Hacker News Reader

Comment by DCKing | Hacker News Reader

This year seems to be the year of big serious ARM performance.

- AWS Graviton 2 is actually a viable option in the public cloud.

- Apple starts transitioning their workhorses to ARM.

- First place in the TOP500, apparently not due to custom magic or GPUs, but due to already existing/standardized ARM vector extensions.

ARM is becoming such a household name that Fujitsu appears to have traded getting a paid ARM license over the royalty free SPARC instruction set they used to work with. I hope POWER can survive this onslaught, as SPARC surely has no hope of survival after this.

View on HN

> already existing/standardized ARM vector extensions.

Yeah, a standardized ISA extension, but I'd bet Fujitsu spent a ton of time on the implementation details. They have a deep history of making high performance vector processors going back to the 80s, and high performance SPARC cores parallel to that. They may not be huge volume, but they know how to make a fast processor.

Fujitsu developed SVE together with ARM.

Let's hope M$ will fix their OS to support ARM properly[1] soon, and that we get nice passive-cooled desktop systems.

[1] no x64 support, limited OpenGL/3D support, no Fax/Scan support... AFAIK.

ARM isn't doing anything magic to get hugely different performance/watt than x86, so anything passively cooled would be in the same performance ballpark as passively cooled x86.

See, e.g., performance/watt of Altra vs Epyc: https://www.nextplatform.com/2020/03/18/stacking-up-arm-serv...

> ARM isn't doing anything magic to get hugely different performance/watt than x86,

Apple is, though.

> performance/watt of Altra vs Epyc

Server CPUs are a different matter altogether, IMO.

That's yet to be seen. Though if they are, then we won't be seeing passively cooled desktop ARM PCs any time soon. Nice, quiet iMacs and Mac Minis, sure. Anyone working in production software is still going to have fans (or an expensive, enormous hunk of fins: https://www.anandtech.com/show/15261/turemetal-fanless-pc-ep...) in their boxes. People running water pump loops from their PCs to underground excepted.

In this era where all chips are getting power-state and speed-state shifts at millisecond speeds, eeking out even a 40% performance/watt benefit over comparable total-performance x86 SKUs in the laptop, desktop, and workstation categories would be a massive win for Apple and enough justification on top of unbridling themselves from Intel to warrant the shift.

40% benefit won't bring your average 60W desktop SKU down to a passively-coolable target. Or the 45W SKUs of a MacBook Pro class system (the passively cooled MacBooks were using 7W SKUs, and Apple axed that experiment after four years because even casual users found them too anemic to be marketable at Apple prices).

Even Raspberry Pi's are getting fans these days, and that CPU never draws more than 6W: https://www.jeffgeerling.com/blog/2019/raspberry-pi-4-needs-...

Lots of the ARM power wins in mobile rely on the light and infrequent use of the device. That's why Intel didn't bother with big.LITTLE style architectures until this year.

This is a good jumping off point if you want to dive more into ARM perf/watt, or see how performance/core is just starting to approach that of high end desktop x86 SKUs (with the A14 likely to approach parity): https://www.anandtech.com/show/14892/the-apple-iphone-11-pro...

That's all telling of apple likely dropping 4-16 core mobile and desktop SKUs that pull about 5W/core and are 30-40% more efficient than their x86 competition.

Windows on arm supports both 32 and 64 bit arm software. x86-64 emulation is missing because Intel threatened to sue (https://newsroom.intel.com/editorials/x86-approaching-40-sti...)

Yep, who wants to guess Intel made some key hires of transpilation experts to develop a nice patent arsenal just for this purpose?

The last of the patents preventing x86_64 binary translation expires Q3 this year, expect fun things to happen. (and no, MS isn't sleeping)

Which patent is that? Genuinely curious.

What is different about Rosetta 2 that is keeping Intel from doing this? Genuinely curious about this.

Rosetta 2 is a binary translator, not an emulator. It merely converts x86 instructions to ARM instructions.

For the Microsoft story I think we're also going to need some people actually making desktop worthy ARM chips. Qualcomm upping the power limit on their smartphone chips (as they are doing now) is not going to be enough to make Windows on ARM that attractive if you ask me.

It doesn't help that ARM themselves are not confidently offering any desktop worthy intellectual property, as the smartphone chipmakers are just using ARM's own core designs.

I think Arm is actually starting to release design targeted for performance this year: https://www.anandtech.com/show/15813/arm-cortex-a78-cortex-x...

Yeah that's how ARM markets it, but if you read more carefully it's just a tweaked Cortex A78. A Cortex A78 is an impressive core design, but it's ultimately still a low power design. I'm saying the time is ripe for ARM to make a full fledged desktop focused design from the ground up, and if not ARM then someone else.

Reply on news.ycombinator.com