NVIDIA IndeX, a 3D volumetric interactive visualization framework that allows scientists and researchers to visualize and interact with massive high performance computing (HPC) datasets, is now on the AWS cloud.
Available as a custom Amazon Machine Image (AMI) from the AWS Marketplace, the NVIDIA IndeX SDK enables users to modify massive data sets and navigate to the most pertinent parts of the data to gather better insights — all in real time.
Users running IndeX on AWS can leverage Amazon Elastic Compute Cloud (Amazon EC2) instances powered by NVIDIA GPUs to achieve scalable performance for real-time visualization, and computing of multi-valued volumetric data together with embedded geometry data. In addition, NVIDIA IndeX on AWS offers a plugin to load compute data sets directly from Amazon Simple Storage Service (Amazon S3).
The benefits of NVIDIA IndeX on AWS include:
- Visualization: Accurate, high-quality data visualization, feature representation and annotation.
- Scalability: Optimization for the latest NVIDIA GPUs, including the recently announced NVIDIA A100 Tensor Core GPU (Amazon EC2 P4d instances), V100 Tensor Core GPU (Amazon EC2 P3 instances) and T4 Tensor Core GPU (Amazon EC2 G4 instances), which transparently scales across multiple GPUs and across multiple nodes.
- Extensibility: Flexibility for a variety of application domains such as microscopy, engineering science, seismic data interpretation and astrophysics.
With these benefits and features, professionals can take advantage of both the performance features that the NVIDIA IndeX SDK offers, and the elasticity and scalability of AWS.
NVIDIA IndeX on AWS offers a couple of different options for 3D volume rendering, single instance rendering and cluster rendering. With single instance rendering, a user can deploy an Amazon EC2 GPU-based instance using the NVIDIA IndeX AMI from the AWS Marketplace. For cluster rendering, users can launch a cluster of Amazon EC2 GPU instances using AWS ParallelCluster, which is an AWS-supported open source cluster management tool that simplifies deploying and managing HPC clusters on AWS.
Users have two options to deploy NVIDIA IndeX:
- Using the standalone IndeX Software Development Kit (SDK) and IndeX native web viewer.
- Using IndeX as a plugin in ParaView, one of the most popular visualization tools in the scientific HPC community.
A few use cases below highlight how NVIDIA IndeX has helped customers manage massive data visualizations:
- BigBrain: A human brain dataset that contains the reconstituted sections in the coronal dimension. NVIDIA IndeX Accelerated Computing technology (XAC API) enables researchers to carve out and identify different features of particular interest inside the visualizations.
- Cholla: NVIDIA IndeX allows researchers and scientists to create specialized visualizations techniques that help answer specific analysis questions regarding large-scale galactic flow phenomena.
- Survey of Parihaka Region in New Zealand: NVIDIA IndeX can be used to implement effective visualizations providing valuable cues and insights into subsurface structures for efficient data interpretation. The visualization of the entire Parihaka survey demonstrates that NVIDIA IndeX can utilize multiple GPUs for interactive exploration of seismic data ultimately at any scale for efficient data interpretation.
Check out the following resources to learn more about NVIDIA IndeX on AWS: