Windows XP 64-Bit Customer Preview Program

MBCook writes "I just notice that Microsoft has a new Windows XP 64-Bit Customer Preview Program starting today (February 3rd). If you have a AMD Opteron or Athlon64, you can go to the download page to get your copy. It's a pre-release copy that will expire in 360 days (which probably means the final will be out by then). Now Intel just changed their 64-bit plans, and all of a sudden this appears. Speculate away!"

Comments

"I just notice"?

[Chuck Bucket]

"I just notice" that this post wasn't proofed before it was posted.

CB

Re:"I just notice"?

[Anonymous Coward]

Hi(gh) Master Bong!

Re:"I just notice"?

[Anonymous Coward]

I just notice this is grammar school.

Re:"I just notice"?

[Anonymous Coward]

the spallign, and punkshuayshun is terabel hear to?

Re:"I just notice"?

[jerky42]

> "I just notice" that this post wasn't proofed before it was posted.

Ha,Ha! You mispeeled proofread!

(Yes, yes, I know. It just makes it funnier.)

Re:"I just notice"?

[FattMattP]

You must be new here.

Re:"I just notice"?

[Anonymous Coward]

you can't be serious. You haven't heard of the word PROFED?

Re:"I just notice"?

[Anonymous Coward]

ok, ill bite. what is PROFED? Why the caps? It's like: OMFG LOLZ YOU SUX! HAHA, but the thing is you are the asshat you mispelled PROOFED. LOL OMFG!

Re:"I just notice"?

[Anonymous Coward]

Ha, you totally 0wned him LOL!!!!1

Actual Performance Difference

[neomage86]

I wonder if a 64 bit OS will make any performance difference for the average desktop user. Since its not like any normal people have more than a gig of ram anyways. Is it possible that it could even slow down 32 bit apps?

Re:Actual Performance Difference

[Paladin128]

My guess is that the initial rev will, in fact, be slower on 64-bit. Microsofts compilers are new to 64-bitness, and a reasonable amount of memory bandwidth will be wasted on larger ints. On the other hand, in 64-bit mode on the Opteron, there are twice as many GPR's, so it could wind up being faster. My bets are still on slower largely due to immaturity of the platform.

Re:Actual Performance Difference

[Vlad_the_Inhaler]

There were linux benchmarks which made /. recently, comparing the speed of 32-bit code and 64-bit code on the Opteron. 32-bit code ran measurably faster.

Re:Actual Performance Difference

[rale, the]

I imagine this has been said on every single other amd64-related slashdot article, but here goes again... Running in 64-bit mode lets the Athon64/Opterons take advantage of a bunch of extra GPRs (general purpose registers), which enables better performance on applications compiled targeting it.

Re:Actual Performance Difference

[Neon Spiral Injector]

Microsoft has had a 64-bit version of NT since almost the start. Also sizeof (int) == 4 on AMD64, same as IA32. Just the pointers are larger.

Re:Actual Performance Difference

[cb8100]

Wasn't there a 64-bit version of Windows NT?

Re:Actual Performance Difference

[cubicledrone]

I wonder if a 64 bit OS will make any performance difference for the average desktop user.

Of course! We need an operating system that will support a pointer to all the RAM on the planet.

Re:Actual Performance Difference

[Tim C]

I don't remember Linux ones, but there were some for Solaris a couple of weeks ago. The benchmarks themselves were pretty widely slated here, though.

Re:Actual Performance Difference

[BeerMilkshake]

In a 32-bit machine, each fetch from memory retrieves 4 bytes. Even if you only use one, the other three are cached. So, when reading sequentially, you get four bytes for the price of one.

In a 64-bit machine, each fetch returns 8 bytes, so you 8 for the price of one.

Re:Actual Performance Difference

[Greedo]

Ask the Mac G5 users ...

Re:Actual Performance Difference

[ikewillis]

I already covered this on another thread of this story, but the primary advantage of AMD64 applications over IA32 is the increased number of registers that the AMD64 instruction set affords, 8 general purpose registers over the 4 provided by IA32. This can significantly improve performance as it reduces the chance code needs to hit cache or main memory in the event that 4 general purpose registers are not sufficient for the task at hand.

Re:Actual Performance Difference

[cookd]

Nope. int and long are still 32 bits, at least on MS platforms. long long is 64 bits. The only difference is with the pointers. Otherwise, you have to specifically request a 64-bit data size. This way, you can keep binary compatibility (struct layout) and avoid memory wastage for places where 64 bits aren't needed. But you get more address space, more registers, and faster 64-bit math (when needed).

I just saw some very simple CPU-bounded benchmarks that put the AMD64 2.0 GHz (on WinXP-64) at about 2X the dhrystones of a P4 2.0 GHz. Dhrystones are mostly meaningless, but they do show something.

Re:Actual Performance Difference

[Tester]

That's bizzare, the benchmarks that we did before porting Gentoo showed that the Opterons were actually faster in 64bit mode than in 32bit.. I attribute this to the presence of twice as many generic registers..

Re:Actual Performance Difference

[Zeinfeld]

I wonder if a 64 bit OS will make any performance difference for the average desktop user. Since its not like any normal people have more than a gig of ram anyways. Is it possible that it could even slow down 32 bit apps?

Its been a long time since I had performance issues due to CPU bottlenecks. My twin processor 650MHz box works just as fast as my 2.4GHz single processor box in practice.

The big issue for me are the cases where the stupid machine just locks up and does fuck all for 20 seconds or so. CPU meter shows 3% utilization, no disk activity. What is the stupid thing doing?

Same goes for UNIX systems, its not the processing thats the issues, or even the legitimate I/O delays, its the cretinous delays built into broken device drivers and applications.

I would like Windows to have a meter built in that would show which processes were waiting and the resources they were waiting on.

My other pet peeve is what the cretins at Checkpoint think is an acceptable VPN client. Every time the credentials time out a box appears for me to re-enter my credentials. Only I use cert based credentials stored in CAPI so all I am doing is hitting OK. Even so the box locks the user interface for about 90 seconds while it does something. Oh @$#(& it did it again.

Re:Actual Performance Difference

[DashEvil]

By Linux, do you mean Solaris? :P

Re:Actual Performance Difference

[Anonymous Coward]

Yeah, I think it ran on DEC's Alpha CPUs.

Re:Actual Performance Difference

[Cuthalion]

In ANY halfway modern architecture each fetch from memory pulls in a whole row of cache. Which is more than 8 bytes. The fact that more data needs to be moved for small operations to be completed is NOT a benefit.

Re:Actual Performance Difference

[Anonymous Coward]

Go their benchmarks aslo show a marked improvement for Linux on 64bit.

Some tests scored about as much as a 20% improvement in performance, athough it's more realistic to expect a 8-10% average improvement across the board.

Of course windows likely will run slower since it's so optimized for the older 32bit platform.

Linux is just a much more mature platform for 64bit computers. I mean we've had Suse 64bit (aviable for free from Suse's ftp install stuff) for almost a year now.

Re:Actual Performance Difference

[supun]

I think the DEC Alpha version was a hacked version of NT. I think they got it to work by masked off the top 32bits.

It's been sometime, so I don't remember if this was correct. I have an old 533Mhz 21164SX sitting in my basement collecting dust right now.

Re:Actual Performance Difference

[NanoGator]

"Ask the Mac G5 users ..."

Oh yeah, there's a civilized discussion brewing.

Re:Actual Performance Difference

[myg]

Actually, there are a few tasks that benefit from 64-bit code: Encryption, Databases, and file-systems. Most modern filesystems allow files >4GB and with digital video the norm now files much larger than 4GB are common.

So the processor spends less clock ticks doing 64-bit arithmatic for file offsets. Cryptography can benefit too. In particular the DH key agreement protocol and RSA public-private key cipher both require the use of "big numbers" (as in 1024 bits and up). And doing these operations 64-bits at a time rather than 32-bits can result in a performance impact. SSL session negotiation may be improved significantly, so that could be a boon to SSL webservers (not that IIS makes a great webserver).

Databases also need 64-bit numbers. Even low-end databases frequently have ID numbers that are 64-bits. For large databases the ability to compute page offsets (which are typically 64-bits) more efficiently can help.

And perhaps a subtle improvement may be in the handling of bitmaps. For example doing a bitwise operation 64-bits at a time will process more pixels than a 32-bit operation in the same amount of time.

But all of those things are really just noise for the special case of amd64. The x86 has always been a register-starved architecture. Going to 64-bit mode gives you 8 more general purpose registers. That alone may very well counter any of the performance loss due to 64-bit integers.

Lots of people on Slashdot have said 64-bit code is slower but haven't pointed out why. Probably the most important thing is cache coherency. 64-bit data structures are (surprise) larger than their 32-bit counterparts. That means that the effective rate of the cache is reduced. As an added bummer, address translation on 64-bit values is slower when there are more levels of translation.

Re:Actual Performance Difference

[irokitt]

If it's a c/c++ compiler, the c standard states that a type 'int' stays constant. A Microsoft compiler, if following standards (a reasonable assumption) would declare a seperat, 64-bit data type.

Re:Actual Performance Difference

[afidel]

Actually Windows kind of does, if you know how to use perfmon you can usually figure out where the box is being resource starved, although not necessarilly what process is being blocked. To do that on any OS you need to open up a debugger, unfortunatly when it comes to things like catching I/O interrupts the very act of debugging a process can make it behave differently.

Re:Actual Performance Difference

[Anonymous Coward]

Oy vey.

Anyone remember hard numbers on how much faster 16-bit computing was over 32-bit computing on the 386? Geez.

By the time of the 486, 16-bit code was SLOWER.

Re:Actual Performance Difference

[Miguelito]

Well I did some benchmarks using openssl's built in speed tests, and running in 64 bit vs 32 bit made a HUGE difference. Of course that was running a 64bit openssl as well. The opterons I have access to even beat the Itanium2s I have access to at work. By a lot in the smaller bit key sizes, but still either tied or beat the ia64 in the larger key sizes.

Here are the charts I made in OpenOffice on the data I collected. Even a 2GHz opteron beat a 3.2Ghz Xeon in 32 bit mode. :)

Of course this was just a benchmark, but it does show that things that use openssl would benefit from running under 64bit on an opteron.

Re:Actual Performance Difference

[Soko]

NT for Alpha had no long pointers and the same 4GB memory limit etc. as its IA32 counterpart. The processor was certainly 64 bits, but the OS was 32 bits at it's core. IIRC there were some places where they had to use 64 in order to get the thing to load, but not where it counted.

If Microsoft had actually used the Alpha to it's fullest potential, all of my servers would likely be runnning 21464s, not Xeons.

Yes, I'm still mad at DEC/Compaq/HP for squandering the Alpha tech. *grumble*

Soko

Re:Actual Performance Difference

[cant_get_a_good_nick]

C/C++ standard only guarantees sizeof(long) >= sizeof(int) >= sizeof(short). MS had this issue going from MSVC 1.5 (a 16 bit compiler, sizeof(int) == 2) to MSVC 4 (32 bit compiler, sizeof(int) == 4).

Java defines sizes. sizeof(int) == 4, and always will.

Re:Actual Performance Difference

[benzapp]

OMFG I can't believe I am still reading posts like this. How do people mod up such innane bullshit?

Can we ever have a 64-bit related discussion without these insanley simplistic criticisms that have been addressed 1000 times already?

I know PLENTY of people who have machines with a gig of ram!! 512 megs of ram has been standard for 2 years now!!! If 1 gig is the standard in a new machine today, don't you fucking think maybe 5 years from now we will need MORE than 4 gigs of ram??? HMM????

Re:Actual Performance Difference

[benzapp]

Actually, there are a few tasks that benefit from 64-bit code: Encryption, Databases, and file-systems.

Don't forget media encoding.

Ripping that DVD will be a LOT faster with a 64-bit optimized encoder.

Re:Actual Performance Difference

[Foolhardy]

Nothing in user mode can hog the cpu without showing up as cpu usage. Actually, cpu usage is measured as 100% minus the amount of time spent in the idle thread, according to the scheduler. Only something in kernel mode (a kernel driver) can hog the cpu like you described (3% usage reported); by sitting at a high IRQL.
Try updating, or changing to alternative drivers (if possible).

