Call a Finnish startup Flow calculation makes one of the wildest claims ever heard in silicon engineering: by adding its proprietary companion chip, any CPU can instantly double its performance, increasing up to 100 times with software tweaks.
If it works, it could help the industry keep up with the insatiable computing demand of AI makers.
Flow is a spinout of it VTT, a Finnish state-supported research organization that is a bit like a national laboratory. The chip technology it is commercializing, which it has called the Parallel Processing Unit, is the result of research conducted at this lab (although VTT is an investor, the IP belongs to Flow).
The claim, Flow is the first to admit, is ridiculous. You can’t just magically squeeze extra CPU performance into architectures and code bases. If so, Intel or AMD or whoever would have done it years ago.
But Flow is working on something like that he’s got it was theoretically possible — it’s just that no one has been able to achieve it.
CPUs have come a long way since the early days of vacuum tubes and punch cards, but in some fundamental ways they are still the same. Their main limitation is that as serial rather than parallel processors, they can only do one thing at a time. Of course, they change this thing a billion times a second across multiple cores and paths – but these are all ways of adjusting the nature of a CPU lane. (A GPU, by contrast, does many related calculations at once, but is specialized in certain functions.)
“The CPU is the weakest link in computing,” said Flow co-founder and CEO Timo Valtonen. “It’s not up to him and that will have to change.”
CPUs have become very fast, but even with nanosecond-level response, there is enormous waste in how instructions are executed simply because of the basic constraint that one task must complete before the next can begin. (I’m simplifying here, I’m not a chip engineer myself.)
What Flow claims to have done is remove this limitation, turning the CPU from a single-lane road into a multi-lane highway. The CPU is still limited to doing one task at a time, but Flow’s PPU, as it’s called, essentially performs on-die nanosecond-scale motion management to move tasks in and out of the processor faster than was possible in past.
Think of the CPU as a chef working in a kitchen. The chef can work so fast, but what if that person had a superhuman assistant who swaps knives and tools in and out of the chef’s hands, cleans the ready food and puts in new ingredients, removes all the tasks that aren’t real chef stuff? The chef still only has two hands, but now the chef can work 10 times faster.
It’s not a perfect analogy, but it gives you an idea of what’s going on here, at least according to Flow’s internal tests and demos with the industry (and they talk to everyone). The PPU does not increase the clock frequency or push the system in other ways that would lead to extra heat or power. In other words, the chef is not asked to chop twice as fast. It just makes more efficient use of the CPU cycles that are already taking place.
This kind of thing isn’t brand new, Valtonen says. “This has been studied and discussed in high-level academia. You can already parallelize, but it breaks legacy code and then it’s useless.”
So it could be done. It just couldn’t be done without rewriting all the code in the world from scratch, which makes it non-original. A similar problem was solved by another Scandinavian computer company, ZeroPoint, which achieved high levels of memory compression while maintaining data transparency with the rest of the system.
Flow’s great achievement, in other words, isn’t handling high-speed traffic, but rather doing it without having to modify any code on any CPU or architecture it’s tested. It sounds a bit far-fetched to say that arbitrary code can run twice as fast on any chip without any modification beyond integrating the PPU with the die.
Therein lies the main challenge to Flow’s success as a business: Unlike a software product, Flow’s technology must be built into the chip design layer, meaning it doesn’t work retroactively, and the first chip with a PPU would necessarily be several streets down the road. from the street. Flow showed that the technology works in FPGA-based test setups, but chipmakers will have to commit a lot of resources to see those gains.
The scale of these gains, and the fact that CPU improvements have been iterative and fractional in recent years, may well have these chipmakers knocking on Flow’s door rather urgently. If you can actually double your performance in a generation with one layout change, that’s a no-brainer.
Further performance gains come from refactoring and recompiling software to work better with the PPU-CPU combination. Flow says it has seen increases of up to 100x with code modified (though not necessarily completely) to take advantage of its technology. The company is working on offering recompilation tools to make this task simpler for software makers who want to optimize for streamable chips.
Analyst Kevin Krewell from Tirias Researchwho was briefed on Flow’s technology and cited as an outside perspective on these issues, was more concerned about industry adoption than fundamentals.
He pointed out, quite rightly, that AI acceleration is the biggest market right now, something that can be targeted with dedicated silicon like Nvidia’s popular H100. While a PPU-accelerated CPU would lead to gains across the board, chipmakers may not want to rock the boat too much. And there’s just the question of whether these companies are willing to invest significant resources in a largely unproven technology when they likely have a five-year plan that will be upset by that choice.
Will Flow’s technology become a must-have component for every chipmaker out there, catapulting it to fortune and prominence? Or will penny-pinching chipmakers decide to stay the course and continue to extract rent from the steadily growing PC market? Probably somewhere in between — but it’s telling that, even if Flow has achieved a major technical achievement here, like all startups, the company’s future depends on its customers.
Flow is just emerging from stealth, with €4 million (about $4.3 million) in pre-seed funding led by Butterfly Ventures, with participation from FOV Ventures, Sarsia, Stephen Industries, Superhero Capital and Business Finland.
