I will believe when I see it.<p>I believed them in 2017 and got a Vega64. ROCm was never propertly integrated into distributions, frameworks or applications, and once it at least trickled in into distributions in some limited form, Vega support is already being deprecated.<p>For me to try again ROCm, the bar will be significantly higher.
People are doubtful of this because AMD has halfassed it over and over in the past, but I do see a lot of desire among MS, google, and AMZ to break nvidia's monopoly on gpu compute. I don't know that ROCm will be the thing that does that but I do think <i>some</i> open source alternative will gain steam. Google is furthest along here with their tensor cores and the support for that, but I could easily see a group rallying behind AMD hardware as the only gpu manufacturer out there that has serious experience with HPC.
You can get it to work now on Linux.<p><a href="https://github.com/RadeonOpenCompute/ROCm/issues/1880">https://github.com/RadeonOpenCompute/ROCm/issues/1880</a>
AMD continues to sabotage itself with their terrible GPU compute support. I don't understand why it's so hard for them to pick a single API and support it on all GPUs and on all major platforms (Linux, Windows).<p>It's no wonder why NVIDIA's market cap is so much higher.
Take AMD's release windows with a grain of salt.<p><a href="https://videocardz.com/newz/amd-has-failed-to-launch-hypr-rx-technology-on-time" rel="nofollow noreferrer">https://videocardz.com/newz/amd-has-failed-to-launch-hypr-rx...</a>
Would be nice if I could pull more nodes per second on LeelaChessZero with my AMD card on Linux. Had to go to war with my drivers just to get OpenCL to clock above 1k, which it does go beyond now....after the war.
I was able to set up ROCm on my Arch system w/ RX 6600 relatively painlessly, and that was a few months ago. Honestly, I had no idea the support was otherwise <i>this</i> bad (at least, according to other comments). Using stable diffusion, for the most part it "just worked" barring some initial slight tweaks.
how will it unify its RDNA and CDNA into ROCm with consistent APIs are the core questions to me, i.e. to merge AI and graphic-rendering at software level, similar to what CUDA does.