This startup hopes photonics will get us to AI systems faster
The problem with waiting for quantum computing to bring in the next wave of AI is that it’s likely to arrive a lot slower than people would like. The next best options include increasing the speed of existing computers somehow -- but there’s now an important added imperative: power-efficient systems that mean we don’t burn up the planet while we get about conjuring the AI singularity into existence.
Meanwhile, the speed of AI computation doubles every three or four months, meaning that standard semiconductor technologies are struggling to keep up. Several companies are now working on "photonics processing", which introduces light into the semiconductor realm which, for obvious "speed of light" reasons, literally speeds up the whole thing markedly.
Salience Labs is an Oxford-based startup that thinks it has the answer, by combining an ultra-high-speed multi-chip processor that packages a photonics chip together with standard electronics.
It’s now raised a seed round of $11.5 million led by Cambridge Innovation Capital and Oxford Science Enterprises. Also participating were Oxford Investment Consultants, former CEO of Dialog Semiconductor Jalal Bagherli, ex-Temasek Board Member Yew Lin Goh and Arm-backed Deeptech Labs.
Salience is a spin-out of Oxford University and the University of Münster in 2021, after it came up with the idea of using a broad bandwidth of light to execute operations to deliver what it calls “massively parallel processing performance within a given power envelope”. The company says the technology is highly scalable and capable of stacking up to 64 vectors into a beam of light.
Vaysh Kewada, CEO and co-founder of Salience Labs, told me: “This technology is going to mean we can do far more calculation for the same power requirement -- which means fundamentally more efficient AI systems."
She thinks the world needs ever-faster chips to grow AI capability, but the semiconductor industry cannot keep pace with this demand. “We’re solving this with our proprietary ‘on-memory compute’ architecture which combines the ultra-fast speed of photonics, the flexibility of electronics and the manufacturability of CMOS. This will usher in a new era of processing, where supercompute AI becomes ubiquitous,” she said.
Ian Lane, partner, Cambridge Innovation Capital added: “Salience Labs brings together deep domain expertise in photonics, electronics and CMOS manufacture. Their unique approach to photonics delivers an exceedingly dense computing chip without having to scale the photonics chip to large sizes.”
This is an animation of photonics going off inside the chip: