NotebookCHECK - Notebook Forum

As far as I know, M4 introduced new instruction set aka AVX and new version of Geekbench simply is using it. There is no true 20% better single thread performance.
Some years ago when Geekbench started using new instruction set from Intel to do encryption, Intel was ahead of other CPU in this benchmark, but the support was removed, because it was not fair. So now with M4 is it fair?
I'm not sure, but probably there are some result of Geekbench 6.x with AVX512 enabled on Intel and it scores more than 4600 in signle thread...

This performance review is pretty vague and deviates heavily from the high quality journalism notebookcheck is known for. Geekbench with its AVX instructions kicks M3 out with Intel touching nearly 5K on single thread with same benchmark.

There isn't a single benchmark that scales with real-world performance. I'd be ashamed to post that.

Quote from: LifePo7 on May 20, 2024, 14:53:42There isn't a single benchmark that scales with real-world performance. I'd be ashamed to post that.

There is - Cinebench. But yes, you are correct.

GB is such a terrible benchmark that it makes the 96-core TR almost on par with the M3 max. The company behind this benchmark should be investigated, I'm sure there is something very rotten hidden there

Why do ppl compare Apple and PC CPUs? Those are two completely different ecosystems. Nobody is going to go to Mac to run PC software just bc it is 20% faster. In the current state, we have an oversupply of CPU performance. Nobody cares if a CPU runs a little faster anymore. Very fast CPUs are useful only for special applications like games, AI, etc., so it's pointless to evaluate fast CPU without running it in its intended applications.

Do you have guys any links to those sub 5k single-core scores of intel cpu?

Quote from: ksc on May 20, 2024, 16:20:46Very fast CPUs are useful only for special applications like [...] AI [...]

Typical AI runs on dGPUs (or sometimes TPUs). The CPU is only a secondary factor. Higher single thread speed and more cores have slight impacts but the dGPU is the bottleneck, as I experience daily running AI. Only if one uses several dGPUs, many CPU cores in Threadripper and huge amounts of RAM can be useful. On servers with many dGPUs, as Huang tells us, also the network speeds for inter-dGPU communication matters. (Some kinds of AI, especially those with huge models, profit from fast inter-dGPU communication already for 2 dGPUs. For other kinds, it is immaterial for a small number of dGPUs. It can depend on how an AI is programmed.)

IMX, two dGPUs would double the speed. Higher CPU single thread speed might raise dGPU load by just a few percents and much more only ca. 5% of the time. More CPU cores would cope with even less frequent 100% dGPU load for several seconds, rarely for a longer time.

Forgetting for the moment that the majority of the Charts included in the article DO NOT support the article title...

Ok, silly Apply dropped their new M4 chip(s) into iPad's.

How many MORE HOURS of run time do these have over my current M1 11" iPad-Pro?

What EXACTLY can these new M4 powered devices DO that my M1 powered device can't?

As others mentioned, the applications and use patterns are different across the PC, Mac and YES iPAD computing environments.

However only time will tell if between Qualcomm & Apple we can FINALLY ditch the gawd awful x86 crap we've been stuck with for +40yrs!

The point is that the whole benchmark here is irrelevant when a 3 y.o. Ryzen 7 H can push 4000+ single core as soon as you benchmark it with Android booted from live USB stick. And on Windows it's not getting past 1700.

Quote from: RobertJasiek on May 20, 2024, 18:55:10

Quote from: ksc on May 20, 2024, 16:20:46Very fast CPUs are useful only for special applications like [...] AI [...]

Typical AI runs on dGPUs (or sometimes TPUs). The CPU is only a secondary factor.

ksc was reacting to Apple's claims about SME2 and enhanced next-gen ML accelerators which are in the CPU, not part of the NPU.

dont stand a chance seems like an overstatement....

Could you double check whether Geekbench Single-core test score is version 6.2 or version 6.3? Since version 6.3 has SME support in Object detection and background blurring workload.   

Impressive numbers put out of context, mashing up apples & oranges along the way.

If there were any political undertone to this, it'd get dismissed as fake news.

Despite the tough competition from AMD, Intel and Qualcomm, Apple continues to be the best in the processor chips while raising the performance bar. In addition, Apple is a in-house closed ecosystem which ensures better compatibility than their competition.

Just quick question- is security issue sorted (potential unauthorized access to encrypted data) or we still pretending it does not exist? I believe it would be worth to mention something about it in review.

Quote from: edhun on May 22, 2024, 00:48:49Just quick question- is security issue sorted (potential unauthorized access to encrypted data) or we still pretending it does not exist? I believe it would be worth to mention something about it in review.

According to a comment on the german subforum the issue was fixed yesterday with an bugfix update.

That is quite interesting. This security issue was described as uncatchable, with possible "workaround" leading to drop in performance in range of 30-40%. I haven't heard nothing official from Apple yet, possibly because simply it didn't happen. If it did, Apple would be very laud about it. People on the forums may write many things they believe in; it does not mean it is a true.

sorry @ edhun:

I've mixed up your question with something else: I thought you were talking about the recent issue of allegedly deleted photos reappearing on iPhones again (which is an issue on 2nd hand devices). And only that issue was fixed yesterday.

