On Fri, 1 Oct 2021 18:02:42 -0400 Mingzhe Hu <mh4...@columbia.edu> wrote:
> https://colab.research.google.com/drive/1KNmXwEQY7oS-nyDRkXwgl3Sw9dV3MW6P?usp=sharing, > where you can know my environment and GPU type, etc. Shouldn't block and grid tuples be of the same lenth ? Moreover, the number of threads in a block is limited to 1024. Since 512x512 is larger, there is an issue block.x<1024 block.y<1024 block.z<64 block.x*block.y*block.z<1024 Cheers, Jerome _______________________________________________ PyCUDA mailing list -- pycuda@tiker.net To unsubscribe send an email to pycuda-le...@tiker.net
