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.

Benchmarks for Blaze, A high-performance C++ math library

63 pointsby wall_wordsover 9 years ago

7 comments

dengover 9 years ago
I remember this library being discussed on the Eigen list in 2012. Here&#x27;s the thread:<p><a href="http:&#x2F;&#x2F;thread.gmane.org&#x2F;gmane.comp.lib.eigen&#x2F;3423" rel="nofollow">http:&#x2F;&#x2F;thread.gmane.org&#x2F;gmane.comp.lib.eigen&#x2F;3423</a><p>The main critique at the time was that Blaze always assumes perfectly aligned data, including inside(!) the matrix, and pads the data with zeros if that is not the case. Of course, this makes it impossible to map external data, which is a huge downside. I&#x27;m not sure if that is still the case, but from skimming through the docs it doesn&#x27;t look to me like this has changed.
评论 #10120498 未加载
therobot24over 9 years ago
better link: <a href="https:&#x2F;&#x2F;bitbucket.org&#x2F;blaze-lib&#x2F;blaze" rel="nofollow">https:&#x2F;&#x2F;bitbucket.org&#x2F;blaze-lib&#x2F;blaze</a>
评论 #10119738 未加载
评论 #10118965 未加载
评论 #10118473 未加载
east2westover 9 years ago
I am considering converting a C++03 math library to C++14 as a side project to learn C++14 and I examined Eigen and Blaze. Eigen&#x27;s code size seems to be a fraction of Blaze, even though their functionalities are similar. Eigen also has some design documents while Blaze has papers but not much more. It seems I will try my hands on Eigen library for now. It is amazing that a couple of people could do in a few years; Blaze has hundred of thousands of lines of code.
评论 #10118885 未加载
评论 #10118393 未加载
评论 #10118678 未加载
评论 #10118450 未加载
shepardrtcover 9 years ago
Does Blaze implement its own BLAS subroutines? Or does it wrap around an existing BLAS library?
评论 #10120573 未加载
santaclausover 9 years ago
It would be interesting to see benchmarks of sparse operations, as well.
wall_wordsover 9 years ago
I&#x27;ve had great success with Blaze, despite the fact that it has received little publicity compared to alternatives like Eigen, Armadillo, etc. Blaze is consistently the leader of the pack in benchmarks, and even outperforms Intel MKL on the Xeon E5-2660 (the CPU for which the benchmark results are shown).
评论 #10118458 未加载
fizixerover 9 years ago
In the first plot, why do all libraries slow down at the n=1000 mark? something to do with cache?
评论 #10118537 未加载
评论 #10118463 未加载