๐ Excited to release mKernel: a set of fast multi-node, multi-GPU fused kernels.
๐ป Code: https://t.co/y2WfdMVTfC
๐ Blog: https://t.co/wGomxmeRxr
mKernel fuses compute + communication into one persistent GPU kernel, covering both intra/inter-node with GPU-initiated communication.
Amazing team: @yangzhouy, Chon Lam Lao, Costin Raiciu, Scott Shenker, @istoica05
It is exciting to announce that I'll be joining Harvard CS @hseas as a PhD student advised by Professor @minlanyu and continue my research on programmable networks and systems.
Hopefully I can contribute more to these areas in the following years!
We will have three paper appearing at NSDI '21: Whiz (authored by Arjun, Robert and Raajay); ATP (Lam, Yanfang, Kshiteej); and a paper on running BGP at scale in Facebook datacenters (Archie, Kausik). Congratulations to all!