[clang] e831a32 - [Clang][OpenMP] Clang adding the addrSpace according to DataLayout fix (#65483)
via cfe-commits
cfe-commits at lists.llvm.org
Tue Sep 12 12:44:44 PDT 2023
Author: Aaron Jarmusch
Date: 2023-09-12T15:44:39-04:00
New Revision: e831a32c93c1ab404785773cc7c08c01730d61e5
URL: https://github.com/llvm/llvm-project/commit/e831a32c93c1ab404785773cc7c08c01730d61e5
DIFF: https://github.com/llvm/llvm-project/commit/e831a32c93c1ab404785773cc7c08c01730d61e5.diff
LOG: [Clang][OpenMP] Clang adding the addrSpace according to DataLayout fix (#65483)
Fix for an issue where clang was not adding the address space according
to the data layout, instead was using the default which resulted in a
crash at times. The fix includes changes to the cases of
LargeCapMemAlloc and CGroupMemAlloc where we are setting the AddrSpace
according to the DataLayout.
Added:
clang/test/OpenMP/test_target_uses_allocators_large_cap_codegen.cpp
Modified:
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
Removed:
################################################################################
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 1ec9bb3d5234714..2e022b5cdf762f4 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3362,6 +3362,7 @@ Address CGOpenMPRuntimeGPU::getAddressOfLocalVariable(CodeGenFunction &CGF,
break;
case OMPAllocateDeclAttr::OMPLargeCapMemAlloc:
case OMPAllocateDeclAttr::OMPCGroupMemAlloc:
+ AS = getLangASFromTargetAS(CGF.CGM.getModule().getDataLayout().getDefaultGlobalsAddressSpace());
break;
}
llvm::Type *VarTy = CGF.ConvertTypeForMem(VD->getType());
diff --git a/clang/test/OpenMP/test_target_uses_allocators_large_cap_codegen.cpp b/clang/test/OpenMP/test_target_uses_allocators_large_cap_codegen.cpp
new file mode 100644
index 000000000000000..3ec4ba4c075a263
--- /dev/null
+++ b/clang/test/OpenMP/test_target_uses_allocators_large_cap_codegen.cpp
@@ -0,0 +1,296 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _ --version 3
+// Test host codegen.
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK1
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK3
+
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK9
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK9
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK11
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK11
+
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+
+// Test host codegen.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK1
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK3
+
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK9
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK9
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK11
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK11
+
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
+
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+#define N 1024
+
+enum omp_allocator_handle_t {
+ omp_null_allocator = 0,
+ omp_default_mem_alloc = 1,
+ omp_large_cap_mem_alloc = 2,
+ omp_const_mem_alloc = 3,
+ omp_high_bw_mem_alloc = 4,
+ omp_low_lat_mem_alloc = 5,
+ omp_cgroup_mem_alloc = 6,
+ omp_pteam_mem_alloc = 7,
+ omp_thread_mem_alloc = 8,
+ KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
+};
+
+
+int test_uses_allocators_large_cap() {
+ int x = 0;
+ int device_result = 0;
+
+#pragma omp target uses_allocators(omp_large_cap_mem_alloc) allocate(omp_large_cap_mem_alloc: x) firstprivate(x) map(from: device_result)
+{
+}
+
+ return 0;
+}
+
+#endif
+// CHECK1-LABEL: define dso_local noundef signext i32 @_Z30test_uses_allocators_large_capv(
+// CHECK1-SAME: ) #[[ATTR0:[0-9]+]] {
+// CHECK1-NEXT: entry:
+// CHECK1-NEXT: [[X:%.*]] = alloca i32, align 4
