BlackCat_Tensors
A GPU-supported autograd and linear algebra library, designed for neural network construction
stream_synchronization.h
Go to the documentation of this file.
1 /*
2  * Stream_Synchronization.h
3  *
4  * Created on: Dec 16, 2019
5  * Author: joseph
6  */
7 
8 #ifndef BLACKCAT_STREAM_SYNCHRONIZATION_H_
9 #define BLACKCAT_STREAM_SYNCHRONIZATION_H_
10 
11 #include "../common.h"
12 
13 namespace bc {
14 namespace streams {
15 
16 inline void host_sync() {
17  BC_omp_bar__
18 }
19 
20 inline void device_sync() {
21  BC_IF_CUDA(cudaDeviceSynchronize();)
22 }
23 
24 inline void synchronize() {
25  host_sync();
26  device_sync();
27 }
28 
29 }
30 }
31 
32 
33 
34 
35 #endif /* STREAM_SYNCHRONIZATION_H_ */
bc::streams::host_sync
void host_sync()
Definition: stream_synchronization.h:16
bc::streams::device_sync
void device_sync()
Definition: stream_synchronization.h:20
BC_IF_CUDA
#define BC_IF_CUDA(...)
Definition: common.h:68
bc::streams::synchronize
void synchronize()
Definition: stream_synchronization.h:24
BC_omp_bar__
#define BC_omp_bar__
Definition: common.h:270
bc
The Evaluator determines if an expression needs to be greedily optimized.
Definition: algorithms.h:22
Generated by   doxygen 1.8.13