When you purchase through links on our site, we may earn an affiliate commission.Heres how it works.
Its architecture takes an all-digital compute-in-memory approach, using modified SRAM cells for speed and energy efficiency.
It achieves a total of 9.6 PFLOPs FP4 compute power with 2GB of SRAM-based performance memory.
d-Matrixs approach eliminates the bottleneck by enabling computation directly within memory.
CEO Sid Sheth toldEE Timesthe company was founded in 2019 after feedback from hyperscalers suggested inference was the future.
Of course, that all changed post 2022 andChatGPT.
We also bet on transformer [networks] pretty early on in the company.
