No announcement yet.

CUDA vs. OpenCL GPGPU Performance On NVIDIA's Pascal

  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    Originally posted by Stebs View Post
    Would this situation change when/if Nvidia would release a OpenCL 2.0 or even 2.1 driver? Or are the missing features and/or performance independed of the availabe version of OpenCL. (And did you use OpenCL 1.2 for Nvidia, or still 1.1?).
    The code in question is OpenCL 1.2 (but it uses little from the 1.2-only features). I highly doubt OpenCL 2.0 will change the picture much, workgroup build-ins may help a bit. Part of the performance difference (although I have not quantified how much especially as performance measurements tools are crippled) is due to the lack of lane shuffle and floating point (or 64-bit integer) atomics support. Frankly, they could expose all those (and more like the __ldg builtin) even OpenCL 1.2 -- that's what vendor extensions are for. Of course, there needs to be will to support OpenCL which seems to be seen as a danger to CUDA evangelization, so I believe the quality of the NVIDIA OpenCL support, without serious pressure on them, will remain be poor.