ARM Server is going to be Big Business
Looks very much like the ARM based server business is going to be a big fast growth business and . ultimately a significant challenge to intel . . .
RISC chip designer ARM Holding has closed out a record Q4 and 2010, and is laying the foundations to expand into desktop PCs and servers through the aggressive and enlightened self-interest of its growing licensee base. In the fourth quarter ended in December, ARM (the company) had £113.9m in total revenues, up 34 per cent. …
Despite all their claims about porting Windows to ARM, you need to do a lot more than that to make the platform viable. They learnt that when NT came in builds that supported Alpha, MIPS, PowerPC etc. It's all well and good to have your OS support a different architecture, but if the applications aren't also ported across then it is completely pointless.
Microsoft will have a hard enough time porting their own multitude of products over let alone all the third party devs. How many years do you think it will be before Exchange, Sharepoint and SQLServer are fully ported and offer a seamless admin experience? Personally, I don't think that it will ever happen. To the extent that they port Windows to ARM I think they will limit themselves to porting their consumer OS only along with a not-quite-fully-compatible port of office in the hope of capturing some of the nascent tablet market. I doubt very much that they will port their server products at all.
Which brings me to wondering what the point of porting even consumer Windows to ARM is?
Oh, I understand it from the PoV of MS, they want to be able to sell tablets and not miss out on all the fun but from the consumer perspective what is the point? The Windows UI is not well designed for a touch screen and one of the main reasons for using Windows cited by all of the fanbois is having access to the "millions and millions of windows applications". Apparently, if you can't run these millions and millions of applications on your tablet then you may as well not bother. This is one of the main reasons that Linux is scoffed at by the Windows crowd.
Well, guess what fanboys, with Windows on ARM you will be *unable* to run those millions and millions of applications as well.
So, if you can't run all your precious Windows apps and the UI kinda sucks for touch then what, I ask you, is the attraction of a Windows tablet?
@"more than 6.1 billion ARM chips were sold in 2010, a 55 per cent unit increase from 2009"
Bloody hell, that's an amazing growth! ... well done ARM! :)
I guess no one told them there was a recession on! :) ... what would these figures have been if the world wasn't still in an economic mess!
I can see ARM in web/disk servers - why do I have to have a XEON sitting there cooking my Server because thats my only choice if I want 8 drive bays or dual gig-e?
Having the 'Server' be a single board the size of a few Sata sockets and a couple of RJ-45s pulling less power than the drives would be nice.
Not convinced by running Windows on it. I can run a web server on ARM with Linux and Apache very well now. If I need W2003 server IIS, SQL-Server and Exchange then I'm probably talking about a fairly heavy machine - so swapping a XEON + 24Gb of ram + all the other junk for a bunch of ARM, 24Gb of Ram and all the other junk doesn't seem to save me much overall.
>Not convinced by running Windows on it. I can run a web server on ARM
>with Linux and Apache very well now. If I need W2003 server IIS,
>SQL-Server and Exchange then I'm probably talking about a fairly heavy machine -
I think that MS have a private, unvoiced calculation that ARM based machines will in due course become heavy enough to do all that kind of thing. Consider that there are currently 2 core multi-GHz ARMs available right now, and plenty of manufactureres talking about quad core 2GHz. That's pretty meaty already. 64bit will come in time, but there's not really as much need for it in the ARM world as there was in the inefficient x86 world. ARM aren't gunning for a single big machine that can run all your IIS, SQL Server, etc. They're aiming for you to be able to have a separete machine for all those services and still come in massively more efficient than a single x86 server running the lot.
Putting consumer Windows on to ARM gives MS a head start on putting Windows server on as well (same kernel, libraries, etc). You really can do Linux and Apache right now on ARM, and all it takes is for some data centre operator to say "We tried it and liked it, look at our much reduced electricity bill" for the whole world to see the light and follow suit. Microsoft can't afford to be left without an offering when that day comes round. And it almost certainly will come round, probably sooner than anyone is really expecting.
MS can't afford to miss this particular bandwagon. As it stands the ARM cart is already moving at quite a lick, kicking up dust, and MS after many years of ignoring the cart's imminent departure are now hanging on to the back desparately trying to climb in where Android, Linux and iOS are already sat. As things stand I think that Google and Apple have made some serious implementation miskates (Google -> anarchy, Apple -> too expensive and restrictive), which does leave MS some room to get a toe hold.
MS didn't really kill the netbook. ARM netbooks currently mean Linux, and despite many improvements Linux does not offer the same complete user experience (drivers, software, etc. Plus Linux is terribly fragmented) that Windows and OSX do. Intel netbooks running Linux don't make sense (why not put an ARM in if you're going to run Linux?), and Intel's Atom is just too power hungry and slow to make the Windows experience worthwhile. MS and Intel do work very closely, but I think that Intel have badly cocked up with Atom and MS are paying a price for their over reliance on them.
The fact that plenty of people are willing and eager to spout anti-Linux FUD to end users means that Microsoft is in the driver's seat here. They can take their sweet time in deploying ARM ports.
The biggest problem for Microsoft is all of that much vaunted "superior" app and device support will EVAPORATE. All of that stuff has to be recompiled and tested by all of the various proprietary vendors. This isn't just about whether or not Microsoft decides to embrace ARM but the entire "ecosystem" that surrounds it.
Linux (fragmented or not) is at much less of a disadvantage in this regard.
I can recompile my favorite apps myself.
"Linux does not offer the same complete user experience (drivers, software)
None of the existing Windows drivers and software will work on Windows for ARM so your point is moot. It will take years for all the 3rd party devs and hardware vendors to get around to porting all their sundry crap over to ARM and even then they won't bother with legacy stuff. And they probably won't even bother starting in the first place unless they are pretty certain that Windows on ARM is going to be a winner and they can see a big market for it.
The irony is that this leaves WinARM in much the same position as Linux. Devs and vendors don't bother developing for it because it doesn't have enough market share and it doesn't gain market share because the "software and drivers" are pretty much non existent.
It happened before when Windows support MIPs and Power et al
Copyright, copyright, ... , copyright.
Might also be a good idea to recruit an IP bloodhound?
If it takes Chipzilla or any one else a year to set up a run line that might be copyright challenged, another year to be identified as IP challenged and another 2 years for the courts to sort it out, well, ARM could be another AMD but with not enough in the bank to defend its IP?
If I might offer a word of advise to ARM based on my own previous experience developing sofrware in a partnership with MS:
- do not allow your relationship with MS to distract your senior management, nor allocate more resources to working with MS than you absolutely have to;
- do allow for the possibility (likelihood) that it may all come to naught, at which point you really dont want to have wasted too much time, attention, or other company resource;
- do not assume there is a wodge of money to be got if you can just handle things right (and that therefore it is worth ignoring the first two points).
"It will take years for all the 3rd party devs and hardware vendors to get around to porting all their sundry crap over to ARM and even then they won't bother with legacy stuff. " .... Goat Jam Posted Tuesday 1st February 2011 23:44 GMT
But whenever ARM provides a porting vehicle/laundering service, is it done in a trice/flash.
"It is a pity that ARM is not moving the quad-core, 40-bit Cortex-A15 to market faster and talking about either 64-bit kickers or how it will manage virtualized 32-bit applications on multi-core ARM servers such that no one cares that they are 32-bit applications. It is very expensive to virtualize six-core Xeon servers with VMware hypervisors, and the server industry is spoiling for a clever alternative.
A slew of startup companies are spoiling to get into the ARM server racket, too, because of the cost and power issues with x64-based chips and their hypervisors. And there is a tidal wave of companies making ARM-based smartphones and tablets. As 2010 came to an end, ARM had 743 licensees, up 35 during the fourth quarter."
