Slashdot Mirror
Are We Not Ready For 64-Bit?
Q3vi1 writes "The Inquirer posted an intriguing article about how Intel doesn't think that we'll be ready for mainstream 64-bit computing until 2007. Coupled with the fact that MS isn't supporting the Opteron yet for their Windows 2003 Server, we may see a delay in consumer applications for 64-bit computing. However, as this article states, some people don't really care and will just go for Linux and AMD as a nice marriage."
Microsoft says "No" and Intel runs away, crying.
Even Intel is at the whim of the Microsoft Monopoly(tm).
Doing the Right Thing should not be preempted by making a buck.
Apple will come out with a 64-bit OS X sometime in the next year (with the 970). Critics will say "Wow!", and then ignore it. Apple sales won't change a bit and three years later MS will come out with 64-bit computing to universal acclaim and the market will buy it like hotcakes...
while stocks last!
[your statutory rights are not affected, not compatable with other offers]
99.9% of the population do not use the currently level of computing power available. As a consultant I get the question all the time "Do I need to upgrade to a faster machine" when all the person is doing is a little word processing and surfing the net.
they're counting on $3000 IA-64 chips to preserve their profit margin, but if 64 bit catches on in the mainstream, they're going to have to follow AMD with x86-64 at much lower margins.
Microsoft says "No" on the "standard edition" release and Intel runs away, boo hoo.
Hopefully we'll see the matured Linux on AMD x86-64 code ready on the hardware release. The simulator's been out for a while, and the port is active.
Doing the Right Thing should not be preempted by making a buck.
I could fit "you suck" or something equally insightful into one processor word. Other than that, I don't care. Do you?
I think the problem is that if microsoft don't adopt opteron then AMD will not get the volumes needed to substantially undercut the price of itanium - if it isn't highly price/performance competitive with intel/sparc then your average linux shops simply won't adopt it.
.
:^)
So once again microsoft have the power to crush a fantastic new technology before it even gets off the ground
like a weight looming overhead - have to say i know that feeling
Before adopting WHATWG, read the moonlight.NET EULA [http://www.microsoft.com/interop/msnovellcollab/moonlight.mspx]
take off every sig for great justice
What to tell the pointy-haired boss:
Linux finally has a feature M$ Windows doesn't have, 64 bit support! It's why we need to switch all our servers to Linux!
Overrated Moderation: This posts sucks... because.
Here's something in German that you might want to run through: http://www.heise.de/ct/03/07/026/
:-)
Yes, go translate it, unless you can read and understand German, or just don't care to read it.
4th paragraph under what babelfish translates as "Imbedding"
"Nevertheless one will not only be able to select to the planned Launch between different 64-Bit-Linuxen. Microsoft announced in the meantime, one day before the planned launching of a vessel, thus on 21 April to bring the Windows-XP-Server-2003-Version out for AMDs 64-Bit-Prozessor officially."
Looks like the story is still up in the air...
fair.org counterpunch.com truthout.com indymedia.org salon.com
eff.org guerrilla.net debian.org gentoo.org
Just yesterday a few people suggested on apple.slashdot.org that the next release of OS X, code named 'Panther', may include 64-bit support. Apple may think we're ready.
But do we need it? Will the benefits outweigh the cost. I think Apple's offloading of CPU tasks to the graphics board for Quartz Extreme is an example of just one of the alternatives for speeding up machines. Offload more tasks to other intelligent subsystems.
I am ready, since when the 64-bit machines come out I can pick up a 32-bit on the cheap!
My user name was a mistake. Input wasn't restricted, my bad.
I'd be interested to know how many operations on today's computers actually even use up all 32 bits available to them. I'd expect those situations to be rare: Matrix math operations, some addressing.
64 bit computing might speed up your data processing if you are a scientist, but it would probably slow down business applications.
In general, scientists that need high processing speeds can buy supercomputer time, or extra 32 bit machines. Why would we want to move to 64 bit on the desktop?
"4GB addressable memory ought to be enough for everyone."
The last time we ran this story, Intel said they were "in no hurry". So I'm not surprised they haven't changed their mind exactly one month later ;-)
If this current situation shows anything, it is what happens to companies when they make deals with Microsoft. AMD's Chairman and former CEO Jerry Sanders agreed to testify on Bill G's behalf for the antitrust trial as long as MS ported windows to Opteron and Athlon 64.
With a switch to 64-bit, I could put *timestamps* on *every* item of data my current 32-bit programs use.
This'd be nice. Every var has its own timestamp.
If you don't know why that's cool, or why that would be cool to someone like me, well
; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
As Apple has always been forward thinking to gain market share and attention, I think this will be yet another rush of sales for them, especially if Intel offerings start to have DRM built into the chips and continue to stretch processor pipelines to absurd stage numbers >20.
Yell & scream & rant & rave... it's no use... you need a shaaaave ~ Bugs Bunny
I dont think home users make a good example of users. I consult primarily with engineering, architectural and graphics firms. Programs like AutoCAD, Revit, 3DStudio, Photoshop and a bunch of number crunching engineering apps i've never heard of. All of which are dying to use 64 bit systems. not only that more and more applications are using a more complex and demanding UI. Have you used word or excell lately ?
I just hope AMD realises that the platform should belong to the owner and keep Opteron/Athlon64 free of TCPA. This together with a Palladium free Linux would be the major reason for me to leave the comfort of the Wintel platform.
But I fear if AMD state they are remaining TCPA free they've got no chance of seeing a Palladium enabled Windows 200x on Opteron/Athlon64 - goodbye mass(ive) market.
$2B OR NOT $2B = $FF
95% of endusers wouldn't even notice any difference. How could they be "not ready"?
Seems to me Intel is just trying to conceal their own develppment problems.
Is this Apple's chance to catch up to wintel's speeds?
I've got two 64-bit machines at home, myself - an SGI Indigo2 and a DEC AlphaStation 200. Yeah, they're seriously out of date now, but they're still nice little workstations. *nix has been doing just fine on 64 bits for some time now. I do have to put up with all sorts of 'cast to pointer from integer of different size' warnings when I compile stuff, but I'm able to run 99% of the stuff I'd run on an x86 box on the Alpha.
Microsoft and Intel think we're not ready for 64 bit systems eh? I bet they think we still are doing just fine with that 640 K RAM. :)
You know it makes sense, a little reminder from jointm1k.
Its really nice to break the two-gig barrier in program buffers. Sun-SPARC and SGI-MIPS have been 64-bit since 1994.
ready for 64!
Finally a chance for Linux gaming to get a one up
on windoze games.
Screw windoze users, release the chips, take the
loss for the first year and then clean up for the
next 3 when Linux gaming explodes on the market.
What's the delay?
Let's go already!!!!
I wanted to find some more information myself about Linux supporting 64-bit processors and this is what I found. Mandrake will have support by early 2003, I'm not sure if it's done now or not but it should be nearly done. Redhat is also offering support for the X86-64, check out the news release. Personally I think this is a great oppertunity for Linux to catch up to MS in market share. I look forward to upgrading...
"I believe in everything in moderation. Including moderation." -Dean DeLeo, Stone Temple Pilots
Clearly, there's no significant need for 64-bit x86-compatible processors, because they've been available for purchase now for several years.
Can you please explain to those of us who clearly don't know any better why certain PC applications are "dying" for 64-bit processors? Hint: they won't magically become faster.
- A.P.
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
As I have been MS free since 2000, I really couldn't care less what they do or don't do. As for Intel, here's some news for them, they DO NOT have a monopoly like their special friend. I'll gladly purchase an AMD Opteron to run my shiny new Linux 2.6 kernel sometime this fall while the WinTel boys play their reindeer games. In fact, dare I say it, I'm GLAD this is happening. Hopefully, this will finally show Intel that their future is not tied to MS as it was in the past.
Good people do not need laws to tell them to act responsibly, while bad people will find a way around the laws-Plato
I am ready for 64 bit. I have been ready for a long time. And I want it now. Not for my desktop, though. I'm not sure why 64 bit would be really helpful there. I'm still using an ancient PIII as a workstation, and it's more than I need for Linux to run happily.
No, I need 64 bit for a server application that requires more than 4GB VM addressibility (or with Linux, more like 2 GB, which is about all you really get for user space apps w/o some major hacking). Until now, you had to buy expensive Sparc hardware and run Solaris, or the like. No cheap, open consumer hardware (i.e. PC) was available until now. But now that it's available, I can get what I need w/o having to pay disgustingly expensive prices for computers that aren't even as fast as a PC at 1/4 the cost.
Oh yes, I'm ready for 64 bit.
32bit 386 was launched in 1985, 32bit was Windows 95 launched in 1995. However, this didn't slow the sales of 386.
