511a68af3fdd37fe81cf7.diff
LOG: [Clang][OpenMP] Fix the issue that list items in `has_device_addr` are still mapped to the target device
This patch fixes the issue that list items in `has_device_addr` are still mapped
to the target device because front end emits map type `OMP_MAP_TO`.
Fix #59160.
Reviewed By: jyu2
Differential Revision: https://reviews.llvm.org/D141627
Added:
clang/test/OpenMP/bug59160.c
Modified:
clang/lib/CodeGen/CGOpenMPRuntime.cpp
Removed:
################################################################################
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index 8900f33383e21..ff6d1d4ed869f 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -8640,9 +8640,7 @@ class MappableExprsHandler {
CGF.getTypeSize(CGF.getContext().VoidPtrTy), CGF.Int64Ty,
/*isSigned=*/true));
CombinedInfo.Types.push_back(
- (Cap->capturesVariable()
- ? OpenMPOffloadMappingFlags::OMP_MAP_TO
- : OpenMPOffloadMappingFlags::OMP_MAP_LITERAL) |
+ OpenMPOffloadMappingFlags::OMP_MAP_LITERAL |
OpenMPOffloadMappingFlags::OMP_MAP_TARGET_PARAM);
CombinedInfo.Mappers.push_back(nullptr);
return;
diff --git a/clang/test/OpenMP/bug59160.c b/clang/test/OpenMP/bug59160.c
new file mode 100644
index 0000000000000..49522fe9ef859
--- /dev/null
+++ b/clang/test/OpenMP/bug59160.c
@@ -0,0 +1,175 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-globals --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" --prefix-filecheck-ir-name _
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -fopenmp-version=51 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp-simd -fopenmp-version=51 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
+// expected-no-diagnostics
+
+void zoo(void) {
+ short x[10];
+ short *(xp[10]);
+ xp[1] = &x[0];
+ short **xpp = &xp[0];
+ x[1] = 111;
+#pragma omp target data map(tofrom: xpp[1][1]) use_device_addr(xpp[1][1])
+#pragma omp target has_device_addr(xpp[1][1])
+ {
+ xpp[1][1] = 222;
+ }
+}
+//.
+// CHECK: @.offload_sizes = private unnamed_addr constant [2 x i64] [i64 8, i64 2]
+// CHECK: @.offload_maptypes = private unnamed_addr constant [2 x i64] [i64 67, i64 19]
+// CHECK: @0 = private unnamed_addr constant [23 x i8] c"
+// CHECK: @1 = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 22, ptr @0 }, align 8
+// CHECK: @.__omp_offloading_34_735f4a3a_zoo_l13.region_id = weak constant i8 0
+// CHECK: @.offload_sizes.1 = private unnamed_addr constant [1 x i64] [i64 8]
+// CHECK: @.offload_maptypes.2 = private unnamed_addr constant [1 x i64] [i64 288]
+// CHECK: @.omp_offloading.entry_name = internal unnamed_addr constant [37 x i8] c"__omp_offloading_34_735f4a3a_zoo_l13\00"
+// CHECK: @.omp_offloading.entry.__omp_offloading_34_735f4a3a_zoo_l13 = weak constant %struct.__tgt_offload_entry { ptr @.__omp_offloading_34_735f4a3a_zoo_l13.region_id, ptr @.omp_offloading.entry_name, i64 0, i32 0, i32 0 }, section "omp_offloading_entries", align 1
+// CHECK: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 0, ptr @.omp_offloading.requires_reg, ptr null }]
+//.
