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

571–580 of 640 posts

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

#571

Post by pabs3 »

dapperdrake wrote: post #14
dmitrygr wrote: post #11

There is one positive to all of this. Finally, we can stop listening to people who keep saying that Apple Silicon is ahead of everyone else because they have access to better process. There are now chips on better processes than M1 that still deliver much worse performance per watt.

Go down the rabbit hole of broken compiler settings for debian default builds, if you want to see how much low-hanging fruit we still have. Who here would be interested in testing a distro like debian with builds optimized for the Framework devices?

Got a link about the Debian issue? Is it just that they build for the CPU baseline to maximise hardware support?

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

#572

Post by diffeomorphism »

reaperducer wrote: post #532
bitwize wrote: post #391

Earlier quoted context omitted.

Microsoft is pushing "Modern Standby" over actual sleep, so laptops can download and install updates while closed at night.

Microsoft is pushing "Modern Standby" over actual sleep, so laptops can download and install updates while closed at night. Apple has this. It's called Power Nap. But for some reason, it doesn't cause the same problems reported by people here on HN.

It does cause the same problem but seems to be somewhat less frequent.

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

#573

Post by usr1106 »

Cthulhu_ wrote: post #345
jonwinstanley wrote: post #185

Earlier quoted context omitted.

A huge reason for the low power usage is the iPhone. Apple spent years incrementally improving efficiency and performance of their chips for phones. Intel and AMD were more desktop based so power efficiency wasnt the goal. When Apple's chips got so good they could transition into laptops, x86 wasn't in the same ballpark. Also the iPhone is the most lucrative product of all time (I think) and Apple poured a tonne of t…

I vaguely remember Intel tried to get into the low power / smartphone / table space at the time with their Atom line [0] in the late 00's, but due to core architecture issues they could never reach the efficiency of ARM based chips. [0] https://en.wikipedia.org/wiki/Intel_Atom

Intel and Nokia partnered around 2007 .. 09 to introduce x86 phone SoCs and the required software stack. Remember MeeGo? Nokia engineers were horrified by the power consumption and were convinced it wouldn't work. But Nokia management wanted to go to a dual supplier model instead of just relying on TI at all cost.

MeeGo proceeded far too slowly and Elop chose his former employers' Windows instead in 2011. Nokia's decline only increased and Intel hired many Nokia engineers.

Soon Nokia made no phone anymore and Intel did not even manage to make their first mass-selling product.

ARM-based SoCs were 10 years ahead in power saving. The ARM ecosystem did not make any fatal mistakes, Intel never caught up.

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

#574

Post by brokencode »

kalleboo wrote: post #555
brokencode wrote: post #521

Earlier quoted context omitted.

Yeah, why would ARM prevent other companies from paying more for the better license? All they care about is that companies buy an ARM license, not that they use the boilerplate ARM CPU design. Those designs are there to make it easier for companies to make ARM-based chips who would otherwise never be able to design their own.

Then why are they so shy about granting Qualcomm a license?

Qualcomm has a lot of money and Arm wants it. They’re not shy, but greedy.

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

#575

Post by jerome-jh »

This is a modularity vs integration tradeoff.

- Linux is a patchwork of SW, written in a variety of programming languages, using a variety of libraries, some of which having the same functionality. There is duplication, misalignment, legacy.

- MacOS is developed by a single company. It is much more integrated and coherent.

Same for the CPU:

- x86 accesses memory through an external bus. The ability to install a third party GPU requires an external bus, with a standardized protocol, bus width, etc. This is bound to lag behind state of the art

- Apple chips have on die memory, GPU (actually same package but not same die). Higher speeds, optimization, evading from standardized protocols: all this is possible.

This has an impact on kernel/drivers/compilers:

- x86: so many platforms, CPU versions, protocol revisions to support. Often with limited documentation. This wastes hell a lot of engineering time!

- Apple: limited number of HW platforms to support, full access to internals.

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

#577

Post by greatgib »

I think that you are wrong to extrapolate anything about the hardware capabilities based on your experience on a few tasks.

Difference are more software related in my opinion. And it might be just appearance as Apple is used to do tricks. Like for example it was shown in a good old time that people were thinking that the iphone was faster to load things because of using animation at load time despite taking the same time as other phones.

For example, for the many tabs in Chrome, the difference might be that macos is aggressively throttling things when your linux laptop will give you the maximum performance possible and so producing more heat. I often noted that with osx and especially when you don't have a lot of ram. The os will easily put to sleep and evict other programs, but also other windows and other tabs I guess as part of them are separated process. Then, when you need them, it reload the memory. Good in term of power efficiency but in my experience I was experiencing terrible latencies like going from one window to another. Let's say like 1s. Not obvious if you are not used to better.

In the same way that a lot of persons are used to electron based ide like vscode and feels perfectly ok, but for me the latency of typing code and it showing on the screen is awful compared to my native ide.

In the same way for macos, you can see how often the laptop will go to sleep, or lower the display light unexpectedly with default settings. Like these guys that suddenly quit Google meet meetings because the mac went to sleep despite the active call.

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

#578

Post by ben-schaaf »

aurareturn wrote: post #222
yaro330 wrote: post #205

Earlier quoted context omitted.

> Apple Silicon is 2-4x more efficient than AMD and Intel CPUs during load while also having higher top end speed. This is false, in cross platform tasks it's on par if not worse than latest X86 arches. As others pointed out: 2.5h in gaming is about what you'd expect from a similarly built X86 machine. They are willing due to lower idle and low load consumption, which they achieve by integrating everything as much as…

This is false, in cross platform tasks it's on par if not worse than latest X86 arches. This is Cinebench 2024, a cross platform application: https://imgur.com/a/yvpEpKF They are willing due to lower idle and low load consumption, which they achieve by integrating everything as much as possible - something that's basically impossible for AMD and Intel. Weird because LNL achieved similar idle wattage as Apple Silicon.…

> This is Cinebench 2024, a cross platform application: https://imgur.com/a/yvpEpKF

Cool, now compare M1 to AI 340. The AI 340 has slightly better single core and better multi-core. If battery life was all about race to idle like you claim then the AI 340 should be better than the M1.

See also Snapdragon X Elite, which is significantly slower than the AI 340, uses more power under load, so in total has much less efficient cores, and yet still beats the AI 340 on battery life.

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

#580

Post by pdimitar »

umbra07 wrote: post #547
john01dav wrote: post #141

Earlier quoted context omitted.

Power efficiency is very important to servers too, for cost instead of for battery life. But, energy is energy. Thus, I suspect that the power draw is in userland systems that are specific to desktop, like desktop environments. Thus, using a simpler desktop environment may be worthwhile.

I assumed the same thing, until I tested my hypothesis. KDE Plasma 6 uses less power on idle than just `Hyprland` (tiling WM) without anything like a notification daemon, idler, status bar, etc.

Were you able to find out why? This is very interesting and I'd never guess it.
Post reply on HN