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

16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

twitter.com

Post reply on HN
Print view View original

151–160 of 529 posts

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#151

Post by masklinn »

whalesalad wrote: post #48

I love everything about the move to Apple Silicon with the exception of the decision to put memory on-die or in-package (not sure how it is configured). They call it 'Unified Memory'. It makes a lot of sense but I don't know if they are going to be able to pack enough memory in there. A lot of folks are fixated on CPU performance lately (which is rad) but I think that there is a tendency to ignore memory. I have 32gb…

> They call it 'Unified Memory'. It makes a lot of sense but I don't know if they are going to be able to pack enough memory in there.

Unified memory and on-die (or in-package) memory are different thing, and while the latter simplifies the former they're mostly orthogonal.

Unified memory means the physical and logical memory space is directly accessible by both CPU and GPU, at the same time, in their entirety: https://en.wikipedia.org/wiki/Heterogeneous_System_Architect...

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#152

Post by yborg »

minimalist wrote: post #140
whalesalad wrote: post #48

I love everything about the move to Apple Silicon with the exception of the decision to put memory on-die or in-package (not sure how it is configured). They call it 'Unified Memory'. It makes a lot of sense but I don't know if they are going to be able to pack enough memory in there. A lot of folks are fixated on CPU performance lately (which is rad) but I think that there is a tendency to ignore memory. I have 32gb…

Perhaps this will encourage programmers to write true native applications again instead of wrapping web scripting languages in a browser and calling it a day.

I'd say the opposite, this increases the speed of such apps to closer to what is now native speed.

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#153

Post by reilly3000 »

tootie wrote: post #18

Nearly universal praise for the M1 versus it's predecessor but I don't see how this really changes Apple's position the way he implies. Their machines are still far more expensive than Windows and can't use high-powered GPUs like AMD/Nvidia. The people who choose PC, still have the same incentives to do so. For most users, the faster performance will probably not be very noticeable. The reduced power consumption is t…

I agree this doesn't really change Apple positioning and won't immediately impact the desktop market. That said, I think its a big kick in the ass to Microsoft and certainly Intel, and hopefully it forces them to compete. Its certainly making me take a closer look at Rasberry Pi and other ARM compute module boards for my homelab. Apple is going to drive ARM software and compiler support as well as broad adoption among developers. Exciting times.

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#154

Post by epistasis »

tannhaeuser wrote: post #90
whalesalad wrote: post #48

I love everything about the move to Apple Silicon with the exception of the decision to put memory on-die or in-package (not sure how it is configured). They call it 'Unified Memory'. It makes a lot of sense but I don't know if they are going to be able to pack enough memory in there. A lot of folks are fixated on CPU performance lately (which is rad) but I think that there is a tendency to ignore memory. I have 32gb…

Isn't fast on-die/on-package (not sure either) memory access a key factor for Apple's gigantic performance leap, though? With memory pre-soldered on small notebooks for years now, it's not much of a difference for consumers anyway once more than 16GB becomes available.

I'm not sure that the soldering does much to improve memory access.

The anand tech M1 article measures memory latency at more than 90ns [1], which is almost twice what I see for AMD and Intel benchmarks, at 50ns and 70ns [2]. If these are not comparable measurements, I'd love a correction!

It seems to me that there's significant room to improve the memory subsystem for Apple Silicon to reach parity with desktop RAM performance.

[1] https://www.anandtech.com/show/16252/mac-mini-apple-m1-teste...

[2] https://www.techcenturion.com/improve-zen-2-gaming-performan...

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#155

Post by egao1980 »

tonyedgecombe wrote: post #74
cercatrova wrote: post #26

Is anyone else thinking, what the f*ck? Are we in a new era of computing? It certainly feels that way when looking at these desktop class ARM chips, where performance doubled every year or so, just like back in the 80s and 90s.

I suspect HP/Lenovo/Microsoft are squirming in their chairs right now.

Lenovo and Microsoft had started to release ARM devices way before Apple.

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#157

Post by drdebug »

Does anyone know if there is a video encode benchmark available yet? These can be tricky to perform because you need to take into account the quality and size of the output. I assume x264/x265 are not optimized (yet) for M1. I wonder if M1 is designed for that workload at all (encode, not decode).

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#159

Post by Siira »

cercatrova wrote: post #111
tonyedgecombe wrote: post #74

Earlier quoted context omitted.

I suspect HP/Lenovo/Microsoft are squirming in their chairs right now.

I'm not so sure. Some people simply need Windows and now you can't Bootcamp on ARM Macs so people will take the best Windows laptop instead.

Who knows, they might continue to offer an Intel MBP for years to come, or even add Windows ARM support if it commands enough demand. The other manufacturers have no mote here.

Re: 16-inch MBP 2x slower than M1 MacBook Air in a real-world Rust compile

#160

Post by Steltek »

DarmokJalad1701 wrote: post #135
KingOfCoders wrote: post #36

My Ryzen 3900 is also so much faster than my (former dev machine) iMacPro with a Xeon and fast SSD (Rust compiles, TypeScript builds). Tech moves on. But the main thing for me is Linux, as it feels much more responsive than current OS X versions on the iMacPro. (the reason for dropping the iMacPro was no AI learning though not performance).

There are some data-points comparing the M1 to a 3950X https://twitter.com/john_lam/status/1328754454930231299

It's missing KingOfCoders point of these comparisons being all within the Apple ecosystem. MacBooks infamously have cooling problems and macOS is precisely balanced for battery life on Apple hardware, not AMD Hackintoshes with no speed limits. What happens to these benchmarks if you jettison the Apple overhead entirely?
Post reply on HN