diff options
Diffstat (limited to 'test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp')
| -rw-r--r-- | test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp | 40 |
1 files changed, 28 insertions, 12 deletions
diff --git a/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp b/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp index 0c06a60e44..fe0c8dfb63 100644 --- a/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp +++ b/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp @@ -1,6 +1,7 @@ // Test target codegen - host bc file has to be created first. // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix CHECK-DIV64 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -fopenmp-optimistic-collapse -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-DIV32 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 @@ -9,11 +10,12 @@ #define HEADER // Check that the execution mode of all 5 target regions on the gpu is set to SPMD Mode. -// CHECK-DAG: {{@__omp_offloading_.+l32}}_exec_mode = weak constant i8 0 -// CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0 -// CHECK-DAG: {{@__omp_offloading_.+l43}}_exec_mode = weak constant i8 0 -// CHECK-DAG: {{@__omp_offloading_.+l48}}_exec_mode = weak constant i8 0 -// CHECK-DAG: {{@__omp_offloading_.+l56}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l34}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l40}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l45}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l50}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l58}}_exec_mode = weak constant i8 0 +// CHECK-DAG: {{@__omp_offloading_.+l65}}_exec_mode = weak constant i8 0 #define N 1000 #define M 10 @@ -53,6 +55,13 @@ tx ftemplate(int n) { } } +#pragma omp target teams distribute parallel for collapse(2) + for(int i = 0; i < n; i++) { + for(int j = 0; j < n; j++) { + c[i][j] = i + j; + } + } + #pragma omp target teams distribute parallel for map(a, v[:N]) for(int i = 0; i < n; i++) a[i] = v[i]; @@ -67,23 +76,23 @@ int bar(int n){ return a; } -// CHECK-DAG: [[MEM_TY:%.+]] = type { [4 x i8] } +// CHECK-DAG: [[MEM_TY:%.+]] = type { [128 x i8] } // CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer // CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null // CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4 // CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1 -// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l32( +// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l34( // CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x() // CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0) -// CHECK: call void @__kmpc_get_team_static_memory(i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} 4, i16 1, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**)) +// CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} 4, i16 1, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**)) // CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]], // CHECK: [[BC:%.+]] = bitcast i8* [[TEAM_ALLOC]] to [[REC:%.+]]* // CHECK: getelementptr inbounds [[REC]], [[REC]]* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91, // CHECK: {{call|invoke}} void [[OUTL1:@.+]]( // CHECK: call void @__kmpc_for_static_fini( -// CHECK: call void @__kmpc_restore_team_static_memory(i16 1) +// CHECK: call void @__kmpc_restore_team_static_memory(i16 1, i16 1) // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0) // CHECK: ret void @@ -207,12 +216,19 @@ int bar(int n){ // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0) // CHECK: ret void -// CHECK: define internal void [[OUTL4]]( +// CHECK-32: define internal void [[OUTL4]]( +// CHECK-64: define internal void [[OUTL4]]( // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33, // CHECK: call void @__kmpc_for_static_fini( // CHECK: ret void -// CHECK: define weak void @__omp_offloading_{{.*}}_l56(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{[^)]+}}) +// CHECK: define weak void @__omp_offloading_{{.*}}_l58(i[[SZ:64|32]] %{{[^,]+}}, [10 x [10 x i32]]* dereferenceable{{.*}}) +// CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [10 x [10 x i32]]* %{{.*}}) +// CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [10 x [10 x i32]]* dereferenceable{{.*}}) +// CHECK-DIV64: div i64 +// CHECK-DIV32-NO: div i64 + +// CHECK: define weak void @__omp_offloading_{{.*}}_l65(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{[^)]+}}) // CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [1000 x i32]* %{{.*}}, i32* %{{.*}}) // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{.*}}) |