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

A preview of x64 emulation on Windows for ARM

blogs.windows.com

Post reply on HN
Print view View original

51–60 of 418 posts

Re: A preview of x64 emulation on Windows for ARM

#51

Post by emilsedgh »

vbezhenar wrote: post #11
emilsedgh wrote: post #7

I'm wondering what's happening at Microsoft's camp regarding M1. They are in a weird situation. They depend on AMD/Intel to deliver. This is a massive dependency for Microsoft. Are there other large corporations have this big of a dependency? I understand that Microsoft's revenue is shifting towards cloud, services, etc. But I think Windows is still "the" key to a lot of those offerings. Take a massive chunk of marke…

I don't understand why do they need on AMD/Intel to deliver? Their ARM build is an insurance against this dependency.

Only if other ARM vendors can keep competing with Apple.

Re: A preview of x64 emulation on Windows for ARM

#52

Post by pjmlp »

MayeulC wrote: post #40
vaylian wrote: post #31

Earlier quoted context omitted.

I think that's one of the reasons why they created the .NET framework: To be able to create a new "virtual" plattform that can be ported to other environments. There is a lot of C# software out there that should run on ARM without any issues with a .NET runtime.

That was also the raison d'être of the Unified Windows Platform apps: to stop depending on Win32 APIs, which are tied to the system architecture. Not a bad goal IMO. I wish we'd see more architecture-neutral binaries, based on LLVM or webassembly. Of course, Plan 9/Inferno had it before others: https://en.wikipedia.org/wiki/Limbo_(programming_language)#V... (By virtue of being designed as a distributed OS, targeting…

Mainframes, Xerox Parc, ETHZ workstations and UCSD Pascal had it before others.

Re: A preview of x64 emulation on Windows for ARM

#53

Post by rasz »

Dylan16807 wrote: post #34
scoopertrooper wrote: post #15

Earlier quoted context omitted.

While that's true, Intel has steadily extended x86 over the years and many programs depend on those extensions, which are still patent protected.

How many programs depend on SSE3 or later? Any earlier extensions are free now.

Games, pretty much all of the AAA ones. ~10 years ago you would read cries of AMD x64 users not able to play SSE3 games. 2-5 years ago situation was repeating with AMD Phenom I/II owners and SSSE3/SSE4.

Re: A preview of x64 emulation on Windows for ARM

#54

Post by emilsedgh »

pjmlp wrote: post #49
emilsedgh wrote: post #7

I'm wondering what's happening at Microsoft's camp regarding M1. They are in a weird situation. They depend on AMD/Intel to deliver. This is a massive dependency for Microsoft. Are there other large corporations have this big of a dependency? I understand that Microsoft's revenue is shifting towards cloud, services, etc. But I think Windows is still "the" key to a lot of those offerings. Take a massive chunk of marke…

Only on HN bubble does it matter. Apple devices are out of budget for most countries, and they only own 10% of the worldwide market share in computing. Outside desktop, Android owns the mobile market. Really, it is just US analysts going crazy with M1.

M1 can accelerate the shift of home users to Macs.

Microsoft devices are already out-fashioned by apple. The Windows UX is also subpar comparing to Apple. Now the hardware is also gonna completely fall behind.

If all the young people get mac's for their home computers, will the next generations use Windows at workplace?

Im talking about 10-20 years landscape for Windows and Office.

Re: A preview of x64 emulation on Windows for ARM

#56

Post by andy_ppp »

kalleboo wrote: post #35
scoopertrooper wrote: post #15

Earlier quoted context omitted.

While that's true, Intel has steadily extended x86 over the years and many programs depend on those extensions, which are still patent protected.

Rosetta 2 doesn't support the SIMD extensions AVX (2011) and newer, but compatibility still seems pretty good

This is because very little uses AVX instructions, hasn't it always been better to optimise software for the GPU rather than AVX instructions, even though they are not perfectly interchangeable.

Re: A preview of x64 emulation on Windows for ARM

#57

Post by cesarb »

simfoo wrote: post #5

What happened to the patent issues surrounding x86 emulation? For example I remember reading this: https://arstechnica.com/information-technology/2017/06/intel... First Apple and now Microsoft. Do they license the patents from Intel or did they expire? Or are they working around that somehow?

According to Wikipedia (https://en.wikipedia.org/wiki/X86-64#History), AMD's x86-64 was announced in 1999 and the full specification was released in 2000. Assuming patents last for 20 years, they should have all expired by now. For SIMD, this includes everything up to SSE2; most software which uses any of the newer SIMD extensions should have a fallback to SSE2, since older CPUs don't have these newer extensions.

Re: A preview of x64 emulation on Windows for ARM

#58

Post by oblio »

AmericanChopper wrote: post #42
oblio wrote: post #19

Earlier quoted context omitted.

Totally agreed. I'd also want to add something for this: > Businesses above a certain size overwhelmingly use pcs unless they are in specific arty sectors. M1 won't change that, or at least not rapidly. Besides the fact, which many HN users working for FAANGS or startups don't encounter, that big enterprises are both rigid and also quite locked into the Microsoft/Windows/Office mono culture, big companies tend to hav…

I’ve contracted in lots of large enterprise, and software engineers who prefer (and are provisioned) Macs are everywhere. I’ve even seen a number of .NET teams who bootcamp with them. I’m contracting in a reasonably large bank right now, and most of the people in my office use MacBooks. It’s true that large enterprise is slow and cumbersome. But they really don’t care too much if they’re buying you a MacBook, or a su…

Yeah, but check out large enterprises where software engineers are not the norm, common, or some times, not even present at all :-)

Re: A preview of x64 emulation on Windows for ARM

#59

Post by rusticpenn »

lars-b2018 wrote: post #41

I think the bigger story here is that computing based on ARM64 has been, and continues to, surround the traditional x86-64 territory. ARM dominates phones, and is popping up in server environments as well, where it is cheaper to run for many workloads than X86-64. We have migrated to ARM based Gravitron processors to deliver our services at my company, and we have been able to reduce our AWS EC2 costs by 40% or so, w…

I do not understand why ARM is considered lesser technology. RISC was always considered to be better then CISC in many academic circles.

Re: A preview of x64 emulation on Windows for ARM

#60

Post by opsunit »

pjmlp wrote: post #52
MayeulC wrote: post #40

Earlier quoted context omitted.

That was also the raison d'être of the Unified Windows Platform apps: to stop depending on Win32 APIs, which are tied to the system architecture. Not a bad goal IMO. I wish we'd see more architecture-neutral binaries, based on LLVM or webassembly. Of course, Plan 9/Inferno had it before others: https://en.wikipedia.org/wiki/Limbo_(programming_language)#V... (By virtue of being designed as a distributed OS, targeting…

Mainframes, Xerox Parc, ETHZ workstations and UCSD Pascal had it before others.

I've worked on zSeries machines running S/360 binaries from the early 70s. It is one of the primary reasons banking and related sectors that are heavily regulated stick with such platforms for core accounting.

The single whole-bank migration I was involved with was zSeries to zSeries.

This is where the challenger banks really have an advantage. They're not saddled with the baggage of an overnight batch run of JCL decks and Data Sets to arrive at what their regulators consider the reconciled position of the bank.

Post reply on HN