tf.data: TensorFlow Input Pipeline
This talk covers an overview of the project and highlight best practices for creating performant input pipelines.
Tags: conference, data orchestration, data orchestration summit, tensorflow
On-Demand Video
Online Meetup: Powering Data Science and AI with Apache Spark, Alluxio, and IBM
Learn why leading companies are moving towards a decoupled compute and storage architecture, and the associated challenges and requirements. Hear about how Spark and Alluxio together can solve the challenges.
Tags: analytics, compute storage separation, hdfs, meetup, performance, spark, use case
Tech Talk: From limited Hadoop compute capacity to increased data scientist efficiency
Want to leverage your existing investments in Hadoop with your data on-premise and still benefit from the elasticity of the cloud?
Like other Hadoop users, you most likely experience very large and busy Hadoop clusters, particularly when it comes to compute capacity. Bursting HDFS data to the cloud can bring challenges – network latency impacts performance, copying data via DistCP means maintaining duplicate data, and you may have to make application changes to accomodate the use of S3.
“Zero-copy” hybrid bursting with Alluxio keeps your data on-prem and syncs data to compute in the cloud so you can expand compute capacity, particularly for ephemeral Spark jobs.
Tags: cloud bursting, hadoop, hybrid bursting, tech talk, zero copy
Community Office Hour: Accelerating Hive with Alluxio on S3
Learn more about Bazaarvoice’s use case leveraging Apache Spark, Hive, and Alluxio on S3. Along with how to set up Hive with Alluxio so that Hive jobs can seamlessly read from/write to S3.
Tags: alluxio engineering, aws s3, compute storage separation, hdfs, hive, office hour, spark
Data Orchestration for AI, Big Data, and Cloud
Haoyuan Li offers an overview of a data orchestration layer that provides a unified data access and caching layer for single cloud, hybrid, and multicloud deployments.
Tags: big data, cloud, compute, conference, data orchestration, storage
Online Meetup: Cybersecurity and fraud detection at ING Bank using Presto & Alluxio on S3
In this online presentation, we present how ING is leveraging Presto (interactive query), Alluxio (data orchestration & acceleration), S3 (massive storage), and DC/OS (container orchestration) to build and operate our modern Security Analytics & Machine Learning platform. We will share the challenges we encountered and how we solved them.
Tags: aws s3, machine learning, meetup, presto, security
Tech Talk: Accelerating analytics with EMR on your S3 data lake
EMR has become a widely used service to run big data analytics in the public cloud. But issues around slow/inconsistent EMR performance due to S3 data lakes creates challenges for organizations.
Alluxio is a data orchestration layer for the cloud that increases performance of analytic workloads running on AWS EMR using S3 as the storage.
Join us for this webinar where we will show you how to set up EMR Spark and Hive with Alluxio so jobs can seamlessly read from and write to your S3 data lake. You’ll see the performance gains with Alluxio in your EMR/S3 stack.
Community Office Hour: Building a Cloud Native Stack with EMR Spark, Alluxio, and S3
Learn how to set up EMR Spark with Alluxio so Spark jobs can seamlessly read from and write to S3. See the performance comparison between Spark on S3 with Spark, and Alluxio on S3.
Tags: aws s3, cloud, emr, office hour, performance, spark
Tech Talk: Accelerating Spark with Kubernetes
Kubernetes is widely used across enterprises to orchestrate computation. And while Kubernetes helps improve flexibility and portability for computation in public/hybrid cloud environments across infrastructure providers, running data-intensive workloads can be challenging.
When it comes to efficiently moving data closer to Spark or Presto frameworks, co-locating data with these frameworks and accessing data from multiple or remote clouds is hard to do. That’s where Alluxio, an open source data orchestration platform, can help.
Alluxio enables data locality with your Spark and Presto workloads for faster performance and better data accessibility in Kubernetes. It also provides portability across storage providers.
In this on demand tech talk we’ll give a quick overview of Alluxio and the use cases it powers for Spark/Presto in Kubernetes. We’ll show you how to set up Alluxio and Spark/Presto to run in Kubernetes as well.
Tags: cloud, hybrid cloud, kubernetes, locality, presto, spark, tech talk