|
|
@ -12,8 +12,7 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
See the License for the specific language governing permissions and
|
|
|
|
See the License for the specific language governing permissions and
|
|
|
|
limitations under the License. */
|
|
|
|
limitations under the License. */
|
|
|
|
|
|
|
|
|
|
|
|
#ifndef HL_BASE_H_
|
|
|
|
#pragma once
|
|
|
|
#define HL_BASE_H_
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#include <cstddef>
|
|
|
|
#include <cstddef>
|
|
|
|
|
|
|
|
|
|
|
@ -207,8 +206,8 @@ typedef struct {
|
|
|
|
|
|
|
|
|
|
|
|
#ifdef __NVCC__
|
|
|
|
#ifdef __NVCC__
|
|
|
|
|
|
|
|
|
|
|
|
#include "cuda_runtime.h"
|
|
|
|
#include <cuda_runtime.h>
|
|
|
|
#include "hl_cuda.h"
|
|
|
|
#include "paddle/cuda/include/hl_cuda.h"
|
|
|
|
#include "paddle/utils/Logging.h"
|
|
|
|
#include "paddle/utils/Logging.h"
|
|
|
|
|
|
|
|
|
|
|
|
extern __thread bool g_sync_flag;
|
|
|
|
extern __thread bool g_sync_flag;
|
|
|
@ -243,6 +242,4 @@ __shfl_sync(unsigned, T val, int src_line, int width) {
|
|
|
|
mask = __ballot_sync(FULL_WARP_MASK, (predicate))
|
|
|
|
mask = __ballot_sync(FULL_WARP_MASK, (predicate))
|
|
|
|
#endif
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
|
#endif /* __NVCC__ */
|
|
|
|
#endif // __NVCC__
|
|
|
|
|
|
|
|
|
|
|
|
#endif /* HL_BASE_H_ */
|
|
|
|
|
|
|
|