Today was Day 1 of the Keeneland Workshop. Many great talks were given, across a broad range of GPU computing topics.
With last week’s ArrayFire Webinar fresh in mind, it was interesting to see similar conclusions drawn in a presentation by Kyle Spafford of Oak Ridge National Laboratory. Kyle independently ran a number of benchmarks over a period of time which show how quickly OpenCL has matured and where it yet has room for improvement. The slide below comes from Kyle’s presentation. For numbers >1, CUDA is faster. For numbers <1, OpenCL is faster. Performance in most cases is close to equivalent.
Just as we showed in the ArrayFire webinar, OpenCL performance is quite comparable with CUDA performance. The Achilles heel for OpenCL right now seems to be in the FFT and a few other cases related to texture memory optimizations.
Many other great talks were given at the workshop. ArrayFire and Jacket were also covered in the library talks.
If you are looking at solving HPC type problems with GPUs, you should follow the activities of the Keeneland group. These guys are leaders in GPU computing for HPC.
Pingback: Algunos benchmarks sobre OpenCL y CUDA | Paralelizados.com