Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
六月暴雪飞梨花
Paddle
提交
9ea0661a
P
Paddle
项目概览
六月暴雪飞梨花
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
9ea0661a
编写于
11月 22, 2016
作者:
L
Luo Tao
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
clang format off on some cuda .cc file
上级
80c68d38
变更
3
显示空白变更内容
内联
并排
Showing
3 changed file
with
63 addition
and
37 deletion
+63
-37
paddle/cuda/src/hl_cuda_cublas.cc
paddle/cuda/src/hl_cuda_cublas.cc
+9
-3
paddle/cuda/src/hl_cuda_device.cc
paddle/cuda/src/hl_cuda_device.cc
+40
-23
paddle/cuda/src/hl_cudart_wrap.cc
paddle/cuda/src/hl_cudart_wrap.cc
+14
-11
未找到文件。
paddle/cuda/src/hl_cuda_cublas.cc
浏览文件 @
9ea0661a
...
...
@@ -56,9 +56,14 @@ void *cublas_dso_handle = nullptr;
#define DYNAMIC_LOAD_CUBLAS_V2_WRAP(__name) DYNAMIC_LOAD_CUBLAS_WRAP(__name)
// include all needed cublas functions in HPPL
// clang-format off
#define CUBLAS_BLAS_ROUTINE_EACH(__macro) \
__macro(cublasSgemv) __macro(cublasDgemv) __macro(cublasSgemm) \
__macro(cublasDgemm) __macro(cublasSgeam) __macro(cublasDgeam)
__macro(cublasSgemv) \
__macro(cublasDgemv) \
__macro(cublasSgemm) \
__macro(cublasDgemm) \
__macro(cublasSgeam) \
__macro(cublasDgeam) \
DYNAMIC_LOAD_CUBLAS_V2_WRAP
(
cublasCreate
)
DYNAMIC_LOAD_CUBLAS_V2_WRAP
(
cublasDestroy
)
...
...
@@ -81,6 +86,7 @@ CUBLAS_BLAS_ROUTINE_EACH(DYNAMIC_LOAD_CUBLAS_V2_WRAP)
}
/* namespace dynload */
// clang-format on
#ifndef PADDLE_TYPE_DOUBLE
#define CUBLAS_GEAM dynload::cublasSgeam
#define CUBLAS_GEMV dynload::cublasSgemv
...
...
paddle/cuda/src/hl_cuda_device.cc
浏览文件 @
9ea0661a
...
...
@@ -57,10 +57,14 @@ void *curand_dso_handle = nullptr;
#endif
/* include all needed curand functions in HPPL */
// clang-format off
#define CURAND_RAND_ROUTINE_EACH(__macro) \
__macro(curandCreateGenerator) __macro(curandSetStream) \
__macro(curandSetPseudoRandomGeneratorSeed) \
__macro(curandGenerateUniform) __macro(curandGenerateUniformDouble)
__macro(curandCreateGenerator) \
__macro(curandSetStream) \
__macro(curandSetPseudoRandomGeneratorSeed)\
__macro(curandGenerateUniform) \
__macro(curandGenerateUniformDouble)
// clang-format on
CURAND_RAND_ROUTINE_EACH
(
DYNAMIC_LOAD_CURAND_WRAP
)
...
...
@@ -99,25 +103,38 @@ void *cudart_dso_handle = nullptr;
#endif
/* include all needed cuda functions in HPPL */
// clang-format off
#define CUDA_ROUTINE_EACH(__macro) \
__macro(cudaMalloc) __macro(cudaHostAlloc) __macro(cudaFree) \
__macro(cudaFreeHost) __macro(cudaMemcpy) __macro(cudaMemset) __macro( \
cudaMemcpyAsync) __macro(cudaSetDevice) __macro(cudaGetDevice) \
__macro(cudaGetDeviceCount) __macro(cudaGetDeviceProperties) \
__macro(cudaDeviceSynchronize) __macro(cudaDeviceCanAccessPeer) \
__macro(cudaMalloc) \
__macro(cudaHostAlloc) \
__macro(cudaFree) \
__macro(cudaFreeHost) \
__macro(cudaMemcpy) \
__macro(cudaMemset) \
__macro(cudaMemcpyAsync) \
__macro(cudaSetDevice) \
__macro(cudaGetDevice) \
__macro(cudaGetDeviceCount) \
__macro(cudaGetDeviceProperties) \
__macro(cudaDeviceSynchronize) \
__macro(cudaDeviceCanAccessPeer) \
__macro(cudaDeviceEnablePeerAccess) \
__macro(cudaStreamCreate) __macro(cudaStreamDestroy) \
__macro(cudaStreamSynchronize) __macro( \
cudaStreamWaitEvent) __macro(cudaEventCreate) \
__macro(cudaEventRecord) __macro(cudaEventQuery) \
__macro(cudaEventDestroy) __macro( \
cudaEventSynchronize) \
__macro(cudaEventElapsedTime) __macro( \
cudaSetDeviceFlags) \
__macro(cudaGetLastError) __macro( \
cudaFuncSetCacheConfig) \
__macro(cudaStreamCreate) \
__macro(cudaStreamDestroy) \
__macro(cudaStreamSynchronize) \
__macro(cudaStreamWaitEvent) \
__macro(cudaEventCreate) \
__macro(cudaEventRecord) \
__macro(cudaEventQuery) \
__macro(cudaEventDestroy) \
__macro(cudaEventSynchronize) \
__macro(cudaEventElapsedTime) \
__macro(cudaSetDeviceFlags) \
__macro(cudaGetLastError) \
__macro(cudaFuncSetCacheConfig) \
__macro(cudaRuntimeGetVersion) \
__macro(cudaGetErrorString)
// clang-format on
CUDA_ROUTINE_EACH
(
DYNAMIC_LOAD_CUDART_WRAP
)
...
...
paddle/cuda/src/hl_cudart_wrap.cc
浏览文件 @
9ea0661a
...
...
@@ -47,10 +47,12 @@ extern void *cudart_dso_handle;
} __name;
/* struct DynLoad__##__name */
/* include all needed cuda functions in HPPL */
// clang-format off
#define CUDA_ROUTINE_EACH(__macro) \
__macro(cudaLaunch, cudaError_t) __macro(cudaSetupArgument, cudaError_t) \
__macro(cudaLaunch, cudaError_t) \
__macro(cudaSetupArgument, cudaError_t) \
__macro(cudaConfigureCall, cudaError_t) \
__macro(__cudaRegisterFatBinary, void **)
\
__macro(__cudaRegisterFatBinary, void**)
\
__macro(__cudaUnregisterFatBinary, void) \
__macro(__cudaRegisterFunction, void) \
__macro(__cudaRegisterVar, void) \
...
...
@@ -58,6 +60,7 @@ extern void *cudart_dso_handle;
__macro(__cudaInitModule, char) \
__macro(__cudaRegisterTexture, void) \
__macro(__cudaRegisterSurface, void)
// clang-format on
CUDA_ROUTINE_EACH
(
DYNAMIC_LOAD_CUDART_WRAP
)
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录