+// CHECK-LABEL: define {{[^@]+}}@zoo
+// CHECK-SAME: () #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[X:%.*]] = alloca [10 x i16], align 2
+// CHECK-NEXT: [[XP:%.*]] = alloca [10 x ptr], align 8
+// CHECK-NEXT: [[XPP:%.*]] = alloca ptr, align 8
+// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [2 x ptr], align 8
+// CHECK-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [2 x ptr], align 8
+// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [2 x ptr], align 8
+// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS7:%.*]] = alloca [1 x ptr], align 8
+// CHECK-NEXT: [[DOTOFFLOAD_PTRS8:%.*]] = alloca [1 x ptr], align 8
+// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS9:%.*]] = alloca [1 x ptr], align 8
+// CHECK-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
+// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i16], ptr [[X]], i64 0, i64 0
+// CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [10 x ptr], ptr [[XP]], i64 0, i64 1
+// CHECK-NEXT: store ptr [[ARRAYIDX]], ptr [[ARRAYIDX1]], align 8
+// CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [10 x ptr], ptr [[XP]], i64 0, i64 0
+// CHECK-NEXT: store ptr [[ARRAYIDX2]], ptr [[XPP]], align 8
+// CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [10 x i16], ptr [[X]], i64 0, i64 1
+// CHECK-NEXT: store i16 111, ptr [[ARRAYIDX3]], align 2
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[XPP]], align 8
+// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[XPP]], align 8
+// CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds ptr, ptr [[TMP1]], i64 1
+// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[XPP]], align 8
+// CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
+// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[ARRAYIDX5]], align 8
+// CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i16, ptr [[TMP3]], i64 1
+// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK-NEXT: store ptr [[TMP0]], ptr [[TMP4]], align 8
+// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK-NEXT: store ptr [[ARRAYIDX4]], ptr [[TMP5]], align 8
+// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
+// CHECK-NEXT: store ptr null, ptr [[TMP6]], align 8
+// CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
+// CHECK-NEXT: store ptr [[ARRAYIDX4]], ptr [[TMP7]], align 8
+// CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
+// CHECK-NEXT: store ptr [[ARRAYIDX6]], ptr [[TMP8]], align 8
+// CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
+// CHECK-NEXT: store ptr null, ptr [[TMP9]], align 8
+// CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK-NEXT: call void @__tgt_target_data_begin_mapper(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 2, ptr [[TMP10]], ptr [[TMP11]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
+// CHECK-NEXT: [[TMP12:%.*]] = load ptr, ptr [[TMP4]], align 8
+// CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
+// CHECK-NEXT: store ptr [[TMP12]], ptr [[TMP13]], align 8
+// CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
+// CHECK-NEXT: store ptr [[TMP12]], ptr [[TMP14]], align 8
+// CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_MAPPERS9]], i64 0, i64 0
+// CHECK-NEXT: store ptr null, ptr [[TMP15]], align 8
+// CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
+// CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
+// CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
+// CHECK-NEXT: store i32 2, ptr [[TMP18]], align 4
+// CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
+// CHECK-NEXT: store i32 1, ptr [[TMP19]], align 4
+// CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
+// CHECK-NEXT: store ptr [[TMP16]], ptr [[TMP20]], align 8
+// CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
+// CHECK-NEXT: store ptr [[TMP17]], ptr [[TMP21]], align 8
+// CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
+// CHECK-NEXT: store ptr @.offload_sizes.1, ptr [[TMP22]], align 8
+// CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
+// CHECK-NEXT: store ptr @.offload_maptypes.2, ptr [[TMP23]], align 8
+// CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
+// CHECK-NEXT: store ptr null, ptr [[TMP24]], align 8
+// CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
+// CHECK-NEXT: store ptr null, ptr [[TMP25]], align 8
+// CHECK-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
+// CHECK-NEXT: store i64 0, ptr [[TMP26]], align 8
+// CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
+// CHECK-NEXT: store i64 0, ptr [[TMP27]], align 8
+// CHECK-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
+// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP28]], align 4
+// CHECK-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
+// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP29]], align 4