64bit won't be any different. You don't need 64bit to run a browser or a word processor, however 64bit will be useful for high-end PCs pretty soon. Epic is already working on 64bit port of UT2003, and many 3D applications use a lot of memory.
Do I need 64 bits? No.
Do I want competition to the Xeon in 4 way systems? (price and spec them, it is insane! 1.6 Ghz and 1200 a pop). Hell^yeah.
Opteron is not about 64 bits, it is just a nice addition. Opteron is about competition in the low end server/high end desktop market (which is intel dominated btw). The reaosn intel is naysaying 64 bits is because they have no competing thec in this area other than the Xeon which has terrible price/performance numbers.
There is nothing wrong with being gay. It's getting caught where the trouble lies.
If they're cheap enough, 64bit will help gaming in a big way. The counter-strike team reported a ~30% increase in performance just by recompiling. Granted CS doesn't need a cray to run, but Battlefield 1942 has had some 64 player servers which I believe needed dual Athlons. 64 people is fun, but how bout 128?
Not only that, but with an (relatively)inexpensive 64bit chip out there I could see more servers popping up to play on. More servers hosting large games would be great! Feed my addiction please.
-- taking over the world, we are.
The Opteron will still run x86 code fine so a install that will work on any x86 system will still work on the Opteron (although wasting the 64bit capability).
Although there is a reason it's called Wintel.
If you don't know why that's cool, or why that would be cool to someone like me, well ...
God you're a tool...
Your view of 'when are we ready for 64-bits' largely depends A) on how much money you are willing to spend on RAM and B) how soon your OS supports more than 4 GB of RAM on potential 64-bit hardware (PAE hacks notwithstanding).
If you're willing to spend $200 for RAM in your system, then when 4 GB of RAM is cheaper than $200, you'll basically be wanting a 64-bit system (PAE hacks notwithstanding).
With pricewatch.com showing 1 GB of PC133 SDRAM going for as little as $120, I'd guess that another 4x drop in RAM prices would lead to substantial consumer demand for 64-bit hardware.** And that doesn't even include the demand for 4+GB RAM now in database applications. Whatever the case, this would seem to be earlier than 2007. Unless Microsoft doesn't get its act together (they were pretty late with 32-bit 386 support, IIRC)... which wouldn't be such a bad thing, for Linux at least. But I wouldn't count on that.
--LP
** Yes yes, technically you probably need to spend a bit more to get higher density RAM so that you can fill or exceed 4 GB given the limited number of memory slots available in your system.
Just sticking an extra 32 lines on the address bus isn't going to work. You need to be able to actually address all that extra memory above 4Gb, and how will you do that if your registers and instructions expect to be using 32bit values? So you do have to make changes to both the memory adressing and the ALU. If you're going to do that, you may as well go the whole hog and with 64bit general registers and new opcodes to take advantage of your new found high 32bits.
i understand return on investment. but the industry is moving to 64 bit. weather it's intel, amd, or some other cpu chip maker is not the issue, it's who is going to lead the market is the issue
imagine how web pages could look like if there was access to 64 bit processors. we could start to finally have 3D shopping sites. we could see explosions of the product. applications of the product, and even comparisons. consider this argument: "the ability to create products, simulate performance, apply the product to all known laws..", ( hmmm, i think i've got a new patent concept here...).
Then apply known marketing models to see if people would even buy the item. Uppppps, that spaming. Never mind...
...the RIAA and MPAA have issued a joint statement that consumers are not ready for the power of file-sharing networks, and should be content with CDs and DVDs for the foreseeable future.
Seen any BadMarketing lately?
The 64 bit chips are really needed on servers and workstations. Not on the average desktop. On servers and workstations windows support is nice but not required Unix/Linux support is good enought. If the become popular then Microsoft will support it.
Told us that we weren't ready for the internet, and didn't have a need for fiber optic cable either.
Intel doesn't think that we'll be ready for mainstream 64-bit computing until 2007
I think this is Intel's subtle way of saying that they won't be ready for mainstream 64-bit computing until 2007.
Multimedia editing is a desktop app that can make good use of 64 bits. It isn't uncommon to to have uncompressed DV captures 17GB in size. Add effects and a few edits and the address space of a 32-bit machine can start to hurt in a hurry. The end result will have to be compressed as well. Yes there are ways to cope with it but it re-introduces the segment offset nightmares of old school x86 programming. Also memory sizes on end user desktops are increasing. Anything more than 2GB on an x86 box starts getting painful. Yes, I know they can `technically' handle 4GB but kludgery starts setting in at 2GB.
"Mom" is starting to use this "PC Thingy" to make home movies. I see "Mom" needing 64 bits before long.
64 bit server computing has been around for at least a decade. I was using a 64 bit DEC alpha
box back in 1994. Why is it that whenever middle aged or even old technology appears on in the PC
world its suddenly a Big Deal? I realise that Joe Sixpack won't have ever heard of 64bit (or probably even be able to spell it)
but surely the more technologically savvy types who read this site should know better?
Now what were you saying again?
It may be easier for a person who only knows MS but to anyone who knows unix (as I admin both), SSH is preferable to Terminal Services (PC Anywhere or whatever). And if you really need a GUI then tunnel VNC.
Unix tools kick the living shit out of Windows tools. That is why Unix is king on the server side.
Well, fairly simple. Many applications are married to Windows. In a typical small firm it is wise to use all the same apps. Doesnt' make sence to have your graphic guys on OSX, your engineers on UNIX (yea i know OSX is unix) and your cad guys on MS. MS is really the only unifying OS. Prior you could use ALPHA processours but MS no longer supports that. So what do we do now.
Can you please explain to those of us who clearly don't know any better why certain PC applications are "dying" for 64-bit processors? Hint: they won't magically become faster.
Addressable memory. Right now the limit is 4GB. With Windows XP, the OS sets 2GB aside for the OS, so apps only get 2GB, and that's shared across all the apps.
For word processing and surfing the net as it currently is now, none of this matters.
But if you want rich multimedia content, the ability to do serious 3D imaging on the fly (think 3D operating systems) and the like, you're going to need more RAM. The only way to get that is with a 64-bit chip.
The AutoCAD and 3D Studio and Photoshop apps the parent poster mentioned *are* dying for more RAM. I have 3D models that are pushing that 2GB limit.
My journal has hot
Nintendo moved away from 64-bit (Nintendo 64) back to 32-bit (Gamecube, Gameboy Advance) and Atari's 64-bit Jaguar failed in the market. This is what they're probably basing their predictions on. /joke
Seriously though, I don't think that the move towards a 64-bit desktop needs to happen tomorrow but it is going to be soon. When Apple starts showing systems with >4GB RAM, graphic designers will flock to them... wait, never mind.
Clearly, there's no significant need for 64-bit x86-compatible processors, because they've been available for purchase now for several years.
64-bit processors has been available for a few years, but none of them were x86-compatible. AMD is the first company trying to make such a processor. This might be what it takes to get 64-bit processors to a large number of users. I sincerely hope so, because we need 64-bit processors and has actually been needing them for a few years already, we want no more workarounds because of an insufficient architecture. If I cannot mmap my harddisk, my address space is too small.
Do you care about the security of your wireless mouse?
Intel has plenty of problems on their own!
What they really mean to say is that we won't be ready for the Itanium, even well after 2007!!!
Encryption.
.. I want more than 4 gigs of texture maps in my games .. thanks.
In the future I hope all email and even web traffic is encrypted. That's mainly why I want faster cpu's and/or 64 bit computing.
hopefully 64 bit chips will do encryption much faster than todays chips.
Second biggest reason? GAMES
2GB, and that's shared across all the apps.
:-)
Linux can do better than that. In Linux you get 3GB per process.
Do you care about the security of your wireless mouse?
They're trying to sound geeky but failing. Everyone knows that 'x == true' is better stated as just 'x'. Couldn't they have just written it in English?
-- Ed Avis ed@membled.com
Apple has yet to announce whether or not they'll use IBM's chip, but (John Dvorak's unusual beliefs notwithstanding) it's a relatively safe bet they probably will.
Get off my virtual lawn, you damned virtual kids!
Yeah, but we'll see just how long Microsoft ignores Opteron when everyone starts buying low-cost servers based on Linux and Opteron. They will have no choice but to adopt it. Even then, it will be growing on the desktop.
Keep in mind that these processors are going to be *replacements* for the current line of consumer-grade AMD stuff... Not Intel server chips. Not SPARC. As long as AMD continues to beat Intel to the punch in terms of performance and features at a low price, I don't think it will be a problem... And that's exactly what they have in mind.
