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

481–490 of 529 posts

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

#481

Post by duskwuff »

enzo1982 wrote: post #453
unsigner wrote: post #405

Earlier quoted context omitted.

One of the reasons Rosetta 2 works so well is Apple silicon sticks to the more restricted x86 memory model.

Does it? Apple's documentation seems to disagree [1]: "A weak memory ordering model, like the one in Apple silicon, gives the processor more flexibility to reorder memory instructions and improve performance, but doesn’t add implicit memory barriers." [1] https://developer.apple.com/documentation/apple_silicon/addr...

It's switchable at runtime. Apple silicon can enable total store ordering on a per-thread basis while emulating x86_64, then turn it back off for maximum performance in native code.

Here's a kernel extension someone built to manipulate this feature: https://github.com/saagarjha/TSOEnabler

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

#482

Post by minimalist »

bufferoverflow wrote: post #447
minimalist wrote: post #177

Earlier quoted context omitted.

I'm referring to the second point about memory that OP made. You know, having to allocate 700MB of memory in order to run an electron chat application.

It's seems wasteful, but RAM is so cheap, who cares? You can get 16GB for $52 on Amazon. That 700MB is equivalent to $4.64 one-time payment. There are more important things to worry about, seems to me.

Not everyone lives in the first world. Not everyone has a new computer.

It is this sort of hubris that likely explains my feeling that personal computing has regressed in many ways for the average individual over the recent years. I'm not talking about the hacker who can run surf+i3 on their cyberdeck, I'm talking about the person with an 8-year old computer bought on sale or a 4-year old smartphone.

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

#483

Post by duskwuff »

jjtheblunt wrote: post #417
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…

Maybe ARM binaries are smaller than x86_64? ARM has some sophistication in its ISA, THUMB mode instructions for example, that might be in play here.

Thumb isn't a factor. The Thumb encoding is only used for 32-bit ARM instructions; 64-bit instructions use a fixed-width 32-bit encoding.

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

#484

Post by powerapple »

epistasis wrote: post #192
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.

So though it's a new age in some ways, I don't think it will benefit many people. It will just increase the churn. Witnessing all the cries of "16GB of RAM isn't enough!" makes it quite apparent that software behaves like a gas rather than a liquid, and will expand to consume whatever hardware is available to developers. I think that for consumer products, which these are targeting, software responsiveness, usability…

Definitely agree with you. The current software were developed for a 2x slower spec, and tested, tuned against a 2x slower spec, the speed gain will disappear once the development platform changes to M1, however, there will be more functionality, more animation in interface, as it has happened in past years.

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

#485

Post by imtringued »

AgloeDreams wrote: post #226
ogre_codes wrote: post #78

Earlier quoted context omitted.

The CPU gains on ARM have been increasing consistently year over year for the past decade. People have posted benchmarks of the A11/ A12/ A13 versus Intel for a while so this has been pretty obvious. It's just surfacing because suddenly we have a desktop CPU with desktop software like compilers and other things where it's more obvious outside of benchmark tools. Apple is just jumping onto their existing ARM track, on…

I think another shock here is that a lot of people discredited the ability of ARM cpus as well. Back when the iPad Pro with the A10X came out, Apple claimed it was faster than half of all Laptops sold and people in the PC space were yamming on and on about how numbers don't show how much better x86 cpus are at 'desktop stuff' and that ARM cpus can't equal x86, even with the same thermal envelope and shouldn't ever be…

>people in the PC space were yamming on and on about how numbers don't show how much better x86 cpus are at 'desktop stuff' and that ARM cpus can't equal x86, even with the same thermal envelope and shouldn't ever be compared.

It needs 30W at 4 cores 3.2Ghz. Ryzen needs around 5W per core but it's on a worse process. The entire system does use less power than a x86 system but that has nothing to do with the processor. It's more about how the SoC is arranged and that RAM is (almost) on the same package. It means they can get away with higher bandwidth and lower power consumption for the entire system.

The idea that it's all about the processor is completely wrong. Yet all we have heard is how fanboys cry it's going to be 3x faster than desktop CPUs because of misleading TDP numbers.