+// CHECK1-NEXT: [[DEVICE_RESULT:%.*]] = alloca i32, align 4
+// CHECK1-NEXT: [[X_CASTED:%.*]] = alloca i64, align 8
+// CHECK1-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [2 x ptr], align 8
+// CHECK1-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [2 x ptr], align 8
+// CHECK1-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [2 x ptr], align 8
+// CHECK1-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
+// CHECK1-NEXT: store i32 0, ptr [[X]], align 4
+// CHECK1-NEXT: store i32 0, ptr [[DEVICE_RESULT]], align 4
+// CHECK1-NEXT: [[TMP0:%.*]] = load i32, ptr [[X]], align 4
+// CHECK1-NEXT: store i32 [[TMP0]], ptr [[X_CASTED]], align 4
+// CHECK1-NEXT: [[TMP1:%.*]] = load i64, ptr [[X_CASTED]], align 8
+// CHECK1-NEXT: [[TMP2:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK1-NEXT: store i64 [[TMP1]], ptr [[TMP2]], align 8
+// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK1-NEXT: store i64 [[TMP1]], ptr [[TMP3]], align 8
+// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
+// CHECK1-NEXT: store ptr null, ptr [[TMP4]], align 8
+// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
+// CHECK1-NEXT: store ptr [[DEVICE_RESULT]], ptr [[TMP5]], align 8
+// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
+// CHECK1-NEXT: store ptr [[DEVICE_RESULT]], ptr [[TMP6]], align 8
+// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
+// CHECK1-NEXT: store ptr null, ptr [[TMP7]], align 8
+// CHECK1-NEXT: [[TMP8:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK1-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
+// CHECK1-NEXT: store i32 2, ptr [[TMP10]], align 4
+// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
+// CHECK1-NEXT: store i32 2, ptr [[TMP11]], align 4
+// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
+// CHECK1-NEXT: store ptr [[TMP8]], ptr [[TMP12]], align 8
+// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
+// CHECK1-NEXT: store ptr [[TMP9]], ptr [[TMP13]], align 8
+// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
+// CHECK1-NEXT: store ptr @.offload_sizes, ptr [[TMP14]], align 8
+// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
+// CHECK1-NEXT: store ptr @.offload_maptypes, ptr [[TMP15]], align 8
+// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
+// CHECK1-NEXT: store ptr null, ptr [[TMP16]], align 8
+// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
+// CHECK1-NEXT: store ptr null, ptr [[TMP17]], align 8
+// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
+// CHECK1-NEXT: store i64 0, ptr [[TMP18]], align 8
+// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
+// CHECK1-NEXT: store i64 0, ptr [[TMP19]], align 8
+// CHECK1-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
+// CHECK1-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP20]], align 4
+// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
+// CHECK1-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP21]], align 4
+// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
+// CHECK1-NEXT: store i32 0, ptr [[TMP22]], align 4
+// CHECK1-NEXT: [[TMP23:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102.region_id, ptr [[KERNEL_ARGS]])
+// CHECK1-NEXT: [[TMP24:%.*]] = icmp ne i32 [[TMP23]], 0
+// CHECK1-NEXT: br i1 [[TMP24]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
+// CHECK1: omp_offload.failed:
+// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(i64 [[TMP1]]) #[[ATTR2:[0-9]+]]
+// CHECK1-NEXT: br label [[OMP_OFFLOAD_CONT]]
+// CHECK1: omp_offload.cont:
+// CHECK1-NEXT: ret i32 0
+//
+//
+// CHECK1-LABEL: define internal void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(
+// CHECK1-SAME: i64 noundef [[X:%.*]]) #[[ATTR1:[0-9]+]] {