Who cares about 64 bits if the mainstream applications are written in a way that keeps wasting CPU power left and right without much care about peformance or efficient design ? Twice as large addressing space. Ok, so what ?
:)
The one of the only few areas where 64 bits will make an actual tangible difference is a crypto and OS themselves, but these would not probably be a factor enough to speed the introduction of 64 bits CPU.
I mean if the money Intel spent on R&D would've gone on to the (re-)eduction of applicaiton designers, we would've still be doing just fine with old'n'trusty Pentiums. Slightly exagerrated, of course, but you got the point
3.243F6A8885A308D313
The reason 64-bit would be good for mainstream PC's would be to finally provide good, reliable voice recognition.
Ruby on Rails Screencast
You assume people are important; they are not. People die all the time. More are born to replace them.
Correct me if I'm wrong, but isn't the PowerPC/G4 based off of the POWER4 architecture... but with all the 64-bit (as well as several other "high-end" features) stripped out?
Anyhoo, I know 64-bit sounds nice and all... But my question is: will moving from 64-bit integers, floats, and memory addresses actually improve performance? To my understanding of processor architecture, the answer is definitely 'maybe.'
If the 'new' processor just adds 64-bit extensions, and doesn't actually optimize further than the previous generation, then your 'new' 64-bit chip is now handling data that is twice as large... and probably doesn't need to be twice as large. I mean, really... how often does any of our software make use of 64-bit integers or floats? How often do you need to break the 4GB memory barrier? Sure, years down the road these limitations (especially the memory) will be problems... but for right now, why get all hyped over 64-bit when it will do nothing but double the size of everything?
Personally, for the time being, I'd much rather see highly optimized and blazing fast 32-bit processors on the market. Leave the 64-bit for when I actually need over 4 gigs of memory.
Come on guys.... you know I'm right. Unless you're in the scientific fields that use huge numbers and insane gobs of memory, 64-bit data paths will be wasted cpu-real-estate.
/dev/random
Why do we need a 3D operating system, though? I can see needing to do serious 3D imaging for modeling and other purposes, but for the OS?
So you can actually do register allocation with this architecture (as opposed to vanilla x86 where you pretty much have to keep everything in memory), and you'll already see some performance gain, as its much cheaper to keep a variable in a register than in memory.
The Raven
They need the faster chips to support the next generation of pornography. Once you view 64-bit porn, you'll wonder how you ever got by with the 32-bit variety.
Ergonomica Auctorita Illico!
Instead of moms driving around in minivans taking the kids to the soccer games.. Mom is now gonna be sitting behind the new 64bit computer editing movies and playing video games telling the kids to drive themselves to the soccer games....
If your comment were followed to the nth degree, technically an iMac is a Samsung/Sony/Motorola/Western Digital - less than 10% of an iMac is full in house Apple made (or specially made with Apple designs)
Yell & scream & rant & rave... it's no use... you need a shaaaave ~ Bugs Bunny
- interactive adjustments of full-resolution digital photographs
- real-time high-quality video compression, indexing, and analysis
- real-time camera-based user interfaces and interaction
- better speech recognition
- better indexing and analysis of text
We have barely scratched the surface of what is possible and useful.Faster machines and bigger address spaces also enable a lot of other things and improve software quality. For example, on today's machines, we can write real-time video games in Perl and word processors in interpreted Scheme. Using higher level languages reduces programming effort, "time-to-market", and improves software quality. One of the biggest problems with current desktops (e.g., Windows, KDE, Gnome) is that they are mostly not written in high level languages, so adding features and debugging take forever.
Even for C/C++ programs, with fast machines, programmers need to waste much less time on assembly coding or tuning software. 64bit address spaces will greatly simplify dealing with video and databases, as programmers don't have to deal with as many hacks.
Altogether, faster machines and bigger address spaces mean cheaper software, higher quality software, and the creation of applications that we dreamed of decades ago but that are only now becoming possible.
Of course, if you run Windows, it's fine to be a couple of generations behind--Microsoft knows well that in order to maximize profit, they want those upgrade dollars from people still using older machines, so they hold back on features. Apple, on the other hand, profits from hardware upgrades, so they put compute-intensive features into their systems. And with Linux, it's your choice: you can run a desktop and applications that work just fine on a 75MHz Pentium, or you can run something that barely functions on an Athlon XP 3000+ with 2G of memory.
But if you want rich multimedia content, the ability to do serious 3D imaging on the fly (think 3D operating systems) and the like, you're going to need more RAM. The only way to get that is with a 64-bit chip.
Consider, of course, that the average amount of RAM in use in deskop PCs 256MB. Few people go above 512MB, even for 3D rendering. And, very, very, very few people have 1GB. So if the 2GB limit were a serious problem, you'd expect to have a significant percentage of PCs maxed out at 2GB, and that's hardly the case. 0.1% of all industrial PC users needs more than 2GB, and I accept that, but that's not a reason to switch to 64-bit across the board, for everyone.
If you ever do solid modeling (solidworks, edge, etc) you are ALWAYS saying, "Man I wish this thing would go faster."
Don't forget that games are between the apps that more need computing power, and the more likely to require 64bit power from "normal" users.
Until you start making DV videos and DVDs, which take gbs and gbs of storage each...
Then you'll want a 64 bit (Apple?) machine.
GPL Deconstructed
This could put Intel in an interesting spot when they finally decide to release consumer 64-bit chips. Say it's 2006, Intel is 12 months from releasing their new chip. Normally they would be showing it off at trade shows and starting on a major advertising campaign, lauding it's performance and superiority over competitors. However now everytime the tout the benefits of 64-bits and how great it will be when they release it in 12 months AMD will be sitting there with their machines saying "yea heres our 64-bit computer, we've had it out for a few years now, you can head down to best buy and get one today if you like what you see"
"Intel doesn't think that we'll be ready for mainstream 64-bit computing until 2007"
=
Intel doesn't believe they've had time to replace the desktop computer market with 64-bit processors until 2007...?
Beware: In C++, your friends can see your privates!
Are we ready for 64-bit on the desktop? yes. Do we need it? No, but that isn't the point of a lot of computer hobbyists. Most of us don't really need the latest video card from ATi or nVidia. Mose of us don't need the latest processor from AMD or Intel. But we still buy the latest and the greatest. Why? Could be a matter of manhood, or for the woman, womanhood. Whatever reason it is for this phenomenon, there is no doubt that it happens. Yes, we are ready, and no, we don't need it, but the hobbyist will still buy them if the average computer consumer won't.
---Baseball is not right, a man can not walk with four balls. mike9010
MS already has a 64 bit OS: NT 3.51
i have 2 DEC Alpha stations that where running it when i got them (needless to say, i got rid of NT very quickly).
How come MS can't do it anymore? i realise that 64 Alpha isn't quite the same as i64, but really, how hard can it be?
Addressable memory. Right now the limit is 4GB. With Windows XP, the OS sets 2GB aside for the OS, so apps only get 2GB, and that's shared across all the apps.
Are you sure about that? Since each process gets its own address space, I would assume that it also gets its own 2GB limit. (*some* of it is shared, like system dlls)
Of course, I'm not absolutely certain, but this sounds suspicious.
if you want rich multimedia content
Define "rich." You can do a lot of multimedia in 2GB.
the ability to do serious 3D imaging on the fly
System RAM won't help you much there. You want to do as much of this as possible in the video card. Having a huge amount of RAM on the other end of a bottleneck isn't that useful.
A: We are Devo!
The neutrality of this sig is disputed.
There's nothing special about 64 bit. Saying "we're not ready for it" is like saying "we're not ready for 1 GB of RAM". It's just an incremental increase - nothing special.
Amount of memory in the average desktop RIGHT NOW.
Think about your argument, oh, I dunno, say 10 years ago. The average PC had just 4 MB of RAM. A few poeple went to 8 or 16MB or even 32 MB.
Back then, there were a lot of people, just like you saying that putting more than 32 MB in a PC just didn't make sense, you wouldn't gain any performance out of much more than that.
Think back, say 15 years ago when IBM said that nobody would ever need to 386, it was just too powerful.
Anybody saying that we don't need more than 2GB is as short-sighted as Bill Gates saying 640K oughta be enough for anybody.
My journal has hot
Windows Xp Pro can be set up to allow 3GB for the user address space. This gives some applications a little more breathing room, although it doesnt move the ceiling that far.
E /PAEmem.asp for info on the /3GB switch.
/3GB" on msdn to find out more...
The main problem I'm coming across with the limited address space is fragmentation of the free space. You can easily get to a point where the is still large amount of free address space available but there are no spaces large enough to allocate the chunk of memory of the size you want.
See http://www.microsoft.com/hwdev/platform/server/PA
Look up a combination of "LARGEADDRESSAWARE, boot.ini, bootcfg,
cheers,
Steve.
