SiFive introduces new processor core designs for AI devices – News

Chip startup SiFive Inc. today debuted four new central processing unit cores optimized to run artificial intelligence models.

Santa Clara, California-based SiFive was valued at $2.5 billion following its most recent funding round in 2022. The company develops CPU designs based on the open-source RISC-V instruction set architecture, or ISA. An ISA defines the collection of low-level computing operations that a chip mixes and matches to process data.

SiFive’s new cores expand upon RISC-V’s feature set by adding vector extensions. Those are components that allow a chip to more efficiently process multiple data points at once. The ability to parallelize computations can significantly speed up AI models, which use a large number of relatively simple computations to crunch data.

The new lineup is headlined by the X160 and X180. Both designs include vector processing features that speed up convolutions, which are calculations used by computer vision models to process images. The features can also accelerate certain data filtering and transformation tasks.

The X160 and X180 can both be configured to run a real-time operating system. This is a type of operating system that ensures calculations are always carried out in a predefined amount of time, which is important for certain systems. A manufacturer, for example, may wish to guarantee that a factory sensor will always generate an alert about equipment failures within three seconds of detecting them.

The X160 ships with up to 200 kibibyte of cache and a 2-mebibyte memory. Besides industrial equipment, SiFive also sees the chip finding use in consumer devices such as fitness trackers. Furthermore, the X160 can be installed in systems that contain multiple AI accelerators to manage the chips and block firmware tempering.

The X180 is 10% faster than the X160. It can also hold more data thanks to two built-in caches with a combined capacity of more than 4 mebibytes. According to SiFive, the chip lends itself to training AI models and powering certain types of data center equipment.

The two other cores that the company debuted today are upgraded versions of existing designs. The X280 is geared toward consumer devices such as augmented reality headsets, while X390 can also power cars and infrastructure systems. The latter core performs vector processing four times faster.

According to SiFive, its engineers enhanced the two designs with a new co-processor interface. The technology will make it easier to integrate the cores into systems-on-chip that also include AI accelerators. Additionally, the company has upgraded the memory subsystem in the X280 and X390 to reduce latency.

SiFive expects customers to start producing chips based on its new core designs in the second quarter of 2026. 

Photo: SiFive