cd0ea03e6f
Summary: We carried a lot of unused and untested code in the device runtime. Among other reasons, we are planning major rewrites for which reduced size is going to help a lot. The number of code lines reduced by 14%! Before: ------------------------------------------------------------------------------- Language files blank comment code ------------------------------------------------------------------------------- CUDA 13 489 841 2454 C/C++ Header 14 322 493 1377 C 12 117 124 559 CMake 4 64 64 262 C++ 1 6 6 39 ------------------------------------------------------------------------------- SUM: 44 998 1528 4691 ------------------------------------------------------------------------------- After: ------------------------------------------------------------------------------- Language files blank comment code ------------------------------------------------------------------------------- CUDA 13 366 733 1879 C/C++ Header 14 317 484 1293 C 12 117 124 559 CMake 4 64 64 262 C++ 1 6 6 39 ------------------------------------------------------------------------------- SUM: 44 870 1411 4032 ------------------------------------------------------------------------------- Reviewers: hfinkel, jhuber6, fghanim, JonChesterfield, grokos, AndreyChurbanov, ye-luo, tianshilei1992, ggeorgakoudis, Hahnfeld, ABataev, hbae, ronlieb, gregrodgers Subscribers: jvesely, yaxunl, bollu, guansong, jfb, sstefan1, aaron.ballman, openmp-commits, cfe-commits Tags: #clang, #openmp Differential Revision: https://reviews.llvm.org/D83349
87 lines
3.5 KiB
C++
87 lines
3.5 KiB
C++
// 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 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
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
// Check that the execution mode of all 2 target regions on the gpu is set to NonSPMD Mode.
|
|
// CHECK-DAG: {{@__omp_offloading_.+l25}}_exec_mode = weak constant i8 0
|
|
// CHECK-DAG: {{@__omp_offloading_.+l30}}_exec_mode = weak constant i8 0
|
|
// CHECK-DAG: {{@__omp_offloading_.+l35}}_exec_mode = weak constant i8 0
|
|
// CHECK-DAG: {{@__omp_offloading_.+l40}}_exec_mode = weak constant i8 0
|
|
|
|
#define N 1000
|
|
|
|
template<typename tx>
|
|
tx ftemplate(int n) {
|
|
tx a[N];
|
|
short aa[N];
|
|
tx b[10];
|
|
|
|
#pragma omp target simd
|
|
for(int i = 0; i < n; i++) {
|
|
a[i] = 1;
|
|
}
|
|
|
|
#pragma omp target simd
|
|
for (int i = 0; i < n; i++) {
|
|
aa[i] += 1;
|
|
}
|
|
|
|
#pragma omp target simd
|
|
for(int i = 0; i < 10; i++) {
|
|
b[i] += 1;
|
|
}
|
|
|
|
#pragma omp target simd reduction(+:n)
|
|
for(int i = 0; i < 10; i++) {
|
|
b[i] += 1;
|
|
}
|
|
|
|
return a[0];
|
|
}
|
|
|
|
int bar(int n){
|
|
int a = 0;
|
|
|
|
a += ftemplate<int>(n);
|
|
|
|
return a;
|
|
}
|
|
|
|
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+l25}}(
|
|
// CHECK: call void @__kmpc_spmd_kernel_init(i32 %{{.+}}, i16 0, i16 0)
|
|
// CHECK-NOT: call void @__kmpc_for_static_init
|
|
// CHECK-NOT: call void @__kmpc_for_static_fini
|
|
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
|
|
// CHECK: ret void
|
|
|
|
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+l30}}(
|
|
// CHECK: call void @__kmpc_spmd_kernel_init(i32 %{{.+}}, i16 0, i16 0)
|
|
// CHECK-NOT: call void @__kmpc_for_static_init
|
|
// CHECK-NOT: call void @__kmpc_for_static_fini
|
|
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
|
|
// CHECK: ret void
|
|
|
|
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+l35}}(
|
|
// CHECK: call void @__kmpc_spmd_kernel_init(i32 %{{.+}}, i16 0, i16 0)
|
|
// CHECK-NOT: call void @__kmpc_for_static_init
|
|
// CHECK-NOT: call void @__kmpc_for_static_fini
|
|
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
|
|
// CHECK: ret void
|
|
|
|
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+l40}}(
|
|
// CHECK: call void @__kmpc_spmd_kernel_init(i32 %{{.+}}, i16 0, i16 0)
|
|
// CHECK-NOT: call void @__kmpc_for_static_init
|
|
// CHECK-NOT: call void @__kmpc_for_static_fini
|
|
// CHECK-NOT: call void @__kmpc_nvptx_end_reduce_nowait(
|
|
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
|
|
// CHECK: ret void
|
|
|
|
|
|
#endif
|