I'm running a Pentium 3 on my desktop computer. And most all I do on the desktop is word processing, spreadsheets, surf the Net and e-mail. 64-bit processors will not help me out at all.
More addressable memory, registers and better float math is not helping at all. I'm like many other computer users out there and I don't see anyone buying into it.
Even if the processors are the same price, my computer still works fine. Until smoke starts spewing out from the case, I'm not upgrading.
What Intel is really saying here is that INTEL isn't ready for mainstream 64-bit computing.
Both AMD (Hammer) & IBM (PPC970) 64-bit processors will run 32-bit applications with no modification, and at more than full speed, unlike Intel's Itanium processors. By the time Intel gets around to a 'mainstream' 64-bit processor, both AMD & IBM will have years of experience with mainstream 64-bit CPUs, and in the CPU game, experience is invaluable. Then again, watching someone else make the mistakes often has an advantage, too, and I doubt Intel is going out of business anytime soon.
Multimedia editing does not read in the entire file at one time to work on. It reads in a few frames at a time from the file. Are there any operations that require more than 4GB of main memory for video apps?
:)
64bit is needed for large (ASIC synthesis for example) jobs that require you to load the entire image into memory at once. Yes, you can break that job into smaller chunks, but then the complexity gets harder to manage.
Or I could be totally wrong.
-W
I only ever use 28 or 29 of my 32 available bits. What on earth would I need another 32 bits for?
Anyone who works in the graphics industry knows we need 4 - 8 gigs of memeory as a minimum on current apps to do hollywood quality graphics(i.e. LOTR anyone?). As those of you who have payed attention to trends will note Hollywood is only 12 months ahead of the game industry (seen Weta's realtime LOTR renderer? I did 12 month ago).
The only thing stand between you and a LOTR quality realtime video game is those that don't want to move to 64 bit.
MS has something against the number 64, last time they fought it the 640k bugaboo bit them in the ass so hard people still make fun of them for it to this day.
"No one will ever need 64 bit." will be a laughing point in a year or two.
Evilman
-B
Ash and Hickory, straight-grained and true, make excellent bludgeons, dandy for the cudgeling of vegetarians.
Not the games themselves, but the tools used to create the graphic worlds and environments for those games.
Lack of 64 bit for the user means fewer mods and maps.
Remember BillG at the NYC roll-out of the 386 16-bit OS-2? The lead engineer at the time told me he could have a production 32-bit version in two weeks. It took a lot longer.
Why do we need a GUI, the CLI is all you need.
;)
I do agree that the GUI, if not implemented correctly, is useless bloat. However if the GUI is implemented correctly, it provides a wealth of information in one glance to a section of a screen, no matter how fast your digits are it's easier to look at a krell than to Alt+F# to a virtual console or fg a job.
The 3D GUI, in my opinion will enhance this ability even more, provided of course that it's correctly implemented. GUI's, if used correctly are not eye candy to make your computer look stylish, although that is a nice side effect, but rather are extremely powerfull tools that help you work more effeciently.
Just wait, you'll be monitoring your system in 3D space before long, and you'll wonder what you did without it. Imagine a surface plot of top with processes on one access, time on the other, and usage information on the third. With the correct color coding you can spot the process of interest with one glance to see what it's doing.
Our physical world is in three diemensions, why shouldn't our window managers be? And I'm not talking about menu drop shaddows
(B) + (D) + (B) + (D) = (K) + (&)
It's not wasting time, I'm educating myself.
Now our legacy products are getting used with more and more data. These things are heavy enough to resist the re-engineering attempt to multiple processes.
Our product support people are getting more and more calls from customers who are using too much data. Both the customers and the support people seem to be surprised when they hear that the out of memory error is due to the limitations of 31-bit address spaces. 640k^H^H^H^H2 GB is not enough for everyone. We need our 64-bit address spaces.
Again, we can give a bit or two to Bill Gates as a sacrifice!
-- Imperial units must die --
NO SCSI?!
Please. Apple makes purty parts, but it's still soft and squishy.
Blar.
Im curios AMD says its going to release the 64 bit processor, but i cant really find a date for it. also usually you would have price guesses. does anybody know how much amd 64 processors will cost.
another thing that i find scary. i ran some simulation software on an alpha and i really didn't see any performance increase. i hope thats not the case with amd.
I'm having a hard time believing this. I know there is a 2G limit in user-space, but it needs to be *shared* by all the apps? There's no hardware or software reason why it has to be that way.
Is Microsoft really *monumentally* stupid?
Just because they don't use it doesn't mean that they wouldn't benefit from it...
As a matter of fact, jumping from 512MB to 1024 MB offeres a substantial increase in performance. Did you know that the majority of the time that it takes for your PC to perform work is generally due to waiting for the OS to read and write back to the swapfile? I personally have 1024 MB of RAM, and under Linux, my swapfile almost never gets used... However, it *does* happen. I was compiling some pretty intensive software a few weeks ago, and the swapfile *was* actually used.
For normal use, web browsing, MP3 playback, then less than 1024 MB is ideal... 512 isn't enough for me. It's too slow from the swap-work, especially on Windows 200, which insists on using a pagefile despite your attempts to get it to stop. But for graphics, webserving, major audio work, and other things... It's essential.
Seriously though... Despite sounding a bit excessive, you will never grow to appreciate 1024 MB of RAM until you own a machine that has that much... Even when you only do regular every-day tasks.
Most floating point calculations are already done in 64-bit (double precision) or 80-bit (extended precision). 32-bit (single precision) floating point is of limited usefulness on commodity Intel hardware.
Mea navis aericumbens anguillis abundat
Since memory is 64 bit addressed, then in a two-hyperthread cpu one can divide the address space into two 32 bit partitions whereby each pseudo processor/partition has it's own 4Gig (32 bit) address space.
/proteomic modeling for those sites that collect the data.
Hmmm.... Now a need has been created.
I'd like to use them to do home 64 bit distributed molecular
"The AutoCAD and 3D Studio and Photoshop apps the parent poster mentioned *are* dying for more RAM. I have 3D models that are pushing that 2GB limit."
Then buy an Itanium workstation or wait for Opteron. The point here isn't that nobody needs 64-bit, but that the majority of users don't need it yet. I know plenty of folks who use photo shop who never get anywhere near the 2Gb limit.
** The opinions expressed here are my own, and do not reflect those of my employers - past, present, or future**
I was ready for 64 bit a while ago, bu sadly, the Nintendo 64 didn't live up to my expectations. I'm sure somebody has already put Linux on it though ;)
You need a FREE iPod Nano
Intel has worked out that their Itantium/Pentium performance/cost manufacturing curves cross in 2007.
Also, asking the question presupposes there's an answer. "Mom, are you ready for 64-bit computing?" "64 what?" Most people don't know or care what their system architecture is, they just want their apps to work.
Which is why 2007 is really too late - we need a 64-bit time_t in production by 2007 so that 30-year mortgages can be properly calculated. (32-bit time_t values run out in 2038) Remember, that's how the Y2K problem was 'discovered'. If Y2K is any gauge, 4 years is about how long people will need to get all the systems fixed, so we ought to be getting started just about now.
Thanks, Apple.
My God, it's Full of Source!
OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
You'll at least have the slowdown associated with alignment penalties for anything that's only 4-byte aligned.
Of course, such slowdown will affect only 64-bit move instructions, not 32-bit move instructions.
Will I retire or break 10K?
SCOOP:
Excerpt: "Nevertheless one will not only be able to select to the planned Launch between different 64-Bit-Linuxen. Microsoft announced in the meantime, one day before the planned launching of a vessel, thus on 21 April to bring the Windows-XP-Server-2003-Version out for AMDs 64-Bit-Prozessor officially. For the Opterons AMD wants to do without a projected clock scale such as QuantiSpeed and introduce simple model designations."
My wife is an attorney (corporate health care law; if you want to buy an HMO, she's your girl!), and found that to get decent performance with her day-to-day work (given the characteristics of MS -- and adobe! -- bloatware), she needed to go with 1 GB RAM; 512K was not enough.
And for what I do (serious environmental modeling), having to live within the limits of dinky little 2 GB files is ridiculous. And we wind up doing the analysis on desktops instead of directly on the supercomputers... Thank God (or Linux, or Alan...) for Large File Summit support in the recent Linux releases!
"My opinions are my own, and I've got *lots* of them!"
christ man, what do you consider to be everyday work? I have 512 MB in all of my computers, and I hardly ever use the swap/page file.
Don't forget SuSE as well: OS News.
In addition, 64-bit Mandrake has been available for almost 2 weeks now.
Seriously though... Despite sounding a bit excessive, you will never grow to appreciate 1024 MB of RAM until you own a machine that has that much... Even when you only do regular every-day tasks.
Do you consider developing high-end 3D games to be more than regular every-day tasks? I have 512MB under Windows 2000 and I never hit the swap file. I have zero reasons to upgrade either my RAM or processor. Zero.
Is Microsoft really *monumentally* stupid?
If you have to ask that...
Memory is too expensive now, but will be much cheaper in 2007. More memory is the most important reason for 64-bit. 64-bit registers will help very little as you say.
Linux can do better than that. In Linux you get 3GB per process.
You're preaching to the converted.
My journal has hot
The opteron has a 32-bit compatibility mode, where the Intel solution does not, so Windows 2003 Server *does* support the Opteron.
Alphas, Sparcs. PowerPC (as in, from IBM, not as in from Apple), even.
Hell, Tru64 Unix is named for it. And Solaris has presumed its use if you want decent performance for years.
Is the consumer market not ready for 64-bit computing? Who knows, maybe it's not really necessary.
It's certainly an integral part for Veritas, Oracle, and other enterprise software I use out here in the real world with (marketing) data warehousing...
Do you have a
The display certainly isn't 3D, I don't see why the GUI would want to be. That said, I'd love to see a working concept for a useful 3D computer GUI. So far, all I've seen was terrible.
Switch back to Slashdot's D1 system.
Some of the other responses have sort of alluded to my point, but...
AMD plans to eventually replace the current Athlon with the Athlon64. Further, AMD claims that the overhead for adding 64 bit capability was somewhere in the ballpark of 10% additional transistors. So... whether MS releases an x86-64 bit OS or not, and assuming AMD keeps selling 10-20% of the market, there WILL BE millions of 64bit mainstream CPUs in a year or two.
To reiterate, x86-64 is a nice and simple (relatively) enhancement... in some ways comparable to SSE or MMX. Opterons and Athlon64's will be built, and they will most definitely have a price/performance ratio better than Itaniums... and probably the Pentiums too.
Well, Microsoft has already committed to Opteron...therefore the rest of your argument is a straw man. :^)
By the way, Miguel, (having just noticed who I'm replying to) I still think your adoption of .Net/C# over Java was a horrible decision. You could be using the increasingly stable and useful gcj instead.
I wonder how long it'll be until Mono is tied up in patent/copyright lawsuits...
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
The point is, nobody is saying that. People aren't saying 2 GB is enough for everybody in 15 years, what people are saying is 2 GB is enough for most people at the moment. And that certainly appears to be true. I don't think anybody thinks that 64-bit computers will never rule supreme - it's pretty clear they will, the argument is whether that time is now.
Switch back to Slashdot's D1 system.
I had migrated to Sun/Solaris for my 64 bit needs some time ago. Since Intel/Mrcrosoft seem to think they know what's best for me, this will be the final push for me to go to AMD/Linux for my x86 needs. I'm tired of arogant companys telling me I'm not ready...
Ohhhh, 2007?? But I want it NOW!
"I bow to no man" - Riddick
Few people go above 512MB, even for 3D rendering
I beg to differ...I am a proffessional 3D modeler...and I partake in several industry discussion groups/forums filled w/ like proffessionals. The topic of new machines/building your own/buying from Boxx/etc comes up very often, and the majority of purchasers of 3D modeling/rendering stations are opting for 1-2GB of RAM. For machines that are meant to only be part of a renderfarm, 512MB is common (but quickly giving ground to 1GB), but for workstations where a comibination of Photoshop, 3DStudio/Maya, and a video editing app. are the expected use, 1-2GB is the norm. Most people would go to 4GB if the benefit was there (unfortuneately stability limitation is on hardware and OS).
I'm out of my mind right now, but feel free to leave a message.....
"Apple also doesn't lose on margin to gain marketshare (gateway), bloat sales statistics to education (dell) or have high overhead and channel inventory (HPaq) - nor does any PC company even come remotely close to presence for assistance and help on the internet!"
:(
Apple does lose on margin to gain market share (iMac), they do bloat sales statistics to education (see your comment, also 1988-1998 SEC filings) and oh, they DO have high overhead and channel inventory (maybe because they contain everything from R&D to Sales under one roof?) and I am sorry to tell you, but the web presence customer service is laughably paltry compared to MSFTs, the 10^9 greater customer base notwithstanding.
It is as if you do not even know what the terms you are throwing about actually mean.
I was probably not the only person expecting that my next upgrade would not be a Pentium 4 (which I had never heard of yet), but rather a IA-64 machine?
I also remember a few developer surverys going around which indicated that most people expected to be developing for IA-64 within the next year or two.
A couple of years later, and the mainstream is still stuck on 32 bits, the legendary Alpha has been buried by Intel despite (or more cynically, because of) being objectively better than IA-64, and Intel are now saying that the 'mainstream' won't get 64-bit computing until 2007?
My real hope is that AMD succeeds big time, Intel stocks plummet and they decide to abandon IA-64 in exchange for reviving Alpha on the high-end, and licensing x86-64 for the low-end.
Well, duh, my watch has more then 512K I think
I believe while the first release of Windows Server 2003 (which will ship in April) won't support the x86-64 registers of the Opteron/Athlon 64 CPU, I'm sure that Microsoft will have a Service Pack and/or updated version of Windows Server 2003 shipping by September 2003, the release date of the desktop-based Athlon 64 CPU.
So can Windows, although the app has to be aware to take advantage of it.
Yeah, we'll be really ready for 64 bit in 2038.
No, the 2G limit is per-process.
The thing AMD needs to do is put 16 or 32 DIMM slots in the motherboard for their 64-bit processor. As many others have pointed out, RAM is dirt cheap for up to 1GB DIMMs. I could buy a 64-bit processor and motherboard plus 32GB of RAM for a reasonable sum.
That's 32 gigabytes. Just the disk caching speedups alone would be worthwhile. My firm belief is the only reason these huge RAM sizes aren't common is the 4GB physical / 3GB per process limits of current 32 bit OSs.
The 2G limit is per-process. And the shared libraries don't even come into play, each library mapped into a process's address space takes up the same amount per process even though it's only in memory one time. So if loading MFC.dll takes up 10M of virtual address space, it takes up 10M in each app's space that needs it, even though it's only using 10M physical memory.
Oracle SGAs have been living on 64-bit systems since they ported to the Alpha; Oracle can rightly look upon MS SQL Server and call it a bit player because it is bound to a 32-bit architecture with a theoretical maximum of 4GB of directly addressable memory - it is effectively running in the memory of a pocket calculator when compared to enterprise Oracle.
Even if MS SQL Server pounds Oracle in every benchmark TPC can muster, you still shouldn't implement standard SQL Server for an enterprise system because Oracle can have 10-100 times the cache. Yes, datacenter edition and memory bank switching address this problem, but they are ugly hacks, and I don't particularly want to go back to LIM EMS 4.0.
Remember, the very first application that MS ported to Itanium was SQL Server - it is obvious that MS feels this pain. In the meantime, Oracle is 64-bit now, has been quite cozy with Linux for sometime, and now beats SQL Server clusters on the same hardware with Linux. Opteron will only make this worse.
MS may be ignoring Opteron at the insistence of Intel. If they are doing so, they will pay a terrible price - the enterprise Win32 environment will be destroyed.
I fully agree, all of the 3D GUI's are terrible so far. The display is 2D, but it can portray a 3D image fairly well, and the human brain can conceptualize 3D extremely well, so the ability of a 2D screen to portray a 3D image and the power of our brain to conceptualize that 3D space is a very powerful combination that expands our working potential. I know that if I could at a glance view a 3D visulization of what is going on in my computer or on my network I would be able to accomplish things faster and more effeciently.
The design of a powerfull 3D desktop is a very complicated task, and it must be done extremely well in order to facilitate a change. So I don't see this coming down the pipe anytime soon. Kind of makes me want to read up on GUI design though.
(B) + (D) + (B) + (D) = (K) + (&)
Microsoft was the primary developer of the x86-64 instruction set along with AMD. They basically told AMD "Here's what we want in a 64-bit instruction set" and AMD produced. They have a vested interest to see Opteron/Hammer succeed. They only developed a version of Windows for Itanium because they felt they had to, not because they wanted to. Itanium is just a weird fit with Microsoft.
Even if that were not the case, x86 is not going anyhere anytime soon. So Hammer will run anything Microsoft puts out just fine. Hammer will kick the crap out of ANYTHING Intel puts on the market and is doing so right now.
And Microsoft will be coming out with x86-64 versions of Windows, rest assured. That is not speculation.
