ALLUXIO COMMUNITY NEWSLETTER

SEPTEMBER 2021

Highlights


Improving Presto performance with Alluxio at TikTok | On-Demand
See TikTok Tech Lead, Frank Hu, describe how they are improving Presto performance by adopting Alluxio for the cache layer without introducing additional services. 

Building a 10X Faster Presto with Alluxio at Facebook | On-Demand
See Facebook software engineer, Rohit Jain, describe how they are getting 10x faster Presto query performance with RaptorX, Alluxio, and hierarchical caching.

Modernizing Your Data Platform for Analytics and AI in the Hybrid Cloud Era | On-Demand
Seeking a good overview of how Alluxio helps modernize your data platform? Alluxio’s, Adit Madan, covers how Alluxio Data Orchestration can simplify data access and improve workload performance in the hybrid cloud and multi-cloud era.

Alluxio Day V (user presentations from Microsoft, MOMO, Boss) | On-Demand
This community event was recently hosted in China with Alluxio users from Microsoft, MOMO, Boss, as well as Alluxio’s experts sharing their experiences and learnings.

UPCOMING EVENTS


Speeding up TensorFlow & PyTorch with Alluxio
Sep 9 – 11:00 AM PDT | Alluxio Tech Talk
Learn how Alluxio’s improved POSIX interface streamlines Machine Learning, such as TensorFlow & PyTorch. With version 2.6, we introduced a new JNI-based FUSE implementation to support POSIX data access, as well as many improvements in relevant data operations.

The Rise of Data Orchestration – DM Radio
Sep 16 | DM Radio
Listen in to Erik Kavanagh of Bloor Group upcoming podcast interview with Alluxio’s own Bin Fan on the Rise of Data Orchestration in the modern data era. 

Data Orchestration for TensorFlow & PyTorch 
Sep 22 | ApacheCon
If you’re headed to ApacheCon, be sure to catch Alluxio’s VP of Open Source, Bin Fan, present on how Alluxio Data Orchestration can be used to speed Machine Learning and onboard more data-intensive applications.

GOOD READS


Design and Implementation of Alluxio POSIX Support
Applications such as Tensorflow and PyTorch can access data through Alluxio FUSE service without modifying any code, just like accessing their local file systems with Unix/Linux POSIX API. This whitepaper describes the design and implementation of Alluxio FUSE service, its current status, and future plans.

Alluxio Praised for Technology Innovation in Cloud, Data Analytics and Data Management with Recent Industry Awards
Alluxio, together with help from our vibrant community of contributors, have earned multiple industry awards in 2021. Let’s keep things rolling!

Open Source Contributor Spotlight 


In this month’s Contributor Spotlight, we are honored to feature Peter Roelants, an Alluxio Open Source project contributor from Belgium. Peter Roelants is Lead Machine Learning Engineer at Aspect Analytics, a bioinformatics startup building tools to mine the rich molecular data coming from Mass Spectrometry Imaging (MSI) technology. Over the last few months Peter has been building Aspect’s machine learning computation platform, in which Alluxio’s data consolidation layer plays a central role. While working to integrate Alluxio FUSE as a data access point, Peter contributed to help deploy Alluxio FUSE in containerized environments. Check out Peter’s talk Alluxio-FUSE as a data access layer for Dask!