HackerTrans
TopNewTrendsCommentsPastAskShowJobs

gdcohen

no profile record

Submissions

Decoding GPU Efficiency: The FLOPs Fallacy

clockwork.io
3 points·by gdcohen·4 месяца назад·0 comments

comments

gdcohen
·4 месяца назад·discuss
I agree. If you can reliably recover from failures by migrating instead of restoring from checkpoints, then the need to checkpoint frequently becomes far less important and reduces the overhead of taking checkpoints. Similarly, a lot of users are experimenting with asynchronous checkpoints to reduce the blocking penalty, but there are big tradeoffs there with DRAM usage. So being able to take checkpoints far less frequently gives you more flexibility on the type of checkpointing you use as well.
gdcohen
·7 месяцев назад·discuss
Take a look at Exploiting a Natural Network Effect for Scalable, Fine-grained Clock Synchronization - https://www.usenix.org/conference/nsdi18/presentation/geng (commercial version by the same authors - clockwork.io).