M1 Apple Silicon for Chess?

Discussion of anything and everything relating to chess playing software and machines.

Moderator: Ras

Ckappe
Posts: 81
Joined: Sun Feb 14, 2021 11:50 am
Full name: Rütger Andersen

Re: M1 Apple Silicon for Chess?

Post by Ckappe »

acepoint_de wrote: Sat Feb 27, 2021 11:38 am @Ckappe: thx for your benchmarks. Is there a certain reason that you only published the output of 16 threads but not 1, 2 and 4 (which would at least give some comparability)?

Ciao

acepoint
If you think lowering the number of threads would yield higher NPS, I would try it otherwise I don't see what it would bring in "comparability"
I think its the same rationale as you did not test with 16 threads on your 8core M1... right...

It's sort of like comparing a 6-geared sports-car car with a 4-gear one to what the top-speed only on gear one is.

Benching cores could be fine for tuning purposes and optimization within the SAME architecture but provide little comparability between completely different architectures imhop.

Just for refence though, I did a completely meaningless 8 thread bench.

Avg cFish 8-thread values:

Asus Duo 15 - 4900H
"Cfish-18022021 AVX2.exe bench 10 8" (default=mixed)
===========================
Total time (ms) : 2,434
Nodes searched : 56,803,468
Nodes/second : 23,433,774

So the conclusion is that going from 8-16 threads yields about 40% on a 4900H for cFish. But it is kind of irrelevant for comparing different architected CPUs like the M1 imop.

Asus Duo 15 - 4900H
"Cfish-18022021 AVX2.exe bench 10 16" default=mixed)
==========================
Total time (ms) : 7,209
Nodes searched : 233,263,127
Nodes/second : 32,357,210
Last edited by Ckappe on Sat Feb 27, 2021 5:37 pm, edited 1 time in total.
George Sobala
Posts: 44
Joined: Sat Feb 03, 2018 2:42 pm
Location: Yorkshire, England

Re: M1 Apple Silicon for Chess?

Post by George Sobala »

make -j profile-build ARCH=apple-silicon will generate faster binaries for stockfish. Also Cfish which needs numa=no as well.

Stockfish will be even faster with a g++ rather than Apple clang compile, needs homebrew g++. Cfish is faster with clang.
Ckappe
Posts: 81
Joined: Sun Feb 14, 2021 11:50 am
Full name: Rütger Andersen

Re: M1 Apple Silicon for Chess?

Post by Ckappe »

Ras wrote: Sat Feb 27, 2021 4:02 pm
Ckappe wrote: Sat Feb 27, 2021 3:26 pmWell..the 4900H supports iGPU
But you will not find a laptop that has the 4900H and iGPU only - not even as advertised model, let alone in one that you could actually order right now.
Why would you limit yourself to only iGPU when you can get a powerhouse GPU as well without paying extra for it.
You essentially get the extra raytracing, deeplearning/ai, fast GPU for free if you compare it with Apple's M1 laptop pricing.
Ras wrote: Sat Feb 27, 2021 4:02 pm
The laptops shipped with 4900H beef up the battery to get good stamina
Yeah, because these are gaming laptops. They are also quite a bit bulkier and louder.
They are slightly heavier but most are not "bulky" by definition and If you are satisfied with performance only on par with M1-laptops you can run them longer and completely fanless. They will only get louder when you push them far beyond what the M1 can do.
Ras wrote: Sat Feb 27, 2021 4:02 pm
and still 200 USD less expensive than an M1 pro with similar RAM/SSD.
I have a 4700U laptop, pretty sleek, and I'm happy not to have paid the completely insane price that Apple charges for their prorietary flash storage because my laptop takes an M.2 2280 SSD at normal market price. Also, I can exchange the battery myself if need be because it isn't glued. And it runs Linux properly, including graphics acceleration.

However, there are a number of ways I can influence e.g. the Ipman benchmark in any direction I like, to the point that the benchmark becomes meaningless:
  • It starts out turbo'ing at 3 GHz with 8 cores loaded (no SMT in that CPU) and slowly goes down to 2 GHz, which is the advertised base clock rate. Means, the first benchmark run will be better than what you get at sustained load.
  • This was on AC, but on battery, the clock rate is only half of that so that it ends up at only 1 GHz with sustained load.
  • It depends on the power profile you set in the BIOS - maximum performance or pretty silent (the M1 Air doesn't even have a fan, and the M1 book is still pretty quiet).
  • What kind of cooling solution the laptop manufacturer has built in.
Yes. The thing is that Apple is probably even worse than other brands to make use of these factors to their advantage in their influencer-based marketing :-) ... But the previously discussed benchmarks of a number of nodes search for SF13 until the battery is done for is pretty "honest" and also max sustained avg NPS on plugged-in benches...given that the CPU gets the sustained cooling it has and power it needs.
Last edited by Ckappe on Sat Feb 27, 2021 5:50 pm, edited 1 time in total.
Ckappe
Posts: 81
Joined: Sun Feb 14, 2021 11:50 am
Full name: Rütger Andersen

Re: M1 Apple Silicon for Chess?

Post by Ckappe »

AlexChess wrote: Sat Feb 27, 2021 4:55 pm I'm not speaking about Apple, but about the whole market, from consumers to professionals. All manifacturers are switching to ARM.

https://www.theverge.com/2021/1/11/2222 ... h-ces-2021
And to prove your point you link to an article titled "Intel’s 12th Gen chips look to challenge ARM" .. Fanboy much???
:D
BetaPro
Posts: 19
Joined: Wed Nov 25, 2020 7:11 pm
Full name: Jean-Roy Lee

Re: M1 Apple Silicon for Chess?

Post by BetaPro »

Ckappe's laptop is more of a desktop crammed into an incredibly large laptop..

The bigger MacBook Pros should be here soon (still way smaller than Ckappe's). Then watch this thread's Apple haters not talking about SF performance on Mac's anymore.
acepoint_de
Posts: 86
Joined: Tue Jun 11, 2013 1:14 am

Re: M1 Apple Silicon for Chess?

Post by acepoint_de »

Ckappe wrote: Sat Feb 27, 2021 5:07 pm
acepoint_de wrote: Sat Feb 27, 2021 11:38 am @Ckappe: thx for your benchmarks. Is there a certain reason that you only published the output of 16 threads but not 1, 2 and 4 (which would at least give some comparability)?
If you think lowering the number of threads would yield higher NPS, I would try it otherwise I don't see what it would bring in "comparability"
What exactly in
The M1 doesn't actually have the same number of cores because four of them are low-power ones meant for maximum battery life.
didn't you understand? But, don't bother, I won't ask or go into your postings/troll attempts anymore.

Ciao

acepoint
User avatar
Ras
Posts: 2696
Joined: Tue Aug 30, 2016 8:19 pm
Full name: Rasmus Althoff

Re: M1 Apple Silicon for Chess?

Post by Ras »

Ckappe wrote: Sat Feb 27, 2021 5:28 pmWhy would you limit yourself to only iGPU when you can get a powerhouse GPU as well without paying extra for it.
Specifically with Nvidia GPUs, I don't want any of that because they refuse proper open source drivers. It's always a hassle under Linux. I'm perfectly fine with AMD's integrated Renoir graphics that enjoy support right in the kernel because AMD are working on that themselves. Though that's of course also a point over the M1 which will never have more than half-baked, reverse engineered Linux drivers because Apple won't invest into that.
But the previously discussed benchmarks of a number of nodes search for SF13 until the battery is done
Should be scaled to the battery capacity, of course, but that could indeed make sense, provided that screen, wifi, and bluetooth are switched off during most of the test.
Rasmus Althoff
https://www.ct800.net
User avatar
AlexChess
Posts: 1562
Joined: Sat Feb 06, 2021 8:06 am
Full name: Alex Morales

Re: M1 Apple Silicon for Chess?

Post by AlexChess »

Ckappe wrote: Sat Feb 27, 2021 5:33 pm
AlexChess wrote: Sat Feb 27, 2021 4:55 pm I'm not speaking about Apple, but about the whole market, from consumers to professionals. All manifacturers are switching to ARM.

https://www.theverge.com/2021/1/11/2222 ... h-ces-2021
And to prove your point you link to an article titled "Intel’s 12th Gen chips look to challenge ARM" .. Fanboy much???
:D
Not really. I hate iPhone X and I use Mac mini M1 more like a Linux workstation than what you could expect :)
Chess engines and dedicated chess computers fan since 1981 :D macOS Sequoia 16GB-512GB, Windows 11 & Ubuntu ARM64.
ProteusSF Dev Forum
Ckappe
Posts: 81
Joined: Sun Feb 14, 2021 11:50 am
Full name: Rütger Andersen

Re: M1 Apple Silicon for Chess?

Post by Ckappe »

Ras wrote: Sat Feb 27, 2021 6:47 pm
Ckappe wrote: Sat Feb 27, 2021 5:28 pmWhy would you limit yourself to only iGPU when you can get a powerhouse GPU as well without paying extra for it.
Specifically with Nvidia GPUs, I don't want any of that because they refuse proper open source drivers. It's always a hassle under Linux. I'm perfectly fine with AMD's integrated Renoir graphics that enjoy support right in the kernel because AMD are working on that themselves. Though that's of course also a point over the M1 which will never have more than half-baked, reverse engineered Linux drivers because Apple won't invest into that.
Easy to disable and run on iGPU only if you don't want to use Nvidia. And if you don't want more powerful graphics then you can save even more by buying the models with the cheapest GPU, and save money. I don't think the market is big for high-end CPU laptops only having a "sucky" GPU in general though (Apart from maybe Apple's carved Niché).
Ras wrote: Sat Feb 27, 2021 6:47 pm
But the previously discussed benchmarks of a number of nodes search for SF13 until the battery is done
Should be scaled to the battery capacity, of course, but that could indeed make sense, provided that screen, wifi, and bluetooth are switched off during most of the test.
I don't agree at all that "it should be scaled to the battery capacity".... Battery capacity is an integral part of the overall package... So I prefer the benchmarks to reflect REAL config, not some "what if" the computer had this or that fictional capacity/spec... It's not like a 15 inch 2kg bezel-less slim modern gaming/chess-laptop is too "bulky" to carry around for most chess players... If you really want best perfromance/size ratio a modern smartphone is probably a more portable option than any laptop...
Last edited by Ckappe on Sat Feb 27, 2021 9:03 pm, edited 2 times in total.
Ckappe
Posts: 81
Joined: Sun Feb 14, 2021 11:50 am
Full name: Rütger Andersen

Re: M1 Apple Silicon for Chess?

Post by Ckappe »

AlexChess wrote: Sat Feb 27, 2021 7:57 pm
Ckappe wrote: Sat Feb 27, 2021 5:33 pm
AlexChess wrote: Sat Feb 27, 2021 4:55 pm I'm not speaking about Apple, but about the whole market, from consumers to professionals. All manifacturers are switching to ARM.

https://www.theverge.com/2021/1/11/2222 ... h-ces-2021
And to prove your point you link to an article titled "Intel’s 12th Gen chips look to challenge ARM" .. Fanboy much???
:D
Not really. I hate iPhone X and I use Mac mini M1 more like a Linux workstation than what you could expect :)
OK.. And partly I agree that arm/risc is "the future"... But it's been "coming" for a while now, and still is lacking in the higher-end spectrum where performance is more important than only power-efficiency. (I still remember the excitement when I programmed the first Sparcs :-) ). But as I said before I don't think Apple brings much to the table apart from hype, brand-religion, lock-ins, and proprietary, un-open, DRM-destroyed hw/sw solutions :-(