Re:Actual Performance Difference

[Doktor Memory]

My other pet peeve is what the cretins at Checkpoint think is an acceptable VPN client.

Shudder. Twitch. Scream.

I literally once quit a fairly lucrative job because we made the mistake of standardizing on Checkpoint for our firewall/vpn solution, and I was the lucky bastard who got to try to support SecuRemote on all of the company's assorted roaming laptops.

Never, EVER again. I spent three months on the phone with Checkpoint tech support every day trying to get that complete piece of shit to merely do what it was supposed to to. And as far as I know, the situation never improved, even after I left.

It will be a cold day in hell before I ever do business with Checkpoint again.

Re:Actual Performance Difference

[jkovach]

It depends on what you're doing. I recently gave myself a 1.8 GHz Opteron system for Christmas and have been running some performance tests comparing 32 and 64 bit versions of the same applications.

Using LAME compiled from source with the default compiler options and "--alt-preset standard" encoding settings, it took 4m20s to encode an 11 minute MP3 with the 32 bit version and 2m51s to encode using the 64 bit version - about 30% faster. However, comparing some of the filters in a 64 bit GIMP 1.3.23 compiled from source with default settings to the GIMP 1.3.23 from the Debian distribution was quite different - running the "Diffraction Patterns" filter with default options on a 512x512 image took 11 seconds with the 32 bit version and 16 seconds with the 64 bit version - about 50% slower!

Of the other tests I ran, MP3 decoding with mpg123, bzip2 compression and AES encryption with OpenSSL were faster in 64 bit mode, and 3DES encryption with OpenSSL was faster in 32 bit mode. Of course, one of the advantages of having a hybrid 32/64 bit processor is that you can run whichever version is faster for a given task, onlike on the Itanium which until recently had only software emulation for 32 bit code.

I have also heard that 64 bit Windows on Opteron is slower at running 32 bit code than 32 bit Windows on Opteron, which has made me want to rerun my 32 bit tests under a 32 bit kernel. I also want to run the same tests on a Mac G5 and a Pentium 4 for comparison. Some other time...

Re:Actual Performance Difference

[vrt3]

No, no: what he meant was that sometimes (quite often, actually) one process or the whole desktop becomes unresponsive, even though almost no CPU time is being used, the hard drive isn't working, no network traffic should be occuring etc. You just have to assume that something is waiting for something, but there is absolutely no indication what it is.

I see such delays almost every day; mostly on Windows (XP and 2000), but occasionaly on Linux too.

Re:Actual Performance Difference

[Anonymous Coward]

Why? Video is stream oriented -- the 9GB of a DVD never needs to be entirely in memory.

Re:Actual Performance Difference

[nfgaida]

The big issue for me are the cases where the stupid machine just locks up and does fuck all for 20 seconds or so. CPU meter shows 3% utilization, no disk activity. What is the stupid thing doing?

Same here. I experience this quite often on my dual AMD 1800 box at work (winxp). Often a ctrl-alt-del will show (explorer.exe) as "not responding". Frustrating.

Re:Actual Performance Difference

[Paul Crowley]

Bignum math would benefit enormously, but it's an atypical application...

Re:Actual Performance Difference

[Threni]

It's late, but I've two questions.

1) Why not have, say, 100, or 1000 registers on a chip?

2) What's the brightest, in theory, in terms of reflectivity - silvery chrome (like a mirror) or white? There was a thing on Slashdot a few months back about JPL Black - is there a white equivalent?

Re:Actual Performance Difference

[Tsiangkun]

I remember that story well . . .
prolly the first time 'hello world' was used as a benchmark. Some seriously fine reporting there.

Tsiangkun

Re:Actual Performance Difference

[Anonymous Coward]

No, no: what he meant was that sometimes (quite often, actually) one process or the whole desktop becomes unresponsive...

I see such delays almost every day; mostly on Windows (XP and 2000), but occasionaly on Linux too.

That sounds like it could be a hardware problem (since it happens regardless of your OS). I had similar problems when my power supply was failing. The hard drive wasn't receiving enough power and would occasionally spin down. If the OS tried to access the swapfile, the system would freeze; and if any application tried to access the hard drive, that application would freeze.

A hard drive with bad sectors or other problems could cause similar symptoms.

Re:Actual Performance Difference

[Zeinfeld]

No, no: what he meant was that sometimes (quite often, actually) one process or the whole desktop becomes unresponsive, even though almost no CPU time is being used, the hard drive isn't working, no network traffic should be occuring etc. You just have to assume that something is waiting for something, but there is absolutely no indication what it is. I see such delays almost every day; mostly on Windows (XP and 2000), but occasionaly on Linux too.

Yep, that is it. I know how to use perfmon, I can recognize an explorer crash. But sometimes the thing just goes off to sleep.

I noticed a similar issue with dotNET, it can take an awful long time to parse XML and while it is busy it can be stuck at 22% utilization on a 2 proc machine.

Outlook is also good at doing this when you make the mistake of using MAPI connect mode. The idiots at MSFT used RPC. The program can hang for an hour synchronizing.

This is all stupid programming, not all in the O/S. I want the O/S to point the finger at the programmer responsible. I want his picture on a Web site.

Re:Actual Performance Difference

[overturf]

>What is the stupid thing doing?

You may want to have a look at: MSKB.244139

This will set you up to generate a kernel dump on-demand with a key-sequence. If you're so inclined, you can analyze the kernel dump and see just what's backed up at the time of the hang...

Re:Actual Performance Difference

[Anonymous Coward]

And Windows NT ran on Alpha and MIPs a decade ago. NT was written to be platform independant. x86 wasn't even the CPU it was designed for, it was designed for the Intel n-ten prototype which never saw the light of day.

Re:Actual Performance Difference

[Anonymous Coward]

This is all stupid programming, not all in the O/S. I want the O/S to point the finger at the programmer responsible. I want his picture on a Web site.

So that you can voodoo him/her? ;-)

Re:Actual Performance Difference

[Skuld-Chan]

Funny as I've never had any of these problems on windows or linux (and I've got several dual proc systems) - maybe you guys have scsi termination issues.

Re:Actual Performance Difference

[Anonymous Coward]

Apparently you don't rip DVD's

Ripping a DVD to divx or whatever is a time consuming process.

When people say "rip a dvd" they aren't referring to simply the process of copying the .vob files to your hard disk. They are referring to compressing that MPEG-2 data into some other format.

Re:Actual Performance Difference

[gnosys]

Actually I have a gig of ram, and it does seem to be speedier with both Adobe Photoshop Elements and Corel Draw / Photopaint

Re:Actual Performance Difference

[grahamdrew]

I wonder if a 64 bit OS will make any performance difference for the average desktop user. Since its not like any normal people have more than a gig of ram anyways. Is it possible that it could even slow down 32 bit apps?

At this point it probably isn't going to make a big diffrence for Mr. Joe Average Desktop User. Most normal people don't have 64-bit processors, though. The ones that do have 64-bit systems are the power users who are going to dump in a gig of ram, anyway. After spending a few hundrad dollars on a new 64-bit system and motherboard, what are the chances you're going to cut corners and buy 512M of ram, anyway?

Re:Actual Performance Difference

[Anonymous Coward]

Yes, having your SCSI or IDE bus reset will effectively lock up both the Windows Explorer and prevent you from launching any new programs -- I see this all the time on 1 machine I have with some flakey old CD burners.

Re:Actual Performance Difference

[Anonymous Coward]

I accept that MPEG encoding is time consuming, but I don't see how 64-bit improves the situation.

Re:Actual Performance Difference

[Anarke_Incarnate]

www.netscreen.com and never look back

Re:Actual Performance Difference

[Anarke_Incarnate]

what are you using now? Please don't say PIX. I have tried like hell to get my company to stop using that crap. Its miniport drivers screw up networks like nobody's business. I hate it with a passion and wish they'd go to netscreen or something else. The firewall itself is not bad, but I wish we didn't run it on a 2K box.

Re:Actual Performance Difference

[vrt3]

I don't think it is hardware related, since I have seen it on my very old desktop, my old desktop, my laptop, my computer at work and other machines.

Re:Actual Performance Difference

[Anonymous Coward]

For all the pseudo-experts whining about how a 64-bit OS won't help desktop users, this performance difference isn't due to 64-bit code so much as the extra registers in x86-64 mode, which would help any operating system that isn't completely braindead. Even regular apps should run faster that way. x86 has always been far behind the competition in the number of registers.

Re:Actual Performance Difference

[jaavaaguru]

This just reminds me of the discussions about 64-bit desktops that have already taken place on Slashdot and OSnews regarding Suns and Apples. Is there any reason why desktop user experience with 64-bit machines will be any different for Windows users? (apart from the obvious differences caused by using Windows instead of Solaris/OSX).

Re:Actual Performance Difference

[Moraelin]

The biggest actual performance difference will not be because of 64 bit integers, and definitely not because of having 8 GB of RAM.

The big difference is that in 64 bit mode you have twice the registers, and a bunch of new instructions. So basically switching to 64 bit mode doesn't just give it long-onna-register, it almost gives you a completely new RISC-like CPU.

Re:Actual Performance Difference

[GreatDrok]

Microsoft has had a 64-bit version of NT since almost the start. Also sizeof (int) == 4 on AMD64, same as IA32. Just the pointers are larger.

Ummmm, no. While NT was able to run on the 64 bit Alpha processor, the code was all 32 bit. It is only very recently that MS has got around to doing 64 bit code. Compared with Linux they are very late in the game, Linux was running in full 64 bit mode way back in '93 or so.

Re:Actual Performance Difference

[Xabraxas]

And Windows NT ran on Alpha and MIPs a decade ago. NT was written to be platform independant. x86 wasn't even the CPU it was designed for, it was designed for the Intel n-ten prototype which never saw the light of day.

And in that ten years or so Windows has become x86-centric. For most of that time x86 has been the only platform that Microsoft has focused on for Windows.

Re:Actual Performance Difference

[Anonymous Coward]

No, Linux (and *BSD etc., plus the portable Unix/X11 software that runs on all of them) is mature as a 64-bit platform because support for 64-bit systems has been there for many years, starting with the Alpha back in the mid-90s.

Adding yet another 64-bit platform is easier because the hardcoded 32-bit assumptions have been eliminated long ago (Linux was originally full of not only 32-bit assumptions but also x86-specific assumptions) and maintaining cross-platform compatibility has kept them from creeping back in (MS might not have been so lucky, as they dropped Alpha support long ago).

If Linux had only got 64-bit support with the recent amd64 support, I definitely wouldn't consider it mature yet.

Re:Actual Performance Difference

[ckaminski]

Linux was barely runnable in 93 or so. 95, 96 I can believe, but 93? Got a CVS tree to back that up? I'm genuinely curious, not trying to start a war...

Re:Actual Performance Difference

[ckaminski]

1) Why not have, say, 100, or 1000 registers on a chip?

Transistor space. I don't know about you, but I only have about 100 sq inches of space in my 19" racks for a motherboard. Can't make CPU's much bigger than that.

2) What's the brightest, in theory, in terms of reflectivity - silvery chrome (like a mirror) or white? There was a thing on Slashdot a few months back about JPL Black - is there a white equivalent?

Hmmm... good question. Are we talking theoretical pure white, or real live white stuff, like sugar? Having worked with lots of white powders in my day (plastics precursors), I'd have to go with silvery chrome. I've never been blinded by the sun glinting off a pile of sugar, but I sure have when it glinted off the bumper of my '84 Buick tank.

Re:Actual Performance Difference

[GreatDrok]

My bad. I did a quick search and the first occurance of arch/alpha in the kernel tree was version 1.1.67 dated Nov 28 1994. I was a little early on my estimate with 93. I started using Linux in 94 using a 1.0 kernel which was perfectly usable to me coming from SUNOS 4.1 on SPARC. I remember seeing my first Alpha boxes two years earlier running DEC OSF (yuk!). The first alpha releases were 32 bit, DEC demo'd axp-linux in May 1995 which is said to have been fully functional so that may or may not have been 64 bit. I believe Linux was fully 64 bit by the time 2.0 was released anyway and that was certainly in 1995. I didn't start running Alpha/Linux until 1998 by which point they were very well supported. Either way, it is fair to say that Linux has been 64 bit for a long time now, probably 9 years.

Re:Actual Performance Difference

[Threni]

> Are we talking theoretical pure white, or real live white stuff, like sugar?

Anything that's makeable, like the JPL black.

> I've never been blinded by the sun glinting off a pile of sugar, but I sure have > when it glinted off the bumper of my '84 Buick tank.

Sure. But there's snow blindness - the light from that is pretty powerful. And I guess there's no reason why your bumper coulnd't be metallic red and perhaps more or less equally blinding.

Re:Actual Performance Difference

[GreatDrok]

Damn. 2.0 was 1996 not 1995, too quick off the mark. So, linux has been 64 bit for 8 years anyway.

Re:Actual Performance Difference

[Bert64]

SSL benchmarks really benefit from 64bit platforms, my 6yr old alphastation still runs very well on those benchmarks...
On a side note, openssh on solaris doesn`t like being compiled as 64bit, it screws up the wtmp logging for some reason

Re:Actual Performance Difference

[Bert64]

No, there was no 64bit version of NT.. Altho it did run on a 64bit processor (Alpha) it used what DEC called "taso" which emulates 32bit pointers and address space.
sizeof(int) is 4 on virtually every unix platform, including 64bit ones... sizeof(long) is usually 8 on 64bit platforms (atleast solaris, digital unix, irix and linux/alpha) and 4 on 32bit platforms

Re:Actual Performance Difference

[Bert64]

Wanna sell it?

Re:Actual Performance Difference

[Bert64]

Thousands of registers might make batch processing faster.. but it would make context switching (switching between different processes) very slow...
you`d effectively be building a machine that could do one thing at a time very quickly, but the performance increase wouldn`t be worth the difficulty of implementing it like this..
I can imagine certain ASICs having large sets of registers, for tasks where it`s appropriate.

Re:Actual Performance Difference

[Bert64]

If it locks for 20 seconds without cpu usage... sounds like a hardware problem, one of my linux boxes used to do that, but reading the dmesg log showed a disk problem and the 20 seconds pause was while it reset the scsi bus..
As for a dual cpu box appearing faster than a single, thats normal.. theres less latency with multiple cpus, even if the cpus are slower.

Re:Actual Performance Difference

[Ben Hutchings]

I have also heard that 64 bit Windows on Opteron is slower at running 32 bit code than 32 bit Windows on Opteron, which has made me want to rerun my 32 bit tests under a 32 bit kernel.

That sounds reasonable. The 64-bit version has to switch modes and convert parameters for each Win32 call that requires a system call (and possibly for some that don't).

Re:Actual Performance Difference

[Threni]

It would be good for games though.

Re:Actual Performance Difference

[Anonymous Coward]

Wrong!

Should be faster, as the new complier has makes use of the extra registers, and the system has been recompiled.

Its not hugely faster, depening on what your doing, you get between 5 and 15%.

And if you start doing multithreaded stuff on a dual box it will also take advatnage of the NUMA architecture, if the CPU's have their own memory (more expensive boards)

Re:Actual Performance Difference

[Anonymous Coward]

generate a kernel dump on-demand

why not cast rune stones? It's probably just as effective.

Re:Actual Performance Difference

[Digi Dude Takato]

Im not too knowledalbe on bentchmarks and such, but I do know about processors. One thing that I know about them is that the Xeon is not in the Pentium family. So why do they call it the

COPIED STRAID FROM THE ADVERTISEMENT

3.2 GHz Pentium 4 Xeon DP (1 MB) 3.06 GHz Pentium 4 Xeon DP (1 MB) 2.8 GHz Pentium 4 Xeon DP (512 KB)

Thats just a question I would like answered.

Re:Actual Performance Difference

[Vlad_the_Inhaler]

I am sure you are right. I was just about to head off for a week and did not have the time (or inclination at that point - it was 23:40 local) to look it up.

:-)

Vlad

Speculation ?

[Space cowboy]

We don' need no stinkin' speculation, why this is as obvious as a cow on a haystack!

Seriously, just what grounds do you need for bringing charges of industrial manipulation of the market by the two largest players ? Ok, there's no evidence (yet!), but just how thin can you stretch credulity before SNAP! ?

Simon

Re:Speculation ?

[fnord123]

I don't get your logic.

If MS & Intel where in league, wouldn't MS not release this until Intel had an x86-64 chip out?

Re:Speculation ?

[Anonymous Coward]

So you don't offer any evidence for a claim that you don't even make. You just say we don't need speculation to see what is happening. You don't offer to tell us what exactly is happening, nor do you tell us why we should believe your claim, which you never made in the first place. And this gets modded insightful. Rigor at its finest.

Re:Speculation ?

[Xocet_00]

Let me see if I understand your argument. You read the article, which means you must've read this: "Important: Windows XP 64-Bit Edition for 64-Bit Extended Systems is only compatible with 64-bit AMD Opteron- or Athlon 64-based computers. It cannot be successfully installed on 64-bit Intel Itanium-based systems." ...and conclude from it that Microsoft and Intel are out to beat up on AMD. Microsoft releases an AMD only copy of it's flagship operating system, for FREE, prior to the release of Intel's 64-bit offerings, and this is somehow a conspiracy to hurt AMD's marketshare? RTFA

Re:Speculation ?

[Steven Reddie]

Get a grip people. Microsoft have had this 64-Bit version in the works for a while (of course; but I've also read about it on their website over the last month). What, you think that Intel announce a change in plans and Bill persuades the coders at Microsoft to stay up all night producing a 64-Bit version of XP. If only it were really that easy. Give me a minute and I'll produce a 128-Bit version of the internet... There, done!?

Re:Speculation ?

[tunah]

No, he's talking about the two largest players in a single market - massive scale collusion by Intel and AMD!

Re:Speculation ?

[Anonymous Coward]

Versions of Windows for the Itanium have been out for years.

Re:Speculation ?

[Xocet_00]

I wasn't talking about the IA64, I was talking about Intel's x86-64 offerings which, I'm sure you'll agree, aren't out.

Re:Speculation ?

[dellis78741]

Well, in fact, they -haven't- released it...just a still-buggy demo version. You can be pretty sure that a full production version will come out -very- close to the point in time when Intel has full production hardware in the channel. So on the one hand MS tells AMD "Yeah, we'll write a version of Windows for your new chip" and then turns around and tells Intel "You need to join this party but we'll give you a break and sit on it until your are ready so the other guy doesn't get too much of a head start".

Re:Speculation ?

[drinkypoo]

It would probably be enough to simply wait until they decided what they were going to do with their chip. Then the beta comes out, then the release of the intel chip and the new release of windows more or less coincide.

Intel will have to follow AMD

[Random BedHead Ed]

At this point there's enough Opteron stuff out there that Intel can't avoid implementing an architecture compatible with amd64. Yes, I think the timing is probably not a coincidence. Though I'm sure Microsoft wasn't waiting for Intel, they probably informed Groves and Co. of the release in advance.

If Intel can't stay compatible with AMD's lineup they could end up behind. That would certainly be a first for Intel.

Re:Intel will have to follow AMD

[Gactaculon]

Actually, a second... witness Athlon vs. the early P4. With both companies pursuing such widely divergent strategies in chip design, anything could happen, and Intel is certainly not unassailable.

Re:Intel will have to follow AMD

[Slack3r78]

That would certainly be a first for Intel.

Not really, it'd just be reverting back to where things were about 4 years ago. AMD was the first to break 1GHz, remember? It wasn't until later with the introduction of SSE2 (which the Athlons lack) and AMD hitting a brick wall with ramping up the clockspeed on the Athlons that Intel regained the overall performance lead. When it comes to price/performance, Intel has always lagged behind.

Re:Intel will have to follow AMD

[Jeff DeMaagd]

At this point there's enough Opteron stuff out there that Intel can't avoid implementing an architecture compatible with amd64

Huh? Last I saw any numbers (a week ago?) there were about ten thousand Opteron systems sold last year, with about five thousand Itanium systems, when compared to a market of millions of PCs.

That alone isn't really enough to scare anyone, although it is mostly the same core logic as A64 so anything made for Opteron may trickle into software for the cheap desktop version of the chip.

Re:Intel will have to follow AMD

[Deliveranc3]

Behind, infront it's all marketshare. We all know where the price performance ratio rests and it's green not blue :)

Re:Intel will have to follow AMD

[dellis78741]

The thing that annoys me the most is that Intel has guessed wrong badly twice in trying to drive the market deeper into their corner(RAMBUS, Itanium) and AMD has guessed right both times (DDR, X86-64) and all the time Intel cranks out a profit every quarter and AMD come's up for air for a couple of quarters every other year. If Intel were going against an equal-sized adversary they'd be chapter 11 some years ago for making such mistakes.

Re:Intel will have to follow AMD

[Anonymous Custard]

The thing that annoys me the most is that Intel has guessed wrong badly twice in trying to drive the market deeper into their corner(RAMBUS, Itanium) and AMD has guessed right both times (DDR, X86-64) and all the time Intel cranks out a profit every quarter and AMD come's up for air for a couple of quarters every other year. If Intel were going against an equal-sized adversary they'd be chapter 11 some years ago for making such mistakes.

I wonder if Intel's exclusive, deep discount intel-only deal with Dell will ever come up in an anti-trust hearing. Dell gets to remain ahead of the competition with awesome processor prices, and Intel gets guaranteed market share.

Re:Intel will have to follow AMD

[joib]

Yup, I think Intel is between a rock and a hard place.

- drop ia64 prices to compete with amd64 => forget the wet dreams about huge profit margins on the high end stuff.

- introduce something amd64-like (yamhill?) => ia64 market fails, no huge profit margins on high end stuff. Also big PR loss. Lots of money wasted on ia64 project.

- keep going as is. amd64 commodizes high end market => no huge profit margins.

Regardless of what they do, they lose! Not a nice place to be in. IMHO the least bad option for intel (and perhaps users too) would be the first one, but it appears that they are going for the second one?

Re:64 bit

[Xugumad]

It's particularly frustrating for me, as I have a motherboard for a 64bit processor, but the processor has disappeared into the postal system. I'm taking bets on how many weeks it takes before I finally have a complete working system...

Simple

[Tenfish]

Intel and Microsoft may or may not have a business deal to promote Intel's 64-bit processors. Microsoft wouldn't do this for AMD, because splitting the processor targets would cost Microsoft money. Developing for two processors is more expensive than developing for one. There's no need to delve into anti-corporate mumbo-jumbo to explain this one. It's simple economics, and probably good business from Bill Gates' point of view.

Re:Simple

[diamondsw]

Looks like someone needs to double-check that with Bill, then:

"Important: Windows XP 64-Bit Edition for 64-Bit Extended Systems is only compatible with 64-bit AMD Opteron- or Athlon 64-based computers. It cannot be successfully installed on 64-bit Intel Itanium-based systems."

I don't see any mention of an upcoming Intel it will run on, either.

Re:Simple

[dreamchaser]

There is already native Windows XP for the Itanium.

Re:Simple

[cubicledrone]

64-Bit Edition for 64-Bit Extended Systems is only compatible with 64-bit

You will need 64-bit RAM and a 64-bit CPU and the latest versions of Disk64, Monitor64 and Soundcard64 with the extra-fast super-amazing 8064-bit VIDEOZAP ULTRA MEGA ZING FLAPPA ULTREON WOW VIDEO card.

"Then can I write this 27-line spreadsheet?"

Re:Simple

[Comatose51]

For MS to port Windows over the x86-64 is relatively easy when compared to porting it over to a totally different architecture. The way Windows is designed, much of the hardware is hidden. So MS only needs to change the code before the hardware abstraction layer. Furthermore, x86-64 is an extension of x86 so I can't imagine it being too difficult to do. So, if it doesn't cost MS too much, doing this just for AMD is a good way of hedging their bets. If the Opteron takes off in the server market, they don't want all of it to go to Linux.

Re:Simple

[Anonymous Coward]

Before you start with the conspiracy theory crap, you should probabally realize that this has been in the works @ MS for a few months at least now. This didn't "Just Happen" because Intel cranked out a 64 bit proc. MS was working on this right after AMD announced their 64 bit stuff.

I can't help it that the editor is an idiot looking for bias and conspiracy theories.

Re:Simple

[mlafranc]

I have an AWE-64 in my linux box, seems like a good starting point heh.

Speculation...