If there's ever anything Microsoft understands, its "volume" and "price".
praaaaaiiiiiiiiisssssse jeeeeeeeeeeeeeessssssssssus
You're talking about 3D graphing; that makes some sense to me. But go beyond information display and explain to me how a 3D interface will improve my ability to switch between active processes, manage files (beyond 3DX style file-size cylinders), etc. And don't resort to "why would anyone need a GUI" kind of argument, that's argument from false analogy, as you haven't proved why a change from 2D to 3D is analogous to the change from command line to gui. Seriously, I'd be very interested in your ideas.
When people see they can use a PPC or a 64bit AMD, and still have the same Linux desktop, I think it'll be a real Linux advantage.
As it stands, Windows users won't get a Mac because they have to learn a new system and Mac users won't go PC, because they'd have to learn a new system.
Linux users don't have that problem, we're already getting first on new platforms, MS already can't/won't keep up.
Here's to hoping IBM will offer some sweet deals on PPC970 desktops running Linux. (and don't you think they'd love to piss of M$ by doing so?)
BTW, how far apart are PPC970 and Sony's "cell" processor? Will I be able to get a laptop with 4 PPC970 cells onboard? How about a thin laptop with cell upgrades by slapping other cell panels on the bottom, like a 1" notebook might have 4 cells, and a 2" notebook might have 8, and if I was a fanatic, my "notebook" would be 6" thick with 24 cells. could I then get 400fps in Quake? imagine a beowulf cluster of these!!!!
"The Most Fun Possible on 4 wheels" is at SunBuggy in Las Vegas
Is that the changes AMD made outside of adding 64-bit support go by the wayside. The x86-64 has twice the general purpose registers, but only when it is x86-64 mode, not in 32-bit mode. And you can only be in x86-64 mode when you are running an operating system that handles it. The extra registers allow a good compiler to have lots of fun and can equal up to a 30% increase in speed, with a simple recompile. The 64 bits is nice, but the other changes to the x86 architecture are more important.
If 76 Trombones really led the big parade, why did they have anyone else in it?
If 64 bit computing is what it takes to get rid of all the stupid annoying 2 terabyte limits, then I'm all for it! ARghghghg.
Fellowship 9/11
Now you tell me if you want that machine to support more than 4 Gigs of RAM or not.
The 80386 processor introduced more than just 32-bit register addressing. It was also the first processor to support the protected mode interface to the processor and not to mention the ability to "virtualize" memory by paging to another medium. Windows 3.0 took advantage of the new features of the processor while still being a 16-bit operating system.
In what sense did the 80386 introduce any of these things? Leaving aside mainframe CPUs, Motorola's single chip CPUs preceded it.
The 68020 was released in 1984 (the 386 in 1985) and had all of these features. The 68000 (1979) only had 24-bit addressing and lacked a PMMU.
Intel has done an extraordinary job in predicting the market and following demand.
It's good to be smart. It's better to be lucky.
That may be fine and dandy for some people, but some of us will still prefer the command line.
;)
If you did have a 3D window manager, I bet I can guess what your top surface plot would look like
-phish
Garbage Collection
"Real Languages" use garbage collection (ha, just trolling).
Seriously, the ability to use an address space that is gignormous is really worth a lot for garbage collection algorithms. For example, you can allocate into reserved portions of the address space and then the type of an object can be determined by its location. You can also use copying collectors without a big hit. Reserving half your address space for copying sucks at 2GB, it doesn't matter much for 17179869184 GB.
Also the "single address space" operating system concept needs more research. However, to get that research going now would require low cost plentiful hardware.
The fact is, there are tons of useful reasons to have 64 bits, we just don't know what they are because we haven't had 64 bits on a commodity platform.
If you have 64 bit addresses and about 1GB of flash RAM, you can completely avoid all the trouble of traditional filesystems. Have your OS use the disk like one big area of RAM, buffer into the NV RAM, keep all the metadata in NV ram, and use a journaled approach for metadata. Speed and simplicity instead of B-trees and inodes and such.
There are all kinds of reasons for 64 bit.
((lambda (x) (x x)) (lambda (x) (x x))) http://www.endpointcomputing.com a scientific approach to custom computing.
But if you want rich multimedia content, the ability to do serious 3D imaging on the fly (think 3D operating systems) and the like, you're going to need more RAM. The only way to get that is with a 64-bit chip.
Ummm... no. If you want to fix this problem, use an OS that doesn't burn up half available RAM for itself...
; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
Convenient that Intel thinks widespread demand for 64-bit won't occur until 2007 since they don't have a 64-bit desktop processor and Itanium tanked. AMD knows better. Check out their Studio64 which has quotes from tech leaders, analysts, press, etc. on when 64-bit will hit big and what this means for you and me: http://www.amd.com/us-en/Weblets/0,,7832_8366_7823 ,00.html
Are We Not Ready For 64-Bit?
No.
That was easy, give me another.
if you are prepared to patch your kernel.
The real "Libtards" are the Libertarians!
It was a 32-bit kludge running on a 64-bit processor. And we had more issues running this than we had after switching off our dual Aplha boxes and onto dual P-III Xeons. NT 3.51 and 4.0 ran, but not real well, and not in full on 64-bit goodness.
Wu-Tang Name: Half-Cut Skeleton Get your own Wu-Na
What is the profit margin on an Itanium, anyway?
I'm curious about whether they actually cost a thousand or two each to make, or whether it's only in the couple of hundred dollar range.
If it's a huge margin, the price of Itanium will probably plummet once the Hammer hits the streets.
If you take into account that
Opteron is a guaranteed success if priced similarily as the Athlon.
Anybody saying that we don't need more than 2GB is as short-sighted as Bill Gates saying 640K oughta be enough for anybody.
At some point diminishing returns kick in. It is one thing to say "a two cyclinder engine should be enough for anybody" and quite another to say the same thing about an eight cylinder engine. You might get more performance out of ten or twelve cylinders, and certainly such engines have been built, but at the same time there are significant drawbacks: higher fuel consumption, more weight, more expensive, more parts to break.
In the case of 64-bit, there's a small group of people that really need it (and a much larger group who thinks that they do). This is not enough reason to promote moving the entire PC industry to 64-bit processors and huge memories.
Alot of people are bashing Intel because they see the need for 64-bit computers now or in the near future. One thing that people are forgetting is that most slashdot users(even those of us using windows) are not "mainstream" and do not have "mainstream computers". Most of us have computer which should probably be categorized under the workstation category. Intel isn't saying that there is no need for 64-bit right now, they are saying that there is no need for 64-bit on the mainstream desktop until 2007, which is probably true. If you were to go to BestBuy to look at mainstream desktop computers you would find that most of them come with 256MB of RAM. The people that buy these computers don't need anywhere near 4GB of RAM, and won't until at least 2007. These are the people that Intel is talking about. For those who do need 64-bit computing it is here or will be here in a month from both Intel and AMD. Yes they Itanium is really expensive, but most of the applications which need 64-bit computer are already really expensive, so $2000 instead of $500 for a CPU next to $20,000 for software isn't really that big of a deal.
Regardless of whether Microsoft publicly acknowledges support for x86-64, it has ALREADY implemented support for it in the NT source tree.
Microsoft has a very complex relationship with Intel. If Microsoft has to commit to a decision that could have a negative effect on its relationship with Intel, it has to think long and hard about that, and it has to keep information about those decisions as quiet as possible, until it is ready to announce.
To make this more clear:
64 bit flat virtual address space
64 bit General Purpose Registers
8 new GPRs
8 new XMM (SSE) Registers
Discarding of old unused instructions
Noteworthy, no expansion of floating point types: x87 already suports 32, 64 and 80 bit floating points (among other things) and SSE2 also supports 32 and 64 bit floating points.
The 64 bit flat address space is a major advantage if you need it. If you don't, its irrelevant, with the disadvantage the addresses are twice as big, having a slight negative effect on memory usage and performance.
The new 64 bit GPRs are needed to suport the 64 bit addressing, but they don't offer much advantage otherwise for 64 bit data: SSE2 already suports manipulation of 64 bit integers.
The only other advantage are the new registers.
Another possible disadvantage: the best performance in IA-32 has usually been achieved using the Intel compiler, which won't be avaliable for x86-64..
Summing up, there won't be significan performance differences between IA-32 and x86-64 versions of the same software, on the same CPU.
Unless you need the 64 bit address space or the software can take significan advantage of the extra registers, its not worth the hassle to get a x86-64 version instead of the IA-32.
Then there is another problem: drivers. I don't think that x86-64 Windows will be able to use drivers for the IA-32 Windows. Given the huge diversity of PC hardware, use of x86-64 Windows will be severly limited by lack of drivers.
