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

Ask HN: Why hasn't x86 caught up with Apple M series?

news.ycombinator.com

Post reply on HN
Print view View original

151–160 of 640 posts

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#151

Post by pm215 »

yalok wrote: post #85
pjerem wrote: post #70

Earlier quoted context omitted.

Well I don’t think so. First, op is talking about Chrome which is not an Apple software. And I can testify that I observed the same behavior with other software which are really not optimized for macOS or even at all. Jetbrains IDEs are fast on M*. Also, processor manufacturers are contributors of the Linux kernel and have economical interest in having Linux behave as fast as they can on their platforms if they want…

Chrome uses tons of APIs from MacOS, and all that code is very well optimized by Apple. I remember disassembling Apple’s memcpy function on ARM64 and being amazed at how much customization they did just for that little function to be as efficient as possible for each length of a (small) memory buffer.

memcpy (and the other string routines) are some of the library functions that most benefit from heavy optimisation and tuning for specific CPUs -- they get hit a lot, and careful adjustment of the code can get major performance wins by ensuring that the full memory bandwidth of the CPU is being used (which may involve using specific load instructions, deciding whether using the simd registers is better or not, and so on). So everybody who cares about performance optimises these routines pretty carefully, regardless of toolchain/OS. For instance the glibc versions are here:

https://github.com/bminor/glibc/tree/master/sysdeps/aarch64/...

and there are five versions specialised for either specific CPU models or for available architecture features.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#152

Post by merelysounds »

wutwutwat wrote: post #133
purpleidea wrote: post #107

Honestly, I have serious FOMO about this. I am never going to run a Mac (or worse: Windows) I'm 100% on Linux, but I seriously hate it that I can't reliably work at a coffee shop for five hours. Not even doing that much other than some music, coding, and a few compiles of golang code. My Apple friends get 12+ hrs of battery life. I really wish Lenovo+Fedora or whoever would get together and make that possible.

> I seriously hate it that I can't reliably work at a coffee shop for five hours just... take your charger...

They’re relatively heavy, take up space and there’s no guarantee there will be an outlet near your table. When connected, the laptop becomes more difficult to move or pack. It’s all doable but also slightly less convenient.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#153

Post by mschuster91 »

Rohansi wrote: post #143
mschuster91 wrote: post #129

> I am sorely disappointed, using the Framework feels like using an older Intel based Mac. If I open too many tabs in Chrome I can feel the bottom of the laptop getting hot, open a YouTube video and the fans will often spin up. A big thing is storage. Apple uses extremely fast storage directly attached to the SoC and physically very very close. In contrast, most x86 systems use storage that's socketed (which adds phy…

> A big thing is storage. Apple uses extremely fast storage directly attached to the SoC and physically very very close. In contrast, most x86 systems use storage that's socketed (which adds physical signal runtime) and that goes via another chip (southbridge). Why would PCIe SSDs need to go through a southbridge? The CPU itself provides PCIe lanes that can be used directly. > That means, unlike Mac devices that can…

> The CPU itself provides PCIe lanes that can be used directly.

It does, but if you look at the mainboard manuals of computers, usually it's 32 lanes of which 16 go to the GPU slot and 16 to the southbridge, so no storage directly attached to the CPU. Laptops are just as bad.

Intel has always done price segmentation with the number of PCIe lanes exposed to the world.

Threadripper AMD CPUs are a different game, but I'm not aware of anyone, even "gamer" laptops, sticking such a beast into a portable device.

> Latency is also significantly worse when you trigger a page fault and then need to wait for the page to load from disk before the thread can resume execution.

Indeed, but the difference in performance between an 8GB Windows laptop and an 8GB M-series Apple laptop is noticeable, even if all it's running is the base OS and Chrome with a few dozen tabs.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#154

Post by lawn »

> If I open too many tabs in Chrome I can feel the bottom of the laptop getting hot, open a YouTube video and the fans will often spin up.

I've got the Framework 13 with the Ryzen 5 7640U and I routinely have dozens of tabs open, including YouTube videos, docker containers, handful of Neovim instances with LSPs and fans or it getting hot have never been a problem (except when I max out the CPU with heavy compilation).

The issue you're seeing isn't because x86 is lacking but something else in your setup.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#155

Post by asno3030 »

They are pretty similar when comparing the latest amd, and Apple chips on the same node. The buying power from Apple means that they get them earlier than AMD, usually by 6-9 months.

Windows on the other hand is horribly optimized, not only for performance, but also for battery life. You see some better results from Linux, but again it takes a while for all of the optimizations to trickle down.

The tight optimization between the chip, operating system, and targeted compilation all come together to make a tightly integrated product. However comparing raw compute, and efficiency, the AMD products tend to match the capacity of any given node.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#156

Post by FirmwareBurner »

aurareturn wrote: post #117
noelwelsh wrote: post #99

Like a few other comments have mentioned, AMD's Strix Halo / AI Max 380 and above is the chip family that is closest to what Apple has done with the M series. It has integrated memory and decent GPU. A few iterations of this should be comparable to the M series (and should make local LLMs very feasible, if that is your jam.)