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

#486

Post by imtringued »

w0utert wrote: post #280
oarsinsync wrote: post #251

Earlier quoted context omitted.

I was until I tried doing the test myself. It takes 82 seconds to compile on my i5-4200M. I'm not sure this test is deserving of the breathless headline and commentary, especially since the original tweeter later follows up with: > Extra info: The M1 macbooks (air/pro) can't drive 2 external screens, and the air throttles a bit after 3+ minutes sustained compute (20-30%) https://twitter.com/rikarends/status/132875317…

>> We already know the A-series of chips performs incredibly in short workloads. We have no information yet on how it performs under sustained workloads. What makes you think that given sufficient cooling, it will not perform exactly the same as the M1 in the MBA but sustained? It’s not like the ARM architecture changes anything in the thermodynamics of cooling cpus compared to an x86 chip, right? I’d wager that unde…

It's in the same ballpark of power efficiency as AMD's x86 chips. It's slightly more efficient because of 7nm vs 5nm but if you scale it up to desktop frequencies it's going to consume the same amount of power as Ryzen CPUs.

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

#487

Post by imtringued »

wmf wrote: post #205
throwaway894345 wrote: post #195

Earlier quoted context omitted.

I’m guessing the performance improvements derive from integrating the memory onto the same chip (instead of using external memory), not from ARM (although power savings come from ARM). So we will probably see a new era of laptop SoCs, but that also means coupling RAM with CPU (or maybe you can mix and match the on-chip RAM with external RAM?).

I’m guessing the performance improvements derive from integrating the memory onto the same chip Nope, LPDDR4x-4266 is LPDDR4x-4266. Apple, Intel, and AMD all have access to the same RAM. The Firestorm core is the real advantage.

The memory bandwidth you get on the M1 is around what you would expect from a dual channel desktop with good RAM. So basically twice as fast as competing laptops.

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

#488

Post by shahar2k »

foobiekr wrote: post #227
reaperducer wrote: post #187

Earlier quoted context omitted.

Ray Tracing I'm not someone into the inner-working of chips much, but is "ray tracing" a new term used for something in microprocessors now? Or is this the same graphic "ray tracing" we were doing back in the 80's on Amigas and Atari STs?

Realtime ray-tracing is a mix of hardware acceleration for ray intersections and de-noising. The de-noising approaches are certainly novel and not really analogous to previous methods, imho, though the accelerated bounding box hierarchies for accelerating intersections certainly appear in previous iterations.

I think this is the key answer, de-noising, using various neural techniques finally allowed acceptable images to be produced from sometimes This is still not perfect and many ray tracing techniques rely on accumulation over time which limits certain images from working (I imagine raytracing a small particle cloud, or fast shifting objects to be a worst case scenarios)

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

#489

Post by imtringued »

danaris wrote: post #196
egao1980 wrote: post #155

Earlier quoted context omitted.

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

Yeah? And how are they looking today?

I don't know but the fact that Windows on ARM is completely locked down and only lets you install applications from the Microsoft Store made me abandon Windows as a platform for good.

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

#490

Post by imtringued »

ogre_codes wrote: post #277
tempest_ wrote: post #170

Earlier quoted context omitted.

At some point it is easier to have something sitting in a rack somewhere. That way you dont have to cook your ultrabook to run that stuff.

People have been saying this kind of thing for years, but so far it doesn't really math out. Having a CPU "in the cloud" is usually more expensive and slower than just using cycles on the CPU which is on your lap. The economics of this hasn't changed much over the past 10 years and I doubt it's going to change any time soon. Ultimately local computers will always have excess capacity because of the normal bursty natu…

As someone who is using a CPU in the cloud for leisure activities this is spot on. Unless you rent what basically amounts to a desktop you're not going get a GPU and high performance cores from most cloud providers. They will instead give you the bread and butter efficient medium performance cores with a decent amount of RAM and a lot of network performance but inevitable latency. The price tag is pretty hefty. After a few months you could just buy a desktop/laptop system that fits your needs much better.
Post reply on HN