At the Data Works Summit, Hortonworks announced the release of Hortonworks Data Platform (HDP) 3.0.

HDP 3.0 is based on Apache Hadoop 3.1 and includes containerization, GPU support, erasure coding, and namenode federation.

Containerization helps HDP 3.0 enable apps to launch quickly, allowing users to save time and resources. Containerization also makes it possible to run multiple versions from the application, enabling developers to create new features rapidly by developing and testing new versions of services without disrupting old ones. The new version also improves resource utilization and increases task throughput for containers.

GPU pooling enables the sharing of GPU resources with more workloads for cost effectiveness. With GPU isolation, GPUs can be dedicated to an application so that no other application has access to that GPU.

HDP 3.0 allows customers to run their workloads on any cloud, including Amazon S3, Azure Data Lake Store (ADLS), Azure Storage Blob, and Google Cloud Storage (GCS) technical preview.

“HDP 3.0 includes key innovations such as containerization, support for deep learning workloads, and real-time database that further modernize our data platform, ultimately leading to faster insights for the business,” said Eric Endebrock, vice president, Storage Solutions Marketing at Micron Technology.