Graphcore AI Solutions

Graphcore IPU (Intelligence Processing Unit) powered server solutions from Exxact have been built to support new breakthroughs in machine intelligence.

value propositon

NLP Performance

The IPU delivers impressive performance for NLP, including BERT-Large training, cutting hours from AI development cycles.

value propositon

Best for Computer Vision

Graphcore delivers significant performance advantages for AI applications, and running EfficientNet on the IPU requires extra INT8 quantization.

value propositon

Standard Warranty

All Graphcore powered systems come with a standard 1 year warranty and support, and offered with an extended 3 year option.

Explore Graphcore Powered Products

Solution image

IPU-M2000


Solution value property image1 Petaflop Compute system
Solution value property imageFor Proof of Concept using IPU
Solution value property imageDesigned for AI training & inference
Solution value property imageSystems can grow to supercomputing scale
Solution image

IPU-POD16


Solution value property imagePre-configured 4 petaFLOP AI system
Solution value property imageDedicated, Powerful AI Compute
Solution value property imageTurnkey, ready for installation
Solution value property imageExtensive documentation and support
Solution image

IPU-POD64


Solution value property image16 petaFLOPS of AI training or inference
Solution value property imageSimple, Powerful Built in Networking
Solution value property imageFor production deployment workloads
Solution value property imageSimplified data center integration

Poplar® Graph Framework Software

The Poplar SDK is a complete software stack, which was co-designed from scratch with the IPU, to implement our graph toolchain in an easy-to-use and flexible software development environment.

Poplar

Standard Framework Support

Poplar seamlessly integrates with standard machine intelligence frameworks:

  • TensorFlow 1 & 2 support with full performant integration with TensorFlow XLA backend
  • PyTorch support for targeting IPU using the PyTorch ATEN backend
  • PopART™ (Poplar Advanced Runtime) for training & inference; supports Python/C++ model building plus ONNX model input
  • Full support for PaddlePaddle and other frameworks is coming soon
graphcore poplar framework support

Not sure what you need?

Let us know what kind of project you have planned. We can help you decide.

IPU Acceleration Across Industries

use case financial

Finance

use case healthcare

Healthcare

use case telecommunications

Telecommunications