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。

Tensor Memory Bypass Cache?

2 点作者 daly12 个月前
It seems to me that there is a good speedup possible if the GPU and HBM had a &#x27;cache bypass&#x27;. That is, there are likely a large number of frequent matrix multiplies that could be computed by hardware lookup rather than an actual multiply. Such a pre-multiply cache would free up more of the actual multiply hardware, substituting the cache response for the result.<p>This &#x27;memoizing&#x27; trick is widely used in compute-intensive situations but I&#x27;m unaware of any GPU&#x2F;HBM hardware to support this.<p>Given that the multiplies are now computing 4 or 8 bit results this seems like a reasonable number of matrix multiplies could be cached.

暂无评论

暂无评论