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

Apple M1 Max Geekbench Score

browser.geekbench.com

Post reply on HN
Print view View original

651–660 of 917 posts

Re: Apple M1 Max Geekbench Score

#651

Post by keymone »

qayxc wrote: post #473
keymone wrote: post #359

Earlier quoted context omitted.

i doubt it'll even initialize.

These cards can run idle (e.g. desktop 2D mode) at about 15W, so it might run just fine. Actual power draw depends on monitor resolution, number of attached displays, and refresh rate, though.

These cards idle at 15w while m1 max is yielding like half the performance at that wattage.

Sorry, Apple is clearly lightyears ahead. All they need to do is put out a chip with 48 of their gpu cores and they will beat the most expensive top of the line best ever performance gpu on the market… with a laptop-grade SoC.

Re: Apple M1 Max Geekbench Score

#653

Post by MaxikCZ »

genewitch wrote: post #496
amelius wrote: post #351

Earlier quoted context omitted.

My colleague has an M1 Mac. I have a Ubuntu desktop. My colleague always asks me to transcode videos on my machine because on her MacBook it is too slow.

I finally managed to get nvenc working on handbrake and the stupendous frame rate jump actually had me sit in stunned silence, from 3-15FPS to 120FPS on drone 1080p60 footage was jaw dropping. I know the m1 claims to be fast but I'm transcoding on a GPU that's from like 2015!

Just know that HW encoders on nVidia cards are usually inferior in quality compared to software encoders, altho the speed gain is very nice. I originally bought 2070 with its HW HEVC encoder, and apart from few test runs never used it again, because no matter the quality settings, its just worse (and I was never in a hurry).

No idea about HW encoders quality/speed on M1

Re: Apple M1 Max Geekbench Score

#654

Post by dijit »

true_religion wrote: post #640
dijit wrote: post #629

Earlier quoted context omitted.

2011 desktop CPUs will perform about half as well as a modern laptop one. I don’t even think Sandybridge (Intel 2011) CPUs support h264 decode- a pretty common requirement these days for zoom, slack, teams and video streaming sites such as YouTube.

Yes… only half as well as modern laptop. Back on the era of Moore’s law, a new machine would be 32x as fast as a ten year old model. That was a real difference. But in 2021, people still buy laptops 1/2 as slow as other models to do the same work. Heck people go out of their way to buy iPad pros which are half as slow as comparable laptops. Considering that, I think a ten year old machine is pretty competitive as an…

> iPad pros which are half as slow as comparable laptops.

Uh, what?

iPads are using comparable CPUs to the M1 (some even use the M1) and are some of the fastest CPUs for rendering JavaScript on the planet.

I think you’re right that people buy slow laptops. But I think that often comes from a place of technical illiteracy and willingness to spend.

Put simply: they can’t often comprehend the true value of a faster system and opt to be more financially conservative.

Which I fully understand.

Re: Apple M1 Max Geekbench Score

#655

Post by dijit »

true_religion wrote: post #643
dijit wrote: post #607

Earlier quoted context omitted.

A new M1 laptop is likely to last 4-5 years as a good specification of machine. A second hand laptop has much less advantage to doing that. I think this is a false economy. “The poor man pays twice” But regardless: the cost isn’t outrageous when compared to the Dell XPS/latitude or HP Elitebook lines (which are the only laptops I know of designed to last a 5y support cycle). If you’re buying a new laptop, I don’t thi…

The trade in value for my 6 year old MacBook Air is 150 dollars. Old computers depreciate so fast, that you can afford to buy ten of them for the price of one new computer.

Looks like they’re selling for more than twice that on ebay.co.uk though. And considering MacBook airs are $1000~ devices that’s really high.

6 years is also beyond the service life of a(ny) machine.

If I look at 3 year old MacBook airs they’re selling for £600 on eBay, which is, what, half of the full cost. Not great for an already old machine with only a few good years left.

I guess you might save a bit of money using extremely old hardware and keeping it for a while. But this is a really poor argument against an objectively good evolutionarily improved cpu in my opinion.

Re: Apple M1 Max Geekbench Score

#656

Post by Slartie »

baybal2 wrote: post #355
PragmaticPulp wrote: post #245

Earlier quoted context omitted.

> I just can't figure out what I'm missing on the "M1 is so fast" side of things. Two reasons: 1. M1 is a super fast laptop chip. It provides mid-range desktop performance in a laptop form factor with mostly fanless operation. No matter how you look at it, that's impressive. 2. Apple really dragged their feet on updating the old Intel Macs before the transition. People in the Mac world (excluding hackintosh) were stu…

> were stuck on relatively outdated x86-64 CPUs. We came to a point when X86 is faster to emulate, than to run on a more modern microarchitecture. One point is clear: per-transistor performance of X86 is dimishing with each new core generation, and it is already losing to M1. X86 makers will not be able to keep up for long. They will have to keep releasing bigger, and hotter chips to keep parity, until they cannot.

> We came to a point when X86 is faster to emulate, than to run on a more modern microarchitecture.

Since you are clearly referring to Rosetta 2:

- It is not an emulation. It is a translation. That alone is a 10-100x speed difference.