+// CHECK1-NEXT: entry:
+// CHECK1-NEXT: [[X_ADDR:%.*]] = alloca i64, align 8
+// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
+// CHECK1-NEXT: store i64 [[X]], ptr [[X_ADDR]], align 8
+// CHECK1-NEXT: [[DOTX__VOID_ADDR:%.*]] = call ptr @__kmpc_alloc(i32 [[TMP0]], i64 4, ptr inttoptr (i64 2 to ptr))
+// CHECK1-NEXT: [[TMP1:%.*]] = load i32, ptr [[X_ADDR]], align 4
+// CHECK1-NEXT: store i32 [[TMP1]], ptr [[DOTX__VOID_ADDR]], align 4
+// CHECK1-NEXT: call void @__kmpc_free(i32 [[TMP0]], ptr [[DOTX__VOID_ADDR]], ptr inttoptr (i64 2 to ptr))
+// CHECK1-NEXT: ret void
+//
+//
+// CHECK1-LABEL: define internal void @.omp_offloading.requires_reg(
+// CHECK1-SAME: ) #[[ATTR3:[0-9]+]] {
+// CHECK1-NEXT: entry:
+// CHECK1-NEXT: call void @__tgt_register_requires(i64 1)
+// CHECK1-NEXT: ret void
+//
+//
+// CHECK3-LABEL: define dso_local noundef i32 @_Z30test_uses_allocators_large_capv(
+// CHECK3-SAME: ) #[[ATTR0:[0-9]+]] {
+// CHECK3-NEXT: entry:
+// CHECK3-NEXT: [[X:%.*]] = alloca i32, align 4
+// CHECK3-NEXT: [[DEVICE_RESULT:%.*]] = alloca i32, align 4
+// CHECK3-NEXT: [[X_CASTED:%.*]] = alloca i32, align 4
+// CHECK3-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [2 x ptr], align 4
+// CHECK3-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [2 x ptr], align 4
+// CHECK3-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [2 x ptr], align 4
+// CHECK3-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
+// CHECK3-NEXT: store i32 0, ptr [[X]], align 4
+// CHECK3-NEXT: store i32 0, ptr [[DEVICE_RESULT]], align 4
+// CHECK3-NEXT: [[TMP0:%.*]] = load i32, ptr [[X]], align 4
+// CHECK3-NEXT: store i32 [[TMP0]], ptr [[X_CASTED]], align 4
+// CHECK3-NEXT: [[TMP1:%.*]] = load i32, ptr [[X_CASTED]], align 4
+// CHECK3-NEXT: [[TMP2:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK3-NEXT: store i32 [[TMP1]], ptr [[TMP2]], align 4
+// CHECK3-NEXT: [[TMP3:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK3-NEXT: store i32 [[TMP1]], ptr [[TMP3]], align 4
+// CHECK3-NEXT: [[TMP4:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
+// CHECK3-NEXT: store ptr null, ptr [[TMP4]], align 4
+// CHECK3-NEXT: [[TMP5:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
+// CHECK3-NEXT: store ptr [[DEVICE_RESULT]], ptr [[TMP5]], align 4
+// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
+// CHECK3-NEXT: store ptr [[DEVICE_RESULT]], ptr [[TMP6]], align 4
+// CHECK3-NEXT: [[TMP7:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
+// CHECK3-NEXT: store ptr null, ptr [[TMP7]], align 4
+// CHECK3-NEXT: [[TMP8:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
+// CHECK3-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
+// CHECK3-NEXT: store i32 2, ptr [[TMP10]], align 4
+// CHECK3-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
+// CHECK3-NEXT: store i32 2, ptr [[TMP11]], align 4
+// CHECK3-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
+// CHECK3-NEXT: store ptr [[TMP8]], ptr [[TMP12]], align 4
+// CHECK3-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
+// CHECK3-NEXT: store ptr [[TMP9]], ptr [[TMP13]], align 4
+// CHECK3-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
+// CHECK3-NEXT: store ptr @.offload_sizes, ptr [[TMP14]], align 4
+// CHECK3-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
+// CHECK3-NEXT: store ptr @.offload_maptypes, ptr [[TMP15]], align 4
+// CHECK3-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
+// CHECK3-NEXT: store ptr null, ptr [[TMP16]], align 4
+// CHECK3-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
+// CHECK3-NEXT: store ptr null, ptr [[TMP17]], align 4
+// CHECK3-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
