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

AMD claims Arm ISA doesn't offer efficiency advantage over x86

techpowerup.com

Post reply on HN
Print view View original

61–70 of 446 posts

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#61

Post by gigatexal »

pengaru wrote: post #51
gigatexal wrote: post #12

You’ll pry the ARM M series chips of my Mac from my cold dead hands. They’re a game changer in the space and one of the best reasons to use a Mac. I am not a chip expert it’s just so night and day different using a Mac with an arm chip compared to an Intel one from thermals to performance and battery life and everything in between. Intel isn’t even in the same ballpark imo. But competition is good and let’s hope they…

Your Intel mac was stuck in the past while everyone paying attention on PCs were already enjoying TSMC 7nm silicon in the form of AMD Zen processors. Apple Silicon macs are far less impressive if you came from an 8c/16t Ryzen 7 laptop. Especially if you consider the Apple parts are consistently enjoying the next best TSMC node vs. AMD (e.g. 5nm (M1) vs. 7nm (Zen2)) What's _really_ impressive is how badly Intel fell b…

that ryzen laptop chip perform it'll just do it at a higher perf/watt than the apple chip will... and on a laptop that's a key metric.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#62

Post by x0x0 »

bryanlarsen wrote: post #53
x0x0 wrote: post #50

Earlier quoted context omitted.

> That's not mostly because of a better ISA Genuinely asking -- what is it due to? Because like the person you're replying to, the m* processors are simply better: desktop-class perf on battery that hangs with chips with 250 watt TDP. I have to assume that amd and intel would like similar chips, so why don't they have them if not due to the instruction set? And AMD is using TSMC, so that can't be the difference.

What's it due to? At least this, probably more. - more advanced silicon architecture. Apple spends billions to get access to the latest generation a couple of years before AMD. - world class team, with ~25 years of experience building high speed low power chips. (Apple bought PA Semi to make these chips, which was originally the team that build the DEC StrongARM). And then paid & treated them properly, unlike Intel &…

interesting, ty

re: apple getting exclusive access to the best fab stuff: https://appleinsider.com/articles/23/08/07/apple-has-sweethe... . Interesting.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#63

Post by tinktank »

bfrog wrote: post #39
tinktank wrote: post #17

Earlier quoted context omitted.

PPA results comparing x86 to ARM say otherwise; take a look at Ryzen's embedded series and Intel's latest embedded cores.

Have they reached apple m level of performance/watt after half a decade of the apple m parts being out yet? Do either AMD or Intel beat Apple in any metric in mobile?

Yes and yes - again, go look at the published results.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#64

Post by toast0 »

mananaysiempre wrote: post #31
YetAnotherNick wrote: post #11

Earlier quoted context omitted.

> how they sucked Care to elaborate. I had the 9" mini laptop kind of device based on Atom and don't remember Atom to be the issue.

I had a Atom-based netbook (in the early days when they were 32-bit-only and couldn’t run up-to-date Windows). It didn’t suck, as such, but it was definitely resource-starved. However, what I meant is Atom-based Android tablets. At about the same time as the netbook craze (late 2000s to early 2010s) there was a non-negligible number of Android tablets, and a noticeable fraction of them was not ARM- but Atom-based. (T…

Android x86 devices suffer when developers include binary libraries and don't add x86. At the time of Intel's x86 for Android push, Google didn't have good apk thinning options, so app developers had to decide if they wanted to add x86 libraries for everyone so that a handful of tablets/phones would work properly... for the most part, many developers said no; even though many/most apps are tested on the android emulator that runs on x86 and probably have binary libraries available to work in that case.

IMHO, If Intel had done another year or two of trying, it probably would have worked, but they gave up. They also canceled x86 for phone like the day before the Windows Mobile Continuum demo, which would have been a potentially much more compelling product with x86, especially if Microsoft allowed running win32 apps (which they probably wouldn't, but the potential would be interesting)

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#65

Post by tracker1 »

gigatexal wrote: post #61
pengaru wrote: post #51

Earlier quoted context omitted.

