Cloudera Knowledge Platform to combine with Nvidia’s accelerated Apache Spark 3.0 libraries

Cloudera mentioned that it’ll combine its Cloudera Knowledge Platform (CDP) and Nvidia’s accelerated Apache Spark 3.0 libraries.

In line with Cloudera, the combination will speed up knowledge pipelines and make it simpler so as to add machine studying workflows to processes.

Cloudera Knowledge Platform added Utilized Studying Prototypes (AMPs) earlier this yr. AMPs usually run on Nvidia GPU {hardware}.

The Apache Spark 3.0 libraries are accelerated utilizing Nvidia’s RAPIDS platform. Cloudera is seeking to remove bottlenecks for knowledge scientists and assist them scale machine studying fashions.

Nvidia’s GPU acceleration for Apache Spark goals to hurry up knowledge preparation duties and practice fashions quicker, orchestrate pipelines from knowledge to coaching to visualization and save on infrastructure prices.

Cloudera mentioned GPU-accelerated Apache Spark 3 runs natively on CDP and may plug into excessive efficiency compute instruments.

The general public cloud implementation of Nvidia RAPIDS-accelerated Apache Spark 3.0 libraries is now usually accessible. On-premises integrations can be accessible in the summertime.  

https://www.zdnet.com/article/cloudera-data-platform-to-integrate-with-nvidias-accelerated-apache-spark-3-0-libraries/#ftag=RSSbaffb68