So, IA-32 applications are likely to remain dominat in the mainstream software and x86-64 capabilite a small bonus for consumers.
I think 'WE' are all ready for 64 bit processors, the title should read 'Microsoft not ready for 64bit computing'
We being people who Just Say No To Windows.
The keyword here is MAINSTREAM. Grandma won't need 64bits anytime soon, neither will little Johnny and Sally. Nor will dad as he VPNs to the office and surfs pr0n. I doubt the small business with 50 users will need it on their server anytime soon, they sure don't need it on their workstations.
Excuse be, BUT Microsoft will be coming out with a Windows-64 to support the AMD Opteron/Athlon-64 chips at, or very very near to launch.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
While most people don't need over 4GB of RAM, having 64 bits can make life much easier for programmers and provide significant performance advantages. For example, no more relocation will need to occur for shared libraries. Every library could be mapped to a unique address without worry of address clashes so no relocation is necessary (although one of the benefits of the Opteron is better support for relocatable code in 64-bit mode).
Memory mapped files could be the norm. Handling large files becomes much simpler, especially random access.
-Aaron
This post is encrypted twice with ROT-13. Documenting or attempting to crack this encryption is illegal.
Until the end of 1995.
To be fair, Intel was already there with 32-bit chips, just M$ had to change all its 16-bit code and update its OS. This time it looks like the positions are reversed (unless Itanium ever takes off).
Funny. I read post after post about "why would PC people (including business) switch from PC to Apple when they can buy cheap commodity hardware." Then I read posts like this that complain that apple is sacrificing features for cost (read: less expensive commodity hardware to save money).
I'm confused... I don't know which it is that business and PC people want????
you are an idiot. This "miguel" is a troll. Check his profile and posts.
I have 3D models that are pushing that 2GB limit.
;)
That's because the applications you are using (AutoCAD or 3DS) are written poorly. So how many polys are in this 2GB model?
Good 3D modelers should be able to handle 8 million or more polys in less than 2GB of RAM (yes, I'm including UV mapping and animation data).
And if you don't think that's possible then just wait till I release my modeler
They have 512MB PC2100-DDR for $40.01. That mean $320.08 for 4GB.
Back around '84, the ancestors of what is now known as ia64, or, EPIC, was VLIW, or Very Long Instruction Word. This new way of thinking about CPU instructions which did away with runtime pipelining and pushed it into compile time optimization. This would allow them to rid a CPU of the expensive task of pipelining, and use transistors for processing instead of organizing instructions.
They found, back in those days, that the memory architecture and processor speed required to generate the variable length (>= 256 bit) words cramming smaller sub-instructions into a single word, and move them from memory into a CPU were too demanding for hardware of the day, and found they would benefit more by removing those bottlenecks first.
Intel and HP then decided back in the early 90's that it was finally time to use the earlier research and develope what is now known as EPIC.
I've inevitably made some historical mistakes, but those aside, it's really easy to see some key reasons why 64 bit (in the for of EPIC) is not ready for Joe Sixpak.
1. Being different, the hardware is completely new, and therefore expensive. HP and Intel will be looking to big business to pay for all that R&D over the last decade and a half through large systems and their equally large price tags.
2. "Compatible" has always played out as "better" in the marketplace. Currently, what Intel has for 64 bit is compatible, but is slower than anything made with older technology in compat mode making the point moot.
3. 64 bits mean larger code size on disk, and people still like getting software on CDs. Think "MS Office 64", shuffling cds like the floppies of old... No thank you. Plus, size does matter when it comes to application speed.
AMD, however, is taking the practicle approach. I, for one, am ready for 64 bit... At least as AMD defines it. (Or Sun... or Motorola...)
I'm really starting to think Intel and HP were just jerking themselves off with technology all this time.. Technological masturbation.
Compared to war, all other forms of human endeavor shrink to insignificance. God, how I love it. - Gen. George Patton
*sheesh*
I think common sense would have dictated that we were talking about PCs. But, if that wasn't clear 'nuff for you...
Ayup
How does that work? Voice recognition needs 64-bit pointers? We already have 64-bit ints (int64_t, long long) ...
Actually, I believe that 64 bit CPUs are the right direction, though one could argue about the timing. But I doubt that there will be any need for registers larger than 64 bits (except for floating point). Certainly that's what the mainframes decided. A few were built with 92 or 128 bit CPUs, but they were trial balloons, that turned out to be lead.
... as long as it handles the job you need it to handle. But the profits are at the high end.
So when we need to go above 64 bits, either there will be a very new architecture, or we will finally enter parallel processing. Parallel processing we sort of know how to do, and you can't depend on a new architecture showing up just because you nee it. And the clock is ticking NOW. Decisions made now shape were we are heading for the next decade. If Intel stays at 32 bits, then that implies a much heavier push at parallel processing than we've had so far. Or Intel will sink down to the low end of the market, and leave the premium CPUs to AMD.
You can say "most people don't need it", but most people buy the cheapest computer that will do their job (and frequently a bit less). Not a bad strategy the way Moore's law has been handling hardware. It's cheaper to buy a $500 computer every year than a $5000 computer once every five years. And much of the time you'll have a better computer.
I think we've pushed this "anyone can grow up to be president" thing too far.
Here we go again, Intel and microsoft decide that we don't deserve faster, better hardware (there's nothing wrong with 32 bit windows os's etc), here, buy some 32 bit crap hardware and software..if the mainframe world went 64 bits decades ago, why do we let intel and microsoft strech out their expensive monopolies when things like gaming, communications (real on line video over optical internet and without the artificallity of expensive per/bit charges of delivery). Push the frontier forward, one example is the price of dram, it was held at small chip sizes for years because it was proffitable for the chip companies (they justifed their pricing saying that nobody needed bigger chips because the current ones of the day were solling for so much). I's time people broke the artificial limits imposed..we need os's that work, are intelligent (fuzzy, conventional AI and neural net AI (requiring lots of cpu/memory power).
Well, proof will be in the pudding. Considering MS's (recent) past history on projected release dates, I have a near zero faith level in them.
I don't cry when my dog runs away
I don't get angry at the bills I have to pay
I don't get angry when my mom smokes pot,
hits the bottle and goes back to the rock
F-it, fight it, it's all the same
Livin' with loui dog's the only way to stay sane
Let the lovin come back to me
If nothing else, it FEELS good to say "I've got a 64-bit processor in my desktop" and AMD (and anybody else) is gonna use that to its fullest marketing potential.
I'm comfortable saying that 75-85% of the people who are buying desktops in BB/CUSA wouldn't know if they bought a 16-bit or a 32-bit system. But if you can park it next to a 64-bit system and say "64 is TWICE as big as 32", people are gonna want it.
"Buy two! I'm not sharing with Kaitlyn!"
Come and see the violence inherent in the system!
I develop simulation software at work. Runs on Linux, HP-UX and Windows (with Cygwin for now). Some of the intermediate steps involve really huge datasets. If a cheap, fast Opteron/Linux system works well for my software, I'd buy one in a second. You're probably right about volume sales, but what Microsoft does will have no effect on me--other than some of our users will buy Opteron/GNU/Linux systems for now.
adéu,
Mateu
"And we're happy here, but we live in fear, we've seen a lot of temples crumble..." - Concrete Blonde
Thirty-two bits should be enough for everybody.
---- The above post was generated by the Turing Institute. Maybe.
Keep in mind that I am not a GUI designer, so take all of this with a grain of salt. I do, however, think that a properly designed 3D GUI could be very usefull, what we have right now in the 3D GUI arena is not what I would consider usefull at all. Basically all I have seen are OpenGL apps to switch virtual desktops.
A complete 3D framwork that allows you to navigate through your system, and group tasks and processes logically is more like what I envision. If I could see a cluster of 3D widgets that represented all of my daemons and at a glance determine what the utilization of one of those is, how many users attached, and by hovering my mouse or holding a hotkey view what the process is currently working on.
Another area of my screen would have a widget representing all of the file systems on the machine, another click or hotkey and I could zoom into the file system arena and graphically view the status. Collections of information grouped logically in 3D space that are easily navigable is what I would like to see.
I am a firm believer in the CLI and text files for nearly everything that needs to be done on a system, I never use a GUI app to configure anything (unless there is no alternative), and I very much prefer the CLI nature of *NIX operating systems. I use vim to program and I prefer the CLI frontends to databases, but I do also enjoy the visual information that a GUI affords. I can have a performance monitor running on my desktop and with one glance get a complete snapshot of what my system is doing. My desktop tells me the weather, news, time, programs running, mounted file systems, how much email I have, and what song I'm listening to and I never have to use the mouse. This is the power of a GUI to me, and I think a 3D GUI could help portray that much more information.
