TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

AMD to Expand ROCm Support to Consumer RDNA 3 GPUs This Fall

90 pointsby f_devdalmost 2 years ago

12 comments

vetinarialmost 2 years ago
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.
评论 #36574544 未加载
wing-_-nutsalmost 2 years ago
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&#x27;s monopoly on gpu compute. I don&#x27;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.
评论 #36576350 未加载
评论 #36578160 未加载
评论 #36585510 未加载
collsnialmost 2 years ago
You can get it to work now on Linux.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;RadeonOpenCompute&#x2F;ROCm&#x2F;issues&#x2F;1880">https:&#x2F;&#x2F;github.com&#x2F;RadeonOpenCompute&#x2F;ROCm&#x2F;issues&#x2F;1880</a>
评论 #36574179 未加载
评论 #36573549 未加载
评论 #36579223 未加载
peppermint_gumalmost 2 years ago
AMD continues to sabotage itself with their terrible GPU compute support. I don&#x27;t understand why it&#x27;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&#x27;s no wonder why NVIDIA&#x27;s market cap is so much higher.
Aardwolfalmost 2 years ago
Why did they wait so long? No decent ML support makes their consumer cards so much less attractive, it&#x27;s crazy
评论 #36572597 未加载
评论 #36574036 未加载
评论 #36576348 未加载
Hamukoalmost 2 years ago
Take AMD&#x27;s release windows with a grain of salt.<p><a href="https:&#x2F;&#x2F;videocardz.com&#x2F;newz&#x2F;amd-has-failed-to-launch-hypr-rx-technology-on-time" rel="nofollow noreferrer">https:&#x2F;&#x2F;videocardz.com&#x2F;newz&#x2F;amd-has-failed-to-launch-hypr-rx...</a>
bfrogalmost 2 years ago
I mean.. would have been nice from the get go, frankly has made me a skeptic of just what will be supported and for how long.
Havocalmost 2 years ago
Wild that they’re not working round the clock to get this sorted. Free money to Nvidia I guess
galleywest200almost 2 years ago
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.
thekombustoralmost 2 years ago
I was able to set up ROCm on my Arch system w&#x2F; 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 &quot;just worked&quot; barring some initial slight tweaks.
justincliftalmost 2 years ago
Better late than never I guess. ;)
synergy20almost 2 years ago
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.