Forgot your password?
typodupeerror
Open Source

+ - New GPGPU Standard Takes On "Crappy" CUDA->

Submitted by Anonymous Coward
An anonymous reader writes "Compiler developer PathScale has just unveiled a new GPGPU (general purpose GPU) programming model, which it reckons will do a much more efficient job than Nvidia's own CUDA technology. Teaming up with CAPS, a developer of software tools for many-core architectures, PathScale has now introduced a compiler suite called ENZO that uses CAPS' Hybrid Multicore Parallel Programming (HMPP) model. PathScale's CTO Christopher Bergstrom explained that "Nvidia are still pushing their antiquated — dare I say crappy — CUDA programming model, which is highly explicit and very expensive for people who write large bodies of code." However, he says that PathScale and CAPS will "make a new evolution possible in the GPGPU programming model that has been long overdue." Although the system is designed specifically for Nvidia GPUs, Bergstrom says that Nvidia was not involved in the development process. "It's just a situation where we think we can build something better than them," he says, "and basically kick their ass and push open source.”"
Link to Original Source
This discussion was created for logged-in users only, but now has been archived. No new comments can be posted.

New GPGPU Standard Takes On "Crappy" CUDA

Comments Filter:

"If that makes any sense to you, you have a big problem." -- C. Durance, Computer Science 234

Working...