Live data from Hacker News

Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

macrumors.com

931–940 of 1001 posts

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#931

Is there a common linear algebra benchmark? Would love to see a non-Intel chip + OpenBLAS beating out Intel + MKL

Why would you use OpenBLAS rather than Apple's Accelerate.framework? Since you're already using the Intel MKL, the only fair comparison is Accelerate.framework.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#933
post #380

Earlier quoted context omitted.

In what respect is Apple “locking down their software hard” with respect to these new Macs?

Apple is moving to basically ban non-Apple store installs of Mac software. It's been in progress the last few years but they are on the final stages of turning Macs into iPhones. Gotta take their 30% cut of everyone's revenue.

Probably not, since there are many crucial pro-level applications related to image editing, modelling and animation, video and audio production that realistically wouldn't be on the App Store (well, apart from Apple's own products).

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#934

Earlier quoted context omitted.

Until all software is ported to ARM, it will run in emulation, which is going to be slower in most cases. People invested in plug-in ecosystems, like DAWs or video editing, will likely have an endless long tail of plug-ins that aren't getting ported, or that require a re-purchase to get an ARM version. And due to Rosetta's architecture, you can't mix ARM and x86 plug-ins (in-process, like VSTs - Apple wants you to us…

Rosetta2 is mind blowing. “ fun fact: retaining and releasing an NSObject takes ~30 nanoseconds on current gen Intel, and ~6.5 nanoseconds on an M1” https://mobile.twitter.com/hhariri/status/132678854650246349... “…and ~14 nanoseconds on an M1 emulating an Intel”

How does it handle DSP inner loops? SIMD? x87 code? Floating point corner cases like denormals? What about the inevitable cases where impedance mismatch between the architectures causes severe performance loss? Is Rosetta2 binary translated code guaranteed to be realtime-safe if the original code was? What about the JIT? There's no way that is realtime-safe. What happens if some realtime code triggers the JIT?

We still can't emulate some 20-year-old machines at full speed on modern hardware due to platform impedance mismatches. Rosetta2 may be good, but until someone runs a DAW on there with a pile of plug-ins and shows a significant performance gain over contemporary Intels (and zero unexpected dropouts), I'm not buying the story of Rosetta2 amazingness.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#935
post #752
post #720

Earlier quoted context omitted.

> it's pretty clear their focus is not their power users' focus Depends on the definition of "power user". Music producers, video editors, and iOS developers will be served quite well. > lenovo thinkstation p340 tiny. you can configure it with 64gb ram and core i9 with 10 cores and 20 threads for less $$$ than what an underpowered 6 core mac mini is selling for. When making that calculation, one should also take powe…

Taking power consumption into account makes sense when the machine is running on battery power, but all modern processors are power efficient enough for the cost of electricity to be negligible for a tiny desktop computer.

Hypothetical scenario: You save 50W (maybe too high, maybe not), use the machine for 10h every day, and a kWh costs you €0.40 (eg in Germany). You save €0.20 per day, €73 per year, and €365 in 5 years. Definitely a factor in areas with high electricity prices.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#936
post #751

Earlier quoted context omitted.

Until all software is ported to ARM, it will run in emulation, which is going to be slower in most cases. People invested in plug-in ecosystems, like DAWs or video editing, will likely have an endless long tail of plug-ins that aren't getting ported, or that require a re-purchase to get an ARM version. And due to Rosetta's architecture, you can't mix ARM and x86 plug-ins (in-process, like VSTs - Apple wants you to us…

won't emulation catch up in those timeframes ? still, 3+ yrs which is a long time...

We still can't emulate some 20+ year old machines at native speed on modern hardware under certain conditions. Emulation always has corner cases where some awkward impedance mismatch between both architectures causes severe performance loss.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#937
post #847

Earlier quoted context omitted.

Quite likely what happened, a second geekbench score has shown up for the pro and it matches the air: https://browser.geekbench.com/v5/cpu/search?utf8=&q=MacBookP... My guess: in geekbench air and pro score the same, because geekbench is shortlived and not thermally constrained. In cinebench you'll see the pro pulling ahead.

Who uploads these results, are they unverified?

Anyone on the Internet can upload results. They are not verified.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#938

Earlier quoted context omitted.

Hence why Cinebench is often used these days when evaluating real-world performance with sustained workloads.

Different tests. Different purposes. GB deliberately avoids running up the heat because it is focused on testing the chip, not the machine's cooling ability. Cinebench, as you say, tests "real-world" conditions, meaning the entire machine, not just the chip.

That's not true at all about Geekbench.

"Geekbench 5 is a cross-platform benchmark that measures your system's performance with the press of a button. How will your mobile device or desktop computer perform when push comes to crunch? How will it compare to the newest devices on the market? Find out today with Geekbench 5"

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#939
post #103

Earlier quoted context omitted.

Dunno, seems like most professionals would want to use docker, virtual machines, or enough video/data to want more than 16GB ram. Or maybe even plug in more than a charging cable and one more device. Or run more than one external monitor. Doesn't seem very "pro" to me. The MBP16" intel has 4 x USB-c ports, can drive two monitors, and can have >= 32GB ram.

The MBP16 actually can do 4 displays if they're only 4k displays. It's why I bought one over a MBP13 which can only do 2. The two limit seems to be for 6016x3384 which I assume is 5k.

That's the resolution of the Pro Display XDR at 6k. It can run 2.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#940
All: there are multiple pages of comments; if you're curious to read them, click More at the bottom of the page, or like this:

https://news.ycombinator.com/item?id=25065026&p=2

https://news.ycombinator.com/item?id=25065026&p=3

https://news.ycombinator.com/item?id=25065026&p=4

Post reply on HN