- It is not always faster; it highly depends on the specific code to run. Some code is miraculously faster, some is only at about 50% or lower.

- The comparison is "apples vs. oranges" because it's only comparing against Intel Macs, which do not use the fastest x86-64 chips on the market. Most importantly, AMD processors are not included in this comparison at all.

Constructing a general superiority of ARM vs. x86 based on this flawed premise is really far-fetched.

Re: Apple M1 Max Geekbench Score

#657

Post by lliamander »

drewpc wrote: post #542
PragmaticPulp wrote: post #245

Earlier quoted context omitted.

> I just can't figure out what I'm missing on the "M1 is so fast" side of things. Two reasons: 1. M1 is a super fast laptop chip. It provides mid-range desktop performance in a laptop form factor with mostly fanless operation. No matter how you look at it, that's impressive. 2. Apple really dragged their feet on updating the old Intel Macs before the transition. People in the Mac world (excluding hackintosh) were stu…

I disagree with this perspective. I think it's important to recognize that the M1 is a System on a Chip (SoC), not simply a CPU. Comparing the Apple M1 to "mid-range 8-core AMD desktop CPUs from 2020" is not comparing apples to apples. The M1 Max in the Geek Bench score has 10 cores whereas the AMD desktop CPUs you mention have 8-cores. That would be more of an apples to apples comparison. Where the M1 architecture r…

I really hope Qualcomm/NUVIA (or Nvidia/ARM) release a competitive ARM SoC that will eventually become part of a framework mainboard module.

Re: Apple M1 Max Geekbench Score

#658

Post by boopmaster »

tarsinge wrote: post #646
soylentnewsorg wrote: post #615

Earlier quoted context omitted.

I do get it - you define pro as a guy at work running his backup application in a web browser, and the hipster at starbucks doing "graphic design." I define pro as "a workstation." The m1 does not emulate x86. You literally don't know what you're talking about. Which explains why you define a kid's toy as "pro." I get it - you're getting paid. So is the barista at the starbucks you work from. Kia might define their k…

Just say it: using a laptop on battery power is for hipsters.

Right? I’m curious what pro’s do “at the indy 500”. Most devs where I work use 15” macs and probably a blend of apps from jetbrains toolbox. Mostly connected to power outlets to be fair. So we’re talking local installs of spring boot app Java servers, front end Webserver, an IDE to work on one of those, because opening a second one on a Intel mac will either run the dev out of RAM or the heat will cause a shutdown.

The thing is, the corporate DELL windows machines available were largely unsuitable to dev work due to the trashy interfaces (low resolution screens, bad trackpads, battery life so bad you can’t make it through a 2 hour meeting undocked). The Windows laptops available really failed hard when they needed to be laptops.

Re: Apple M1 Max Geekbench Score

#659

Post by baybal2 »

calaphos wrote: post #480
baybal2 wrote: post #355

Earlier quoted context omitted.

> were stuck on relatively outdated x86-64 CPUs. We came to a point when X86 is faster to emulate, than to run on a more modern microarchitecture. One point is clear: per-transistor performance of X86 is dimishing with each new core generation, and it is already losing to M1. X86 makers will not be able to keep up for long. They will have to keep releasing bigger, and hotter chips to keep parity, until they cannot.

Per transistor performance in M1 isn't any better than the x86 opposition, quite the opposite in fact. The standard M1 has 60% more transistors than a current gen Ryzen mobile chip, while having halve the large cores (and significantly worse multi ore performance).

You need to compare cores alone, not whole SoCs, with cache.

Re: Apple M1 Max Geekbench Score

#660

Post by aenis »

dijit wrote: post #587
soylentnewsorg wrote: post #569

Earlier quoted context omitted.

I love how you read the first line, ignore the rest of the paragraph addressing your specific point, then proudly strut around like you called out a gotcha. "bud." Dell Precision. 6 core xeon, 128GB RAM, 9 hour battery life. Thin and under 7lb. Metal and solid, can run over it w/ a car just like the Lenovo you're talking about. Has had a 4k screen and keyboards that don't break or imprint on the display. 5 years ago.…

I also have a Xeon laptop. (45w TDP E3-1505m v6 in a dell precision). Xeons are not magically faster than their i7/i9 counterparts (mine being not faster than a i7-7820HQ which is its contemporary flagship high performance mobile CPU). In fact they can be slower because the emphasis is on correctness and multi core, not usually single thread performance. Xeons are also slower than a modern AMD chip which also can hav…

My experience as well. I, too, have a dell precision with a 8 core xeon part, and while it looks decent its heavy and not noticeably faster than the m1 I replaced it with when it came out. The xeon would get hot and noisy when running teams or hangouts. It sits in my drawer for the last year or so.

M1 does not. Code compile is about as fast. Battery lasts a 3 day business trip or a hackaton without charging. I never heard its fan. I dont care much about brands, but lightweight, fast enough and well built M1 is praiseworthy. I am not getting the pro or max, as the benefits for me as a software dev are probably not worth the extra weight and power consumption.

Post reply on HN