Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Apple M1 CPU & GPU speed is very disappointing
- Thread starter Appletoni
- Start date
- Sort by reaction score
- Status
If you want gaming inside a Mac besides simple games and older ported titles when so many Audio, Video and creative types that use Mac OS!
It has already been explained to you multiple times about the chess benchmark is not optimized for Apple Silicon and that means the benchmark is faulty when run on Apple Silicon. You need to prove that the benchmark is a valid measure when run on Apple Silicon. You have not provided any proof of your hypotheses. And the result of the benchmark is not proof if the code is not testing properly. A good software engineer would know this.
Intel provides a lot more detail on the hw, interfaces and low-level software, drivers, bios, etc. They are open to integrating with various vendors' GPUs, memory subsystems, and configurations. I think Apple is way more proprietary than Intel. Intel works a lot with different partners in an open way (they even work with Apple). Apple is open to no one else. Rather the opposite. Even try to stop 3rd parties to access hw and running different OS: es etc.. Very different stance than, for example, Intel and AMD.
asmFish Benchmark - OpenBenchmarking.org
I think you have missed the mark on benchmarking overall.. A benchmark is not "faulty" beacuse it is not specifically tweaked for a certain vendor..
And you keeping proving the point that the chess benchmark is not optimized for Apple Silicon and that is why it runs so poorly on the Apple Silicon. Yes, let's get real. You think just simply recompiling the code is enough. It requires having knowledge of the target hardware and how best to utilize that in the code. Has anyone at StockFish ever used Apple Silicon and examined the source code to see what needs to be changed in order for the code to take advantage of said hardware? Since you seem to be the expert on this, you tell us as you are the one who needs to prove that the benchmark code is correct for Apple Silicon. Somehow, I think your response will be to deflect away from this question and not answer it.
Yes, they have.. Are you able to follow find the other pages of this thread?
You said that the code was compiled for ARM that is not the same thing as knowing how to take advantage of the Apple Silicon to test it properly. A benchmark is designed to test a given hardware to determine its performance. If the code is not utilizing the hardware properly then the results of that benchmark are wrong.
Why do you claim the ARM tweaked code does not utilize the hw suffiently.. by just guessing?
Why don't you apply this reasoing to all benchmarks not just this..
How do you for example know geek-bench is fully optimized for the latest gen 11 Intel CPU?
Are you saying all benchmarks are irellevant, or just the one where your "pet" does poorly?
Let me ask you which benchmarks meets your criteria of beeing 100% optimized for each hw compared?
Neither does AMD.
Neither 3090 nor 4090 are in a laptop. 4090 isn't even available for purchase yet. 3090 currently more expensive than an entire m1-pro machine.
3090 runs in 300-400 watts. M1 Pro is 60.
Nvidia doesn't have an afterburner on board.
?♂️
Last edited:
Clearly you have never written a line of code in your life. Anyone who has done even a basic programming course knows that algorithm changes can be HUGE.
From entry level programming...
Time Comparison of Quick Sort, Insertion Sort and Bubble Sort
Comparing different sorting algorithms for time performance has always been amusing. It has been done tons of time. But you should try it out for yourself. Apart from fun, this comparison is very u…
vinayakgarg.wordpress.com
Hardware instructions can have massive impact
A Look at the Performance Impact of Hardware-Accelerated AES - Scott Brown Consulting
In 2010, semiconductor manufacturers began migrating the algorithmically intensive portions of the AES cipher on-die in the form of the AES-NI instruction
www.scottbrownconsulting.com
I guess this means the OP will have consult with his chess club to come up with more chess game data proving absolutely nothing.
Hi. Really interesting thread. I've been glued to it from the first page. Thanks to all those involved.
I've been wondering if it might be worthwhile performing some chess benchmarks on the M1 Pro/Max? It's obvious that these new chips are great performers on a wide variety of tasks. It'd be interesting to see some numbers for chess though. Once they get a chance to optimise these benchmarks for Apple Silicon, I think they'll do great.
Also, can anyone point me to some numbers for hashcat runs on the the M1 Max?
I've been wondering if it might be worthwhile performing some chess benchmarks on the M1 Pro/Max? It's obvious that these new chips are great performers on a wide variety of tasks. It'd be interesting to see some numbers for chess though. Once they get a chance to optimise these benchmarks for Apple Silicon, I think they'll do great.
Also, can anyone point me to some numbers for hashcat runs on the the M1 Max?
This right here is excellent evidence you've never done porting and optimization work. In fact, based on your presentation of yourself, I doubt you've ever written a single line of C or C++.
Let's get really real: you're a troll who's not attempting an honest discussion. Reality constantly shifts in everything you write. Your only goal is to get a rise out of people. It's quite easy to see.
Like right here, you try to spin someone saying Stockfish could be much better optimized for M1 as if it's equivalent to claiming software could be optimized to make M1 perform better than M1 Max. That's a ridiculous leap, the OP didn't say anything like that, you know it, you just said this to provoke outrage.
Sure, it's an apple header file. Have you written your own?
Thats great.. Reality is always more interesting than wishful thinking from fanboys...
You can download the best chess engines on github... (can be compiled with homebrew)..
https://github.com/official-stockfish/Stockfish (stockfish)
https://github.com/LeelaChessZero/lc0 (Leela Zero, a spin of project with the origins from Googles Alpha Zero)
A very good page with lots of ready made compiles and stuff for Apple silicon is..
Apple | acepoint's home | Seite 3
acepoint.de
Preliminary results are quite dissapointing for the M1 Max as well.. But try for yourself... You can compare with other platforms... Especailly Leela should perform much better on M1 Max with OpenCL due to the beefier GPU parts.
That’s the one I found too, but the GitHub page does not reference an ARM macOS version. The arm code looks like it was last updated 4 years ago.asmFish Benchmark - OpenBenchmarking.org
openbenchmarking.org
This is why no one takes your open bench results all that seriously and why your dislike of propriety code makes little sense.
Paid code gets updated, it gets optimization, rare and obscure code with minimal effort in the Mac branches does not make a great counter example.
Written my own Apple supplied header includes??? LoL u are funny dude...
Hey, thanks so much for your reply. It's a fascinating area to investigate.Thats great.. Reality is always more interesting than wishful thinking from fanboys...
You can download the best chess engines on github... (can be compiled with homebrew)..
https://github.com/official-stockfish/Stockfish (stockfish)
https://github.com/LeelaChessZero/lc0 (Leela Zero, a spin of project with the origins from Googles Alpha Zero)
A very good page with lots of ready made compiles and stuff for Apple silicon is..
Apple | acepoint's home | Seite 3
The benchmark will need a great deal of work to be anything more than a novelty .. But try for yourself... You can compare with other platforms... Especailly Leela should perform much better on M1 Max with OpenCL due to the beefier GPU parts.
View attachment 1920990
Broadly, I think we're in agreement that the M1 looks amazing and as soon as devs start taking advantage of it, performance will be great. I'm not sure I'd go quite as far as you in saying Intel and AMD have a great deal to worry about though. I think they'll be just fine.
I'd be grateful for any links to quality chess benchmarks though. I'm having a hard time finding any.
- Status