mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2025-05-14 01:46:41 +00:00
f05b58a946
I'm using clang to compile CUDA code. And just found that clang doesn't support the per-thread stream option for NV CUDA. I don't know if there is another solution. Reviewed By: tra Differential Revision: https://reviews.llvm.org/D154822
45 lines
1.8 KiB
Plaintext
45 lines
1.8 KiB
Plaintext
// RUN: %clang_cc1 -target-sdk-version=8.0 -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=CUDA-OLD,CHECK
|
|
// RUN: %clang_cc1 -target-sdk-version=9.2 -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=CUDA-NEW,CHECK
|
|
// RUN: %clang_cc1 -target-sdk-version=9.2 -emit-llvm %s -o - \
|
|
// RUN: -fgpu-default-stream=per-thread -DCUDA_API_PER_THREAD_DEFAULT_STREAM \
|
|
// RUN: | FileCheck %s --check-prefixes=CUDA-PTH,CHECK
|
|
// RUN: %clang_cc1 -x hip -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=HIP-OLD,CHECK
|
|
// RUN: %clang_cc1 -fhip-new-launch-api -x hip -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=HIP-NEW,LEGACY,CHECK
|
|
// RUN: %clang_cc1 -fhip-new-launch-api -x hip -emit-llvm %s -o - \
|
|
// RUN: -fgpu-default-stream=legacy \
|
|
// RUN: | FileCheck %s --check-prefixes=HIP-NEW,LEGACY,CHECK
|
|
// RUN: %clang_cc1 -fhip-new-launch-api -x hip -emit-llvm %s -o - \
|
|
// RUN: -fgpu-default-stream=per-thread -DHIP_API_PER_THREAD_DEFAULT_STREAM \
|
|
// RUN: | FileCheck %s --check-prefixes=HIP-NEW,PTH,CHECK
|
|
|
|
#include "Inputs/cuda.h"
|
|
|
|
// CHECK-LABEL: define{{.*}}g1
|
|
// HIP-OLD: call{{.*}}hipSetupArgument
|
|
// HIP-OLD: call{{.*}}hipLaunchByPtr
|
|
// HIP-NEW: call{{.*}}__hipPopCallConfiguration
|
|
// LEGACY: call{{.*}}hipLaunchKernel
|
|
// PTH: call{{.*}}hipLaunchKernel_spt
|
|
// CUDA-OLD: call{{.*}}cudaSetupArgument
|
|
// CUDA-OLD: call{{.*}}cudaLaunch
|
|
// CUDA-NEW: call{{.*}}__cudaPopCallConfiguration
|
|
// CUDA-NEW: call{{.*}}cudaLaunchKernel
|
|
// CUDA-PTH: call{{.*}}cudaLaunchKernel_ptsz
|
|
__global__ void g1(int x) {}
|
|
|
|
// CHECK-LABEL: define{{.*}}main
|
|
int main(void) {
|
|
// HIP-OLD: call{{.*}}hipConfigureCall
|
|
// HIP-NEW: call{{.*}}__hipPushCallConfiguration
|
|
// CUDA-OLD: call{{.*}}cudaConfigureCall
|
|
// CUDA-NEW: call{{.*}}__cudaPushCallConfiguration
|
|
// CHECK: icmp
|
|
// CHECK: br
|
|
// CHECK: call{{.*}}g1
|
|
g1<<<1, 1>>>(42);
|
|
}
|