Giuseppe Bilotta<p>Even now, Thrust as a dependency is one of the main reason why we have a <a href="https://fediscience.org/tags/CUDA" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CUDA</span></a> backend, a <a href="https://fediscience.org/tags/HIP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HIP</span></a> / <a href="https://fediscience.org/tags/ROCm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ROCm</span></a> backend and a pure <a href="https://fediscience.org/tags/CPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CPU</span></a> backend in <a href="https://fediscience.org/tags/GPUSPH" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GPUSPH</span></a>, but not a <a href="https://fediscience.org/tags/SYCL" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SYCL</span></a> or <a href="https://fediscience.org/tags/OneAPI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OneAPI</span></a> backend (which would allow us to extend hardware support to <a href="https://fediscience.org/tags/Intel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Intel</span></a> GPUs). <<a href="https://doi.org/10.1002/cpe.8313" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.1002/cpe.8313</span><span class="invisible"></span></a>></p><p>This is also one of the reason why we implemented our own <a href="https://fediscience.org/tags/BLAS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BLAS</span></a> routines when we introduced the semi-implicit integrator. A side-effect of this choice is that it allowed us to develop the improved <a href="https://fediscience.org/tags/BiCGSTAB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BiCGSTAB</span></a> that I've had the opportunity to mention before <<a href="https://doi.org/10.1016/j.jcp.2022.111413" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.1016/j.jcp.2022.111</span><span class="invisible">413</span></a>>. Sometimes I do wonder if it would be appropriate to “excorporate” it into its own library for general use, since it's something that would benefit others. OTOH, this one was developed specifically for GPUSPH and it's tightly integrated with the rest of it (including its support for multi-GPU), and refactoring to turn it into a library like cuBLAS is</p><p>a. too much effort<br>b. probably not worth it.</p><p>Again, following <span class="h-card" translate="no"><a href="https://peoplemaking.games/@eniko" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>eniko</span></a></span>'s original thread, it's really not that hard to roll your own, and probably less time consuming than trying to wrangle your way through an API that may or may not fit your needs.</p><p>6/</p>
Recent searches
No recent searches
Search options
Not available on socel.net.
socel.net is one of the many independent Mastodon servers you can use to participate in the fediverse.
Socel is a place for animation professionals, freelancers, independents, students, and fans to connect and grow together. Everyone in related fields are also welcome.
Administered by:
Server stats:
324active users
socel.net: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.3.7
#oneapi
0 posts · 0 participants · 0 posts today
Benjamin Carr, Ph.D. 👨🏻💻🧬<p>Just how deep is <a href="https://hachyderm.io/tags/Nvidia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Nvidia</span></a>'s <a href="https://hachyderm.io/tags/CUDA" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CUDA</span></a> moat really?<br>Not as impenetrable as you might think, but still more than Intel or AMD would like<br>It's not enough just to build a competitive part: you also have to have <a href="https://hachyderm.io/tags/software" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>software</span></a> that can harness all those <a href="https://hachyderm.io/tags/FLOPS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FLOPS</span></a> — something Nvidia has spent the better part of two decades building with its CUDA runtime, while competing frameworks for low-level <a href="https://hachyderm.io/tags/GPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GPU</span></a> <a href="https://hachyderm.io/tags/programming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>programming</span></a> are far less mature like AMD's <a href="https://hachyderm.io/tags/ROCm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ROCm</span></a> or Intel's <a href="https://hachyderm.io/tags/OneAPI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OneAPI</span></a>.<br><a href="https://www.theregister.com/2024/12/17/nvidia_cuda_moat/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">theregister.com/2024/12/17/nvi</span><span class="invisible">dia_cuda_moat/</span></a> <a href="https://hachyderm.io/tags/developers" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>developers</span></a></p>
Sriram Ramkrishna<p>Howdy all - registrations are still open for the first oneAPI DevSummit hosted by the UXL Foundation! Learn about GPGPU programming, oneAPI and how companies are coalescing around <a href="https://mast.hpc.social/tags/oneapi" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>oneapi</span></a> / <a href="https://mast.hpc.social/tags/sycl" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sycl</span></a> <br><a href="https://linuxfoundation.regfox.com/oneapiuxldevsummit2024" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">linuxfoundation.regfox.com/one</span><span class="invisible">apiuxldevsummit2024</span></a></p><p>Registration will closeat 5pm today. The DevSummit will start at 8pm PT or 8:30am IST. See you there!</p>
pafurijaz<p>This is what <a href="https://mstdn.social/tags/CUDA" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CUDA</span></a> is, a prison from which there seems to be no possibility of escaping, and also the fault of developers who rely on this, forcing anyone to necessarily buy these cards, I hope this nightmare ends soon, I'm done with having to buy Nvidia products. <a href="https://mstdn.social/tags/NVIDIA" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NVIDIA</span></a> <a href="https://mstdn.social/tags/SYCL" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SYCL</span></a> <a href="https://mstdn.social/tags/intel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>intel</span></a> <a href="https://mstdn.social/tags/OneApi" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OneApi</span></a> <a href="https://mstdn.social/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a></p>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload