The Great x86 CPU Stagnation? ARM seems to have made some great leaps forward in recent years.
Coincidentally Ampere One was announced today and it looks pretty mediocre.
The Great CPU Stagnation
51–60 of 222 posts
Re: The Great CPU Stagnation
#52This has to be coupled with 'The Great Software Decay'. I hope we will have 'real' innovation in Software Engineering where people take writing performant code seriously and many Software Engineers actually know what a compiler does and what the CPU does etc. The frameworks have been helpful but at the same time -- rounding buttons is not software engineering.
The problem is that many algorithms simply cannot be parallelised well and that ever since the 90s the iron is cheap whereas the programmer's time is expensive.
So instead of spending weeks or even months on trying to squeeze the last bit of performance out of an application that's "good enough" performance-wise, developers can use that time to roll out features or fix bugs instead, i.e. generating value for their customers.
It's simply a question of economics.
Re: The Great CPU Stagnation
#53The answer to this might be more application specific accelerators and 3D stacking. You can't afford to have all of a chip switched on at once because of the power consumption and dissipation, so you build more optimised accelerators and keep flipping between them as you encounter different pieces of code that may benefit from each accelerator. Only a fraction of the device is ever in use at once. You 3D stack the ch…
The industry term for the idea that most of your chip is switched off at any given time is “dark silicon”.
What about silicon that's perpetually switched off because of defects and binning (Like apple's 7 core graphics offerings and so on), that's an even darker silicon?
Re: The Great CPU Stagnation
#54Earlier quoted context omitted.
The leading Arm chip (by apple) is arguably the best in class.
Apple's chips are very power efficent, yes, but the article and parent are talking/asking about raw power. Despite all the Intel hate the past 5 years, I don't think there's been even a moment where another company's leading chip has outperformed Intel's in benchmarks. See for example https://www.cpubenchmark.net/compare/4922vs5022vs5008vs5189/...
The M2 Pro isn't doing too bad when you consider you're comparing a laptop chip with 14+ hour battery life against Intel's latest and greatest, high-TDP desktop CPU with twice as many cores. On a performance-per-core basis it's not even far behind.
Re: The Great CPU Stagnation
#55Earlier quoted context omitted.
I’m ignorant about this. Can a Qualcomm or Samsung chip match Intel’s raw power?
The leading Arm chip (by apple) is arguably the best in class.
Much of Apple's success in the area seems to stem from the fact that they're simply buying other parties out of the latest manufacturing processes, e.g. https://appleinsider.com/articles/23/05/15/apple-has-a-stran...
So if others want to compete, they'll always be a few years behind, since the fab capacity is reserved to Apple. So any competitor either has to magically improve the architecture dramatically - which they can't, since that would require an architectural license which Apple has, but most others don't - or find a fab that can compete with TSMC's latest tech both in terms of price and available volume.
Re: The Great CPU Stagnation
#56Earlier quoted context omitted.
The leading Arm chip (by apple) is arguably the best in class.
Apple's chips are very power efficent, yes, but the article and parent are talking/asking about raw power. Despite all the Intel hate the past 5 years, I don't think there's been even a moment where another company's leading chip has outperformed Intel's in benchmarks. See for example https://www.cpubenchmark.net/compare/4922vs5022vs5008vs5189/...
>125W
And that is a lie, to achieve those scores it turbos and consumes 300W+ at turbo.
Today, right now, is a moment where AMD's enterprise product are outperforming Intel's in benchmarks.
Except for a very small set of specific use cases, I think anyone recommending Xeon for enterprise solutions is professionally negligent.
Re: The Great CPU Stagnation
#57We've known about this for a long time. Everyone expected it to happen. There are some key upcoming technologies that have the potential to cause a step in scaling (CFETs, backside power delivery) but it's still not going to be anywhere near Moore's law levels. I think this is part of why GPU power is skyrocketing and why Apple, Qualcomm, and the like are trying to shift towards services.
> I think this is part of why GPU power is skyrocketing and why Apple, Qualcomm, and the like are trying to shift towards services. IMHO it's only a very small part of why GPU power consumption is going up. The main reason is the completely unnecessary chase for the performance crown. From personal testing: my GPU manages to get 95% of its peak performance while being power limited to 80%. So the in order to squeeze…
I would also think that GPU workloads have something to do with it. Almost none are serial workflows, and instead highly parallel work.
GPU workloads will eventually run into the same scaling limits. That is we will be unable to speed up each execution unit any further, or the primary work we give the GPU will not be able to be split into more threads and accomplish useful work.
Re: The Great CPU Stagnation
#58The cores/money comparison doesn't looks like it accounts for inflation.
Indeed. I was also wondering why people would buy newer chips if they don’t show performance increases per dollar.
Because the vendor will no longer give the the old chips? That an lack of support around security.
Re: The Great CPU Stagnation
#59In fact the CPU stagnation is worse. In contrast to the shrinking chip size and higher frequencies of past scaling laws, CPU core count does not easily translate to performance gains. It needs specialized and careful designed software to tap the capability. In fact if CPU core count did translate more easily to performance gains I think already with the existing CPU's we'd have a fairly signficant one-time boost. May…
> It needs specialized and careful designed software to tap the capability.
I've been suggesting engineers get more cores of lower speed to gain insight on what will be performant a few years down the road since I saw my first Xeon Phi.
It's been a while since clock speeds got higher (IBM has been pushing 5GHz in their highest end for the past couple years now and it doesn't seem likely they'll cross 6 anytime soon), but we get more cores every year. We now have 4-core entry-level machines and 2-core/4-thread ones are the bottom of the barrel, with a decent one being 8-core. Ampère just announced a 192-core server beast.
And then we have another thing: performance for most users has been "good enough" for the past couple decades. I haven't gotten a new computer just because it had a faster CPU since the early 2000's - they usually turn to dust well before they become too slow to use. My wife will need to upgrade her Macbook soon-ish for regulatory reasons (when Apple EOLs and stops patching macOS 12) and her laptop is still going strong. Considering that, there is little advantage in making all but the most demanding software more parallel.
This leaves the high-end, the stuff that needs a POWER10 or a Telum to run at acceptable speeds, and the cloud vendors, who'd kill to be able to serve 1% more VMs per kilowatt because 1% of their revenue is the GDP of a small country.
Re: The Great CPU Stagnation
#60At least now people will start to focus on how bloated and slow software has become in the meantime. And stop referring to it as “tech”.
Its not like biological creatures are highly optimized.
Eh, for the amount of work your brain accomplishes, it is insanely hyper optimized at around 20 watts. We don't have human level AI/image processing quite yet, but it would take hundreds of thousands of watts to accomplish the same thing at this time.