OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Made copy_tensor() use cudaMemcpyAsync() rather than cudaMemcpy().

This commit is contained in:
Davis King 2017-08-14 09:52:53 -04:00
parent aafa411672
commit 89c9267e46
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dlib/dnn/cuda_dlib.cu
View File

@ -1401,7 +1401,7 @@ namespace dlib
for (long i = 0; i < src.num_samples(); ++i)
{
CHECK_CUDA(cudaMemcpy(dest_p, src_p, block_size * sizeof(float), cudaMemcpyDeviceToDevice));
CHECK_CUDA(cudaMemcpyAsync(dest_p, src_p, block_size * sizeof(float), cudaMemcpyDeviceToDevice));
dest_p += dest_sample_size;
src_p += src_sample_size;

1
dlib/dnn/tensor_tools.h
View File

@ -1558,6 +1558,7 @@ namespace dlib { namespace tt
- dest.k() - dest_k_offset >= count_k
- src.k() - src_k_offset >= count_k
- is_same_object(dest,src) == false
- The memory areas of src and dest do not overlap.
ensures
- performs: dest[i, k + dest_k_offset, r, c] = src[i, k + src_k_offset, r, c], where k in [0..count_k]
Copies content of each sample from src in to corresponding place of sample at dest.