[ackthpt]

Now Intel just changed their 64-bit plans, and all of a sudden this appears. Speculate away!"

I speculate in a couple days Microsoft will deny this release exists, as they suddenly pull it to give their old cartel partner a chance to catch up and save face.

Consider this:

Microsoft has an evaluation operating system for the Yamhill before Intel actually ships. That doesn't just look like they've been playing patty-cake, but that Intel is running to keep up with AMD. How embarrassing. What's Moore's Law got to say about this? "Every 2 years Intel will get a little further behind where they need to be, by an ever increasing margin until operating systems exists for processors they haven't even designed yet."

Re:Speculation...

[cubicledrone]

Yamhill

Sounds like a tractor.

Re:Speculation...

[NanoGator]

"Sounds like a tractor."

I can't tell if it sounds like a river or a major street in Portland. Not sure about tractor, tho.

Re:Speculation...

[concordeonetwo]

Yamhill is a street in Portland. It also is the name of a county in Oregon.

Thank you!

[Call Me Black Cloud]

I appreciate the link to Microsoft's website. I've been looking all over for that thing and haven't had any luck finding it. You've saved me from a lot more time spent searching, my friend.

Re:Thank you!

[higgins]

I was very confused and kept going to this Mike Rowe guy's site instead. I tell ya. There oughta be a law.

Re:Thank you!

[zhevek]

Wow, me too... I thought it was mikerowesoft.com!!

Re:Thank you!

[vDave420]

I was very confused and kept going to this Mike Rowe guy's site instead. I tell ya. There oughta be a law.

Funniest post of the year. Laughed out loud for awhile!
Too bad it was 4:00AM. The neighbors probably think I am nuts!

-dave-

Dennis Kucinich for President! He has all the right ideas.

Re:what does it mean anyway?

[Moth7]

It's going to give the rich kids yet another spec increase to show off about ;)

I've been using it for a while.

[Sheetrock]

Very crisp. Despite the double memory/instruction access time created by accessing words twice the size of the 32-bit chips, I think they're using the new chaining instruction set to double or triple most of their refresh operations. And it's still got Solitare.

Re:I've been using it for a while.

[petabyte]

And it's still got Solitare.

Ooooh, I never thought of that! Anyone have the benchmarks on how much faster solitare is in 64-bit? :)

Re:I've been using it for a while.

[kma]

Despite the double memory/instruction access time created by accessing words twice the size of the 32-bit chips, I think they're using the new chaining instruction set to double or triple most of their refresh operations.

Yeah, that "double memory/instruction access time" is a doozy. Luckily they reversed the polarity of the "chaining instruction set" to create a discontinuity in the computron field. By rerouting the tachyons to the ALU, they've been able to double-pump the, umm, chain cache.

Re:I've been using it for a while.

[ctid]

My apologies for asking what is probably a stupid question, but does this thing run existing 32-bit applications as well?

Re:I've been using it for a while.

[Anonymous Coward]

Um, yeah, considering it'd end up a market failure if it didn't....

Re:I've been using it for a while.

[cubicledrone]

Ooooh, I never thought of that! Anyone have the benchmarks on how much faster solitare is in 64-bit? :)

Yeah. It gets about 520 frames per second on a half-gig video card. The bouncing card animation after winning takes about 0.8 seconds.

Re:I've been using it for a while.

[Anonymous Coward]

Well, duh. Does a 32 bit processor run 16 bit applications? This is a rhetorical question, please do not answer it.

Re:I've been using it for a while.

[Anonymous Coward]

Go back to managing servers assmonkey.

Re:I've been using it for a while.

[Gryll]

I was disappointed to find out that this is the same version (v1069) which has been available on MSDN for months now. I have used it only slightly as there are still no audio drivers for the NForce3 chipset.

I can't bring myself to put a sound card in the single PCI slot on my Shuttle XPC just to see how fast Warcraft III loads with a 64bit OS, is there any other program worth running on Windows?

Re:I've been using it for a while.

[Lord Kestrel]

Civ3, Xcom and Nethack.

Re:I've been using it for a while.

[addaon]

Wait, you can win?

Windows Media Player?

[ikewillis]

Will the AMD64 build include Windows Media Player? It was left out of the IA64 version due to what I can only assume are 64-bit cleanliness issues with the DirectShow API and WMP code. I can only assume that an AMD64 build would allow 32-bit builds of DirectShow and WMP which execute through the WoW abstraction layer.

Re:Windows Media Player?

[OrenWolf]

You don't need to abstract it.

That's the point. The chip can execute 32 bit code natively. All you need are appropriate 32-bit libraries (DLL's in windowsspeak).

That's how Linux does it. want a 32 bit app? Install the 32 bit glibc and you're good to go.

Statically compiled apps need *nothing*.

Re:Windows Media Player?

[ikewillis]

Evidently you haven't heard about the Windows-on-Windows (WoW) subsystem utilized on AMD64 processors:

"The Microsoft(R) WOW64 (Windows(R) on Windows) subsystem will allow most 32-bit applications to launch seamlessly on 64-bit Windows," said Brian Marr, Windows product manager. "WOW64 is designed to provide interoperability and great performance on AMD64 processors across the 32/64-bit boundaries. As customers migrate to 64-bit Windows XP and Windows Server, they will have a code base that will support both 32- and 64-bit applications."

While it's wonderful Linux understands multiple ABIs natively, Windows does not, and utilizes WoW to seamlessly launch 32-bit applications on 64-bit builds of Windows.

Re:Windows Media Player?

[Deagol]

How far down will XP-64 thunk, anyway? Are the 16-bit and 32-bit layers at the same level? Or does 16-bit sit on top of 32-bit? So a 16-bit Windows app will be thunked through 2 layers now?

(Sorry -- I just had to make this post. I remember when all the rags had countless articles on "thunking" when Win95 came out. Will we have the same when the first mass-market 64-bit OS hit the streets? Not that I know of any good PC rags these days -- suggestions?)

Re:Windows Media Player?

[4of12]

This WOW64 looks like Microsoft is preparing to make the migration from 32 bit to 64 bit with the same mellowy smoothness that characterized their 16 bit to 32 bit migration. *shiver*

Re:Windows Media Player?

[afidel]

I would imagine that the Win16 subsystem would in fact run under WOW64 since it makes use of 32 bit Windows system code.

Re:Windows Media Player?

[daina]

Yes, Build 1069 of Windows XP 64-bit includes Media player. It is a common misconception that Media Player was left out of the OS, but it is untrue.

I have been running 1069 for several weeks, and Media Player has been working fine with two exceptions: it has no support for DVDs and I have had some trouble installing nonstandard codecs. I am not sure why.

Build 1069 also includes a 64-bit build of IE, which is noticeably very much faster at drawing and reflowing complicated pages as compared with the 32-bit version on the same machine under old Windows XP.

Unfortunately, I have not been able to find a single benchmark compiled for AMD64 in order to do further speed testing, nor in fact any other AMD64 applications for real-world type comparisons. Apparently Sisoft Sandra has been released for AMD64, but I cannot find it.

Expanding zip archives with WinRAR is so fast on my AMD 3200+ system with 1GB DDR400 and MSI MB that, at first, I sat there waiting for something to happen, not realizing the operation had completed without raising an hourglass. I suspect that this may be a chip architecture effect, rather than a speed advantage of XP64, however, since it seems fast under XP32 and my version of WinRAR is certainly not complied for AMD64.

The only real problem is drivers. I managed to get a Promise SATA driver running well in SATA (rather than RAID) mode by downloading the very latest drivers from Promise.

System requirements

[Faust7]

Windows XP 64-Bit Edition is designed to address the most demanding needs of technical workstation users who require large amounts of memory

System Requirements:
PC with an AMD Athlon64 or Opteron processor
256MB RAM

Yeah, I know they're minimum requirements, but it's amusing to think that anyone who needed this OS would actually have to refer to them.

Re:System requirements

[greymond]

"it's amusing to think that anyone who needed this OS would actually have to refer to them." lol

and since when do people who need/use a 64bit processor think 256MBs of memory is "a lot of memory"

Re:System requirements

[Anonymous Coward]

"Yeah, I know they're minimum requirements, but it's amusing to think that anyone who needed this OS would actually have to refer to them."

Minimum requirements: 2^32 bytes of memory. Anyone with less should install the old system...

Re:System requirements

[PaulK]

From the xp_amd64.txt file on the downloaded iso:

512 megabytes (MB) of RAM (minimum)

I'm sure that Microsoft would never deliberately mislead anyone, so this must be a simple error on their website or in their release documentation.

There's a first time for everything. :)

Re:System requirements

[Anonymous Coward]

Only if you think about recent 64-bit processors, but considering that 64-bit processors have been around for more than a decade...256MB is more than a lot of 64-bit Alpha workstations had back in the 90s.

Re:System requirements

[Anonymous Coward]

true, but you have to keep in mind these are the system requirments/blurb listed on a new product thats going to be released for a current hardware.

it's just somewhat humorous(sp?)

Why 64 on Desktops

[tymbow]

We'll probaly have to wait for the next "killer app" (god I hate that phrase) before it becomes mainstream for desktop users. I can't see a need for it on the desktop just yet. Big database clusters on the other hand...

Re:Why 64 on Desktops

[ikewillis]

The primary advantage of AMD64 applications over IA32 is the increased number of registers that the AMD64 instruction set affords, 8 general purpose registers over the 4 provided by IA32. This can significantly improve performance as it reduces the chance code needs to hit cache or main memory in the event that 4 general purpose registers are not sufficient for the task at hand.

Re:Why 64 on Desktops

[ProtonMotiveForce]

This is a minimal benefit. The percentage performance increase due to this is no bigger than typical benefits of other processor improvements from one generation to the next.

Meaning - you can get a similar benefit from higher GHz, better branch prediction, more cache, etc... without having to recompile all your shit.

Re:Why 64 on Desktops

[pyropaul]

People who work on the back-end physical aspect of chip design have been using 64-bit processors for some time now. Back-annotated post-route netlists consume far more than 4Gbytes of memory. This is why 64-bit HP and Sun workstations are used, even though their Mhz ratings (which are meaningless anyway) don't compare with the clock-multiplied intel 32-bit chips.

Re:Why 64 on Desktops

[pla]

I can't see a need for it on the desktop just yet.

One word - Ramdisk.

Set yourself up with a nice 1GB ramdisk, and make everything with a user-settable temp and/or cache directory point to it (most media apps, MSIE, Mozilla/Netscape). Also point your "temp" and "tmp" environment variables to it.

Personally, I still use 2K and consider XP a total dog. Circumstances recently having forced me to use it quite a bit, however, I found that it hits the disk constantly. Setting just a 64MB ramdisk (on a machine with only 256MB) literally doubled its responsiveness. And theoretically, this should increase the life, and decrease the fragmentation, of your HDD.

The one down side, some programs will complain if they can't fit their data on the temp dir (so for example, in Netscape, which for some unknown reason stores your downloads there before moving them to their real destination, downloading a 70MB file with only a 64MB temp ramdisk will make it complain). At a GB or two, though, I expect that would very rarely cause any problems.


Another reason, that the recent so-called "benchmark" failed to consider - We've had 128b and even 256b GPUs for a while now. AGP (and PCI64, currently rare but 64 bit CPUs should push it into the mainstream) will benefit GREATLY from native 64b drivers. Perhaps we'll finally see Doom 3?

Re:Why 64 on Desktops

[tymbow]

How do you do ramdisk in W2K/XP (I'm too lazy to Google it)? Also, I'm fairly sure IE does the temp download thing just like Netscape (download a large file and look at the filename as it "copies" it to your nominated location). I think we'll see DukeNuke Forever before Doom3 :)

Re:Why 64 on Desktops

[pla]

How do you do ramdisk in W2K/XP (I'm too lazy to Google it)?

It doesn't come with Windows, but a number of 3rd-party programs (mostly all based off a reference MS driver, ironically enough) exist to do it for you.

Personally, I like QSoft's, which installs easily and works well. The free version theoretically has a 64MB limit, but I've had no problem telling it to use half-a-gig (and the pulldown menu goes to 1GB, but I don't have a machine with enough RAM to try that one).

And, as I mentioned, just 64MB makes a HUGE difference in responsiveness under XP. Still helps on 2k, but not nearly as noticeable.