Timothy, Loose lips sink ships. All the best captains with cargo holds bursting with booty keep their plans and routes to ports/treasury vaults to themselves. IP theft is a multi-trillion $ industry, with every man and his dog and bespoke suited parasite phishing for a free lunch/ride. And a slew of startup companies are NOT spoiling to get into the ARM server racket, too, because of the cost and power issues with x64-based chips and their hypervisors. Oh No. They are spoiling to get into the ARM server racket, too, because of the phenomenal returns and controlling powers which great chip architectures guarantee and deliver on issues/programs/projects with x64-based chips and their hypervisors.
ARM are in the Head Space Great Game and the Secret of Fab Success in those IP Fields is to Groom Leadership Applications to recognise Prime Source Supply which Complements to Improve Sub-Prime Base Operating Systems. And that is a Priceless Methodology and Truly SMART Algorithm which you can waste countless fortunes on trying to discover, only to discover that it is FailSafe Protected and requires only Virtual Royalty Payments to Access All Benefits.
How Clear and Far is an Immaculate See? Does it have IT with Higher Definition Definite Vision ..... NEUKlearer HyperRadioProActive IT? Or does it fall well short of Fitness for Future Purpose Requirements/Default Needs and Feeds with Sourcing Seeds?
Welcome the new BOSS, and definitely not the same as the old FOSS. And that is in AI Circles, a Beta Operating System System for Front Office Shared Services with Free Originating Source Software ....... a Closed Proprietary Unit for Intellectual Property Protection of Novel AIdDriver Power Communications and Allied Quantum Control Systems.
Ok, I wasn't going to post any board messages today, by I forced myself to read all the way through your post looking for a greater sign of it being English other than the occasional non-English buzzword thrown in.
As an example that Goat Jam was right, go ahead and download the Adobe Photoshop or Premier versions for Linux. They are developed using Qt and can be ported by a skeleton crew in weeks. Yet, there is none.
Get a 64-bit Windows version of a browser. I know they exist in mythical worlds somewhere, but it looks like IE is the only one readily available. Porting a browser to 64-bit is easy. I ported Opera to SGI IRIX 64-bit 10 years ago and Sun Solaris the following day. I don't know if we ever released them. There just was no market for them.
I wrote drivers for HP printers, charges $5 for them and sold several hundred copies of them 8 years ago. If I could find my old mac that had the source code, then I could port them for 64-bit support, but I won't bother. People using this printers are using old macs too.
Fact is, many programs that I've written take far less time and effort to port to Windows for ARM than reading your response which I think was generated by a buzz-word randomizer. Yet, I won't bother since there will likely not be a market case for it.
Windows for ARM is primarily interesting in the tablet space. Meaning, not the utility space. It's a great iPad competitor and I'm really looking forward to getting my hands on it, but for big iron, I think that x86, Sparc, HP, IBM etc... will hold on to that market for a while longer.
The one thing I haven't heard anyone mention is the availability of a compiler for ARM for Windows. Microsoft will release their standard Visual C++ compiler tool, GCC will probably generate for Cygwin and mingw, but in the end, there's no PGI, Intel, etc... compilers for the platform planned that I've heard about.
Without high end compiler tools, the quality of the software will suffer drastically. ARM will have to be twice as fast per clock to compete with Intel. Sure, someday this might happen, but it's probably not any time soon. Intel took 10 years to make their compiler as good as it is. ARM has been working on their half baked compiler forever and it's still crap. The code it generates is so poor, they should be ashamed of themselves. GCC is much better.
Don't get all excited about things it appears you simply don't understand. Don't pretend to think you understand engineering well enough to speculate on things like how many apps will be ported just because you can. Also, don't forget that it would require that companies buy large numbers of developer grade systems to cover the porting process, the testing process, the sales process, etc... It would mean an investment probably of two machines to every one.
A good market now would be dual processor laptops, one high end Intel x86 and one high end ARM so a single computer can be use for developing, testing and selling both platforms.
....... they become ever more difficult, and eventually, inevitably impossible and/or too time consuming/slow. Ergo KISS Rules Rule.