+// CHECK3-NEXT: store i64 0, ptr [[TMP18]], align 8
+// CHECK3-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
+// CHECK3-NEXT: store i64 0, ptr [[TMP19]], align 8
+// CHECK3-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
+// CHECK3-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP20]], align 4
+// CHECK3-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
+// CHECK3-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP21]], align 4
+// CHECK3-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
+// CHECK3-NEXT: store i32 0, ptr [[TMP22]], align 4
+// CHECK3-NEXT: [[TMP23:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102.region_id, ptr [[KERNEL_ARGS]])
+// CHECK3-NEXT: [[TMP24:%.*]] = icmp ne i32 [[TMP23]], 0
+// CHECK3-NEXT: br i1 [[TMP24]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
+// CHECK3: omp_offload.failed:
+// CHECK3-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(i32 [[TMP1]]) #[[ATTR2:[0-9]+]]
+// CHECK3-NEXT: br label [[OMP_OFFLOAD_CONT]]
+// CHECK3: omp_offload.cont:
+// CHECK3-NEXT: ret i32 0
+//
+//
+// CHECK3-LABEL: define internal void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(
+// CHECK3-SAME: i32 noundef [[X:%.*]]) #[[ATTR1:[0-9]+]] {
+// CHECK3-NEXT: entry:
+// CHECK3-NEXT: [[X_ADDR:%.*]] = alloca i32, align 4
+// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
+// CHECK3-NEXT: store i32 [[X]], ptr [[X_ADDR]], align 4
+// CHECK3-NEXT: [[DOTX__VOID_ADDR:%.*]] = call ptr @__kmpc_alloc(i32 [[TMP0]], i32 4, ptr inttoptr (i32 2 to ptr))
+// CHECK3-NEXT: [[TMP1:%.*]] = load i32, ptr [[X_ADDR]], align 4
+// CHECK3-NEXT: store i32 [[TMP1]], ptr [[DOTX__VOID_ADDR]], align 4
+// CHECK3-NEXT: call void @__kmpc_free(i32 [[TMP0]], ptr [[DOTX__VOID_ADDR]], ptr inttoptr (i32 2 to ptr))
+// CHECK3-NEXT: ret void
+//
+//
+// CHECK3-LABEL: define internal void @.omp_offloading.requires_reg(
+// CHECK3-SAME: ) #[[ATTR3:[0-9]+]] {
+// CHECK3-NEXT: entry:
+// CHECK3-NEXT: call void @__tgt_register_requires(i64 1)
+// CHECK3-NEXT: ret void
+//
+//
+// CHECK9-LABEL: define weak_odr protected void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(
+// CHECK9-SAME: i64 noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK9-NEXT: entry:
+// CHECK9-NEXT: [[X_ADDR:%.*]] = alloca i64, align 8
+// CHECK9-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
+// CHECK9-NEXT: store i64 [[X]], ptr [[X_ADDR]], align 8
+// CHECK9-NEXT: [[DOTX__VOID_ADDR:%.*]] = call ptr @__kmpc_alloc(i32 [[TMP0]], i64 4, ptr inttoptr (i64 2 to ptr))
+// CHECK9-NEXT: [[TMP1:%.*]] = load i32, ptr [[X_ADDR]], align 4
+// CHECK9-NEXT: store i32 [[TMP1]], ptr [[DOTX__VOID_ADDR]], align 4
+// CHECK9-NEXT: call void @__kmpc_free(i32 [[TMP0]], ptr [[DOTX__VOID_ADDR]], ptr inttoptr (i64 2 to ptr))
+// CHECK9-NEXT: ret void
+//
+//
+// CHECK11-LABEL: define weak_odr protected void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z30test_uses_allocators_large_capv_l102(
+// CHECK11-SAME: i32 noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK11-NEXT: entry:
+// CHECK11-NEXT: [[X_ADDR:%.*]] = alloca i32, align 4
+// CHECK11-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
+// CHECK11-NEXT: store i32 [[X]], ptr [[X_ADDR]], align 4
+// CHECK11-NEXT: [[DOTX__VOID_ADDR:%.*]] = call ptr @__kmpc_alloc(i32 [[TMP0]], i32 4, ptr inttoptr (i32 2 to ptr))
+// CHECK11-NEXT: [[TMP1:%.*]] = load i32, ptr [[X_ADDR]], align 4
+// CHECK11-NEXT: store i32 [[TMP1]], ptr [[DOTX__VOID_ADDR]], align 4
+// CHECK11-NEXT: call void @__kmpc_free(i32 [[TMP0]], ptr [[DOTX__VOID_ADDR]], ptr inttoptr (i32 2 to ptr))
+// CHECK11-NEXT: ret void
+//
More information about the cfe-commits
mailing list