Apache Spark has won the SIGMOD Systems Award, and Photon won the Best Industry Paper Award! This is a great testament to the adoption and impact of these two systems.
If you are at SIGMOD this wk, please come by and say hi.
https://t.co/nWb3JXlzhi
Databricks Photon engine just hit public preview, bringing significant speedups to SQL workloads! It's also now the default in SQL Endpoints. https://t.co/etdi5fdIg1
The CFP for the SOSP Student Research Competition is up: https://t.co/UKSf2e3fWj Excited to chair this with @apanda and looking forward to the amazing work of undergrad and grad students. This is a great way to increase the visibility of your work and get feedback. Please submit!
Congrats to @paroma_varma, Co-founder and Head of Solutions at Snorkel, for being recognized on @GVteam's Impact List, highlighting 25 exceptional women for #IWD2021— https://t.co/pyWakAZ6fK. We are proud and privileged to work alongside you.
#GVImpact
Tomorrow at around 11:15am ET I will be presenting some exciting in-progress work at Hotnets on a new way to think about offloads.
You - yes, you - are invited to watch!
YT livestream: https://t.co/FbBid7m5eG
Paper: https://t.co/t468O1Dh8L
I'm getting closer to graduating (hoping by Nov 1), and it's time to figure out what's next! I'd like to continue working on @rustlang and its ecosystem, ideally on open-source libraries and tools, so if you know of a good fit that supports remote work from LA, please reach out!
This is a pretty big deal -- Databricks is launching a new native execution engine for Spark SQL at this #SparkAISummit, which runs existing workloads up to 18x faster. It's optimized for cloud storage and Delta & Parquet formats. @rxin is giving a talk about it on stream now.
Really proud of my student @sppalkia who passed his (online) PhD defense today! He's the first of my students to graduate, and he did awesome work accelerating data applications with Weld, Mozart and other systems. You can see his talk and slides here: https://t.co/s5eyGjXkPL
Cool work by my student @sppalkia. Many groups are building compilers for data & ML apps, but this is time-consuming and complex. @sppalkia shows you can get most of the speedup with existing library functions (NumPy, pandas etc) by managing data movement: https://t.co/qGV3MNXMZQ
Great #snorkelML workshop at Stanford this week- thanks to our friends from industry (Google, Microsoft, Facebook, Salesforce, VMware, NG), gov't & medicine who attended! Tutorials https://t.co/HoPqfBEg9Y & slides https://t.co/f6XschVjVe; more soon w/ v0.9 https://t.co/VZaMAPhHRP
@JeffDean@paroma_varma is a huge reason I do research today! gave me great balance of ownership and guidance— so grateful to work with such an awesome human! 😃👋
Glad KDD is trying out double-blind, but preventing prior ArXiv subs is regressive & against early dissemination of ideas. "... non-anon. papers ... issued as tech. reports or similar, in particular in arXiv, either prior to .. submission or during .. review, cannot be submitted"
Learned profilers estimate codepath performance dynamically at runtime, enabling lower overhead and more accurate estimates than alternatives like cProfile and statprof: https://t.co/7U4ELZPPtk (with @sppalkia, @meep_me, @matei_zaharia at NIPS ML for Systems Workshop)
ITS HERE!!!!
Rust 1.31 and Rust 2018 is finally out! https://t.co/wbvYXA5Rar
Thank you so much to everyone who has contributed over these past three years. ❤️❤️❤️