Your Intel mac was stuck in the past while everyone paying attention on PCs were already enjoying TSMC 7nm silicon in the form of AMD Zen processors. Apple Silicon macs are far less impressive if you came from an 8c/16t Ryzen 7 laptop. Especially if you consider the Apple parts are consistently enjoying the next best TSMC node vs. AMD (e.g. 5nm (M1) vs. 7nm (Zen2)) What's _really_ impressive is how badly Intel fell b…

that ryzen laptop chip perform it'll just do it at a higher perf/watt than the apple chip will... and on a laptop that's a key metric.

And 20% or so of that difference is purely the fab node difference, not anything to do with the chip design itself. Strix Halo is a much better comparison, though Apple's M4 models do very well against it often besting it at the most expensive end.

On the flip side, if you look at servers... Compare a 128+core AMD server CPU vs a large core ARM option and AMD perf/watt is much better.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#66

Post by bryanlarsen »

gigatexal wrote: post #60
bryanlarsen wrote: post #53

Earlier quoted context omitted.

What's it due to? At least this, probably more. - more advanced silicon architecture. Apple spends billions to get access to the latest generation a couple of years before AMD. - world class team, with ~25 years of experience building high speed low power chips. (Apple bought PA Semi to make these chips, which was originally the team that build the DEC StrongARM). And then paid & treated them properly, unlike Intel &…

How many of those engineers remain, didn't a lot go to Nuvia that was then bought by Qualcomm?

Sure, but they were there long enough to train and instill culture into the others. And of course, since the acquisition in 2008 they've had access to the top new grads and experienced engineers. If you're coming out top of your class at an Ivy or similar you're going to choose Apple over Intel or AMD both because of rep and the fact that your offer salary is much better.

P.S. hearsay and speculation, not direct experience. I haven't worked at Apple and anybody who has is pretty closed lip. You have to read between the lines.

P.P.S. It's sort of a circular argument. I say Apple has the best team because they have the best chip && they have the best chip because they have the best team.

But having worked (briefly) in the field, I'm very confident that their success is much more likely due to having the best team rather than anything else.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#67

Post by toast0 »

x0x0 wrote: post #50
kccqzy wrote: post #34

Earlier quoted context omitted.

That's not mostly because of a better ISA. If Intel and Apple had a chummier relationship you could imagine Apple licensing the Intel x86 ISA and the M series chips would be just as good but running x86. However I suspect no matter how chummy that relationship was, business is business and it is highly unlikely that Intel would give Apple such a license.

> That's not mostly because of a better ISA Genuinely asking -- what is it due to? Because like the person you're replying to, the m* processors are simply better: desktop-class perf on battery that hangs with chips with 250 watt TDP. I have to assume that amd and intel would like similar chips, so why don't they have them if not due to the instruction set? And AMD is using TSMC, so that can't be the difference.

I think the fundamental difference between an Apple CPU and an Intel/AMD CPU is Apple does not play in the megahertz war. The Apple M1 chip, launched in 2020 clocks at 3.2GHz; Intel and AMD can't sell a flagship mobile processor that clocks that low. Zen+ mobile Ryzen 7s released Jan 2019 have a boost clock of 4 GHz (ex: 3750H, 3700U); mobile Zen2 from Mar 2020 clock even higher (ex: 4900H at 4.4, 4800H at 4.2). Intel Tiger Lake was hitting 4.7 Ghz in 2020 (ex: 1165G7).

If you don't care to clock that high, you can reduce space and power requirements at all clocks; AMD does that for the Zen4c and Zen5c cores, but they don't (currently) ship an all compact core mobile processor. Apple can sell a premium branded CPU where there's no option to burn a lot of power to get a little faster; but AMD and Intel just can't, people may say they want efficiency, but having higher clocks is what makes an x86 processor premium.

In addition to the basic efficiency improvements you get by having a clock limit, Apple also utilizes wider execution; they can run more things in parallel, this is enabled to some degree by the lower clock rates, but also by the commitment to higher memory bandwidth via on package memory; being able to count on higher bandwidth means you can expect to have more operations that are waiting on execution rather than waiting on memory, so wider execution has more benefits. IIRC, Intel released some chips with on package memory, but they can't easily just drop in a couple more integer units onto an existing core.

