Startup claims 100x more efficient processor than current CPUs, secures $16M in funding

[snOrdquist]

""So what's their secret sauce? The details get pretty technical, but the key idea behind Fabric is optimizing for parallelism from the ground up""

Already been tried, it was the single worst cpu Intel ever made. Itanium.

Annapurna Semiconductor would like a word. Also all these little I/O tasks (SDR, music playing that isn't Dolby Edgelord Hotness, freaking antivirus etc., nanoGhidra pls?) supposedly running on E cores low key but I don't see the WinAmp kernel logs of it happening yet.

 

[snOrdquist]

With limited information, does not sound anything special. It's well known for decades that CPUs are pretty bad for paraller workloads. GPUs are better but still quite bad. Even comparing this type of paraller maximizer against CPUs and GPUs pretty much tells everything.

Against GPUs this may be OK. Against ASICs it's only advantage is probably ability to use standard compilers and/or ability to use on multiple purposes.

From limited information, this sounds like programmable ASIC-like chip. It probably wll have some use but because ASICs will still be more efficient, there is too much hype right now.

Well, drawing the 1000x thing out, what are you going to do with a 530 W profile Xeon that has to take 0.53 W (and you can't cherry pick the SKUs without paying them out like Apple and M1?) Were you going to use the AMD embedded offering but need that nerfed to do 0.035 W? Get in with DARPA and make those HALO munitions that make combatants have better ideas... without cutting in/out too much energy.

 

[ZedRM]

Another Theranos...

My god, the investors are dumb to think this can even be possible.

Efficiency is linked heavily to the process node. Not even this, but if it was evenly possible, then the big chip makers would already found out.

The theory is sound. Whether or not it will work is another thing. This is why we experiment.