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。

How GPU Computing Works [video]

160 点作者 quick_brown_fox将近 3 年前

5 条评论

Lichtso将近 3 年前
If I understand correctly:<p>CPUs do minimize latency by:<p>- Register renaming<p>- Out of order execution<p>- Branch prediction<p>- Speculative execution<p>They should not be over subscribed as they have to context switch by storing &#x2F; loading registers and the cache coherence protocols scale badly with more threads.<p>GPUs on the other hand maximize throughput by:<p>- A lot more memory bandwidth<p>- Smaller and slower cores, but more of them<p>- Ultra threading (the massively over subscribed hyper threading the video mentions)<p>- Context switching between wavefronts (basically the equivalent of a CPU thread), just shifts the offset into the huge register file (no store and load)<p>The one area in which CPUs are getting closer to GPUs is SIMD &#x2F; SIMT. CPUs used to be able to apply one instruction to a vector of elements without masking (SIMD). In ARM SVE and x86 AVX-512 they can now (like GPUs) mask out individual lanes (SIMT) for ALU operations and memory operations (gather load &#x2F; scatter store).
评论 #32075594 未加载
评论 #32075338 未加载
评论 #32075443 未加载
boberoni将近 3 年前
<i>&gt; (Almost) Nobody (really) cares about flops ...because we should really be caring about memory bandwidth</i><p>In university, I was shocked to learn in a database class that CPU costs are dwarfed by the I&#x2F;O costs in the memory hierarchy. This was after spending a whole year on data structures and algorithms, where we obsessed over runtime complexity and # of operations.<p>It seems that the low-hanging fruit of optimization is all gone. New innovations for performance will have to happen in transporting data.
评论 #32075262 未加载
评论 #32076928 未加载
评论 #32075542 未加载
评论 #32075590 未加载
einpoklum将近 3 年前
This seems like this year&#x27;s version of the talk given last year, which was just recently posted here on HN as &quot;How CUDA Programming works&quot;:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31983460" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31983460</a>
oifjsidjf将近 3 年前
Here is another interesting series of articles which describes in more details how GPUs draw:<p><a href="https:&#x2F;&#x2F;fgiesen.wordpress.com&#x2F;2011&#x2F;07&#x2F;09&#x2F;a-trip-through-the-graphics-pipeline-2011-index&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fgiesen.wordpress.com&#x2F;2011&#x2F;07&#x2F;09&#x2F;a-trip-through-the-...</a>
评论 #32075316 未加载
wrs将近 3 年前
The Wheel of Reincarnation continues. [0] (Though it’s sort of turning the other way, this time around?)<p>[0] <a href="http:&#x2F;&#x2F;www.catb.org&#x2F;jargon&#x2F;html&#x2F;W&#x2F;wheel-of-reincarnation.html" rel="nofollow">http:&#x2F;&#x2F;www.catb.org&#x2F;jargon&#x2F;html&#x2F;W&#x2F;wheel-of-reincarnation.htm...</a>
评论 #32075080 未加载