Cerebras Unveils AI Supercomputer-On-A-Chip

Today unicorn startup Cerebras disclosed a few details about the wafer-scale AI chip it has been keeping under wraps for some three years. While many unanswered questions remain, the new approach could mark a significant milestone in the semiconductor industry, where chips have historically been constrained by the size of a single chip's mask. Basically, Cerebras designed a wafer of 84 interconnected chips that act as one device for compute and memory, interconnected by a super-fast on-die fabric. While building a supercomputer on a chip sounds like a great idea, building a wafer-scale array of chips is not for the faint of heart or talent. Figure 1: The Cerebras "WSE" is some 50 times larger than the largest chip used in AI Training from NVIDIA.