e2cfbfcc0c
In the spirit of TRegions [0], this patch provides a simpler and uniform interface for a kernel to set up the device runtime. The OMPIRBuilder is used for reuse in Flang. A custom state machine will be generated in the follow up patch. The "surplus" threads of the "master warp" will not exit early anymore so we need to use non-aligned barriers. The new runtime will not have an extra warp but also require these non-aligned barriers. [0] https://link.springer.com/chapter/10.1007/978-3-030-28596-8_11 This was in parts extracted from D59319. Reviewed By: ABataev, JonChesterfield Differential Revision: https://reviews.llvm.org/D101976
58 lines
3.2 KiB
C++
58 lines
3.2 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
|
|
|
|
// RUN: %clang_cc1 -verify -fopenmp -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-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-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-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-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 3 target regions on the gpu is set to SPMD Mode.
|
|
// CHECK-DAG: {{@__omp_offloading_.+l29}}_exec_mode = weak constant i8 0
|
|
// CHECK-DAG: {{@__omp_offloading_.+l33}}_exec_mode = weak constant i8 0
|
|
// CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0
|
|
|
|
template<typename tx>
|
|
tx ftemplate(int n) {
|
|
tx a = 0;
|
|
short aa = 0;
|
|
tx b[10];
|
|
|
|
#pragma omp target parallel proc_bind(master)
|
|
{
|
|
}
|
|
|
|
#pragma omp target parallel proc_bind(spread)
|
|
{
|
|
aa += 1;
|
|
}
|
|
|
|
#pragma omp target parallel proc_bind(close)
|
|
{
|
|
a += 1;
|
|
aa += 1;
|
|
b[2] += 1;
|
|
}
|
|
|
|
return a;
|
|
}
|
|
|
|
int bar(int n){
|
|
int a = 0;
|
|
|
|
a += ftemplate<int>(n);
|
|
|
|
return a;
|
|
}
|
|
|
|
// CHECK-NOT: call void @__kmpc_push_proc_bind
|
|
#endif
|