Product Overview
For Innovators making new AI Breakthroughs, the Graphcore IPU-POD16 DA (Direct Attach) is designed to get you up and running in no time. A turnkey system, featuring Four IPU-M2000s, ready for installation in your datacentre. This lets AI teams make new breakthroughs in machine intelligence.
IPU-POD16 DA opens up a new world of machine intelligence innovation. Ideal for exploration and experimentation, the IPU-POD16 is the perfect new tool to develop concepts and pilots consolidating both training and inference in one affordable system. IPU-POD16 is a powerful, standalone AI compute resource. However, it also offers the opportunity for growth, on your terms. Your IPU-POD16 system investment can be expanded later into a larger IPU-POD system.
Designed specifically for the communication requirements of AI workloads at scale, IPU-Fabric is Graphcore’s innovative low-latency, jitter-free interconnect using industry standard IT equipment. It supports highly efficient, deterministic, all-to-all IPU interconnect across your system regardless of size.
Fully integrated and IPU-optimised, Graphcore's Poplar software leverages the unique characteristics of the IPU architecture to build AI applications of unrivalled performance and flexibility. Poplar allows effortless scaling of models from one to hundreds of IPUs without adding development complexity, allowing you to focus on the accuracy and performance of your application.
MSRP: From $149,995
Key Features
16 x GC200 Mk2 IPUs 4 x IPU-M2000 4 petaFLOPS AI compute 526.4GB Exchange Memory (includes 14.4GB In-Processor Memory and 512GB Streaming Memory) 23,552 IPU Cores Air-Cooled System
-
Form Factor
5U
-
Manufacturer
Graphcore
-
Memory
526.4GB
-
Software (Installed)
Poplar SDK
-
System Cooling
Air Cooled
Download the Data Sheet
Created to provide you with in depth information on our bespoke solutions, our product datasheets give you all of the necessary technical information of a product.
Download Data Sheet