VISC CPU 3X the IPC?

[Tsavo]

[/.]I wonder if a Beowolf Cluster of these would be able to run Crysis in Soviet Russia[/.]

 

[SAAA]

Until we see more tests done on the demo hardware and get more information about the 80% of the die area allegedly not concerned with implementing speculative threading (or whatever it is you care to call it), it will be difficult to make any accurate comments regarding its efficiency; ability to scale to higher clockspeeds; or really anything else of substance.

One thing that seems interesting, and a bit odd, is that the provided JPEG/color compression demo that they have released would seem to indicate that there is more than just speculative threading providing an IPC boost to the prototype VISC CPU. Correct me if I am wrong, but the demo shows that two "actual" VISC cores operating as one virtual core @ real clockspeeds of 350 mhz can beat a 1 ghz Haswell core in the same task. If the speculative threading feature is 100% efficient and makes the two physical cores function as a 700 mhz virtual core, you still have a 700 mhz virtual core beating a 1 ghz Haswell core.

Or, to put it a different way, the test seems to indicate that a single "actual" VISC core @ 350mhz would beat a single 500 mhz Haswell core in JPEG/color compression.

That makes one heck of a statement with or without speculative threading. Can the VISC cores manage such a feat in other computational tasks?

This point seems the most important to me, especially after they've claimed A15 class processor. Were in the world an A15 is faster than Haswell in any possible test? ( same clocks of course)

That's just an assumption. Most modern processors can go to 3-5GHz, so it seem quite extraordinary that this one can go to only 1/10th, so to me it seems you need also quite extraordinary evidence. Maybe they simply wanted to have the same power consumption as Apple A7, A15, etc.?

As far as I know, GPUs simply run at 1GHz because that is the best trade-off between voltage/power, performance and die area. If you reduce the clock speed to 1GHz, you can have a lot more shaders within the power budget to improve performance instead of quadratic scaling with voltage.

Also GPUs usually consumes way more than these CPUs tested at 0.35-1.8 GHz, hence it's reasonable to expect some frequency increases.
Hey I'm not claiming anything but Haswell scales to 4GHz in real world from the 1GHz here, what could stop this device from doing the same or at least reach a 2/3x speedup? The biggest limit is probably the short pipeline but the same happened with Core when to increase IPC after hitting the frequency wall they limited max clocks.

 

[DrMrLordX]

[/.]I wonder if a Beowolf Cluster of these would be able to run Crysis in Soviet Russia[/.]

IN SOVIET RUSSIA, Beowulf clusters of VISC CPUs run Crysis on YOU!

This point seems the most important to me, especially after they've claimed A15 class processor. Were in the world an A15 is faster than Haswell in any possible test? ( same clocks of course)

. . . I don't think I've heard of an A15 beating a Haswell before, but hey you never know.

 

[Ajay]

Eh, immediately below that performance chart the articles states that, 'Power consumption is listed as “about” the same' which isn't exactly a good sign. Does that mean that even at such a low clock frequency they still have to be running at a comparable voltage to the other designs? Which could mean that they have just as much or more total logic but are simply dividing the pipeline into less stages - that's a great way to 'improve' IPC. It also could easily mean that their 'virtualization' logic has dependencies which can't be broken up into multiple pipeline stages and hence they're limited to low frequency regardless of voltage.

Or it might be that they aren't so great at actually designing a processor and have some horrible timing paths that are killing their possible efficiency... But given their hype you'd think that they'd be loudly advertising such if it was the case since it'd result in markedly better results than what they're showing.

I was thinking along the same lines in terms of pipeline length, and the article verifies this in a chart:

The 2VC prototype has a 'shallow' pipeline. I also think that you are likely on the right track questioning the virtualization logic. With only a 5% hit in translating x86 or ARM, I'm guessing that virtualization logic is doing some very heavy lifting.

What we really need is a scholarly paper on VISC - not just an article on a enthusiast tech site.