But you probably meant another issue with "unauthorized access to encrypted data". I do not know any details about that, sorry. That issue might still exist.

Quote from: Hotz on May 22, 2024, 13:31:43But you probably meant another issue with "unauthorized access to encrypted data". I do not know any details about that, sorry. That issue might still exist.

This: researchers find unfixable bug in apple computers (https://www.youtube.com/watch?v=-D1gf3omRnw) (Low Level Learning @ YT) ?

Nothing official from Apple, they are aware about it since December 2023 but no update was pushed (or it was but everyone ignores it which I find unlikely). M4 is supposed to have no problem of that kind, time will tell.

Here is the top policy regarding apple: "people will not even notice". This is shocking that on Apple's forum people talking about "missing photos" but they are not aware of very serious problems. It may take even 1h to hack the macbook (time window required between 1-10h). We heard a lot about issues with Asus service in America recently, however I believe that the most basic right of customers around the world is to know if the system they buy is safe, and if not- what they should be aware of. Having full information, customers may make decision to buy the product or not.

They can put a Supercomputer in a Mac, I won't even thouch it with a 10 foot. Unless they replace the awful brain-dead "Finder" with a real File Explorer.  I had a better Finder in my Commodore64 40 years ago. Look at Win10 File Explorer if you need an inspiration

Quote from: Sharki Mano on May 24, 2024, 21:57:53They can put a Supercomputer in a Mac, I won't even thouch it with a 10 foot. Unless they replace the awful brain-dead "Finder" with a real File Explorer.  I had a better Finder in my Commodore64 40 years ago. Look at Win10 File Explorer if you need an inspiration

I have only had experience with i(Pad)OS, whose Files app is useless for local file management. (In a restrictive manner, Files works for very slow SMB file transfer between iDevice and Windows PC though.) I do not know MacOS and Finder but have had hopes that, many years later than Apple's promise, Finder would eventually become available on the iPad and must be much better than Files. However, you describe Finder as very bad and functionally inferior to the Windows File Explorer (not to mention Windows command line recursive batch processing). Please explain why Finder is very bad and inhowfar its functionality is limited compared to the Windows File Explorer!

The amount of butthurt here is so hilarious.

Apple produces high performance systems because they have full control over hardware and software to work together at their best while MS and Intel have to work with customer demands for legacy support which slows down their progress.
 
Apple Silicon is based on ARM (RISC) which is already way ahead of x86 with plenty of room.

Also, TSMC has been very consistent with delivering faster chips every generation which Intel could not do. 

Quote from: Sharki Mano on May 24, 2024, 21:57:53They can put a Supercomputer in a Mac, I won't even thouch it with a 10 foot. Unless they replace the awful brain-dead "Finder" with a real File Explorer.  I had a better Finder in my Commodore64 40 years ago. Look at Win10 File Explorer if you need an inspiration

This is just hilarious how you make it a big deal. Literally never had issues with Finder. Windows Explorer sucked.

And what makes you think you need a complicated "file manager?"

We are doing most of the work on documents/images/videos, not managing files.


 

Quote from: JeffMac on May 30, 2024, 16:39:57what makes you think you need a complicated "file manager?"

Complication itself is not a virtue but availability of all needed actions is essential. GUI file managers tend to omit advanced batch processing only found in command line interfaces. Apart from that, powerful GUI file managers are still outdone for particular classes of actions, such as advanced renaming of many files and folders. If we also ignore this, reasonably powerful GUI file managers must offer every standard action at least on one to all objects in a folder. For this purpose, the Windows file explorer is reasonable as long as one does not need simultaneous views on multiple folders for actions between them; some other file managers do that kind of actions better. If a file manager offers less actions than the Windows file explorer, it is a failure for my usage. And no, the Windows file explorer is not complicated for standard tasks. It only becomes complicated for access to advanced changes of access rights of files and folders because NTFS security is complicated.

QuoteWe are doing most of the work on documents/images/videos, not managing files.

Maybe, but I belong to those for whom managing files is as important as working on file contents. Given my, say, million of files, I need file management that works as well on hundreds of thousands at a time as on one single file. Work on contents and file management are almost alternating tasks. Neither makes much sense without the other. So it is immaterial that one spends 99% of time on contents and only 1% on file management. That is, if the file management is good and powerful enough having to spend only so little time. If file managers are inefficient, a much greater part of one's time might have to be wasted on file management. E.g., for a file action on Windows I might need 1 second while for the same file action to be split in many actions I sometimes need half an hour and in extreme cases months. I do not know about Mac's Finder but hope its usage is closer to Windows than i(Pad)OS.

Quote from: RobertJasiek on May 30, 2024, 19:35:56while for the same file action to be split in many actions I sometimes need half an hour and in extreme cases months

I forgot to write: "on iPadOS".