-
Notifications
You must be signed in to change notification settings - Fork 393
how to implement batch spmv #210
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.
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
Comments
Hi @zhouq123, are matrices in the batch different from each other? Do they multiply with the same vector or vectors are different in the batch? |
please also note that the code should be similar to batched SpMM https://github.com/NVIDIA/CUDALibrarySamples/tree/master/cuSPARSE/spmm_csr_batched |
yes, they are all different from each other |
but there is an error "spmm_csr_batched_example test FAILED: wrong result" when I set B_num_cols to 1 in the example of spmm_csr_batched or spmm_coo_batched |
This bug has been fixed in the latest version. Please upgraded to the latest cuSPARSE to avoid this issue. |
the latest version is cuda toolkit or CUDALibrarySamples? I had upgraded to the latest CUDALibrarySamples but this issue is still exist. |
i have batch matrix A and vector B, how to implement batch spmv
The text was updated successfully, but these errors were encountered: