Connect with us


Did startup Flow Computing just make CPUs 100x faster? Here’s the white paper and FAQs



Flow Computing is making a tough to believe claim: it says it can 100x the performance of any CPU by shifting work to a special parallel processing unit (PPU) inside or outside the chip. And, it claims, it can double the performance of any existing computing code overnight, even if programmers don’t lift a finger to optimize for its new tech. The PPU could even fit into phones and watches, it says, dramatically improving their performance and battery life by offloading work from the CPU.

But the company can’t quite show any of that today — because Flow hasn’t built a chip and doesn’t necessarily intend to build one, its co-founders tell The Verge.

The company is a spinoff of the VTT Technical Research Centre of Finland, and it’s emerging from stealth today with roughly $4.3 million in funding. Like Arm, which builds reusable IP blocks that it sells to major chipmakers, Flow hopes to sign deals with the likes of AMD, Apple, Intel, Nvidia, and Qualcomm to take it from here. At this point, Flow hasn’t validated its claims on genuine silicon but, rather, an FPGA board and some simulations while it works on a design for a PPU core and a compiler that it can license to other firms.

Right now, Flow is just a set of patented techniques, co-founders Martti Forsell and Timo Valtonen explain to me on a call.

The company is simulating three configurations of PPU: a 16-core option for smartwatches, a 64-core option for phones, and a 256-core option for high-end PCs.

The company says it used an in-house processor alongside an FPGA representing its PPU to achieve these results.
Image: Flow Computing

Are those techniques about to change the face of computing? Frankly, I don’t have the background to help figure that out — but I suspect a few Verge readers do. Since Flow Computing provided us with a whole white paper and an extensive FAQ page, I thought you might like to read them yourself in their entirety.

Continue Reading