m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #539 from gangliao/stylecheckcc

Browse Source 
Add style check for *.cc files in cuda directory
avx_docs
Tao Luo 8 years ago committed by GitHub
parent 5d511a16b8 20aac5bba1
commit 0bd7613ea9
6 changed files with 112 additions and 132 deletions
Show Stats Download Patch File Download Diff File

7
paddle/cuda/CMakeLists.txt
Unescape View File

@ -81,5 +81,8 @@ else()
add_library(paddle_cuda ${CUDA_SOURCES})
endif()
add_style_check_target(paddle_cuda ${CUDA_SOURCES})
add_style_check_target(paddle_cuda ${CUDA_HEADERS})
add_style_check_target(paddle_cuda
${CUDA_SOURCES}
${CUDA_HEADERS}
${CUDA_DSO_SOURCES}
${CUDA_CXX_WITH_GPU_SOURCES})

15
paddle/cuda/src/hl_cuda_cublas.cc
Unescape View File

@ -104,7 +104,7 @@ CUBLAS_BLAS_ROUTINE_EACH(DYNAMIC_LOAD_CUBLAS_V2_WRAP)
#endif
const char* hl_cublas_get_error_string(cublasStatus_t status) {
switch(status) {
switch (status) {
case CUBLAS_STATUS_NOT_INITIALIZED:
return "[cublas status]: not initialized";
case CUBLAS_STATUS_ALLOC_FAILED:
@ -181,7 +181,7 @@ void hl_matrix_inverse(real *A_d, real *C_d, int dimN, int lda, int ldc) {
real **inout_d = (real **)hl_malloc_device(sizeof(real *));
hl_memcpy(inout_d, inout_h, sizeof(real *));
int *pivot_d = (int *)hl_malloc_device(dimN*sizeof(int));
int *pivot_d = (int *)hl_malloc_device(dimN * sizeof(int));
int *info_d = (int *)t_resource.gpu_mem;
/* Note: cublasSgetrfBatched is used to calculate a number of
@ -189,10 +189,9 @@ void hl_matrix_inverse(real *A_d, real *C_d, int dimN, int lda, int ldc) {
the API for better performance.
*/
CHECK_CUBLAS(CUBLAS_GETRF(t_resource.handle,
dimN, inout_d, lda, pivot_d,
info_d, 1));
dimN, inout_d, lda, pivot_d, info_d, 1));
int info_h;
int info_h;
hl_memcpy(&info_h, info_d, sizeof(int));
if (info_h != 0) {
LOG(FATAL) << "Factorization of matrix failed: matrix may be singular.\n";
@ -204,8 +203,8 @@ void hl_matrix_inverse(real *A_d, real *C_d, int dimN, int lda, int ldc) {
hl_memcpy(out_d, out_h, sizeof(real *));
CHECK_CUBLAS(CUBLAS_GETRI(t_resource.handle,
dimN, (const real **)inout_d, lda, pivot_d,
out_d, ldc, info_d, 1));
dimN, (const real **)inout_d, lda, pivot_d,
out_d, ldc, info_d, 1));
hl_memcpy(&info_h, info_d, sizeof(int));
if (info_h != 0) {
@ -215,7 +214,7 @@ void hl_matrix_inverse(real *A_d, real *C_d, int dimN, int lda, int ldc) {
hl_free_mem_device(inout_d);
hl_free_mem_device(pivot_d);
hl_free_mem_device(out_d);
CHECK_SYNC("hl_matrix_inverse failed");
}

