A Lightmatter Envise unit in captivity. Image Credits:<\/strong> Lightmatter<\/p>\n<\/div>\n

\u201cWe\u2019ve built a software stack that integrates seamlessly with PyTorch and TensorFlow. The workflow for machine learning developers is the same from there \u2014 we take the neural networks built in these industry standard applications and import our libraries, so all the code runs on Envise,\u201d he explained.<\/p>\n

The company declined to make any specific claims about speedups or efficiency improvements, and because it\u2019s a different architecture and computing method it\u2019s hard to make apples-to-apples comparisons. But we\u2019re definitely talking along the lines of an order of magnitude, not a measly 10% or 15%. Interconnect is similarly upgraded, since it\u2019s useless to have that level of processing isolated on one board.<\/p>\n

Of course, this is not the kind of general-purpose chip that you could use in your laptop; it\u2019s highly specific to this task. But it\u2019s the lack of task specificity at this scale that seems to be holding back AI development \u2014 though \u201cholding back\u201d is the wrong term since it\u2019s moving at great speed. But that development is hugely costly and unwieldy.<\/p>\n

The pilots are in beta, and mass production is planned for 2024, at which point presumably they ought to have enough feedback and maturity to deploy in data centers.<\/p>\n

The funding for this round came from SIP Global, Fidelity Management & Research Company, Viking Global Investors, GV, HPE Pathfinder and existing investors.<\/p>\n<\/p><\/div>\n

<\/br><\/br><\/br><\/p>\n