Code: https://github.com/bshoshany/thread-pool/blob/master/BS_thre...
https://github.com/bshoshany/thread-pool/blob/master/BS_thre...
I don't see how this is built for particularly good performance, or with many-core machines in mind.
https://github.com/bshoshany/thread-pool/blob/master/BS_thre...
I don't see how this is built for particularly good performance, or with many-core machines in mind.
It's an undergrad assignment basically. The writeup is nice, and it's great that it's on arxiv but it's not novel nor publishable research. The implementation that ships with a given OS is sure to run around in circles around it.
Here the author acknowledges that other libraries may be more performant, but describes the motivation for the work as essentially something that’s a small piece of code to maintain, and easy to use.
I didn’t run the code but I read through the paper and it doesn’t seem like it’s made a convincing case for this.