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

Windows 10 on ARM

channel9.msdn.com

Post reply on HN
Print view View original

221–230 of 290 posts

Re: Windows 10 on ARM

#221

Post by qb45 »

pranith wrote: post #174
wolfgke wrote: post #43

Earlier quoted context omitted.

5. How do they solve the problem that x86 has a much stronger memory model than ARM, which makes emulation of multithreaded x86 code pretty hard without introducing a huge performance disadvantage?

Since there are no publicly available details, I would guess this is solved in hardware. The Qualcomm processor can be made to support stronger memory model for translated instructions similar to how the Power processors support strong-access ordering for efficient x86 emulation[1]. [1] https://www.google.com/patents/WO2012101538A1?cl=en

https://news.ycombinator.com/item?id=14319420

Not sure where MikusR gets this info from, but it could be right given that Snapdragon 820 is Qualcomm's custom core.

Re: Windows 10 on ARM

#222

Post by vardump »

wfunction wrote: post #178
valarauca1 wrote: post #172

Earlier quoted context omitted.

Sky lakes OoO window is 224 instructions. With up to 96 in scheduler. 72 loads, and 56 writes. Link: (summery you find hard intel references internally) https://en.wikichip.org/wiki/intel/microarchitectures/skylak... 224 per core. We're talking concurrency. So a 10core, 20HT server class can have 2240 instructions in flight.

Admittedly more than I expected, and thanks for sharing, but "20 CPUs executing a peak of 224 instructions each" is a far cry from "modern processors execute THOUSANDS of instructions AHEAD". It's neither "thousands" of instructions in flight for a single processor, nor is it thousands "ahead" for multiple processors, let alone both. It's like taking 4000 basic single-stage CPUs and claiming they execute thousands of…

Agreed, saying thousands was hyperbole. You do have a point. When talking about instruction windows, one should talk only about one core at a time.

Although the idea of "lots of instructions in flight" was right. From programmers' point of view there's no difference between out-of-order windows of tens, hundreds or thousands. One just needs to be prepared that CPU can and will reorder things within limits of the defined memory model. Which does not define limits for out-of-order window size.

Re: Windows 10 on ARM

#223

Post by Wildgoose »

MrMember wrote: post #64
wand3r wrote: post #37

Earlier quoted context omitted.

I think I get it; but could you expand a bit on what you mean?

A phone form factor device that can run a full desktop OS, or something close to it. Canonical was getting close with Ubuntu Touch but that's essentially dead now. I don't want a gimped version of Windows like I'd get with Continuum, I don't want a "desktop-like" version of Android like Samsung is doing, I want a full version of Linux or Windows that can run desktop applications.

You may be interested in the Gemini PDA (which I've funded on IndieGoGo) which provides an Android/Linux PDA.

https://www.indiegogo.com/projects/gemini-pda-android-linux-...

Re: Windows 10 on ARM

#224

Post by adrianN »

flukus wrote: post #218
bitmapbrother wrote: post #205

Earlier quoted context omitted.

So Linux users should get the shaft because they're the minority? Android Studio and the emulator work very well on all 3 platforms. >Trying to be identical across 3 platforms always means adopting the lowest common denominator and always results in being equally shit on every platform. In that case we're fortunate that Xcode isn't cross platform.

> So Linux users should get the shaft because they're the minority? Linux users should get the best possible experience on the system, so should the windows users. If a better emulator is available on windows why should they get shafted? Linux tools even have the advantage that they may not need full emulation in the first place, but instead we end up with the worst of both worlds. > Android Studio and the emulator w…

So you could spend three times as much money and design completely different products for each platform, or you could have one codebase with a limited number of special cases for the different platforms and invest the saved money into making a better product...

Re: Windows 10 on ARM

#225

Post by wmu »

drewg123 wrote: post #175

I'm surprised that nobody has mentioned FX!32. That was the binary translation layer that Windows NT on DEC Alpha used back in 1996 or so to run x86 Windows binaries. There is an old Digital Technical Journal article about it here: http://www.hpl.hp.com/hpjournal/dtj/vol9num1/vol9num1art1.pd... Everything old is new again!

AFAIR they had a kind of profile-based optimization. It was amazing.

Re: Windows 10 on ARM

#226

Post by skc »

chrisper wrote: post #88
wand3r wrote: post #35

I am seriously impressed with Microsoft. I haven't used windows in years but they are releasing tons of useful things. VSCode is great on Ubuntu and every version of OS X I have run it on. Plus tons of other cool things like bash on win; etc. Also, I have a bizspark Azure subscription and it's not a perfect UX; but man does it beat AWS

Whenever I tried to use Azure, it was soooo slow. Is it better now?

The dashboard is still very slow.

But all in all, the technical offering is pretty good and easy to be productive in.

Re: Windows 10 on ARM

#227

Post by adrianN »

fnord123 wrote: post #125

They are doing this because they want the benefits of great ARM battery life. But they are emulating x86 on ARM. So they believe that emulated x86 on ARM will have a better battery life than native x86. The only way I think this could be possible is if they measure battery life of an idle device. Maybe someone can disabuse me of this belief.

Most computers are idle most of the time.

Re: Windows 10 on ARM

#228

Post by wolfgke »

pranith wrote: post #174
wolfgke wrote: post #43

Earlier quoted context omitted.

5. How do they solve the problem that x86 has a much stronger memory model than ARM, which makes emulation of multithreaded x86 code pretty hard without introducing a huge performance disadvantage?

Since there are no publicly available details, I would guess this is solved in hardware. The Qualcomm processor can be made to support stronger memory model for translated instructions similar to how the Power processors support strong-access ordering for efficient x86 emulation[1]. [1] https://www.google.com/patents/WO2012101538A1?cl=en

While I consider this explanation as interesting and plausible, it is a patent by IBM and not by Qualcomm (there can still license agreements negotiated etc.).

Re: Windows 10 on ARM

#229

Post by flukus »

adrianN wrote: post #224
flukus wrote: post #218

Earlier quoted context omitted.

> So Linux users should get the shaft because they're the minority? Linux users should get the best possible experience on the system, so should the windows users. If a better emulator is available on windows why should they get shafted? Linux tools even have the advantage that they may not need full emulation in the first place, but instead we end up with the worst of both worlds. > Android Studio and the emulator w…

So you could spend three times as much money and design completely different products for each platform, or you could have one codebase with a limited number of special cases for the different platforms and invest the saved money into making a better product...

How did you calculate 3 times as much? No one said nothing can be shared across platforms.

And again, we've got 3 decades of evidence that show precious few good cross platform solutions, so investing the saved money into making a better product doesn't seem to work.

Post reply on HN