Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Status
Not open for further replies.
I‘m not interested in single core performance, because it’s always (fast) enough.
Gee, I wonder why Apple doesn't follow your insight. Why bother with firestorm cores? They use a ton of power! Just make a 64-core SoC with only low-power cores (that's what amazon is doing BTW) to boast about cinebench numbers!

Maybe it's because single core performance is never fast enough...
For what I do (data analysis using R), almost everything is single-threaded.
Even in C4D, on which cinebench is based, the main viewport uses a single thread. In general, app responsiveness relies on single-core performance.
 
  • Like
Reactions: JimmyjamesEU
Such comparisons will get harder and harder as time passes, so it's just seizing the opportunity while it lasts. My guess is that by mid next year, the only point that could be railed against Apple will be about not being able to run legacy software.
 
  • Like
Reactions: JMacHack
I’m not surprised by the OP posts since his intentions are clear, what really surprise me is that people are still feeding him by writing on this topic, it is really beyond me why supposedly adult/smart people keep answer to this nonsense.
 
Yeah, I still don't see why people feel the need to come to Apple sites and bash the platforms. Are there people who do this on Windows forums? Are Xbox forums filled with PS fans ripping on the Xbox, and vice-versa? It seems people have a singular hatred for all things Apple that I can't quite understand.
 
Yeah, I still don't see why people feel the need to come to Apple sites and bash the platforms. Are there people who do this on Windows forums? Are Xbox forums filled with PS fans ripping on the Xbox, and vice-versa? It seems people have a singular hatred for all things Apple that I can't quite understand.
There probably are - haters exist everywhere. But I've noticed Apple's are especially relentless and weirdly emotional about it a lot.
 
There probably are - haters exist everywhere. But I've noticed Apple's are especially relentless and weirdly emotional about it a lot.

Mostly folks who are jealous because they can’t actually afford Apple stuff, or at least can’t afford as much of it as often as they’d like, so they need to rationalize why Apple sucks.
 
  • Like
Reactions: Zdigital2015
You're not even a real Apple fanboy. I have Apple devices dating back to 1977 with Apple II along with II+, IIe, IIc, IIc+, IIgs ROM 1 and ROM 3.
 
I only ever used tape drives on TRS-80’s and my TI-99/4A. Man those things were a pain. Particularly the TRS-80, where you had to manually keep track of the tape counter.
The commodore 64 also had "tape drives" (and whatever the small commodore machine was) I owned 2 computers with cassette drives, a TRS-80 Model I (still have it!) and a C64.

And yes, they were a pain!
 
Some people also said that it’s the fault of Stockfish developers that Stockfish is slow on M1.
Yes yes and they will also say it’s the fault of all these developers, while I’m looking at these 437 Chess Engines running on CPU:
Then go pay way too much money for a Windows machine that will run your chess program the way you want it to and leave the M1 to the rest of us who actually like to use our machines for other tasks. For 99% of the user base, Stockfish is completely irrelevant, and using it as a "benchmark" when there is still work to be done before it's even M1-native is disingenuous at best.
 
Me too! If you haven’t used a hole puncher to convert a 5¼” floppy to double sided, I say hit the bricks.

You never sprung for the specialized version just for 5 1/4" floppies?
 

Attachments

  • commod21.jpg
    commod21.jpg
    66.8 KB · Views: 55
You never sprung for the specialized version just for 5 1/4" floppies?

No, but i remember they existed!

Hell, I’m so old that I used 8” floppies (although, to be fair, I was 13 at the time, writing accounting software for an electrical contractor in Queens, NY to run on an IBM System 23. Because, back then, nobody other than 13 year olds knew how to code anyway).
 
  • Like
Reactions: Zdigital2015
No, but i remember they existed!

Hell, I’m so old that I used 8” floppies (although, to be fair, I was 13 at the time, writing accounting software for an electrical contractor in Queens, NY to run on an IBM System 23. Because, back then, nobody other than 13 year olds knew how to code anyway).
I missed out on the 8 1/4" floppies, mainly because my Commodore VIC20 had the cassette drive. I hated having to queue the tape to the right spot on the counter in order to load a game.
 
I‘m not interested in single core performance, because it’s always (fast) enough.
Only multicore is important, because more and more programs starts to support more and more cores and the number of programs which are running only on one core get smaller and smaller.
The distance between Stockfish on M1 and Stockfish on Threadripper is much higher than the little distance in this benchmark:

Cinebench R23 (Multi-Core)

Cinebench R23 is the successor of Cinebench R20 and is also based on the Cinema 4 Suite. Cinema 4 is a worldwide used software to create 3D forms. The multi-core test involves all CPU cores and taks a big advantage of hyperthreading.

Apple M1Apple M1
8x 3.20 GHz
7760 (10%)Amazon
AMD Ryzen Threadripper 3990XAMD Ryzen Threadripper 3990X
64x 2.90 GHz (4.30 GHz) HT
74422 (100%)Amazon

A CPU with 64 cores and 128 threads drawing 20 times more power but delivers only 9.5 times better performance than a CPU with only 4 power cores (and 4 efficiency cores) and no HT? Looks like a very efficient and cheap chess machine!
 
As an Amazon Associate, MacRumors earns a commission from qualifying purchases made through links in this post.
  • Like
Reactions: JMacHack
A CPU with 64 cores and 128 threads drawing 20 times more power but delivers only 9.5 times better performance than a CPU with only 4 power cores (and 4 efficiency cores) and no HT? Looks like a very efficient and cheap chess machine!

Performance difference can be up to ~15x faster for highly multithreaded workload so performance per watt scales about the same as M1. For some industries time is money so faster results requiring less time wins. That's also why some travelers fly rather than drive.
 
Performance difference can be up to ~15x faster for highly multithreaded workload so performance per watt scales about the same as M1. For some industries time is money so faster results requiring less time wins. That's also why some travelers fly rather than drive.
Not true. Performance per watt does not scale the same as M1. And If you have the money to spend, and you need better performance, you aren’t in the M1 demographic. The M1 is a consumer level, bottom of the barrel chip. It’s like saying “yeah but the M1 is nothing compared to my threadripper and some people actually need the performance” like yeah… of course? That’s kind of obvious.

M1 should be compared to lower level Intel and AMD chips. That’s the demographic. Anything that goes beyond that is just irrelevant.
 
  • Like
Reactions: Fawkesguyy
Status
Not open for further replies.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.