Re:Why 64 on Desktops

[Lord Kano]

Personally, I still use 2K and consider XP a total dog. Circumstances recently having forced me to use it quite a bit, however, I found that it hits the disk constantly.

What are you running? I have XP SP1 on my machine (Athlon XP 1800/512MB) and I only have disk access when I'm doing something. If I launch an App, or compile something big, or load up some pr0n I get lots of disk access, but for more mundane tasks I get almost no disk access.

Maybe you should try disabling some of the unnecessary services.

LK

Extensions?

[Ossifer]

Anyone want to bet on Microsoft already having support for Intel's secret extensions on AMD 64-bit extenions?

Re:Extensions?

[dellis78741]

Those extra extensions need only be used in a few key apps, not Windows itself, to allow Intel to introduce their new hardware with some Powerpoint presentation graphs showing how their implementation of x86-64 beats the competition into the dust. Never mind that 98% of the apps out there either won't use them or wouldn't gain from doing so anyway.

How's this for speculation

[iminplaya]

Micrososft is doing this to keep us distracted away from Linux until Longhorn comes out. Two years is a long time, so we can always expect bits and pieces of "neato" stuff in the meantime.

Re:How's this for speculation

[contrasutra]

You're right, Microsoft couldn't POSSIBLY release a new feature for any other reason. In fact, every single decision they make must involve Linux somehow.

I'm pretty paranoid, but EVERYTHING isn't a conspiracy......or is it? ;-)

Re:How's this for speculation

[iminplaya]

Hey...they said, "Speculate away!" So I'm a speculatin'

I'm pretty paranoid, but EVERYTHING isn't a conspiracy......or is it? ;-)

If it involves more than one person, it's a conspiracy. :-)

Re:How's this for speculation

[Anonymous Coward]

How is this for speculation... Try Three years...

no need to speculate

[ciroknight]

It makes perfect sense, everyone knows about the Wintel relationship, that's why Microsoft hasn't made an operating system to run on an apple computer, and has also stopped the flow of any apps that help to do so *ala, virtual pc*, even though apple's hardware is far superior.

I think the move of Microsoft to put G5's in the Xbox2 will start to shift this although.. Microsoft as well as anyone knows they can't continue to be architecture dependent especially in this new world. AMD has quite a good 64 bit chip now, so does IBM (and from that, Apple). The beauty of killing the old 9x Kernel allows for this, as the NT kernel was designed originally to run on different kind of archetectures, even when the design of 9x was still going on.

Basically.. Microsoft is gearing itself to extend it's hold on computing before it's grip becomes too weak to even matter, no speculation required.

Re:no need to speculate

[swissmonkey]

that's why Microsoft hasn't made an operating system to run on an apple computer, and has also stopped the flow of any apps that help to do so *ala, virtual pc*, even though apple's hardware is far superior.

VirtualPC for Mac can be purchased separately and will come bundled with Office.

Check your facts

Re:no need to speculate

[pokka]

and has also stopped the flow of any apps that help to do so *ala, virtual pc*, even though apple's hardware is far superior.

What are you talking about? Microsoft just released a new, far superior version of Virtual PC which is a G4 optimized (last version was not), native OS-X application. It's 20% faster, puts a start menu in the dock, supports copy/paste between windows/mac, supports seamless networking between win/mac, etc.

Re:no need to speculate

[ProtonMotiveForce]

Oh come on, I though you people had special Troll recognition. I've seen subtler trolls under the bridge leading to my house - they always sneak up on me and mutter stuff about eating my bones.

This guy is 100% troll and it's 110% obvious.

Re:no need to speculate

[BeerCat]

Microsoft as well as anyone knows they can't continue to be architecture dependent especially in this new world. AMD has quite a good 64 bit chip now, so does IBM (and from that, Apple). The beauty of killing the old 9x Kernel allows for this, as the NT kernel was designed originally to run on different kind of archetectures, even when the design of 9x was still going on.

Running old 9x software under emulation on new hardware (G5 powered XBox2, AMD64, Itanium, whatever the next big thing will be) was one of the reasons for buying Connectix. Virtual PC was available for Windows as well as Mac. That the MacBU is bringing out an updated version is a bonus.

Re:no need to speculate

[fnord123]

Microsoft didn't port their OS to Apple PCs because Apple was selling a complete HW/SW system with an already superior operating system to Windows. Who in their right mind would pay a lot of money for an Apple box then throw away the superior MacOS and spend even more money and run Windows?

Some of the posters here have such an extreme dislike for Wintel that they see the Wintel bogeyman everywhere.

Re:no need to speculate

[Anonymous Coward]

Yah to bad their operating systems sucks so it makes it extremely difficult to port it to anything other then x86.

Like was running well on amd64 long before this release came out...

Lets see Windows NT-based OSes run (w2k in 32bit mode) on Alpha proccessors, x86 platform, Intanium, and AMD64...

Linux runs on Sun Sparcs, Alpha, S/370 (IMB mainframes), x86, itanium, amd64, SGI non-x86 intel platforms, SGI workstations, PPC (power3,power4,power5,power970,G3's,G4's) etc etc

As MS will be banging their heads against the wall trying to make the blackhole that is windows code work well on something other then x86 instructions, Linux will be ported first and run faster on anything coming out in the near or distant future at fraction of the cost.

Re:no need to speculate

[Selecter]

Yes, and thats the freakin version for the G4!

If this does not inform as to how ahead the hardware is over the OS's and the software right now on every platform. Apple has the lead over AMD & MS but not by much.

The next 2 years are going to be a blast. I am thankful I was born at the right time (1963) to come of age to see the computing revolution from it's practical start (late 70's) to hopefully 2040 or so, when we are all on stuff we cant even know about yet. It's been neat to see it unfold.

And 15 year old kids will still be arguing about fps. That is the only given. I can tell em stories about how I played Quake 1 as a wee lad.

Re:no need to speculate

[swissmonkey]

NT was running on PPC, MIPS, Alpha & x86 (as well as i860 but never got released) long before Linux even dreamt of running on multiple platforms as it was written for x86 only at the start.

People who know what they're talking about know that NT was designed to be portable, the concept of HAL that NT used since its birth just started appearing in Linux, wonder who's behind...

Re:no need to speculate

[Anonymous Coward]

The 110% was the problem, as it wrapped around, and was seen as -90%. Damn static buffers.

Re:no need to speculate

[Greeneland]

Possibly. But consider that the word is that they had approached VMWare first. Since VMWare does not have a PowerPC-based offering, it would indicate their primary motives are having a solid server-consolidation product. It will be interesting to see how this plays out.

As far as XBox2 goes, I have doubts about the 3 dual-core processor specs. It seems to me that would be pretty expensive.

Re:no need to speculate

[TR0GD0RtheBURNiNAT0R]

even though apple's hardware is far superior.

So that's why apple constantly gets toasted in benchmark competitions...

Microsoft Sold Me an OS!

[tonyr60]

I went to the site and odered a copy of the CD. First Microsoft OS I have bought for many years, but for $US7.95 (including international delivery) the price is quite reasonable and comparable to the competition.

Re:Microsoft Sold Me an OS!

[skinny.net]

$7.95?! That can't be right! Here in the US, 64 bits is $8.

Re:Microsoft Sold Me an OS!

[Darken_Everseek]

*lol*

for those who didn't get that, 2 bits (in the US and Canada, at least) = $0.25, so 64 bits does indeed = $8.00

Re:Microsoft Sold Me an OS!

[Anonymous Coward]

I've heard that a couple of hundred years ago or so, people used to take dollar coins (silver dollars) and cut them up into 8 pieces (like cutting up a pie). One of these pieces was a "bit" of a dollar. Thus two bits is a quarter of a dollar.

This web site tells the story, with more details:

http://www.collectsource.com/americas.htm

Re:Microsoft Sold Me an OS!

[pboulang]

Ok, now how many of you just did the math to make sure that statement was correct in hopes of correcting it? Shame on you.

Re:Microsoft Sold Me an OS!

[Anonymous Coward]

Thank you Captain Obvious!

Re:Microsoft Sold Me an OS!

[Anonymous Coward]

Particularly since you can download the 64 bit version of several Linux distributions for free. Oh, wait, free is less than $7.95. Damn. I guess it's not comparable to the competition given that it's infinitely more expensive!

Re:Microsoft Sold Me an OS!

[MoneyT]

Actualy, I think it's just $7.95 more expensive. That and you have the piece of mind knowing that you won't miss out on the next virus or worm, and that's gotta be worth $7.95 to anyone.

Re:Microsoft Sold Me an OS!

[Bingo Foo]

Apparently there are still some Pentium 1 machines in service at Microsoft.

Re:Microsoft Sold Me an OS!

[joe_bruin]

perhaps it is really just a 63.6 bit os.

Re:Microsoft Sold Me an OS!

[shfted!]

Aha! I bet they didn't include the 64th bit! Cheap bastards!

Re:Microsoft Sold Me an OS!

[kinnell]

for $US7.95 (including international delivery) the price is quite reasonable and comparable to the competition.

Wow! That certainly beats the $699 you have to pay for linux these days.

It's an OLD version

[Ledfoot]

It's build 1069. That's the build they gave us back at the AMD Athlon 64 release event back in September. There are newer builds that are supposed to be better (there's a guy on AMDZone.com that has 1169)...

Basically, if you want to mess with this, go ahead, but there's a LOT of stuff missing and good luck getting drivers for any of your hardware!

Bochs?

[Anonymous Coward]

Bochs supports the AMD64 instruction set, right?

Anyone gonna try to get this thing running in Bochs within 360 days? =P

Re:Bochs?

[jcam2]

It'd probably take about that long to boot, given the speed of Bochs last time I used it.

Intel is not impressing me these days

[AviLazar]

I still recall reading the article in Wired magazine a few months back. A company approached them with an offer to provide them perfect diamond wafers (produced at less then $5/wafer) and Intel did not take the offer because they have not gotten their full investment back on the silicon. So given that they refused to have an easy method of increasing their processor spead by a very big number, it is not surprising that they still haven't gotten 64 bit over AMD... Shame, Intel used to be the best. -A

Re:Intel is not impressing me these days

[ProtonMotiveForce]

Right. Some crackpot came by my house the other day offering me free Enlightenment and perfect contentedness. I guess I'm an idiot for not shaving my head and giving him all my crap.

And Intel had 64-bits long before AMD. Oh - and it makes Opteron look like my grandma when it comes to the real domain of 64-bit computing - science and engineering.

Re:Intel is not impressing me these days

[fnord123]

Did "a company" also provide all the necessary updated tools for lithography, validation, packaging, layout, design, etc.? The wafer is one tiny ingredient in the whole overall process. No company, not even one as rich as Intel, can simply change over to an entirely new substrate just because one single component is improved.

Re:Intel is not impressing me these days

[Anonymous Coward]

Hey, a guy came by my house the other day saying that he could make my car run on tap water. But I haven't fully recovered my investment in the petroleum industry, so I told him that I wasn't interested.

Oh, by the way, has anybody mentioned that you are a freakin' idiot? And whatever moderator(s) gave up the point(s) to mod you "Interesting" is/are on crack.

Re:Intel is not impressing me these days

[AviLazar]

The article was fairly long and detailed, but it did not go into the full technology aspect of the proposal (for a number of obvious reasons, one being that it wouldn't suit the article for Wired Magazine). If I recall correctly Intel already has the technology to utilize the new material. The only reason the technology has not been in use is because a perfect diamond wafer costs ten's of thousands of dollars and cannot be acquired in mass quantities. Considering that they can make these wafers into any shape desired, with a cost of less then $5.00, there is not much of an excuse on a technology side. On a business side Intel said they will not use it because the ROI for silicon has not been met yet. -A

Re:Intel is not impressing me these days

[Psyx]

I'm sure something about this was posted on Slashdot a while ago but here's a link for you regarding the new availability of diamonds. http://www.wired.com/wired/archive/11.09/diamond.h tml

Re:Intel is not impressing me these days

[HardCase]

I still recall reading the article in Wired magazine a few months back. A company approached them with an offer to provide them perfect diamond wafers (produced at less then $5/wafer) and Intel did not take the offer because they have not gotten their full investment back on the silicon. So given that they refused to have an easy method of increasing their processor spead by a very big number, it is not surprising that they still haven't gotten 64 bit over AMD

Yeah, dude, I remember hearing on Art Bell's show about this guy who made a carburator that could get something like 100 miles per gallon in a Lincoln Continental. He took it to all the big auto manufacturers, but they were so tied up with the big oil companies that they turned him down. He threatened to take it to the Japanese car makers and HE DISAPPEARED! It's like the cold fusion technology that the government got from aliens that they're keeping at Area 51...if they let it out, then the oil companies will go out of business. Since the oil companies contribute so much to the politicians, the politicians aren't going to give out that technology. SO WE'RE STILL DEPENDENT ON OIL!!!

Man, I hear you. I'll bet that Intel has some kind of connection to the silicon industry and they're just keeping us tied to slow chips so that the silicon wafer makers won't go out of business. It's all a conspiracy. I'm so glad that Art Bell is back. I really miss Miss Cleo, too.

~h~

Re:Intel is not impressing me these days

[Psyx]

Here's a link for all who shoot first.

Re:Intel is not impressing me these days

[pla]

And Intel had 64-bits long before AMD

Yup... And while an Itanium 2 currently goes for $1500, the Opteron 248 comes in at under $1000, with Athlon64 3400s going for $400.


Oh - and it makes Opteron look like my grandma when it comes to the real domain of 64-bit computing - science and engineering.

In theory, the Itanium-2 beats the Opteron, even at a much lower clockrate. In practice, the benchmarks I've seen (mostly just summaries of material from Spec) show at most a 50% difference on comparable hardware. And that, only on native 64b code. For the desktop market, where 32b will still exist as a significant portion of the available programs for at least another few years, the Opteron and Athlon64 suffer *no* performance hit on 32b code, while the Itanium line slows to a crawl.


Overall, I'd agree that the Itanium fills a particular niche fairly well. With an Intel-optimized Fortran compiler, I doubt anything else can even come close, clock-for-clock. For general-purpose computing, however, AMD has made tradeoffs that I strongly believe will pay off, and not just over the long-term. For desktop use, this seems like a no-brainer - Go with AMD.

Re:Intel is not impressing me these days

[AviLazar]

Well according to those interviewed in the article (one of the people being a retired Navy Admiral who owns one of the two companies with this technology) deBears (sp?) has already implicated threats on his life. Obviously deBears would not be happy about him popping out perfect diamonds! I do not think the oil companies will go out of business anytime soon, they will still provide us with oil (it will take years to get oil based cars off the market) and all the other oil based products we use. Not to mention they will probably jack up their prices to match the difference. Gas prices would be at $10/gallon... Definitly one hand scratches the other. -A

Re:Intel is not impressing me these days

[ProtonMotiveForce]

Seeing as how most desktops come with 512M of memory, and people won't have 3G+ desktops for a long long time, it seems silly to try to pawn off a 64-bit chip on them as if they "need" it.

Their new hardware will be as obsolete as first generation pentiums by the time they need 64-bit processors.

Re:Intel is not impressing me these days

[crgrace]

I still recall reading the article in Wired magazine a few months back. A company approached them with an offer to provide them perfect diamond wafers (produced at less then $5/wafer) and Intel did not take the offer because they have not gotten their full investment back on the silicon. So given that they refused to have an easy method of increasing their processor spead by a very big number, it is not surprising that they still haven't gotten 64 bit over AMD... Shame, Intel used to be the best. -A


As someone working in the semiconductor industry... let me give you my professional opinion.... *coughBULLSHITcough*

Re:Intel is not impressing me these days

[AviLazar]

Ok, educate me as to why the article is wrong. I wouldn't mind getting an expert opinion on the subject.

Re:Intel is not impressing me these days

[crgrace]

Well, for one thing you can't just swap diamond for silicon and things will speed up. An incredible amount of work has been done to develop tools for simulation and manufacturing silicon and diamond is different. Since diamond isn't a semiconductor I don't know where the transistors would come from exactly... I guessing the diamond is just a substrate.

Also, I don't believe the price for one second. Silicon is an amazingly easy material to work with and silicon wafers are much more expensive than $5.

I just don't buy what they're saying in the article.

Re:Intel is not impressing me these days

[AviLazar]

Well they claim the technology is there, and they advertise that price. If they perfected the process, with mass automation it is possible to make it extremely cheap. I won't argue the technology aspect of it, but why is it so hard to believe that it is possible to make these wafers at less then $5 a pop? -A

I only get one every other day...

[bigfatslob]

...so its important to meta-troll.

Windows XP.

What is it all about?

Is it good, or is it whack?

In Soviet Russia, Batman's junk touches YOU!

Quaff, O quaff this kind nepenthe, and forget this lost Lenore!" Quoth the raven, "Don't forget to pay your $699 fee, you cock smoking teabaggers!"

Fuck all of y'all, including:

GNAA, BPAA, CLIT, TrollKore, TrollTech, anti-slash, and anyone I forgot.

Trolling always has been, and will be, an independent endeavour.

with 64 bits...

[vpscolo]

I suppose it means windows will take 1/2 the time to crash and at least twice as long to write out dump files

Rus

Re:with 64 bits...

[Anonymous Coward]

Oh, right. It's funny because Windows crashes. 1995 called, it wants the Microsoft jokes back.

I have Windows 2000 uptimes measured in months - I can't remember when I last saw a bluescreen. The most unstable element of my current system is Mozilla. But even when that crashes (once in the past week), nothing else is taken down with it.

Bashing Microsoft operating systems for their instability is getting really, really old. (XP excluded - apparently there's a high demand for clowns to have their own neon-colored OS - I don't know how stable that is). But the real danger is that it makes Linux advocates complacent. They won't realise when they've been overtaken on the stability front.

Re:with 64 bits...

[MoneyT]

I can remember the last time I saw a blue screen. It was while I was burning a music CD. No wait, I think that happened before it crashed while I was playing Halo. Nope wait a minute, that happened before it blue screened on an attempt to install the Nimo codecs.

Not to mention the almost daily crashes of applications (which granted don't take the machine down but do piss me off to no end)

So yeah... MS is a ways to go yet in terms of stability.

Re:with 64 bits...

[Anonymous Coward]

If it bothers you, maybe you should fix your hardware.

Re:with 64 bits...

[MoneyT]

Again? Hell I've already dumped an additional $700 into this thing on top of the thousand some odd I paid for it originaly. And the damn thing is only a year and a half old.

Re:with 64 bits...

[TR0GD0RtheBURNiNAT0R]

I think I've said something like this before, but I'll say it again: The new 64 bit Windows will crash in approxmatly 1/10 the time, since it is a (more or less) new Microsoft product.

Re:with 64 bits...

[Anonymous Coward]

You must be joking, smoking crack or you have a pre-built ( dell, etc... ) machine. I have 2000 and it crashes at least once every day. Oh yeah i run an Asus mobo with promise controller. Support for this in Win2k is esotheric and has been this way since the day i installed it.

Plus add to this that most games i was playing under 98 are now unplayably slow and that boot time is now 10 times longer.

Re:with 64 bits...

[drinkypoo]

I don't generally have blue screens any more either. My last blue screen on windows xp was when I plugged in my agfa ephoto cl18 camera, which is now broken and thrown in the trash so I guess that's not an issue any more. Its driver did it, far as I could tell. Mostly what happens on my XP system is that software gets stuck and can't be killed from the console because it's using 99% of the CPU. So, I (slowly) ssh in (yay cygwin) and use pslist and pskill to get my system back when some hosed application has my input devices.

Re:with 64 bits...

[TrancePhreak]

What vid card, cpu, & motherboard do you have? Those are all the most likely suspects of your troubles.

Re:with 64 bits...

[MoneyT]

GeForce 440, Athlon XP1700 and Abit KR733, none of them exactly bottom of the barrell parts. And all of them except the processor, replacements of even worse technology.

Re:with 64 bits...

[TrancePhreak]

Windows 2000 systems using AMD Athlon processors can hang when an AGP program such as 3D WinBench 2000 is used. The problem can occur whether or not an NVIDIA video adaptor is installed. The solution is to edit the registry to prevent the Memory Manager from using the processor's Page Size Extension feature. For a more complete explanation see
http://support.microsoft.com/support/kb/articles/Q 270/7/15.ASP

That's all I could find in the brief time I looked... Maybe it can help.

It's great!!

[jamesdood]

I have all of this 64 bit stability, I can load those huge CAD drawings, and it has microsoft's famous stab------------++++carrier lost

Re:It's great!!

[Anonymous Coward]

That's "No Carrier". :-P

Sign of the apocalypse?

[Anonymous Coward]

Microsoft Windows.

Available for download.

Free.

I know the install will self-destruct after 1 year - and they're probably doing this to prevent early AMD64 adopters from running FreeBSD / Linux. But still - it sure is nice of them to give something away for free for a change.

Re:Sign of the apocalypse?

[Anonymous Coward]

In the past with these free evaluation versions from Microsoft all you had to do was set the BIOS clock ahead a few years, install the OS, then set the clock back. Of course I have only heard of this technique.

Knock.
Knock.
Knock.
Hello....Oh Crap
They've got me!! They've got me!!

Re:How much?

[Anonymous Coward]

Dump that Windows workstation today! Quicken runs under linux!

Free? Which kind of free?

[Call Me Black Cloud]

Damn, I never get it straight. Is this software free as in speech or free as in beer? Since the software is only good for about a year, I'd guess this is free as in beer, because my beer has an expiration date too. But does that mean Linux is free as in speech because it doesn't have an expiry? Of course some really skunky beers don't either. Now, can you have free as in beer in a cathedral? All the cathedrals I've been too serve wine. So is this free Windows free as in wine?

See, it's this kind of thing that is holding up the adoption of Linux. It's too confusing.

Speculate what?

[Anonymous Coward]

That I've had been doing 64 bit development since, what, 1997? And I'm not even a 'bleeding-edge' kinda' person. And just to top it off, I doubt this is anymore than (to be genereous) a beta release.

I guess...

[Cytlid]

...the submitter didn't RTFA!

Important: Windows XP 64-Bit Edition for 64-Bit Extended Systems is only compatible with 64-bit AMD Opteron- or Athlon 64-based computers. It cannot be successfully installed on 64-bit Intel Itanium-based systems.

Re:I guess...

[Anonymous Coward]

...you didn't RTFA either! Intel is set to announce 64-bit extentions to their Pentium and Xeons lines in a few days! Hence the speculation. *ahem*

Re:I guess...

[MBCook]

Uh, no. I read the article. That's why I put "If you have an AMD Opteron or Athlon64..." in the submission. Your point makes no sense becasue there is a full version of Windows XP for the Itanium, so WHY WOULD YOU NEED THIS CUSTOMER PREVIEW (read: "Windows Beta")? That's what makes this interesting. It's a version for the Opteron, for x86-64, so it wouldn't run on the Itanium since that's IA64. Nice try.

Re:I guess...

[Anonymous Coward]

No mention about 64-bit Prescott based systems.

Re:I guess...

[Cytlid]

It was a fit of jealous rage. I knew I could eek more info out of it if I tried hard enough. Thanks. ;)

I don't read too much into this

[rabtech]

I don't read too much into this; Microsoft already told Intel that they (Intel) will in fact stay compatible with AMD because they will not be releasing three separate 64-bit editions of their operating systems (Itanium, x86-64, ???).

In this case, I think the monopoly is working for us in preventing Intel from fracturing the market, which I am quite sure they would love to do.

So in this respect, I think Microsoft is just having the usual Microsoft delays. One of the biggest is supporting Read vs ReadExecute memory pages on the x86-64 chips. A Lot of code, including microsoft code (ATL anyone?), breaks the standards and is having to be cleaned up to work.

In addition, Itanium lacked WMP, DirectX, and many other features that customers will NOT do without on Athlon64 systems, meaning even more development time.

Re:I don't read too much into this

[MBCook]

"In addition, Itanium lacked WMP, DirectX, and many other features that customers will NOT do without on Athlon64 systems, meaning even more development time."

That's true, but MS isn't that dumb. There were good reasons for not including those features on the Itanium. As a VERY expensive workstation processor, no end users have them. They are used on expensive computers where rendering is OpenGL and there are no games (so no DirectX) and if I owned Itanium workstations and found my employees usething them to watch videos with WMP I'd fire 'em, so I doubt there was much call for WMP on it.

