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 you to modify massive data sets and navigate to the most pertinent parts of the data to gather better insights—all in real time.
If you are running IndeX on AWS, you can use 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 S3.
The benefits of NVIDIA IndeX on AWS include the following:
- 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)
- 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, you 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, you can deploy an Amazon EC2 GPU-based instance using the NVIDIA IndeX AMI from the AWS Marketplace.
- For cluster rendering, you 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.
There are several options for deploying 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.
The following use cases highlight how NVIDIA IndeX has helped customers manage massive data visualizations
BigBrain
BigBrain is 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 Cholla researchers and scientists to create specialized visualization 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:
