Microsoft Azure IPU Cloud Preview is here
The world's first Graphcore IPU cloud service is now available on Microsoft Azure, letting innovators around the world create new breakthroughs in machine intelligence.Get started
State of the Art with today’s large, complex models
We have achieved state of the art performance and accuracy with the BERT language model, training BERT Base in 56 hours with seven C2 IPU-Processor PCIe cards, each with two IPUs, in an IPU Server system. With BERT inference, we see 3x higher throughput with over 20% improvement in latency to serve up results faster than ever.
Graphcore C2 IPU-Processor PCIe card achieves 3.4x higher throughput at 20x lower latency compared to a leading alternative processor. High throughput at the lowest possible latency is key in many of the important use cases today.