I agree with you that if MS just put the Itanium version on the Opteron, they'd be in trouble, but I think this is the full x86-32 version (feature wise) only for the Opteron.

Re:I don't read too much into this

[evilviper]

I think the monopoly is working for us in preventing Intel from fracturing the market

Well, the M$ monopoly is helping itself out, but I fail to see how anyone else is helped by this...

It's open source, C/C++ code doesn't care if it's being compiled for one 64bit system or another. It would require more effort on the part of OS programmers, but since Intel has killed-off so many other platforms, it's saving programmers more time than it's wasting.

State of Windows 64-bit????

[bangular]

I'm a little confused. Does MS have 64-bit versions of Win2k and Win2k3 available? I've heard plenty about this XP version, but nothing about their server versions (not to say it doesn't exist, I just haven't heard anything).

Re:State of Windows 64-bit????

[nelsonal]

AMD used to have a link on their site to 360 day betas of win2k3 server for both Opteron and Itanium.

Re:State of Windows 64-bit????

[bangular]

So if they don't have any production ready server OS with 64-bit support, why even bother with desktops??? Desktop systems will see the least benefit by far. If I were MS, espically since they have no production ready win2k/2k3, I would be working damn hard to get a server version out.

Re:State of Windows 64-bit????

[R_Harrold]

They do have a Windows Server 2003 64bit for both Itanium and the AMD 64 bit stuff in Beta at this time. MSDN Subscribers will note it under the Platforms tree. I think they started making both availiable to MSDN subscribers about 6 months back. I haven't purchased a 64 bit box that is compatible yet, so I can't say anything about the stability, but the assumption is that the answer is "Yes they are working quite hard to get a server version out". Robert H

Linux for A64

[Anonymous Coward]

Mandrakesoft have a version of 9.2 for Athlon 64 systems.

Fedora, Gentoo, and Debian also have A64 ports in development.

So dont wait for Windows, Join the 64-bit revoloution today, with Linux! Ported faster because the source is open!

Re:64 bit

[TurnerK12]

Yeah, that must be frustrating. I've been thinking about upgrading to a 64bit processor myself. It just seems like not too much of the general population has it right now. So, not too many people would go out and buy a 64bit Windows if it were out right now. It's like decades ago when some broadcasters began telecasting TV shows in color but color televisions had just came out. I'm sure everyone will upgrade to 64bit processors eventually though.
---
http://conradsheldon.web1000.com
The story of an Internet hoax, and the game it inspired.

sizeof on modern OSes

[Anonymous Coward]

char is 8-bit, nearly by definition
short is 16-bit
int is 32-bit (DOS and Xenix are not modern)
long is 32-bit on all Windows OSes
long is the same size as a pointer Linux, BSD, Mac
void* is the natural size for the machine
long long is 64-bit

So 32-bit Windows and 32-bit UNIX have the
same sizes a each other. 64-bit systems differ,
because Windows sets sizeof(long)==4 and a
UNIX system sets sizeof(long)==sizeof(void*).

Re:sizeof on modern OSes

[Anonymous Coward]

char is at least 8 bits by definition
short is at least 16 bits by definition
long is at least 32 bits by definition

iirc, int is at least as big as a short but no bigger than a long. I don't think the standard guarantees that any integer type can hold a pointer, but a void* is big enough to hold any other kind of pointer. (which are not necessarily all the same size)

Relying on anything else is not 100% portable.

Visual C++ has __int8, __int16, __int32, __int64, __int128 instead of long long. (and fwiw, these are different types from char, short, long, not just typedefs) Last time I checked __int128 wasn't supported in the compiler, but they can decorate symbol names for it.

Re:sizeof on modern OSes

[Anonymous Coward]

We know the definitions. However, the subject is OSes, not the C standard.

Re:sizeof on modern OSes

[Rupert]

This is broken.

int should be the native size for the machine. short should not be longer than an int, and long should not be shorter.

Unfortunately, so much code has been written over the years by people who don't understand this, (or more likely just didn't care so long as it compiled) that any compiler vendor who wants their customers existing code to have a hope in hell of compiling is going to have to support the brokenness.

ia 64 come on Linux!

[ratfynk]

Thats what happens when you release a Linux friendly compiler. Good. This will only serve to drive Intel toward Unix and Linux. MS hates competition, now the dead chickens caused by MS will come home to roost. Pissing off Intel is a big mistake, the worlds largest chip manufacture will not take this for long.

Re:ia 64 come on Linux!

[Anonymous Coward]

You don't honestly think Intel is coming to save you from big business, do you?

Re:ia 64 come on Linux!

[ratfynk]

You don't honestly think Intel is coming to save you from big business, do you?

Certainly not, however MS security, or it's obvious absence, is driving more and more people to OSS. The Longhorn solution just does not wash at Intel. Like any other manufacturer, Intel relies on repeat customers. The MS solution of forced hardware upgrades is not a good solution to security. Intel knows this and I am almost willing to bet that they are looking into OSS, big time. MS dropping support for Win98, then quickly backing off tells more about the story than any other recent MS screwup. 64 bit computing for the PC is coming but it cannot be forced upon businesses. Especially marginal ones.

Re:How much?

[MrBlue VT]

It is free for both the download and the CD version. Although I would imagine you have to pay shipping for the CD. Check out the site and click on "Get the Download", and you can see the price is set to FREE.

Terrible...

[Stupid Dog]

After installing this release on my MSI K8T-Neo Board, I have no drivers for scanner, printer (LPT1 unsupported...), ISDN PCI Card, Wireless LAN card and many other things.

I spent nights searching and begging for drivers. Thank you Microsoft for bringing this truly Linux user feeling to the Windows platform.

Re:Terrible...

[seann]

who uses IDSN anymore?
Seriously?

Re:Terrible...

[Anonymous Coward]

Someone besides you. I can see how it would be hard for you to understand this.

Re:Terrible...

[IcePic]

I got the same. A64 on an ASUS mobo. The sata drivers
wont work so its time to dig up some shit-old 4G Piomode4-IDE
so the most recent version of winxp can "handle" it.
8-(

Try looking for sata drivers, scsidrivers or just any
kind of win-drivers made for winxp-amd64. I wont be
holding my breath while you google though.

What MyDoom.B couldn't do...

[Anonymous Coward]

...maybe /. can. Download away!!!

Finally!

[Anonymous Coward]

I can get a 64 bit OS to run on my Intel compatible 64 bit CPU!

Official benchmarks here

[hobuddy]

You can see official AMD benchmark results of various programs running on Windows XP 32-bit edition vs. Windows XP 64-bit edition beginning on page 36 of this PDF. The results have three columns: time in seconds on WinXP 32-bit w/ 32-bit executable, time in seconds on WinXP 64-bit with 32-bit executable, and time in seconds on WinXP 64-bit with 64-bit executable.

Re:Official benchmarks here

[Anonymous Coward]

the only thing this tells me is unless the program you're running is built for 64bit and you're willing to fork over the upgrade cost for 64bit windows XP, you may see a significant improvement. Until I see realistic benchmarks comparing exchange and sql server 32 vs 64bit windows XP, I will reserve judgement. At work we have sql server 32bit running on both windows 32 and 64bit. the performance difference is not noticeable and in some cases slower.

I can wait...

[gbulmash]

Microsoft strongly disclaims this is a preview and is not to be used in production systems.

SuSE 9.0 for AMD64 corrupts my BIOS every second or third time I run it and the next time I try to boot, I have to clear the CMOS and reload default BIOS or my machine freezes at "checking NVRAM".

Though the chip's been out since October, Nvidia didn't get their 64 bit Linux drivers (for their mobo chipsets or graphics cards) out until January, so I've only been able to get my onboard LAN working with ANY 64 bit Linux distribution for a few weeks.

Enough is enough. I'm tired of being a guinea pig for OS releases that aren't production ready. I'll stick with 32 bit for now.

I bought the AMD64 as my "every three year" processor upgrade, figuring that it would serve me better 2 years down the line than the P4 3.2 (not prescott). But the honest truth is that there aren't any significant consumer applications *right now* that need or truly take advantage of its 64-bit abilities. When there are enough 64 bit applications **and 64 bit DRIVERS** to make upgrading to 64 bit XP intriguing, I'll re-consider.

- Greg

Re:I can wait...

[IllForgetMyNickSoonA]

I wouldn't hold my breath waiting for 64Bit drivers for devices most commonly found in desktop machines (such as nVidia graphic cards you were talking about)

The greatest advantage of the 64Bit architecture would be on server, not on desktop. In fact, you should even expect a drop in performance for most applications when run in 64Bit.

Just live with it, you bought yourself a very good processor (when run in 32Bit mode), with 64Bit capabilities you don't actually need, or want, but can now brag about to your friends and colleagues. ;-)

Re:I can wait...

[_Sharp'r_]

I'm tired of being a guinea pig for OS releases that aren't production ready.

Install FreeBSD 5.3 when it comes out as the stable release in a couple of months with full support for AMD64?

Re:I can wait...

[Anonymous Coward]

Install FreeBSD 5.3 when it comes out as the stable release in a couple of months with full support for AMD64?

Haven't you heard? *BSD is dying.

Re:I can wait...

[dbIII]

Though the chip's been out since October, Nvidia didn't get their 64 bit Linux drivers (for their mobo chipsets or graphics cards) out until January,

I got my system on the Thirteenth of October, and wasn't the first. I downloaded the Nvidia drivers for AMD64 that day, and I'm sure I wasn't the first either. I found the drivers by going to the main nvidia website -> drivers -> linux -> linux amd64.

Interesting strategy

[IllForgetMyNickSoonA]

In the mean time, Linux is chugging along on AMD64 quite nicely. This beta version is said to expire in 360 days, meaning that - most probably - the release is not coming any time soon.

How comes Microsoft decided to let the competition get such an advantage on a chip which surely isn't going to go away, which offers a very good performance, and all that at a very affordable price?

Either they don't care at all about the advantage competition might gain (which I doubt, given their aggressive advertising against Linux and Solaris in the past few years), or they never thought AMD64 has much of a chance to survive.

The most hard to believe (although a very sexy, IMO) possibility would be that they simply weren't able to put a working version together before today, resulting in this rather huge delay.

Does anybody know anything about how Sun's plans to port Solaris on AMD64 are doing?

Emulators and Lisp compilers could use 64-bit

[boelthorn]

I guess some emulators could use 64-bit registers to speed up things. Just think of still crawling N64 emulators. But also Lisp compilers could benefit from this.
Then again I still want to get Transmeta Crusoe codemorphing specs...

Re:Emulators and Lisp compilers could use 64-bit

[__past__]

Indeed, languages that use tag-bits for type safety benefit greatly from 64-bit-words. Otherwise 32-bit arithmetic can be pathetically slow, because a fixnum effectively isn't 32 bit wide, but typically something like 29t, the rest encodes the type. Once you need numbers bigger than that, you'll get heap-allocated bignums that are expensive to deal with (unless you use some suitable optimization tricks to allow non-tagged representations of the number, then you can get full 32-bit integers. But that can be pretty hard, especially across function boundaries). Fortunatly, there already are commercial 64bit Lisps (and have been for a long time, just not for IA64 or AMD64 of course), and the excellent free SBCL system has a 64bit port for AMD64 (and probably Alpha) in the works.

The need for tag bits is also why OpenGenera, the successor of the operating systems of the Symbolics Lisp Machines (which had 36 bit words, with hardware support for type checking) was implemented on the Alpha, so it could efficiently emulate the custom LispM hardware. Of course, choosing the Alpha of all 64bit platforms has now proven to be in line with a long history of Symbolics making exactly the wrong stategic decisions... There have been rumors about a port of OpenGenera to the 64bit G5 Macs, but they are as yet unconfirmed, and even if it would work out, I doubt that there is any significant market for an OS written in Lisp, running in an emulator, for $5000 per installation, even if it is still a damn impressive system.

About 32-bit vs. 64-bit

[armando_wall]

If I had some money to spare, I'd buy a 64-bit system, no matter what benchamrks say.

I missed the time when the switch from 16-bit to 32-bit was made. Did this kind of talk take place back then? I mean, the kind of "it's not a mature technology yet", "linux kernel runs better in 16 bits" , and so on...

