Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Leaked Apple M5 9 core Geekbench scores

browser.geekbench.com

Post reply on HN
Print view View original

501–510 of 565 posts

Re: Leaked Apple M5 9 core Geekbench scores

#501

Post by CyberDildonics »

jl6 wrote: post #364
epicureanideal wrote: post #295

Earlier quoted context omitted.

Not necessarily. If single core speed doubled but we also doubled or tripled the number of cores, doesn’t that count as keeping up with Moore?

M1 has 16bn transistors, M4 has 28bn. Increasing the core count is useful for some applications (particularly GPU cores), but there are still many critical workloads that are gated by single-threaded performance.

That's not what was being talked about.

Moore's law was never about single threaded performance, it was about transistor count and transistor cost, but people misunderstood it when single threaded performance was increasing exponentially.

Re: Leaked Apple M5 9 core Geekbench scores

#502

Post by heavyset_go »

ktosobcy wrote: post #492
mort96 wrote: post #464

Earlier quoted context omitted.

100%. A huge issue with the ARM ecosystem is that there's no widely adopted UEFI-like standard, so there's no runtime discovery of hardware configuration and things like the booting process and partitioning are extremely different between different machines. You pretty much need a Linux image built specifically for the particular hardware, unlike in the x86 world where you just need a Linux image which can boot using…

Are there any plans to have similar solution? Is this the reason, why the Android echosystem is so abysmal when it comes to hardware driver support?

The ARM server ecosystem has it solved with SBSA, which includes ACPI, UEFI, etc as part of the standard.

There are some ARM consumer computers that implement UEFI, etc, though.

The issue is that it's cheaper to just put together bespoke boards and not implement industry standards that are expected on PCs. Vendors don't have to worry about supporting anything other than the hardware and images they ship, so they don't see a reason to make third party OS support viable.

> Is this the reason, why the Android echosystem is so abysmal when it comes to hardware driver support?

Theoretically, Android should have all of the same drivers as Linux, along with Android-specific drivers that are abstracted over stable driver interface instead of the unstable Linux interface.

What usually happens is the plethora of drivers that vanilla Linux ships with aren't built for, and distributed with, phones/tablets, and the Android drivers only have to support that specific board's hardware. Then, over time, the kernel doesn't get updated so new hardware won't be supported the longer you use the device.

If you're asking why Android devices have poor support for Linux, the OP's answer is the exact reason why.

Re: Leaked Apple M5 9 core Geekbench scores

#503

Post by zamadatix »

AtlasBarfed wrote: post #322
zamadatix wrote: post #177

Earlier quoted context omitted.

Possibly, at least compared to the previous M4 generation. For the lowest tier M models to this point: M1 (any): 4P + 4E M2 (any): 4P + 4E M3 (any): 4P + 4E M4 (iPad): 3P + 6E M4 (Mac): 4P + 6E M5 (iPad): 3P + 6E (claimed) M5 (Mac): Unknown It's worth noting there are often higher tier models that still don't earn the "Pro" moniker. E.g. there is a 4P + 8E variant of the iMac which is still marketed as just having a…

Are these cores getting way more complex? Because there should be room for 2x - 3x as many cores with die shrinks at this point.

The die shrinks are less than the marketing numbers would make you believe, but the cores are getting significantly more complex. I think E cores had a 50% cache increase this generation, as an example.

The above summary also excludes the GPU, which seems to have gotten the most attention this generation (~+30%, even more in AI workloads).

Re: Leaked Apple M5 9 core Geekbench scores

#504

Post by ktosobcy »

heavyset_go wrote: post #500
ktosobcy wrote: post #491

Earlier quoted context omitted.

Thanks for the heads up. In general Linux hardware support was for a long time hit-or-miss so I kinda expected that. On the other hand I said that with the hope that the things will improve significantly by the time I will be upgrading the machine (which is still years away; I stayed with previous MBP for 8 years so I still have like 3-5 years to go :D)

These days x86 PCs are well supported on Linux, the kinds of problems you can encounter with ARM boards can be unique and just don't exist on PCs for a variety of reasons.

Well, I don't have recent experience with Linux on real hardware since quite a long time but I'm aware that the situation improve significantly to the point where it's mostly no-issue (save for GPU drivers, ekhm) so my hope is same will happen with ARM.

Re: Leaked Apple M5 9 core Geekbench scores

#505

Post by Forgeties79 »

saagarjha wrote: post #410
sys_64738 wrote: post #155

Earlier quoted context omitted.