On Cinebench 2025 single threaded, M4 is roughly 4x more efficient and 50% faster than Strix Halo. These numbers can be verified by googling Notebookcheck. How many iterations to match Apple?

>How many iterations to match Apple?

Until AMD can built a tailor made OS for their chips and build their own laptops.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#157

Post by prmoustache »

purpleidea wrote: post #107

Honestly, I have serious FOMO about this. I am never going to run a Mac (or worse: Windows) I'm 100% on Linux, but I seriously hate it that I can't reliably work at a coffee shop for five hours. Not even doing that much other than some music, coding, and a few compiles of golang code. My Apple friends get 12+ hrs of battery life. I really wish Lenovo+Fedora or whoever would get together and make that possible.

> work at a coffee shop

That doesn't sound super secure to me.

> for five hours.

My experience with anything that is not designed to be an office is that it will be uncomfortable in the long run. I can't see myself working for 5 hours in that kind of place.

Also it seems it is quite easily solved with an external battery pack. They may not last 12hours but they should last 4 to 6 hours without a charge in powersaving mode.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#158

Post by chvid »

john01dav wrote: post #144
chvid wrote: post #83

I don't think there is a single thing you can point to. But overall Apple's hardware/software is highly optimized, closely knit, and each component is in general the best the industry has to offer. It is sold cheap as they make money on volume and an optimized supply chain. Framework does not have the volume, it is optimized for modularity, and the software is not as optimized for the hardware. As a general purpose c…

> It is sold cheap as they make money on volume and an optimized supply chain. What about all the money that they make from abusive practices like refusing to integrate with competitors' products thus forcing you to buy their ecosystem, phoning home to run any app, high app store fees even on Mac OS, and their massive anti repair shenanigans?

Macs today are not designed to be easily repairably but instead to be lighter and otherwise better integrated - I believe that is consequence of consumer preferences and not shady business practices.

As for the services - it is a bit off topic as I believe Apple makes a profit on their macs alone ignoring their services business. But in general I have less of a problem with a subscription / fee-driven services business compared to an advertisement-based one. And as for the fee / alternative payment controversy (epic vs apple etc.) this is something that is relevant if you are a big brand that can actually market on your own / build an alternative shop infrastructure. For small time developers the marketing and payment infrastructure the apple app store offers is a bargain.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#159

Post by mnw21cam »

BlindEyeHalo wrote: post #112
mmcnl wrote: post #92

A lot of insightful comments already, but there are two other tricks I think Apple is using: (1) the laptops can get really hot before the fans turn on audibly and (2) the fans are engineered to be super quiet. So even if they run on low RPM, you won't hear them. This makes the M-series seem even more efficient than they are. Also, especially the MacBook Pros have really large batteries, on average larger than the co…

The macbook air doesn't even have a fan. I don't think you could built a fan-less x86 laptop.

Sure, I have one sitting on my desk right now. It uses an Intel Core m3, and it's 7.5 years old, so it can't exactly be described as high performance, but it has a fantastic 3200x1800 screen and 8GB of RAM, and since I do all my number-crunching on remote servers it has been absolutely perfect. Unfortunately, the 7.5-year-old battery no longer lasts the whole day (it'll do more like 2 hours, or 1 hour running Zoom/Teams). It has a nice rigid all-metal construction and no fan. I'm looking around for a replacement but not finding much that makes sense.

Re: Ask HN: Why hasn't x86 caught up with Apple M series?

#160

Post by aurareturn »

kangs wrote: post #125
aurareturn wrote: post #117

Earlier quoted context omitted.

On Cinebench 2025 single threaded, M4 is roughly 4x more efficient and 50% faster than Strix Halo. These numbers can be verified by googling Notebookcheck. How many iterations to match Apple?

yes and no. i have macbook pro m4 and a zbook g1a (ai max 395+ ie strix halo) In day to day usage the strix halo is significantly faster, and especially when large context LLM and games are used - but also typical stuff like Lightroom (gpu heavy) etc. on the flip side the m4 battery life is significantly longer (but also the mpb is approx 1/4 heavier) for what its worth i also have a t14 with a snapdragon X elite and…

  yes and no. i have macbook pro m4 and a zbook g1a (ai max 395+ ie strix halo)
You're comparing the base M4 to a full fat Strix Halo that costs nearly $4,000. You can buy the base M4 chip in a Mac Mini for $500 on sale. A better comparison would be the M4 Max at that price.

Here's a comparison I did between Strix Halo, M4 Pro, M4 Max: https://imgur.com/a/yvpEpKF

As you can see, Strix Halo is behind M4 Pro in performance and severely behind in efficiency. In ST, M4 Pro is 3.6x more efficient and 50% faster. It's not even close to the M4 Max.

  (but also the mpb is approx 1/4 heavier)
Because it uses a metal enclosure.
Post reply on HN