News for hackers. Stuff that matters.
Re:Volta: Advanced Data Center GPU by slizard on Thursday May 11, 2017 @10:27AM (#14316244)
> It's always been 10-20% slower than CUDA and frankly NVIDIA doesn't have an incentive to make it faster than that.

Incorrect. Our kernels (GROMACS molecular simulation package) are 2-3x slower implemented in OpenCL vs CUDA.

> On the other hand, I believe Google is working on a CUDA compiler

They were. It's upstream clang by now.

There are no comments on this comment yet.