Try installing Vitals.app open source app to see what's going on: https://github.com/hmarr/vitals Stats is another good one too: https://github.com/exelban/stats

Why not just use Activity Monitor

Honestly combed it over and it didn’t tell us anything other than high mem utilization/pressure. I’m not sure what the deal is but I’ve found AM on Mac’s almost…deceptive? It feels like I’m not getting the full story sometimes. We use one at my office for live streams and the math on resources often does not check out. Our head of engineering agrees that his experience with the silicon chips has been that they do not like to let go of tasks/processes and can be a little opaque about what it is doing in the background.

I know it sounds a lot like vibes, because it kind of is, but it’s just what we’ve seen.

Re: Leaked Apple M5 9 core Geekbench scores

#506

Post by sgt101 »

matwood wrote: post #419
porphyra wrote: post #166

Earlier quoted context omitted.

Nice. Lots of people still claim that M1 is super duper fast but now we're at almost twice the performance!

I bought an M1 Max with 64GB of ram on the gamble it would last awhile because future M series would be evolutionary not revolutionary again. It seems like it's paid off since there's never a time it feels slow. I may end up upgrading to the M5 just to go down in screen size because I travel more than I did when I bought the 16" one.

I had a 16' m1 pro until July when work had an M3 with 2GB more ram going free and I thought it would be smart to take it, in the past when I had had a three+ year old machine and upgraded everything was super better.. but this time I don't notice any difference at all in almost any application.

The only place I feel it is when I am running a local llm - I do get appreciably more tokens per second.

Re: Leaked Apple M5 9 core Geekbench scores

#507

Post by justinator »

dwaite wrote: post #282
justinator wrote: post #44

Earlier quoted context omitted.

Chances that there are both a folding iPhone and a Touchscreen Mac somewhere in the skunk works of Cupertino are 100%. The Apple Vision Pro was a far more extreme product and was kept pretty well under wraps. (tho a market failure).

The line for market success for a first generation, $3500 VR headset is drawn in different places for different people.

Market success? I'd go with profitability.

Beta quality and expense without value are just some of the reasons for it's failure.

Re: Leaked Apple M5 9 core Geekbench scores

#508

Post by criddell »

Rohansi wrote: post #499
criddell wrote: post #468

Earlier quoted context omitted.

As someone who has been buying Think Pads for the past 20 years, Lenovo needs to spend more time working on thermals anyway. If I don't power my laptop down before stuffing it in my backpack, I'll have a hot, almost dead machine by the time I get to my destination.

I wonder how much of that issue is related to crappy lid open sensors. AFAIK most of them work by sensing a magnet placed in the frame. MacBooks don't do this so your laptop doesn't sleep randomly when a magnet passes over your laptop. It's dumb that they use a single magnet instead of one on each side, but it sure is cheaper.

I think it's 75% Microsoft's fault with modern sleep. They want the machine to go into a low power state rather than sleep so that it can still receive email and other notifications just like a phone does. But since the thermals are total garbage on most PCs, that means even the lower power modes need active cooling which doesn't really work when the machine is in a bag. After a few minutes all the fans are blasting.

Re: Leaked Apple M5 9 core Geekbench scores

#509

Post by lern_too_spel »

Cheer2171 wrote: post #457
ed_blackburn wrote: post #446

I keep asking, surely, I'm not the only potential customer: where's my ARM 64, Linux Mac mini equivalent? I'd settle for a laptop form if I must.

The Snapdragon X Elite has tons of laptop models and a few mini PCs like: https://www.notebookcheck.net/Lenovo-IdeaCentre-Mini-x-debut... The Elite X2 is near release and supposedly on par with these M5 numbers: https://www.notebookcheck.net/Apple-M5-9-Cores-Processor-Ben...

> The Elite X2 is near release and supposedly on par with these M5 numbers:

It also has hardware AV1 encoding support, so depending on your workload, it can be significantly faster.

Re: Leaked Apple M5 9 core Geekbench scores

#510

Post by olyjohn »

sib wrote: post #365
onionisafruit wrote: post #235

Earlier quoted context omitted.

If they both top out at 60 they are equally fast. One just had better acceleration than the other

Yes - typically the (US English, at least) jargon is "quick" for acceleration and "fast" for top speed...

Nah not really. When you watch drag racing, they're testing acceleration. One car is always faster. Nobody says one is quicker than the other. Quick (when referring to straight line speed) is reserved for cars like the Miata, which has decent acceleration, but certainly can't accelerate like a muscle car. Nobody really compares top speed all that much because it's damn near impossible to hit top speed in a lot of cars, even on a race track. You will find slower cars comparing top speed though. Like an MG Midget, or an early Honda Civic might be able to hit 100mph, but that's an easily attainable speed. Fast cars are just faster than quick cars.
Post reply on HN