The weaker memory model of ARM does help as well. The M series chips have a much wider out of order window, because they don't need to spend as much effort on ordering constraints (except when running in the x86 support mode); this also helps justify wider execution, because they can keep those units busy.

I think these three things are listed in order of impact, but I'm just an armchair computer architecture philosopher.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#68

Post by jdsully »

toast0 wrote: post #36
WithinReason wrote: post #10

Since newer CPUs have heterogeneous cores (high performance + low power), I'm wondering if it makes sense to drop legacy instructions from the low power cores, since legacy code can still be run on the other cores. Then e.g. an OS compiled the right way can take advantage of extra efficiency without the CPU losing backwards compatibility

Like o11c says, that's setting everyone up for a bad time. If the heterogenous cores are similar, but don't all support all the instructions, it's too hard to use. You can build legacy instructions in a space optimized way though, but there's no reason not to do that for the high performance cores too --- if they're legacy instructions, one expects them not to run often and perf doesn't matter that much. Intel droppe…

I don't really understand why the OS can't just trap the invalid instruction exception and migrate it to the P-core. E.g. AVX-512 and similar. For very old and rare instructions they can emulate them. We used to do that with FPU instructions on non-FPU enabled CPUs way back in the 80s and 90s.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#69

Post by fluoridation »

toast0 wrote: post #67
x0x0 wrote: post #50

Earlier quoted context omitted.

> That's not mostly because of a better ISA Genuinely asking -- what is it due to? Because like the person you're replying to, the m* processors are simply better: desktop-class perf on battery that hangs with chips with 250 watt TDP. I have to assume that amd and intel would like similar chips, so why don't they have them if not due to the instruction set? And AMD is using TSMC, so that can't be the difference.

I think the fundamental difference between an Apple CPU and an Intel/AMD CPU is Apple does not play in the megahertz war. The Apple M1 chip, launched in 2020 clocks at 3.2GHz; Intel and AMD can't sell a flagship mobile processor that clocks that low. Zen+ mobile Ryzen 7s released Jan 2019 have a boost clock of 4 GHz (ex: 3750H, 3700U); mobile Zen2 from Mar 2020 clock even higher (ex: 4900H at 4.4, 4800H at 4.2). Inte…

Does anyone actually care at all about frequencies? I care if my task finishes quickly. If it can finish quickly at a low frequency, fine. If the clock runs fast but the task doesn't, how is that a benefit?

My understanding is that both Intel and AMD are pushing high clocks not because it's what consumers want, but because it's the only lever they have to pull to get more gains. If this year's CPU is 2% faster than your current CPU, why would you buy it? So after they have their design they cover the rest of the target performance gain by cranking the clock, and that's how you get 200 W desktop CPUs.

>the commitment to higher memory bandwidth via on package memory; being able to count on higher bandwidth means you can expect to have more operations that are waiting on execution rather than waiting on memory, so wider execution has more benefits.

I believe you could make a PC (compatible) with unified memory and a 256-bit memory bus, but then you'd have to make the whole thing. Soldered motherboard, CPU/GPU, and RAM. I think at the time the M1 came out there weren't any companies making hardware like that. Maybe now that x86 handhelds are starting to come out, we may see laptops like that.

Re: AMD claims Arm ISA doesn't offer efficiency advantage over x86

#70

Post by fanf2 »

torginus wrote: post #18
exmadscientist wrote: post #2

This is an entirely uncontroversial take among experts in the space. x86 is an old CISC-y hot mess. RISC-V is a new-school hyper-academic hot mess. Recent ARM is actually pretty good. And none of it matters, because the uncore and the fabrication details (in particular, whether things have been tuned to run full speed demon or full power sipper) completely dominate the ISA. In the past x86 didn't dominate in low powe…

I remember reading this Jim Keller interview: https://web.archive.org/web/20210622080634/https://www.anand... Basically the gist of it is that the difference between ARM/x86 mostly boils down to instruction decode, and: - Most instructions end up being simple load/store/conditional branch etc. on both architectures, where there's literally no difference in encoding efficiency - Variable length instruction has pretty…

Apple’s ARM cores have wider decode than x86

M1 - 8 wide

M4 - 10 wide

Zen 4 - 4 wide

Zen 5 - 8 wide

Post reply on HN