143
paddle/cuda/src/hl_cuda_cudnn.cc
View File

File diff suppressed because it is too large Load Diff

12
paddle/cuda/src/hl_cuda_device.cc
Unescape View File

@ -203,8 +203,8 @@ inline pid_t gettid() {
#endif
pid_t tid = syscall(__NR_gettid);
#endif
CHECK_NE(tid, -1);
return tid;
CHECK_NE((int)tid, -1);
return tid;
}
void hl_init(int device) {
@ -355,7 +355,8 @@ void* hl_malloc_host(size_t size) {
void *dest_h;
CHECK(size) << __func__ << ": the size for device memory is 0, please check.";
CHECK_CUDA(dynload::cudaHostAlloc((void**)&dest_h, size, cudaHostAllocDefault));
CHECK_CUDA(dynload::cudaHostAlloc(
(void**)&dest_h, size, cudaHostAllocDefault));
return dest_h;
}
@ -364,7 +365,7 @@ void hl_free_mem_host(void *dest_h) {
CHECK_NOTNULL(dest_h);
cudaError_t err = dynload::cudaFreeHost(dest_h);
CHECK (cudaSuccess == err || cudaErrorCudartUnloading == err)
CHECK(cudaSuccess == err || cudaErrorCudartUnloading == err)
<< hl_get_device_error_string();
}
@ -502,7 +503,8 @@ int hl_get_cuda_version() {
return g_cuda_lib_version;
}
void hl_create_thread_resources(int device, thread_device_resources device_res) {
void hl_create_thread_resources(int device,
thread_device_resources device_res) {
CHECK_CUDA(dynload::cudaSetDevice(device));
/* create thread stream */

26
paddle/cuda/src/hl_cudart_wrap.cc
Unescape View File

@ -78,48 +78,38 @@ __host__ cudaError_t CUDARTAPI cudaLaunchKernel(const void *func,
dim3 blockDim,
void **args,
size_t sharedMem,
cudaStream_t stream)
{
return dynload::cudaLaunchKernel(func, gridDim, blockDim, args, sharedMem, stream);
cudaStream_t stream) {
return dynload::cudaLaunchKernel(func, gridDim, blockDim,
args, sharedMem, stream);
}
#endif /* CUDART_VERSION >= 7000 */
__host__ cudaError_t CUDARTAPI cudaLaunch(const void *func)
{
__host__ cudaError_t CUDARTAPI cudaLaunch(const void *func) {
return dynload::cudaLaunch(func);
}
__host__ cudaError_t CUDARTAPI cudaSetupArgument(const void *arg,
size_t size,
size_t offset)
{
size_t offset) {
return dynload::cudaSetupArgument(arg, size, offset);
}
__host__ cudaError_t CUDARTAPI cudaConfigureCall(dim3 gridDim,
dim3 blockDim,
size_t sharedMem,
cudaStream_t stream)
{
cudaStream_t stream) {
return dynload::cudaConfigureCall(gridDim, blockDim,
sharedMem, stream);
}
extern "C" {
void** CUDARTAPI __cudaRegisterFatBinary(
void *fatCubin
)
{
void** CUDARTAPI __cudaRegisterFatBinary(void *fatCubin) {
return dynload::__cudaRegisterFatBinary(fatCubin);
}
void CUDARTAPI __cudaUnregisterFatBinary(
void **fatCubinHandle
)
{
void CUDARTAPI __cudaUnregisterFatBinary(void **fatCubinHandle) {
return dynload::__cudaUnregisterFatBinary(fatCubinHandle);
}

