Our Technology

Intelligence Processing Unit (IPU)

We’ve created a completely new processor that’s the first to be specifically designed for machine intelligence workloads – an Intelligence Processing Unit (IPU) that will set a new pace of innovation.

The IPU has been optimised to work efficiently on the extremely complex high-dimensional models needed for machine intelligence workloads. It emphasises massively parallel, low-precision floating-point compute and provides much higher compute density than other solutions.

Poplar (Graph programming framework)

Poplar is our graph programming framework for IPU accelerated platforms, designed to meet the needs of customers in advanced research teams and those working on commercial deployments in a wide range of industry sectors.

It’s a C++ framework that provides a seamless interface to standard machine learning frameworks, like Tensorflow and MXNet, so your existing applications written for Tensorflow will work out of the box on an IPU.

To support this, Poplar has a full set of drivers, application libraries and debugging and analysis tools to help tune performance and a C++ and Python interface for application development making our IPU systems quick and easy to use.

The Poplar framework is completely scaleable; it is a natural choice for all machine intelligence programming paradigms.

Bow-2000

The Bow-2000 machine is the building block for our Bow Pod systems and for disaggregated machine intelligence infrastructure at scale.

Each 1U blade features 4 Bow IPU processors, and delivers an amazing 1.4 petaFLOP of AI compute, 3.6GB In-Processor-Memory™ and up to 256GB Streaming Memory™. 

Combined with host servers, Bow-2000 technology is at the heart of all Graphcore Bow Pod systems

Bow Pod Systems

Next generation 3D Wafer-on-Wafer IPU systems for AI infrastructure at scale

	Bow Pod16 Ideal for exploration, the Bow Pod16 gives you all the power, performance and flexibility you need to fast-track your IPU prototypes and speed from pilot to production. Bow Pod16 is your easy-to-use starting point for building better, more innovative AI solutions with IPUs whether you're focused on language and vision, exploring GNNs and LSTMs or creating something entirely new.
	Bow Pod64 Built for multi-tenancy and concurrency, Bow Pod64 is a powerful, flexible building block for the enterprise datacenter, private or public cloud. With cloud-native capabilities to support multiple users and mixed workloads across multiple smaller VPods (Virtual Pods) or used as one single system for large training workloads Bow Pod64 gives you faster time to business value for today's models and unlocks a new world of new AI applications.
	Bow Pod256 Among our media interests, we also invest in Perfect Fit Media which owns and operates an extensive network of high quality advertising sites across prime retail and travel hubs, including airports across our investment portfolio.
	C600 IPU-Processor PCIe Card The Graphcore® C600 IPU-Processor PCIe Card is a high-performance acceleration server card targeted for machine learning inference applications. Powered by the Graphcore Mk2 IPU Processor with FP8 support, the C600 is a dual-slot, full height PCI Express Gen4 card designed for mounting in industry standard server chassis to accelerate machine intelligence workloads.