Re:Intel SPMD: Compiler for High-Performance SIMD Programming
by CyberDildonics on Thursday April 14, 2016 @09:20AM
(#11496398)
The problem you highlighted was:
> temperamental GPUs and GPU drivers
I think because Vulkan won't be nearly as niche GPU driver support and consistency will need to be much better than they have been for OpenCL. Where that stands for flexibility of the compute side I can't say.
> temperamental GPUs and GPU drivers
I think because Vulkan won't be nearly as niche GPU driver support and consistency will need to be much better than they have been for OpenCL. Where that stands for flexibility of the compute side I can't say.