+// CHECK-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
+// CHECK-NEXT: store i32 0, ptr [[TMP30]], align 4
+// CHECK-NEXT: [[TMP31:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_zoo_l13.region_id, ptr [[KERNEL_ARGS]])
+// CHECK-NEXT: [[TMP32:%.*]] = icmp ne i32 [[TMP31]], 0
+// CHECK-NEXT: br i1 [[TMP32]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
+// CHECK: omp_offload.failed:
+// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_zoo_l13(ptr [[TMP12]]) #[[ATTR1:[0-9]+]]
+// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT]]
+// CHECK: omp_offload.cont:
+// CHECK-NEXT: [[TMP33:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK-NEXT: [[TMP34:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK-NEXT: call void @__tgt_target_data_end_mapper(ptr @[[GLOB1]], i64 -1, i32 2, ptr [[TMP33]], ptr [[TMP34]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
+// CHECK-NEXT: ret void
+//
+//
+// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_zoo_l13
+// CHECK-SAME: (ptr noundef [[XPP:%.*]]) #[[ATTR2:[0-9]+]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[XPP_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT: store ptr [[XPP]], ptr [[XPP_ADDR]], align 8
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[XPP_ADDR]], align 8
+// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 1
+// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX]], align 8
+// CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i16, ptr [[TMP1]], i64 1
+// CHECK-NEXT: store i16 222, ptr [[ARRAYIDX1]], align 2
+// CHECK-NEXT: ret void
+//
+//
+// CHECK-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
+// CHECK-SAME: () #[[ATTR3:[0-9]+]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: call void @__tgt_register_requires(i64 1)
+// CHECK-NEXT: ret void
+//
+//
+// SIMD-ONLY0-LABEL: define {{[^@]+}}@zoo
+// SIMD-ONLY0-SAME: () #[[ATTR0:[0-9]+]] {
+// SIMD-ONLY0-NEXT: entry:
+// SIMD-ONLY0-NEXT: [[X:%.*]] = alloca [10 x i16], align 2
+// SIMD-ONLY0-NEXT: [[XP:%.*]] = alloca [10 x ptr], align 8
+// SIMD-ONLY0-NEXT: [[XPP:%.*]] = alloca ptr, align 8
+// SIMD-ONLY0-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i16], ptr [[X]], i64 0, i64 0
+// SIMD-ONLY0-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [10 x ptr], ptr [[XP]], i64 0, i64 1
+// SIMD-ONLY0-NEXT: store ptr [[ARRAYIDX]], ptr [[ARRAYIDX1]], align 8
+// SIMD-ONLY0-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [10 x ptr], ptr [[XP]], i64 0, i64 0
+// SIMD-ONLY0-NEXT: store ptr [[ARRAYIDX2]], ptr [[XPP]], align 8
+// SIMD-ONLY0-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [10 x i16], ptr [[X]], i64 0, i64 1
+// SIMD-ONLY0-NEXT: store i16 111, ptr [[ARRAYIDX3]], align 2
+// SIMD-ONLY0-NEXT: [[TMP0:%.*]] = load ptr, ptr [[XPP]], align 8
+// SIMD-ONLY0-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 1
+// SIMD-ONLY0-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX4]], align 8
+// SIMD-ONLY0-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i16, ptr [[TMP1]], i64 1
+// SIMD-ONLY0-NEXT: store i16 222, ptr [[ARRAYIDX5]], align 2
+// SIMD-ONLY0-NEXT: ret void
+//
+//.
+// CHECK: attributes #0 = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="-altivec,-bpermd,-crbits,-crypto,-direct-move,-extdiv,-htm,-isa-v206-instructions,-isa-v207-instructions,-isa-v30-instructions,-power8-vector,-power9-vector,-privileged,-quadword-atomics,-rop-protect,-spe,-vsx" }
+// CHECK: attributes #1 = { nounwind }
+// CHECK: attributes #2 = { noinline norecurse nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="-altivec,-bpermd,-crbits,-crypto,-direct-move,-extdiv,-htm,-isa-v206-instructions,-isa-v207-instructions,-isa-v30-instructions,-power8-vector,-power9-vector,-privileged,-quadword-atomics,-rop-protect,-spe,-vsx" }
+// CHECK: attributes #3 = { noinline nounwind "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="-altivec,-bpermd,-crbits,-crypto,-direct-move,-extdiv,-htm,-isa-v206-instructions,-isa-v207-instructions,-isa-v30-instructions,-power8-vector,-power9-vector,-privileged,-quadword-atomics,-rop-protect,-spe,-vsx" }
+//.
+// SIMD-ONLY0: attributes #0 = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="-altivec,-bpermd,-crbits,-crypto,-direct-move,-extdiv,-htm,-isa-v206-instructions,-isa-v207-instructions,-isa-v30-instructions,-power8-vector,-power9-vector,-privileged,-quadword-atomics,-rop-protect,-spe,-vsx" }
+//.
+// CHECK: !0 = !{i32 0, i32 52, i32 1935624762, !"zoo", i32 13, i32 0, i32 0}
+// CHECK: !1 = !{i32 1, !"wchar_size", i32 4}
+// CHECK: !2 = !{i32 7, !"openmp", i32 51}
+// CHECK: !3 = !{!"clang version 17.0.0"}
+//.
+// SIMD-ONLY0: !0 = !{i32 1, !"wchar_size", i32 4}
+// SIMD-ONLY0: !1 = !{!"clang version 17.0.0"}
+//.
More information about the cfe-commits
mailing list