
Graphcore IPU Put Through the Supercomputing Paces
…With performance comparable to the Nvidia V100 GPU, a common accelerator in HPC but better energy consumption numbers and memory bandwidth potential, Graphcore can turn heads in supercomputing.
…With performance comparable to the Nvidia V100 GPU, a common accelerator in HPC but better energy consumption numbers and memory bandwidth potential, Graphcore can turn heads in supercomputing.
Sponsored by Graphcore
27th January 2021 – 16:00 GMT, 8:00 PT, 11:00 ET
IPU-POD is Graphcore’s unique scale-out solution for high-performance machine intelligence compute, ideal for experimentation to prototype to production systems from IPU-M2000 with 4 IPUs up to supercomputing scale. …
Sponsored by Graphcore
Graphcore, the U.K.-based startup that launched the Intelligence Processing Unit (IPU) for AI acceleration in 2018, has introduced the IPU-Machine. …
There has been a great deal of interest in deep learning chip startup, Graphcore, since we first got the limited technical details of the company’s first-generation chip last year, which was followed by revelations about how their custom software stack can run a range of convolutional, recurrent, generative adversarial neural network jobs. …
The last two years have delivered a new wave of deep learning architectures designed specifically for tackling both training and inference sides of neural networks. …
As a thought exercise, let’s consider neural networks as massive graphs and begin considering the CPU as a passive slave to some higher order processor—one that can sling itself across multiple points on an ever-expanding network of connections feeding into itself, training, inferencing, and splitting off into multiple models on the same architecture. …
On today’s program we talk AI chip innovations with Graphcore co-founder and CEO, Nigel Toon, tap into the Barcelona Supercomputing Center to talk Arm server performance, check in with Sandia for brain-inspired computing advances; talk HDD technologies that keep disk relevant, and also discuss RISC-V with the foundation’s CEO. …
Let’s leave aside all the questions about the long-term viability of AI ASICs and appliances and focus instead on the beauty of a good architecture. …
If you are a sponsor or press that did not register in time contact us for details. …
If we could sum up the near-term future of high performance computing in a single phrase, it would be more of the same and then some. …
All Content Copyright The Next Platform