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

Apple introduces M6 and M5 Ultra

apple.com

Post reply on HN
Print view View original

961–970 of 1001 posts

Re: Apple introduces M6 and M5 Ultra

#961

Post by pjmlp »

flohofwoe wrote: post #908
pjmlp wrote: post #844

Earlier quoted context omitted.

This applies to the whole stack, even ignoring the GUI, you would not find systems with a gazillion of processes, doing OS IPC all over the place, because the hardware could not accommodate it. But hey, microservices and static linking are the future. /s

> But hey, microservices and static linking are the future. /s Aren't those two things contradicting each other? ;) I think macOS getting more sluggish in each release (which is objectively true) is just plain old bad software engineering and prioritising the wrong things. E.g. it's just Apple's version of "What Andy giveth, Bill taketh away.".

Not at all, how do you think The Network is the Computer was achieved before dynamic linking became widespread?

Re: Apple introduces M6 and M5 Ultra

#963

Post by arnorhs »

douglee650 wrote: post #951
temporallobe wrote: post #949

Earlier quoted context omitted.

This eventual sluggishness is due to inevitable OS rot. I bought a brand new MBP in 2017 and it was snappy as hell. Booted up instantly, breezed through complex tasks, and ran GarageBand and Logic Pro X very smoothly. Every OS update seemed to take it down a notch and eventually Logic Pro X - my main production tool - was unusable. I happed to be talking about this to a professional music producer friend of mine and…

Interesting -- seems to be a "Docker for music production" product in there somewhere

how would that work exactly?

Re: Apple introduces M6 and M5 Ultra

#964

Post by andrekandre »

antfarm wrote: post #959
jodrellblank wrote: post #947

Earlier quoted context omitted.

> " the software has become bloated " Casey Muratori has a 20 minute talk on YouTube called "Clean code, horrible performance"[1]. Using an oft-repeated example in C++ he rewrites it uncleanly and then benchmarks. Removing Classes/subclasses/polymorphism: 1.5x faster. That overhead was like reducing an iPhone 14 to an iPhone 11 performance. Replacing Encapsulation with a table-driven calculation: 10x faster. That ove…

Not to forget the fact that websites nowadays can be real memory hogs, are dynamically assembled on your machine and burn cycles on pure eye candy UX like animations and transparency. The web's focus on design and cleverness over content and functionality is partly to blame.

n=1 but my macbook pro constantly runs out of hard disk and memory and the two biggest culprits are jira/confluence/docs and other web apps (like 1gb+ of real memory consumed by a single instance), and the other is dev tools which litters my disk with 100s of gb of caches...

its crazy how our devices have become basically dumping grounds for terribly optimized software

Re: Apple introduces M6 and M5 Ultra

#965

Post by trashface »

wilg wrote: post #478
anshumankmr wrote: post #6

>fluid frame rates in demanding games like Mixtape. not getting on that bandwagon but wasn't that not the most demanding game as its a just a nonstop cutscene.

cutscenes are often the most demanding part of a game!

There are some older games (not that old, one of the metal gear/raiden games had it, so like 10-15 years) where the cut scenes are actually prerendered video playback - so not very demanding. Don't know if mixtape does this though.

Re: Apple introduces M6 and M5 Ultra

#966

Post by andrekandre »

torstenvl wrote: post #958
jodrellblank wrote: post #947

Earlier quoted context omitted.

> " the software has become bloated " Casey Muratori has a 20 minute talk on YouTube called "Clean code, horrible performance"[1]. Using an oft-repeated example in C++ he rewrites it uncleanly and then benchmarks. Removing Classes/subclasses/polymorphism: 1.5x faster. That overhead was like reducing an iPhone 14 to an iPhone 11 performance. Replacing Encapsulation with a table-driven calculation: 10x faster. That ove…

To be fair, Objective C uses message passing, which doesn't have the same performance characteristics as C++ (worse initially dealing with the selector pool rather than a vtable offset; much better later when maintaining stability in your brittle C++ ABI requires pImpl->pImpl patterns jumping all around heap memory).

it is interesting how the early iphone got such good performance and low memory usage with objective-c compared to android (java)

Re: Apple introduces M6 and M5 Ultra

#967

Post by okokwhatever »

A computer created around a GPU and/or a shared ram to run LLMs should not be called a computer anymore. It should be called an inference engine. I'm not against it but it could be stripped down to reduce some cost and it would be the perfect companion in a lab.

