Skip to content

Compile with CUDNN 8+ #2545

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Compile with CUDNN 8+ #2545

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cc734c0
replaced fnc with static algo
JakBio Apr 26, 2022
35fff8c
cleanup
JakBio Apr 26, 2022
375ad39
revert flags in makefile
JakBio Apr 26, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,3 +25,10 @@ ehthumbs.db
Icon?
Thumbs.db
*.swp

# Generated Libs
libdarknet.a
libdarknet.so

# IDEs garbage
.idea/
9 changes: 5 additions & 4 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,11 @@ OPENCV=0
OPENMP=0
DEBUG=0

ARCH= -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=[sm_50,compute_50] \
-gencode arch=compute_52,code=[sm_52,compute_52]
#ARCH= -gencode arch=compute_30,code=sm_30 \
# -gencode arch=compute_35,code=sm_35 \
# -gencode arch=compute_50,code=[sm_50,compute_50] \
# -gencode arch=compute_52,code=[sm_52,compute_52] \
# -gencode arch=compute_75,code=[sm_75,compute_75] \ RTX 20 series
# -gencode arch=compute_20,code=[sm_20,sm_21] \ This one is deprecated?

# This is what I use, uncomment if you know your arch and want to specify
Expand Down
57 changes: 33 additions & 24 deletions src/convolutional_layer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,31 +145,40 @@ void cudnn_convolutional_setup(layer *l)
}
#endif

cudnnGetConvolutionForwardAlgorithm(cudnn_handle(),
l->srcTensorDesc,
l->weightDesc,
l->convDesc,
l->dstTensorDesc,
CUDNN_CONVOLUTION_FWD_SPECIFY_WORKSPACE_LIMIT,
2000000000,
&l->fw_algo);
cudnnGetConvolutionBackwardDataAlgorithm(cudnn_handle(),
l->weightDesc,
l->ddstTensorDesc,
l->convDesc,
l->dsrcTensorDesc,
CUDNN_CONVOLUTION_BWD_DATA_SPECIFY_WORKSPACE_LIMIT,
2000000000,
&l->bd_algo);
cudnnGetConvolutionBackwardFilterAlgorithm(cudnn_handle(),
l->srcTensorDesc,
l->ddstTensorDesc,
l->convDesc,
l->dweightDesc,
CUDNN_CONVOLUTION_BWD_FILTER_SPECIFY_WORKSPACE_LIMIT,
2000000000,
&l->bf_algo);
#if CUDNN_MAJOR >= 8
// Following functions no longer exist in release of CUDNN 8+ and have no replacement. This is the minimal
// intervention necessary for project to work on CUDNN 8+ (CUDA 11+).

// cudnnGetConvolutionForwardAlgorithm(cudnn_handle(),
// l->srcTensorDesc,
// l->weightDesc,
// l->convDesc,
// l->dstTensorDesc,
// CUDNN_CONVOLUTION_FWD_SPECIFY_WORKSPACE_LIMIT,
// 2000000000,
// &l->fw_algo);
l->fw_algo = CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM;
// cudnnGetConvolutionBackwardDataAlgorithm(cudnn_handle(),
// l->weightDesc,
// l->ddstTensorDesc,
// l->convDesc,
// l->dsrcTensorDesc,
// CUDNN_CONVOLUTION_BWD_DATA_SPECIFY_WORKSPACE_LIMIT,
// 2000000000,
// &l->bd_algo);
l->bd_algo = CUDNN_CONVOLUTION_BWD_DATA_ALGO_1;
// cudnnGetConvolutionBackwardFilterAlgorithm(cudnn_handle(),
// l->srcTensorDesc,
// l->ddstTensorDesc,
// l->convDesc,
// l->dweightDesc,
// CUDNN_CONVOLUTION_BWD_FILTER_SPECIFY_WORKSPACE_LIMIT,
// 2000000000,
// &l->bf_algo);
l->bf_algo = CUDNN_CONVOLUTION_BWD_FILTER_ALGO_1;
#endif
}

#endif
#endif

Expand Down