We have not. We’ve been using Mellanox CX5s. The latency is overhead is largely from copying between our C-based benchmark and Rust. We will likely optimize it to remove these copies but will have to switch to unsafe Rust.
-
-
Replying to @schemeprincess @heinz_gies
We're using unsafe / rentals and happy to share what we've learnt.
2 replies 0 retweets 4 likes -
-
Replying to @schemeprincess @darachennis
Holy cow that implements a whole async runtime! o.O
3 replies 0 retweets 4 likes -
-
Replying to @darachennis @heinz_gies
Also, all done by Michael Roberts! I will try and get her on to Twitter!!
1 reply 0 retweets 2 likes -
Replying to @schemeprincess @heinz_gies
Ah sure but your tweet did the adoption magic
1 reply 0 retweets 2 likes -
Replying to @darachennis @heinz_gies
But she’ll be much better for answering your Rust questions as she did all of the implementation. More efficient for me to eliminate the extra hop. :)
1 reply 0 retweets 1 like -
Replying to @schemeprincess @heinz_gies
Lol. Heinz is almost as good as my old mechanical keyboard
But better jokes2 replies 0 retweets 1 like -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.