SAN JOSE, Calif. — Startup Gyrfalcon is moving fast with a chip for inferencing on deep neural networks, but it faces an increasingly crowded market in AI silicon. A year after it got its first funding, the company is showing a working chip and claiming design wins in smartphones, security cameras and industrial automation equipment.
Data centers typically train deep neural networks and run inference tasks on them using banks of servers. Increasingly, client and embedded systems from cars to handsets are adopting accelerators to speed the inferencing jobs.
Apple, Google and Huawei are already shipping smartphones with inferencing blocks in their custom SoCs. Google and Microsoft built inference accelerators for their data centers.
Among merchant suppliers, Movidius, now part of Intel, is shipping inference chips while Cadence, Ceva and Synopsis are suppling IP blocks and Imagination and ARM have announced plans. At least a dozen other startups are still in stealth mode with AI silicon including Groq, founded by a group of former Google chip developers to build an inference chip.
“Most of the action in inference is from the IP suppliers, largely this will be a market for integrated chips,” said Linley Gwennap, principal of market watcher the Linley Group.
For its part, Gyrfalcon has been showing since late last fall working silicon for its Lightspeeur SPR2810 processor for convolutional neural nets (CNNs). The 28nm TSMC chip fits in a 7x7mm package and packs tens of thousands of proprietary cores and embedded SRAM to crank out 9.3 TOPS/Watt without external DRAM. The cores are mainly ALUs with associated memory and logic for controlling dataflows.
The chip uses ideas one of its co-founders, Lin Yang, articulated in a 1988 PhD paper about CNNs while he was at UC Berkeley. The chip only accelerates CNNs, one of the most popular of a wide variety of neural nets in use.
A top-five smartphone maker will use the chip in a future flagship phone, said Frank Lin, head of strategy for the startup. In China, a large insurance company will design it into surveillance cameras and a steel maker in Shanghai will use it in inspection systems.
“We moved very fast from getting our first funding in February last year to having an FPGA verified in April and a chip back from TSMC in md-September,” said Lin.
Next page: Gyrfalcon works with Socionext, QuickLogic