41
paddle/cuda/src/hl_dso_loader.cc
Unescape View File

@ -19,17 +19,18 @@ limitations under the License. */
P_DEFINE_string(cudnn_dir, "",
"Specify path for loading libcudnn.so. For instance, "
"/usr/local/cudnn/lib64. If empty [default], dlopen will search "
"cudnn from LD_LIBRARY_PATH");
"/usr/local/cudnn/lib64. If empty [default], dlopen "
"will search cudnn from LD_LIBRARY_PATH");
P_DEFINE_string(cuda_dir, "",
"Specify path for loading cuda library, such as libcublas, "
"libcurand. For instance, /usr/local/cuda/lib64. "
"(Note: libcudart can not be specified by cuda_dir, since some "
"libcurand. For instance, /usr/local/cuda/lib64. (Note: "
"libcudart can not be specified by cuda_dir, since some "
"build-in function in cudart already ran before main entry). "
"If empty [default], dlopen will search cuda from LD_LIBRARY_PATH");
"If default, dlopen will search cuda from LD_LIBRARY_PATH");
static inline std::string join(const std::string& part1, const std::string& part2) {
static inline std::string join(const std::string& part1,
const std::string& part2) {
// directory separator
const char sep = '/';
@ -49,10 +50,10 @@ static inline std::string join(const std::string& part1, const std::string& part
static inline void GetDsoHandleFromDefaultPath(
std::string& dso_path, void** dso_handle, int dynload_flags) {
VLOG(3) << "Try to find cuda library: " << dso_path
<< " from default system path.";
// default search from LD_LIBRARY_PATH/DYLD_LIBRARY_PATH
<< " from default system path.";
// default search from LD_LIBRARY_PATH/DYLD_LIBRARY_PATH
*dso_handle = dlopen(dso_path.c_str(), dynload_flags);
// DYLD_LIBRARY_PATH is disabled after Mac OS 10.11 to
// bring System Integrity Projection (SIP), if dso_handle
// is null, search from default package path in Mac OS.
@ -62,13 +63,13 @@ static inline void GetDsoHandleFromDefaultPath(
*dso_handle = dlopen(dso_path.c_str(), dynload_flags);
if (nullptr == *dso_handle) {
if (dso_path == "libcudnn.dylib") {
LOG(FATAL) << "Note: [Recommend] copy cudnn into /usr/local/cuda/ \n"
<< "For instance, sudo tar -xzf cudnn-7.5-osx-x64-v5.0-ga.tgz -C "
<< "/usr/local \n sudo chmod a+r /usr/local/cuda/include/cudnn.h "
LOG(FATAL) << "Note: [Recommend] copy cudnn into /usr/local/cuda/ \n" // NOLINT
<< "For instance, sudo tar -xzf cudnn-7.5-osx-x64-v5.0-ga.tgz -C " // NOLINT
<< "/usr/local \n sudo chmod a+r /usr/local/cuda/include/cudnn.h " // NOLINT
<< "/usr/local/cuda/lib/libcudnn*";
}
}
}
}
}
#endif
}
@ -96,19 +97,19 @@ static inline void GetDsoHandleFromSearchPath(
CHECK(nullptr != *dso_handle)
<< "Failed to find cuda library: " << dlPath << std::endl
<< "Please specify its path correctly using one of the following ideas: \n"
<< "Please specify its path correctly using one of the following ways: \n" // NOLINT
<< "Idea 1. set cuda and cudnn lib path at runtime. "
<< "http://www.paddlepaddle.org/doc/ui/cmd_argument/argument_outline.html \n"
<< "Method 1. set cuda and cudnn lib path at runtime. "
<< "http://www.paddlepaddle.org/doc/ui/cmd_argument/argument_outline.html \n" // NOLINT
<< "For instance, issue command: paddle train --use_gpu=1 "
<< "--cuda_dir=/usr/local/cudnn/lib --cudnn_dir=/usr/local/cudnn/lib ...\n"
<< "--cuda_dir=/usr/local/cuda/lib64 --cudnn_dir=/usr/local/cudnn/lib ...\n" // NOLINT
<< "Idea 2. set environment variable LD_LIBRARY_PATH on Linux or "
<< "Method 2. set environment variable LD_LIBRARY_PATH on Linux or "
<< "DYLD_LIBRARY_PATH on Mac OS. \n"
<< "For instance, issue command: export LD_LIBRARY_PATH=... \n"
<< "Note: After Mac OS 10.11, using the DYLD_LIBRARY_PATH is impossible "
<< "unless System Integrity Protection (SIP) is disabled. However, @Idea 1"
<< "unless System Integrity Protection (SIP) is disabled. However, method 1 " // NOLINT
<< "always work well.";
}

Write Preview
Loading…
Cancel
Save