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

Apple's M4 Max chip is the fastest single-core performer in consumer computing

twitter.com

Post reply on HN
Print view View original

431–440 of 551 posts

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#431

Post by GeekyBear »

spoaceman7777 wrote: post #411
GeekyBear wrote: post #380

Earlier quoted context omitted.

SPEC has been the industry standard benchmark for comparing the performance of systems using different instruction sets for decades now. Traditionally, Anandtech would have been the first media outlet to publish the single core and multicore integer and floating point SPEC test results for a new architecture, but hopefully some trusted outlet will take up the burden. For instance, Anandtech's Zen 5 laptop SKU results…

just considering the number of simple calculations a CPU can compute isn't a very good comparison. apple's chips are using an ARM architecture, which is a Reduced Instruction Set Computer (RISC) setup, vs x86-64, which is a Complex-ISC (CISC). The only good comparison is to judge a variety of real world programs compiled for each architecture, and run them.

> The only good comparison is to judge a variety of real world programs compiled for each architecture, and run them.

I'm guessing that you don't realize that you are describing SPEC?

It's been around since the days when every workstation vendor had their own bespoke CPU design and it literally takes hours to run the full set of workloads.

From the same Anandtech article linked above:

> SPEC CPU 2017 is a series of standardized tests used to probe the overall performance between different systems, different architectures, different microarchitectures, and setups. The code has to be compiled, and then the results can be submitted to an online database for comparison. It covers a range of integer and floating point workloads, and can be very optimized for each CPU, so it is important to check how the benchmarks are being compiled and run.

More info:

> SPEC is the Standard Performance Evaluation Corporation, a non-profit organization founded in 1988 to establish standardized performance benchmarks that are objective, meaningful, clearly defined, and readily available. SPEC members include hardware and software vendors, universities, and researchers.

SPEC was founded on the realization that "An ounce of honest data is worth a pound of marketing hype".

https://www.spec.org/cpu2017/Docs/overview.html

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#432

Post by drewbeck »

Terretta wrote: post #365
thfuran wrote: post #216

Earlier quoted context omitted.

In the 90s, you probably wouldn't want to be using a desktop from 4 years ago, but the M1 is already 4 years old and will probably be fine for most people for years yet.

Apple's marketing is comparing this season's M4s to M1s and even two generations of Intel ago. The 2x or 4x numbers suggests they are targeting and catering to this longer cycle where subliminally suggested updates are remarkably better, rather than suggesting an annual treadmill even though each release is "our best ever".

I think it's also part of the sales pitch, tho – a lot of folks are sitting on M1s and pretty happy but wondering if they should upgrade.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#433

Post by masklinn »

Affric wrote: post #253
grahamj wrote: post #188

Earlier quoted context omitted.

Agreed. It might share the title with the M1 Air which was incredible for an ultraportable, but the M1MBP was just incredible period. Three generations later it's still more machine than most people need. M2/3/4 sped things up but the M1 set the bar.

My only regret is getting base RAM. It’s not a server so it’s not a crime to not always be using all of it and it’s not upgradable so it needs to be right the first time. I should have got 32GB to just be sure.

Yep, that's definitely a thing I'm proud or correctly foreseeing. I was upgrading from an old machine on 8GB, but I figured especially with memory being non upgradable it was better being safe than sorry, and if I kept the machine a decade it would come out to sanwitch money in the end.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#434

Post by djmips »

post_break wrote: post #8

What's crazy is that the M4 Pro is in the Mac mini, something so tiny can handle that chip. The Mac Studio with the M4 Max will be awesome but the Mini is remarkable.

Is it crazy? The chip itself is small. I'm not up on the subject but is it unusual? Are we talking power draw and cooling adding greatly to the size? I guess the M4 Pro must have great specs when it comes to running cool.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#435

Post by spoaceman7777 »

GeekyBear wrote: post #431
spoaceman7777 wrote: post #411

Earlier quoted context omitted.

just considering the number of simple calculations a CPU can compute isn't a very good comparison. apple's chips are using an ARM architecture, which is a Reduced Instruction Set Computer (RISC) setup, vs x86-64, which is a Complex-ISC (CISC). The only good comparison is to judge a variety of real world programs compiled for each architecture, and run them.

> The only good comparison is to judge a variety of real world programs compiled for each architecture, and run them. I'm guessing that you don't realize that you are describing SPEC? It's been around since the days when every workstation vendor had their own bespoke CPU design and it literally takes hours to run the full set of workloads. From the same Anandtech article linked above: > SPEC CPU 2017 is a series of s…

took at look at these benchmarks. they appear to be using some extremely antiquated code, and workloads, that do not take advantage of any of the advanced features and instruction introduced over the past 15-20 years in the x86-64 architecture.

additionally, the only updates they appear to have made in the last 5+ years involve optimizing the suite for Apple chips.

thus, it leaves out massive parts of modern computing, and the (many) additions to x86-64 that have been introduced since the 00s.

i'd encourage you to look into the advancements that have occurred in SIMD instructions since the olden days, and the way in which various programs, and compilers, are changed to take advantage of them

ARM is nice and all, but the benchmark you've linked appears to be some extremely outdated schlock that is peddled for $1000 a pop from a web page out of the history books. Really. Take a look through what the benchmarks on that page are actually using for tooling.

I'd consider the results valid if they were calculated using an up to date, and maintained, toolset, like that provided by openbenchmarking.org (the owner of which has been producing some excellent ARM64 vs Intel benchmarks on various workloads, particularly recently).

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#436

Post by alwillis »

taftster wrote: post #420
thfuran wrote: post #216

Earlier quoted context omitted.

In the 90s, you probably wouldn't want to be using a desktop from 4 years ago, but the M1 is already 4 years old and will probably be fine for most people for years yet.

So long as Apple is willing to keep operating system updates available for the platform. This is by far the most frustrating thing. Apple hardware, amazing and can last for years and even decades. Supported operating system updates, only a couple of years. I'm typing this from my mid-2012 retina mac book pro. I'm on Mojave and I'm well out of support for the operating system patches. But the hardware keeps running li…

Apple hardware, amazing and can last for years and even decades. Supported operating system updates, only a couple of years.

That’s not accurate.

Just yesterday, my 2017 Retina 4k iMac got a security update to macOS Ventura 13.7.1 and Safari even though it’s listed as “vintage.”

Now that Apple makes their own processors and GPUs, there’s really no reason in the foreseeable future that Apple would need to stop supporting any Mac with an M-series chip.

The first M1 Macs shipped in November 2020—four years ago but they can run the latest macOS Sequoia with Apple Intelligence.

Unless Apple makes some major changes to the Mac’s architecture, I don’t expect Apple to stop supporting any M series Mac anytime soon.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#437

Post by sho_hn »

throw_that_away wrote: post #430
jchw wrote: post #366

Well, firstly, it isn't. There are higher Geekbench 6 CPU scores, even forgetting the ones that appear to be fake or at least broken. But secondly, that would absolutely not indicate that it is the "fastest single-core performer in consumer computing". That would indicate that it is the highest scoring Geekbench 6 CPU in consumer computing. Whether or not that's actually a good proxy for the former statement is up to…

Remember too back in the day when you're looking at a Mac with 1/4 the power of a PC, and it's 4x the price. I think we're starting to see those ratios reversed completely. And at the same time, the power, heat, etc.. is just sitting at the floor.

Yeah, this rings true. I'm not an Apple customer, but I certainly remember the days when Mac users had to justify the much worse bang-for-the-buck of Apple hardware (then) with it being the only ticket to their preferred software experience.

These days it appears more that the hardware is fantastic, especially in the laptop form factor and thermal envelope, and perhaps the downside is a languishing macOS.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#438

Post by alwillis »

markdown wrote: post #421
readyplayernull wrote: post #266

Earlier quoted context omitted.

Funny that we can buy renewed Intel Macs for less than $200 and do exactly the same.

Where can you get Intel Macs for $200?

I bought an Intel 13-inch MacBook Pro for a friend that I’m working with for $200-$250 from woot.com.

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#439

Post by PUSH_AX »

spoaceman7777 wrote: post #435
GeekyBear wrote: post #431

Earlier quoted context omitted.

> The only good comparison is to judge a variety of real world programs compiled for each architecture, and run them. I'm guessing that you don't realize that you are describing SPEC? It's been around since the days when every workstation vendor had their own bespoke CPU design and it literally takes hours to run the full set of workloads. From the same Anandtech article linked above: > SPEC CPU 2017 is a series of s…

took at look at these benchmarks. they appear to be using some extremely antiquated code, and workloads, that do not take advantage of any of the advanced features and instruction introduced over the past 15-20 years in the x86-64 architecture. additionally, the only updates they appear to have made in the last 5+ years involve optimizing the suite for Apple chips. thus, it leaves out massive parts of modern computin…

Does optimising the tests towards one architecture seem like a fair way of testing?

Re: Apple's M4 Max chip is the fastest single-core performer in consumer computing

#440

Post by mabedan »

jchw wrote: post #366

Well, firstly, it isn't. There are higher Geekbench 6 CPU scores, even forgetting the ones that appear to be fake or at least broken. But secondly, that would absolutely not indicate that it is the "fastest single-core performer in consumer computing". That would indicate that it is the highest scoring Geekbench 6 CPU in consumer computing. Whether or not that's actually a good proxy for the former statement is up to…

> you really need to be able to compare CPUs is a healthy mix of synthetic benchmarks and real-world workloads

I like how Apple got roasted on every forum for using real world workloads to compare M series processors to other processor. The moment there’s a statistic pointing to “theoretical” numbers, we’re back to using real world workload comparison

Post reply on HN