Re: Apple introduces M6 and M5 Ultra

#968

Post by jonplackett »

alain94040 wrote: post #661
jonplackett wrote: post #642

Earlier quoted context omitted.

I think it’s weird to say Apple is faster than Xiaomi when both are just using arm chips and using TSMC to build them, and this chip is only any faster because TSMC made a smaller node. I know Apple do some special hardware software integration magic too.

Apple is not "just using arm chips". They have been designing their own 100% custom cores for more than a decade.

Yes as I said in the comment, I know they do design them - based on arm.

But come on - if they had to use intel’s fab - their chips would be terrible. The reason the m6 is faster is largely because TSMC invented a smaller process node.

Re: Apple introduces M6 and M5 Ultra

#969

Post by alerighi »

teiferer wrote: post #794
alluro2 wrote: post #527

I was blown away by M1 Pro, and used it for 4 years before it became a little sluggish, and replacing it with an Asus S16 running on Ryzen AI 9 HX 370 (an excellent laptop). One of the main reasons was missing my old Linux setup. I've briefly tested M5 Pro in an Apple store and was surprised by how quick it felt and did anything. A tangible and significant difference, and I really feel it would be good getting it, or…

> a little sluggish > surprised by how quick it felt Aren't these properties of the (G)UI rather than of the processor? I've been using systems 20 years ago that were super snappy. The same software would still be snappy today obviously. But the software has become bloated to the point that you need to run the latest generation of CPUs such that things are not sluggish. In principle you don't need 32-core GHz CPUs to…

I have in my basement a PC with Windows 98 that feels way faster using it than a modern Windows 11 full of vibecoded AI slop features.

Re: Apple introduces M6 and M5 Ultra

#970

Post by alerighi »

bayindirh wrote: post #274
bryanlarsen wrote: post #200

Earlier quoted context omitted.

It's been really weird reading laptop reviews over the last few months. I've seen a bunch of reviews where they have their usual bar graphs comparing a bunch of laptops, and the laptop that is at the bottom is an Apple. It's the really inexpensive Neo, of course, but even the M5 laptops are consistently beat on performance and battery life by Intel Windows laptops. I assume the M6 will take the crown back and then a…

x86 is way more complex when compared to ARM processors, as a result their TDP is way higher when you request performance from them. Intel had to reduce the frequency of their processors when running AVX2 instructions and the AVX2 frequency of the processors were non-disclosable to anyone. Also, benchmarking Intel processors and publishing these numbers were forbidden in some cases. I don't know whether this ban is s…

It doesn't really matter, because x86 processors inside are almost similar to modern ARM processors, the instructions that most programs use are more or less the same, and more complex "legacy" instructions are just emulated by splitting them into simpler instructions inside the CPU.

To me people that say that x86 is slow etc. never used an x86 processor with anything other than Windows. Yes, Windows is shit and laptops that run Windows are for the same reason shit. I get it. But on an x86 system you can run other OS, and, for example, a Linux distro with well tweaked power consumption parameters can get you even 3 days of battery life, or even more.

The point is that Windows keeps almost always the CPU above the minimum frequency, because it's full of useless background services, because programs are not well optimized for the hardware (to maximize backward compatibility they don't compile target x86_64 v3 for example and thus don't leverage on features and instructions available on new CPU or fall in the emulation case I've mentioned initially), and other reasons.

With a Linux distro you can keep the CPU at 600Mhz while web browsing, you can even turn off cores that you don't need, and the battery with this configuration surely lasts ages (at that point it becomes more predominant the consumption of other peripherals such as the display).

Post reply on HN