Advance precision timing with an integrated clock chip for AI datacentres

SiTime Corporation has introduced its Chorus family of clock generators for AI datacentre applications. This new MEMS-based clock-system-on-a-chip (ClkSoC) family provides 10X higher performance in half the size, compared to standalone oscillators and clocks. Chorus’ new approach includes clock, oscillator and resonator technologies in an integrated chip, simplifying system clock architecture and accelerating design time by up to six weeks. The family, combined with recently acquired timing products from Aura Semiconductor, builds on the company's strategy to deliver a complete portfolio of highly differentiated solutions.

“AI is driving tremendous needs for higher data throughput in datacentres and lower power consumption, and SiTime is uniquely positioned to help address these issues,” said Piyush Sevalia, executive vice president of marketing at SiTime. “Before Chorus, hardware designers had to use discrete product types, such as clocks, oscillators and resonators, which resulted in performance compromises. Chorus delivers integrated clock generators to solve these problems and is yet another example of how we are transforming the timing market with our unique approach.”

Chorus, with its integrated MEMS resonator, addresses the limitations of legacy clock generators, eradicating problems such as noise and matching the resonator's impedance with the clock. Also, it can decrease the board area for timing by up to 50% by replacing up to four standalone oscillators. Datacentre equipment such as servers, switches, acceleration cards and smart NICs are ideal applications for Chorus.

“SiTime continues to solve the electronics industry’s toughest timing challenges with advances in silicon MEMS timing technology,” said Dave Altavilla, co-founder, president and principal analyst at HotTech Vision and Analysis. “SiTime's new MEMS-based family of clock generators represents a significant leap forward, offering enhanced performance, reliability and integration essential for the evolving needs of big iron AI datacentres.”