Alluxio is a proud sponsor and exhibitor at the AWS Summit in New York. If you weren't able to attend, here are the highlights!
What's AWS Summit? It's a one day conference bringing together the cloud computing community to engage on topics ranging from Machine Learning, Hybrid Cloud, Big Data & Analytics, and more.
What we learned
- Enterprises are advancing along the cloud journey, and data access has become a prevalent challenge, because enterprises adopting hybrid cloud are not able to efficiently access data on-premise and in their public cloud.
- Amazon's CTO Werner Vogels talks about AWS Outposts in his keynote. Amazon's investment in Outposts is another indication of the rise of hybrid cloud.
- Cloud applications are heavily weighed towards data driven applications such as analytics and machine learning applications.
Announcements
We were thrilled to have announced the release of Alluxio 2.0 at the Summit! Alluxio 2.0 is the largest release since inception with over 900 PRs as well as many new features to continue building on to our data orchestration approach for the cloud.
Learn more: Orchestrating Data for the Cloud World with Alluxio 2.0 , Download Alluxio
Thanks to everyone for stopping by the Alluxio booth and the great conversations!
.png)
Blog
In this blog, Greg Lindstrom, Vice President of ML Trading at Blackout Power Trading, an electricity trading firm in North American power markets, shares how they leverage Alluxio to power their offline feature store. This approach delivers multi-join query performance in the double-digit millisecond range, while maintaining the cost and durability benefits of Amazon S3 for persistent storage. As a result, they achieved a 22 to 37x reduction in large-join query latency for training and a 37 to 83x reduction in large-join query latency for inference.
In the latest MLPerf Storage v2.0 benchmarks, Alluxio demonstrated how distributed caching accelerates I/O for AI training and checkpointing workloads, achieving up to 99.57% GPU utilization across multiple workloads that typically suffer from underutilized GPU resources caused by I/O bottlenecks.