The eyes to the brain is the fastest interface I have come across.
Just my $0.02
(B) + (D) + (B) + (D) = (K) + (&)
Many of these upcoming Opteron motherboards have 16 DIMM slots; you can fill them with 8GB of RAM for $800 at today's pricewatch.com prices. This platform is going to be a godsend for anybody running serious workstation apps. It will beat other 64-bit workstation platforms (SPARC/PA-RISC/Itanium) in price/performance by a factor of 4X or more. The days of $4000 workstation and server CPU's are over, and those of $1000 CPU's are numbered.
my first 64-bit system :)
R.I.P.
I have a machine with 1GB of RAM. I also have one with 512MB, 384MB and 256MB. The only one that feels remotely memory-limited is the machine with 256MB, and that's only when playing some games.
If you are seeing a "substantial increase in performance" (a claim in itself I doubt - "substantial" would be a 50%+ performance improvement) moving from 512MB to 1GB, you are already far and away above the level of the average Joe.
There will be a half-year long period where people with Opterons will have to resort to running modern OSes to really show off what their new box can do. This summer, Windows will look as old and obsolete as it is.
The idiots are those who moderated his post +5 Insightful...I presumed it was his celebrity that induced the brain damage... ;-)
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
This is incorrect. In WIndowsXP 2GB is reserved for the OS, yes; however, each process can use 2GB of space for itself, the 2GB per process is NOT Shared. BTW It was nice the Linux finally broke the 1GB RAM limit with 2.4... This was quite a feat, especially considering NT has been able to do 4GB since 1992. Geesh...
can you show a rendering of what a 2Gb model looks like.
sounds very interesting
They will ride the 32bit horse as long as they can get away with it. This isn't a case of available technology, but what they milk out of the consumers.
:)
I think AMD is taking the right road to the 64bit transition.
BTW, Don't for a second think Microsoft is not going to fully support the AMD 64bit platform. It is already there, just not officially released. So don't yell at Microsoft for crushing this technology.
Windows 2003 is already filled with AMD64bit binaries and once the AMD chips hit, there will be 64bit replacements for XP and add-ons to Windows 2003 Server to fully support it.
With an NDA, I cannot say anymore.
Seriously! Mentality like this would have kept us using 16-bit processors because "We don't need 32-bit for Word Processing."
Gimme a break. Put a 64-bit CPU in the hands of every computer user out there and we'll all be better off. Even if my Games, Video editing, and 3d Rendering only goes 20% faster per-Mhz it's worth it to me.
The more 64-bit processors out there, the more cool software will show up to use it.
So get off your "Well, I'M a DBA and *I* KNOW I need 64-bit" high horse and let us have our fun too.
- It's not the Macs I hate. It's Digg users. -
scatology, incest, homosexuality... so much fervor for what is, after all, just an operating system. I'm sorry. I'm truly sorry.
* Realtime DivX encoding
* Point-to-Point encrypted communication
* Many applications of context (predictive) modeling
* Things we haven't really thought of yet
The point is, the usefulness of general purpose 64-bit desktop processing capability is going to be tied to new applications and ways of working that we don't currently use because of the present impracticality. But once the capability exists, the applications will follow, and we will ask how we ever managed to get by with our old 32-bit systems.
Peace and love, y'all
Won't be running out of RAM space quite yet.
It's okay fag, you're the one living the life and I'm running Linux.
That's not really accurate. Windows uses 64-bits to determine the time (in 100-nanosecond offsets from January 1, 1601). It won't roll over until the year 60095.
Of course, everybody will wait until 60094 before they start patching.
Since when is ``grandmother'' a typical cross-section of the computer market? Seriously, what percentage of users are mom-and-pop or grandma?
There are reasons why democracy does not work nearly as well as capitalism.
-- David D. Friedman
The entire commodities sector could greatly benefit from 64 bit computing because the data sets are so large. 64 bit integers mean you get much quicker date arithmetic.
This is my sig.
Here's something I slapped together to express my feellings about all this talk about 64-bit processors. decide.jpg
(appended to the end of comments you post)
In my view, you're all grossly overestimating the average pc. Only recently have I seen cheap desktop computers advertised with 256MB RAM, and in the megasuperstores, only the "high end" models have 512MB. Froogle desktop computers, and you will see that many elcheapos still only include 128MB. As for pcs in use, I know many people who use computers that are several years old and were cheap (i.e. lowspecced) to begin with. The upgrade cycle has slowed, both for businesses and for home users, and home users have typically been more reluctant to upgrade than businesses. Further, the average pc user is not comfortable upgrading their RAM because they are confused by the different varieties and they are trepidatious about taking their boxes apart. I know this because I have family members who wouldn't use the RAM I've given them until I installed it.
It's no surprise that a geek and his successful attorney wife would consume lots of RAM. What makes you think that represents the average computer user, who probably has much less disposable income, less interest in computing, less pressing needs for computing power, or any combination of the above?
I'd expect that the average pc to have no more than 128MB; 64MB or 32MB wouldn't be a shock.
I'd be happy to... If you'll first explain to us why we need a GUI operating system...
That's right, we don't NEED it, per se, but there are ('will be' in this case) many good reasons to have one.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
No. Actually I think the original poster was confusing Microsoft's memory policy with their multiple-processor policy .
With memory, no program can use more than 2GB. With dual-processors, the OS exclusively uses one processor for itself, and the apps must all share the second.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
Good 3D modelers should be able to handle 8 million or more polys in less than 2GB of RAM (yes, I'm including UV mapping and animation data).
;)
:)
And if you don't think that's possible then just wait till I release my modeler
Please, please! Release your modeler!
Windows NT 4.0 Enterprise Edition on Alpha supported large files and filesystems (NTFS) and ran on a 64-bit chip, but did not support large physical memories or address spaces, making it only a token 64-bit contender. Microsoft hadn't done the "hard stuff" yet at that point.
When AMD discontinues their current Athlon line and moves over to Athlon64 / Opteron, everyone who choses AMD CPUs over Intel will have a 64-bit processor under the hood and anyone who wants to use/write software to take advantange of this can. For those of us that don't, we've still got a chip that beats Intel's best in the price/performance ratio, who cares if a few million transistors are going unused?
AMD are giving people 64-bit computing for free with their forthcoming product line. Sounds like a bargain to me.
Addressable memory. Right now the limit is 4GB. With Windows XP, the OS sets 2GB aside for the OS, so apps only get 2GB, and that's shared across all the apps.
Then stop using an operating system with a serious design flaw.
The limit imposed by the Intel processor hardware is 16Gb - if XP is not allowing you to use that much memory, then a new version needs to be released that does.
2Gb per process limit indicates a design hack in the operating system that is ridiculous. It is easily possible for a competent OS to be designed that allows a per process address space of very nearly 4Gb. My linux system will allow a process to have 3.5Gb of address space.
... I was using a Commodore 64 years ago!
Interesting idea. Would this really need to be 3D, though? After all, why couldn't you have a 2D cluster of widgets in a small box that you open up to use?
The interesting issue to me is this: how do you navigate a 3D display? A mouse is a 2D input device. I suppose you could use the scroll button for that purpose, or you could use something like the gyroscopic pointers they had for a while, but adding a z-axis to a pointing device would be a non-trivial usability hurdle, don't you agree?
I do agree that the Z axis presents a bit of a problem. Personally I really like the way that Maya handles the navigation of 3D space with a sphere composed of three circles, each on a different plane. A small "nav" sphere in one of the corners of the screen or accessible by a hot key or mouse button would work. Meta + Arrow keys also might work.
I just see the power of virutal desktops and virtual consoles and think that power could be applied to a 3 Dimensional area and work really well.
I think I'm going to start doodling some diagrams, might be a good way to get back into C++ and learn a little OpenGL on the way.
(B) + (D) + (B) + (D) = (K) + (&)
Good. The more thought put into how to move beyond the desktop paradigm, the better off we'll be in the future.
Top Ten Things Overheard At The ANSI C Draft Committee Meetings:
(10) Sorry, but that's too useful.
(9) Dammit, little-endian systems *are* more consistent!
(8) I'm on the committee and I *still* don't know what the hell
#pragma is for.
(7) Well, it's an excellent idea, but it would make the compilers too
hard to write.
(6) Them bats is smart; they use radar.
(5) All right, who's the wiseguy who stuck this trigraph stuff in
here?
(4) How many times do we have to tell you, "No prior art!"
(3) Ha, ha, I can't believe they're actually going to adopt this
sucker.
(2) Thank you for your generous donation, Mr. Wirth.
(1) Gee, I wish we hadn't backed down on 'noalias'.
- this post brought to you by the Automated Last Post Generator...