Jump to content

GPU Tensor benchmark


MAA

Recommended Posts

I'm afraid we have zero experience about Tensor Core benchmarks or even accessing those  cores.  I suppose the only way to do that right now is via CUDA, but we don't have any actual experience in CUDA.  First we would need to port the existing GPGPU benchmarks from OpenCL to CUDA, and after then we could deal with adding new "juice" to the existing set of GPGPU benchmarks.  We may do that next year, but I cannot promise an actual release date for those CUDA benchmarks right now…

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.



×
×
  • Create New...