TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Frontier: ORNL's 2021 exascale supercomputer will run on AMD CPUs and GPUs

88 点作者 espeed将近 6 年前

4 条评论

hydroreadsstuff将近 6 年前
Here is a recent training from AMD for Frontier: Link: <a href="https:&#x2F;&#x2F;www.exascaleproject.org&#x2F;event&#x2F;amd-gpuprogramming-hip&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.exascaleproject.org&#x2F;event&#x2F;amd-gpuprogramming-hip...</a> Video: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;3ZXbRJVvgJs" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;3ZXbRJVvgJs</a> Slides: <a href="https:&#x2F;&#x2F;www.exascaleproject.org&#x2F;wp-content&#x2F;uploads&#x2F;2017&#x2F;05&#x2F;ORNL_HIP_webinar_20190606_final.pdf" rel="nofollow">https:&#x2F;&#x2F;www.exascaleproject.org&#x2F;wp-content&#x2F;uploads&#x2F;2017&#x2F;05&#x2F;O...</a><p>It will be very interesting to see what AMD came up with to convince ORNL to switch from 7 years (or more?) of NVIDIA to something else. I don&#x27;t think it&#x27;s just a lower price. Perhaps AMD is doing a closer tie-in between CPU and GPU. Since they own both.
评论 #20494109 未加载
评论 #20494715 未加载
xvilka将近 6 年前
Anything that is bad for NVIDIA is good for the FOSS. This company is the enemy of opensource, with its stance against nouveau, monopoly for GPU calculations with CUDA, etc.
评论 #20496749 未加载
评论 #20496576 未加载
gigatexal将近 6 年前
If I recall correctly the AMD hardware is competitive or better in raw compute than their nVidia counterparts but Cuda makes developing software so easy so I’m curious what ORNL’s take on that is.
评论 #20493199 未加载
评论 #20494226 未加载
评论 #20492986 未加载
评论 #20493187 未加载
评论 #20493207 未加载
评论 #20493743 未加载
boulos将近 6 年前
For those discussing it, ORNL explicitly calls out the need to rewrite and retune in the CUDA =&gt; HIP transition on Page 3 of the spec sheet [1].<p>Edit: I assume getting folks to test on Summit is a big part of the de-risking plan.<p>&gt; The OLCF plans to make HIP available on Summit so that users can begin using it prior to its availability on Frontier. HIP is a C++ runtime API that allows developers to write portable code to run on AMD and NVIDIA GPUs. It is essentially a wrapper that uses the underlying CUDA or ROCm platform that is installed on a system. The API is very similar to CUDA so transitioning existing codes from CUDA to HIP should be fairly straightforward in most cases. In addition, HIP provides porting tools which can be used to help port CUDA codes to the HIP layer, with no loss of performance as compared to the original CUDA application. HIP is not intended to be a drop-in replacement for CUDA, and developers should expect to do some manual coding and performance tuning work to complete the port.<p>[1] <a href="https:&#x2F;&#x2F;www.olcf.ornl.gov&#x2F;wp-content&#x2F;uploads&#x2F;2019&#x2F;05&#x2F;frontier_specsheet.pdf" rel="nofollow">https:&#x2F;&#x2F;www.olcf.ornl.gov&#x2F;wp-content&#x2F;uploads&#x2F;2019&#x2F;05&#x2F;frontie...</a>