By: Michael S (already5chosen.delete@this.yahoo.com), June 2, 2022 4:42 am
Room: Moderated Discussions
Anon (no.delete@this.spam.com) on June 2, 2022 12:35 am wrote:
> Eric Fink (eric.delete@this.anon.com) on June 2, 2022 12:20 am wrote:
> > I would agree with everything you said, but there is still the fact that M1 — while prioritising
> > power consumption — is essentially reaching identical performance as the x86 chips. Sure, binned
> > desktop Alder Lake is marginally faster (~20% , but it also pays a significant ~5x penalty in power
> > consumption to get at most ~20% higher ST performance. So I am not sure about the accuracy of the statement
> > that Apple prioritises power over performance — kind of seems to me that Apple gets both.
>
> Apple is using TSMC 5nm while Intel is using 10nm which they call 7nm
You're writing it as if TSMC 5nm were 5nm rather than "they call 5nm".
All this "nm" labels are just code names and were like that since long time ago.
So, I don't say that TSMC "5nm" is not dense than what Intel uses for Alder Lake, but it's hard to believe that it is 4 times denser.
> and AMD uses TSMC's 7nm, and both Intel Intel and AMD supports SMT.
>
> So, yes, Apple achieve almost the same performance at much lower power, but because they have power
> advantage and Intel and AMD are willing to use A LOT of extra power to get 20% single thread.
>
And what if we compare at more favorable point on perf/power curve?
E.g. Alder Lake at the same ST performance as M1?
Or even on 75% of ST performance of M1?
I never looked at it, but would guess that Apple is very significantly ahead in perf/watt even at those points.
> Zen 4 will be more apples-to-Apple comparison, at least on throughput, where perf per watt is what matters.
>
Anecdote: when few weeks ago I launched 64-thread job on EPYC 7543P in our server room, IT person that happened to be in the room at the moment thought that server is dying. He was so concerned by the sound that call me by phone to ask if he has to shut it down ASAP.
By now, he is accustomed to it.
BTW, it's very nice to have easy access to so many threads. For certain tasks it's simply fantastic.
But ST performance is a little disappointing. I expected it to match and sometimes exceed an old Xeon E-2176G that we run downclocked to 4.25GHz max frequency, but so far I had seen it very rarely. For most thing that I do, ST performance of old Xeon is better.
> Eric Fink (eric.delete@this.anon.com) on June 2, 2022 12:20 am wrote:
> > I would agree with everything you said, but there is still the fact that M1 — while prioritising
> > power consumption — is essentially reaching identical performance as the x86 chips. Sure, binned
> > desktop Alder Lake is marginally faster (~20% , but it also pays a significant ~5x penalty in power
> > consumption to get at most ~20% higher ST performance. So I am not sure about the accuracy of the statement
> > that Apple prioritises power over performance — kind of seems to me that Apple gets both.
>
> Apple is using TSMC 5nm while Intel is using 10nm which they call 7nm
You're writing it as if TSMC 5nm were 5nm rather than "they call 5nm".
All this "nm" labels are just code names and were like that since long time ago.
So, I don't say that TSMC "5nm" is not dense than what Intel uses for Alder Lake, but it's hard to believe that it is 4 times denser.
> and AMD uses TSMC's 7nm, and both Intel Intel and AMD supports SMT.
>
> So, yes, Apple achieve almost the same performance at much lower power, but because they have power
> advantage and Intel and AMD are willing to use A LOT of extra power to get 20% single thread.
>
And what if we compare at more favorable point on perf/power curve?
E.g. Alder Lake at the same ST performance as M1?
Or even on 75% of ST performance of M1?
I never looked at it, but would guess that Apple is very significantly ahead in perf/watt even at those points.
> Zen 4 will be more apples-to-Apple comparison, at least on throughput, where perf per watt is what matters.
>
Anecdote: when few weeks ago I launched 64-thread job on EPYC 7543P in our server room, IT person that happened to be in the room at the moment thought that server is dying. He was so concerned by the sound that call me by phone to ask if he has to shut it down ASAP.
By now, he is accustomed to it.
BTW, it's very nice to have easy access to so many threads. For certain tasks it's simply fantastic.
But ST performance is a little disappointing. I expected it to match and sometimes exceed an old Xeon E-2176G that we run downclocked to 4.25GHz max frequency, but so far I had seen it very rarely. For most thing that I do, ST performance of old Xeon is better.