Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
The author has a comment here describing what that would take: https://github.com/vosen/ZLUDA/issues/17#issuecomment-735403....
tl;dr: someone would need to re-implement cuDNN
- Having dropped support for GCN2/3 (https://github.com/RadeonOpenCompute/ROCm/issues/1353#issuec...) making the _only_ supported customer GPU generation Vega, with no support for RDNA/RDNA2.
They obviously don't care about the market as they should, despite anything they might or they might not say. Nothing to see here...
AMD implemented HIP, which is nearly CUDA (if not identical). There is an implementation for Intel too though it is third-party:
https://github.com/cpc/hipcl
Excellent effort. Nvidia has become defacto GPGPU hardware vendor due to CUDA, but I wish it was OpenCL or other general API instead. Even Raspberry Pi's VideoCore has OpenCL support[1].
But a look at HW Acceleration support table at FFmpeg[2] shows why GPGPU Platform API is such a mess. But performance benefits are incredible, using VAAPI for FFmpeg to encode 1080p 2560x1080 screen capture at 60fps reduces CPU usage from 90% to 10% on a old corei5 with intel HD 3000; An old laptop could be perfectly used as an encoding machine for streaming just by using HW Acceleration.
What's funny is that the laptop also has Radeon HD 6490M with 1GB GDDR5 dedicated memory and it's not supported by VAAPI for encoding! Thereby proving the point that GPGPU API/Platform Support are astonishingly messy.
[1]https://github.com/doe300/VC4CL
[2]https://trac.ffmpeg.org/wiki/HWAccelIntro