"Fact is, many programs that I've written take far less time and effort to port to Windows for ARM than reading your response which I think was generated by a buzz-word randomizer." ..... CheesyTheClown Posted Wednesday 2nd February 2011 14:54 GMT
What??? You think the response was generated by a buzz-word randomizer? What is that? A machine?
You cannot be serious, CheesyTheClown, for that would be revolutionary, and give ARM an advantage which would deliver them ...... well, AIMastery of the Universe is only a Beginning.
"The one thing I haven't heard anyone mention is the availability of a compiler for ARM for Windows." ...... Well, of course not, it is a MkUltraSensitive Internal SkunkWork ..... a Hush, Hush, Softly Softly Catchee Money Keys Operation. And as much a driver as a compiler would it be too.
"Don't get all excited about things it appears you simply don't understand. Don't pretend to think you understand engineering well enough to speculate on things like how many apps will be ported just because you can. Also, don't forget that it would require that companies buy large numbers of developer grade systems to cover the porting process, the testing process, the sales process, etc... It would mean an investment probably of two machines to every one." .... No, it doesn't. It simply requires a SMARTer Programmer to write a Captivating Novel Virtual Reality Application that renders Virtual Machinery in Universal Command of Human Control. It is no more difficult than that.
It's easy to be wise after the event, but your warning is timely.
The short version is "Microsoft: business partner = organ donor".
"the point of porting even consumer Windows to ARM is?"
Good question. As far as I can tell, the point is it leads to one single compatible platform standard. ARM systems that meet this standard are capable of running Windows/ARM. Today, because of the history of the vast variety of ARM systems, there is no single compatible platform standard. Of course, any such single platform standard benefits Linux/ARM just as much, if not more, than it benefits MS because there's already plenty of Linux/ARM around, but at the box level rather than chip level, it's not always easy to find a Linux/ARM config for your particular box. Once you know the box is Windows/ARM compatible, you also know it should be Linux/ARM ready.
Or something like that.
After all, having a standard for hardware platform compatibility worked so well for the Advanced RISC Computing folks (Alpha, MIPS, PowerPC), didn't it?
These volumes of hefty, multiple hundreds of MHz ARM cores are paltry compared to the 7TDMI you find in pretty much every WiFi or Bluetooth radio. Even lowly SD cards sport an ARM where it's a throw-away item which runs the BIST once and forever after just manages the SD interface. The ARM instruction set has become what Intel's 8051 was, ubiquitous.
I think it was probably Win3.1 - ran about the same speed under emulation as on the Intel chips of the time. Had MS jumped in then think how fast their o/s would have run without the need for an emulator! Problem was the US "not invented here" syndrome.
If nothing else the MS announcement is a recognition of the importance of ARM and an MS endorsement of the technology.
I regret not buying a load of shares when they fell to a few pence -my HSBC private banking advisor told me "it was uneconomic to hold on to my existing holding" and advised selling it. Luckily I disagreed (and ditched HSBC, they had no clue about investment, managed to consistently lose value in a rising market).
Anyway, 2010 sales: not far short of one ARM chip for everyone on the planet!
My memory is hazy as it was a long time since I was in high school where we had one of these machines set up in a locked cupboard due to the vast expense incurred procuring it, but I can faintly recall a 486 co-processor on a daughter card therein which I believe was there solely to execute the MS binaries. In other words it was a bastard offspring and there wasn't actually any emulation going on.
As an ARM shareholder, I have to say, I'm delighted.
As a software engineer, I have to say, I'm... delighted.
Regarding MS core software products, such as office, SQL Server, Exchange et al, expect them to be increasingly based on .Net technology in the future. Writing them in .Net is the obvious answer, as the same physical binary will run on an Intel desktop machine, or an ARM desktop machine, with only the .NET CLR being targeted to the host platform. That's what VMs are *for*.
Third party application developers will also find .Net more attractive as it means one codebase for two platforms.
I expect both Intel and ARM Windows platforms to converge around .Net over the coming years.
Long may it continue!
Biting the hand that feeds IT © 1998–2022