logoalt Hacker News

pizza234 • today at 10:54 AM • 8 replies • view on HN

I'm quite skeptical; their baseline is a in-order CPU, instead of a modern out-of-order design, and they're testing a small amount of programs.

Also, I'm not an expert in CPUs, but the underlying idea doesn't seem entirely novel - WaveScalar explored dataflow-based architecture 20+ years ago.


Replies

kragen • today at 11:30 AM

They're claiming better performance per watt, not better absolute performance, and out-of-order does worse on that metric than the superscalar in-order design they say they beat by 4.59×. That's why, for example, PULPino is in-order.

A third interesting metric is performance per transistor or per area, and generally the best designs there are the long-forgotten MISC designs like the MuP21 and the GA144.

➕ show 2 replies
rhdunn • today at 11:25 AM

If you are interested in understanding how CPUs work there are a number of "build your own CPU" style video series on YouTube:

- Ben Eater's series "Building an 8-bit breadboard computer!": https://www.youtube.com/playlist?list=PLowKtXNTBypGqImE405J2...

- Fabian Schuiki's series "Build a Superscalar CPU" (breadboard and custom boards): https://www.youtube.com/playlist?list=PLyR4neQXqQo5nPdEiMbaE...

- Polymath Unlimited's series "The CPU you can build (Tutorial Series)" (logisim): https://www.youtube.com/playlist?list=PLe8IZRJAn3oD3E2tDhNpI...

- mattbatwing's series "Let's Make a Redstone Computer!" (Minecraft): https://www.youtube.com/playlist?list=PL5LiOvrbVo8nPTtdXAdSm...

➕ show 1 reply
petra • today at 10:58 AM

Yes, their comparisons are weird.

They also compare their architecture simulation language to RTL, instead of comparing it to existing arcitecture sim languages.

➕ show 1 reply
txdv • today at 12:26 PM

I think that 20 years ago creating your own processor as a startup wasn't really feasible, maybe with AI it has become? Some companies will try it out and history will be the judge of that

➕ show 3 replies
shioyama • today at 1:46 PM

They are using _interaction nets_. Interaction nets date back to the 1990s, they are a fundamentally different programming paradigm which is parallelisable by their nature (graph rewriting that can be done locally in any order).

https://en.wikipedia.org/wiki/Interaction_nets

amelius • today at 11:30 AM

Isn't this more about work-per-joule than about throughput? At least that benchmark graph is in performance-per-watt.

➕ show 1 reply
checker659 • today at 11:14 AM

Maybe it's Itanium reincarnated

motbus3 • today at 11:11 AM

Yeah. Something smells fishy