Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Description

Amazon EC2 UltraClusters allow for the scaling of thousands of GPUs or specialized machine learning accelerators like AWS Trainium, granting users immediate access to supercomputing-level performance. This service opens the door to supercomputing for developers involved in machine learning, generative AI, and high-performance computing, all through a straightforward pay-as-you-go pricing structure that eliminates the need for initial setup or ongoing maintenance expenses. Comprising thousands of accelerated EC2 instances placed within a specific AWS Availability Zone, UltraClusters utilize Elastic Fabric Adapter (EFA) networking within a petabit-scale nonblocking network. Such an architecture not only ensures high-performance networking but also facilitates access to Amazon FSx for Lustre, a fully managed shared storage solution based on a high-performance parallel file system that enables swift processing of large datasets with sub-millisecond latency. Furthermore, EC2 UltraClusters enhance scale-out capabilities for distributed machine learning training and tightly integrated HPC tasks, significantly decreasing training durations while maximizing efficiency. This transformative technology is paving the way for groundbreaking advancements in various computational fields.

Description

The convergence of high-performance computing (HPC) and machine learning is placing unprecedented requirements on storage solutions, as the input/output demands of these two distinct workloads diverge significantly. This shift is occurring at this very moment, with a recent analysis from the independent firm Intersect360 revealing that a striking 63% of current HPC users are actively implementing machine learning applications. Furthermore, Hyperion Research projects that, if trends continue, public sector organizations and enterprises will see HPC storage expenditures increase at a rate 57% faster than HPC compute investments over the next three years. Reflecting on this, Seymour Cray famously stated, "Anyone can build a fast CPU; the trick is to build a fast system." In the realm of HPC and AI, while creating fast file storage may seem straightforward, the true challenge lies in developing a storage system that is not only quick but also economically viable and capable of scaling effectively. We accomplish this by integrating top-tier parallel file systems into HPE's parallel storage solutions, ensuring that cost efficiency is a fundamental aspect of our approach. This strategy not only meets the current demands of users but also positions us well for future growth.

API Access

Has API No 

API Access

Has API No 

Screenshots View All

Screenshots View All

Integrations

AWS Neuron Yes 
Amazon EC2 Yes 
Amazon EC2 Auto Scaling Yes 
Amazon EC2 Capacity Blocks for ML Yes 
Amazon EC2 G5 Instances Yes 
Amazon EC2 Inf1 Instances Yes 
Amazon EC2 P5 Instances Yes 
Amazon EC2 Trn1 Instances Yes 
Amazon EKS Yes 
Amazon Elastic Container Service (Amazon ECS) Yes 
Amazon FSx Yes 
Amazon S3 Yes 
Amazon SageMaker Yes 
Amazon Web Services (AWS) Yes 
Automai Robotic Process Automation No 
Check Point IPS No 
Check Point Infinity No 
PyTorch Yes 
TensorFlow Yes 
XYGATE Identity Connector No 

Integrations

AWS Neuron No 
Amazon EC2 No 
Amazon EC2 Auto Scaling No 
Amazon EC2 Capacity Blocks for ML No 
Amazon EC2 G5 Instances No 
Amazon EC2 Inf1 Instances No 
Amazon EC2 P5 Instances No 
Amazon EC2 Trn1 Instances No 
Amazon EKS No 
Amazon Elastic Container Service (Amazon ECS) No 
Amazon FSx No 
Amazon S3 No 
Amazon SageMaker No 
Amazon Web Services (AWS) No 
Automai Robotic Process Automation Yes 
Check Point IPS Yes 
Check Point Infinity Yes 
PyTorch No 
TensorFlow No 
XYGATE Identity Connector Yes 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Customer Support

Business Hours Yes 
Live Rep (24/7) Yes 
Online Support Yes 

Customer Support

Business Hours Yes 
Live Rep (24/7) Yes 
Online Support Yes 

Types of Training

Training Docs Yes 
Webinars Yes 
Live Training (Online) No 
In Person Yes 

Types of Training

Training Docs Yes 
Webinars Yes 
Live Training (Online) Yes 
In Person No 

Vendor Details

Company Name

Amazon

Founded

1994

Country

United States

Website

aws.amazon.com/ec2/ultraclusters/

Vendor Details

Company Name

Hewlett Packard

Founded

2015

Country

United States

Website

www.hpe.com/us/en/solutions/hpc-high-performance-computing/storage.html

Product Features

HPC

Machine Learning

Deep Learning No 
ML Algorithm Library No 
Model Training No 
Natural Language Processing (NLP) No 
Predictive Modeling No 
Statistical / Mathematical Tools No 
Templates No 
Visualization No 

Alternatives

Alternatives

Lustre Reviews

Lustre

OpenSFS and EOFS