Graphcore
flow-image

Machine intelligence with the IPU server

Published by Graphcore

This whitepaper discusses the Dell DSS8440 Graphcore IPU server, focusing on its dual IPU-Processor C2 cards, each equipped with over 2,400 cores, designed to accelerate AI workloads. It highlights the server's advanced In-Processor-Memory, high-bandwidth IPU-Link interconnect, and capabilities in model parallelism, recomputation, and pipelining, which significantly improve performance in training and inference of large machine learning models.

Download Now

box-icon-download

Required fields*

Please agree to the conditions

By requesting this resource you agree to our terms of use. All data is protected by our Privacy Policy.

Related Categories Artificial Intelligence, Deep Learning, AI Accelerators, AI Servers, AI Processing Units, Unsupervised Learning, Reinforcement Learning, ML Algorithms, Model Training, Model Evaluation, Renewable Energy, Energy Storage, Energy Analytics

More resources from Graphcore