Re:About 32-bit vs. 64-bit

[IllForgetMyNickSoonA]

Actually no, IIRC. 32-bit architectures brought more than enough advantages over their 16-bit predecessors to make virtually everybody want one. The price difference was rather huge, though.

Linux was born on a 32-bit processor (see the legendary Linus vs. Tannenbaum discussion, where Tannenbaum claims - among other things - that normal people are never going to be in a position to afford a 32-bit processor for a home machine)

Re:About 32-bit vs. 64-bit

[cyberman11]

I had just graduated from college when the 386 came out, and yes, these same discussions took place back then. Newspaper and magazine articles gushed about how 32-bit processors crunched twice as much data at a time as 16-bit processors did. Then people went out and bought 32-bit computers and were shocked that 32-bit software ran more slowly than 16-bit software. People continued to run 16-bit DOS and 16-bit software until the memory limitations became too painful to bear.

Re:About 32-bit vs. 64-bit

[IntlHarvester]

Yeah but the reasoning was entirely different back in the 1980s -- When people said "32-bit" software, they really meant protected-mode kernels, security subsystems, and all of the "overhead" of things like UNIX.

So-called, "16-bit" software was old-fashioned DOS stuff that bit-banged directly on the hardware. Fast, but zero safety net.

In fact, protected mode 32-bit software was just as fast or faster than protected mode 16-bit software (like OS/2).

Now that everyone runs a "modern" OS, the perf difference between 32-bit and 64-bit software is mainly due to cache and bandwidth issues, not because the software is fundamentally different.

Well, on Windows

[Kjella]

The big issue for me are the cases where the stupid machine just locks up and does fuck all for 20 seconds or so. CPU meter shows 3% utilization, no disk activity. What is the stupid thing doing?

Same goes for UNIX systems, its not the processing thats the issues, or even the legitimate I/O delays, its the cretinous delays built into broken device drivers and applications.

On Windows, the process locking up everything here most often seems to be explorer.exe. I've found that going into task manager, killing and running it from there (since you just lost your start menu with the run command) will restore the machine to normal.

Using that little trick every time it starts acting stupid, my windows box is running quite nicely for weeks. Doing it doesn't interrupt any of the applications or services running, the kernel is handling that just fine. Quite silly really.

Kjella

Re:Well, on Windows

[DexterX]

On Win2K and higher, you can split out the file system browsing from the desktop instance of Explorer.exe. Run Explorer and select Tools->Folder Options->View->"Launch folder windows in a separate process". It uses a little more memory but prevents a slow device from slowing down the rest of the GUI.

You're right, though; Explorer blocks waiting for I/O way more often than it ought to. Most of the multithreading in GUIs is pretty good on Windows, so I'm not sure why Explorer tends to block on floppy I/O, network I/O, etc. Fortunately, it usually doesn't affect other running apps.

Re:Well, on Windows

[MechaStreisand]

Thanks a million for that advice... I find that Explorer blocks way more than it needs to, and finally I can do something about it. You've helped me make Windows suck just a little less.

Re:Well, on Windows

[varag]

You could bypass explorer altogether by running an alternate shell (litestep, bb4win, ishell, etc.).

Re:Well, on Windows

[Mal-2]

Unfortunately, killing the explorer process also totally mungs your systray. Only the apps that the newly spawned explorer notices get put there, and the others continue running with no way to access them except to kill their processes and restart.

Mal-2

Speculatin

[NanoGator]

"Speculate away!"

I think it's proof of Microsoft's involvement with SCO! Now just bear with me for a sec here...

Hey Intel

[Brian Stretch]

It's time to put up or shut up on your "maybe we have a x86-64 chip too" FUD.

Re:Hey Intel

[Junta]

From what I have heard, you will not be impressed..... Same hardware essentially, just some microcode trickery to offer a richer instruction set...

Re:Windows 64 Bit

[Anonymous Coward]

I think your goals are a little misguided. It would be better to kill off all the welfare scum in this country than the wild dogs.

More money would be saved. They much easier to hunt, just camp out near the projects on mother's day and pop them off when they go to the mailbox.

Right now, we are paying people to do nothing but use up our natural resources. By eliminating this trash, the world will have more resources for the productive members of society. Pollution levels would also decrease. I'm sure that there are more benefits, but I can't think of any. I also have to get back to work.

Bah

[DahGhostfacedFiddlah]

See this image of a cow on a haystack to see just how silly your argument is.

+5 Funny

[Kizzle]

Bla bla beowulf bla bla.

Re:+5 Funny

[Anonymous Coward]

Best +5 funny I've seen in ages. (though not really funny)

Re:64 bit

[Anonymous Coward]

I know the feeling - my motherboard broke and I'm waiting for replacement... 3 weeks so far :(

Re:Free? Which kind of free?

[Anonymous Coward]

Now, can you have free as in beer in a cathedral? All the cathedrals I've been too (sic) serve wine. So is this free Windows free as in wine?

Since Wine is free as in beer, the question is irrelevant.

Could Microsoft be feeling the Slashdot effect?

[igorsway]

Hmm - my download started off fine at 500kbs. Dropped down to 250kbs, then 130kbs, and now 75kbs. I just wonder how many Slashdot readers are downloading this ISO right now?

Re:Could Microsoft be feeling the Slashdot effect?

[MalleusEBHC]

Hmm - my download started off fine at 500kbs. Dropped down to 250kbs, then 130kbs, and now 75kbs. I just wonder how many Slashdot readers are downloading this ISO right now?

Now that you mention the bandwidth crippling we might be putting on them, count at least one more. I just can't wait until they see Safari in their IIS logs. ;)

PS - It really pays to hit the preview button. I almost just posted "Apache" instead of "IIS."

Re:Could Microsoft be feeling the Slashdot effect?

[Anonymous Coward]

Don't flatter yourself. MS doesn't give a shit if you're running an open source browser. Netscape died, noone can challenge MSIE. Not even some obscure Konqueror-based browser.

Re:Could Microsoft be feeling the Slashdot effect?

[Anonymous Coward]

And thats why they ran running and scraming from the MAC right?

Don't hold your breath after 360 days

[Flexagon]

It's a pre-release copy that will expire in 360 days (which probably means the final will be out by then).

Not necessarily, maybe not even likely, particularly for something as big as an XP release. Many's the time that Microsoft has slipped a release beyond such dates. And in many of those cases, an update or date extender patch appeared to cover the slippage (sometimes several such patches).

Re:How much?

[Lord Kestrel]

It ended up being $12.92 (for me) for shipping/handling/tax (although I don't know how they charged tax on a free item).

Well, doh...

[Kjella]

A Ferrari is designed to address the most demanding needs of car drivers who require high velocity.

But the "driver requirements" is just a drivers licence and a fat wallet. If your old grandmother would like to use it to crawl to the nearest shop at 20MPH, she can.

Kjella

Re:Well, doh...

[cant_get_a_good_nick]

If your old grandmother would like to use [the Ferrari] to crawl to the nearest shop at 20MPH, she can.
That would be a pretty tall stack of phone books to have my grandma see over the steering wheel of a Ferrari. Quite a few blocks of wood to have her be able to depress the clutch as well.

Re:Well, doh...

[afidel]

Depends on the car, Ferrari required proof of ownership of either a F40 of F50, or preferably both for purchase of the Enzo. They were also a little more likely to sell it to you if you could show track experience. When you make only 350 of a model you can be a bit picky about who you sell em to =)

Re:Well, doh...

[Datafage]

Factory run is 399 Enzos. 349 was the F50. F40 was originally supposed to be a few hundred but in the end they built almost 1500.

Re:Well, doh...

[EulerX07]

Well, a ferrari 360 is 47" high from the ground to the top of the car. You're grandma would have no problems seeing over the steering wheel, it's your 6'6" uncle that would have issues with the car. By comparison a civic is 55 inches high, and that's a minuscule car by american SUVesque standards.

Intel 64-bit Extend

[Nom du Keyboard]

I speculate that Intel will announce a 64-bit Pentium extensions that incorporate the AMD64 instructions plus SSE3+ and a couple additional instructions in an attempt to make AMD incompatable with new 64-bit applications.

sizeof (long long) == 8...

[Ayanami Rei]

and the Opteron can hold it one register. Just prefix the instruction with the OTHER size prefix byte. (for those who don't already know, most intel instructions if operating on a 16-bit short require a prefix byte. On the Opteron, you use a different prefix to get 64-bit ints and the extended regs)

There are plenty of places where it makes sense to use 64-bit regs, especially in the kernel when involving counters, timers, GIDs, and such.

Re:Intel lost long time

[Anonymous Coward]

Intel did own >1'000'000'000'000 $ and we lost it waiting long time for the inexistent Merced since 1999.

open4free

ObDownloadLink

[Anonymous Coward]

http://download.microsoft.com/download/7/a/f/7af62 a47-5020-42ec-9eb3-0b146bfd7501/srv03sp1_usa_1069_ amd64fre_pro.iso

get your own fucking product ID though

I got only one thing to say to you...

[Kjella]

...the only thing worse than a masochist is a complaining masochist. You volunteered.

Kjella

Re:How much?

[seekr_hidr]

The tax is from Shipping and Handling. When you go to the Post Office to buy a stamp, they tax you for the stamp too. I know because I just bought stamps today :-)

your sig..

[fliptout]

Where can i find this powered armor soccer? :)

Re:your sig..

[Nom du Keyboard]

Where can i find this powered armor soccer? :)

I've given you the reference for the quotation. You can hunt both the name and quotation on Google.

Re:your sig..

[fliptout]

Searched and found porn links. thank you.

Re:your sig..

[Nom du Keyboard]

Searched and found porn links. thank you.

SciFi erotica -- not porn. There is a difference, and Elf's quality of writing is quite good.

Re:Free? Which kind of free?

[cant_get_a_good_nick]

Of course some really skunky beers don't either.
I see you've mistakenly tried Coors Light too....

Re:Free? Which kind of free?

[mj2k]

This is the kind of logic that drives one to drink - BTW, it took a while to write this as I couldn't decide which of the four keyboards acutally existed.

16-bit layer? They threw it away.

[AndersM]

In a technical article about the features they don't support in the 64-bit edition of Windows XP, the 16-bit subsystem is listed. I won't miss it. Mostly because I usually use Linux. =)

Re:16-bit layer? They threw it away.

[Anonymous Coward]

Actually, this page seems to be talking about the "plain" 64-bit edition for Itanium.

Re:16-bit layer? They threw it away.

[Anonymous Coward]

WOW16 won't work on AMD64 either -- all the old style 8086 & 286 instructions are disabled when you are in native 64-bit mode.

(Assuming that MS doesn't package an emulator, like they did on NT/RISC.)

Re:16-bit layer? They threw it away.

[ckaminski]

And I thought that was because the tricks they use to get 16 bit code to run alongside 32 bit code just are not supported in x86-64?

Windows Server 2003 Also Available for Free

[xTK-421x]

Here: http://www.microsoft.com/windowsserver2003/64bit/e xtended/trial/default.mspx

Beta of course.

Re:Windows Server 2003 Also Available for Free

[Anonymous Coward]

Direct Download Location: http://download.microsoft.com/download/7/a/f/7af62 a47-5020-42ec-9eb3-0b146bfd7501/srv03sp1_usa_1069_ amd64fre_pro.iso

tried windows 64bit already

[Anonymous Coward]

it's not faster than 32bit. who cares. unless they significantly rewrote the kernel, I seriously doubt it will make any difference. the only apps that will matter is if you're hosting a huge 500gb database and actually have moderate load. Otherwise, forget about it. small sites should still stick with the 32bit version.

64 bit lies

[bl8n8r]

Finally, we'll be able to have an integer big enough to count the number of lies SCO has told so far.

Re:64 bit lies

[Anonymous Coward]

Considering some of them where half-truths, maybe we should go for a float? :P

64-bit NT

[Anonymous Coward]

Microsoft never commercially released a 64-bit version of NT. Even the DEC Alpha version of NT was still a 32-bit OS.

However, during the mid to late 1990's, Microsoft internally did create a 64-bit version of the NT kernel on the Alpha. They did this to help get NT codebase 64-bit clean, because they knew that Intel was building the 64-bit "Merced" Itanium architecture.

Don't forget IBM in this race.

[kid zeus]

Not only is the G5 a beaut, but the upcoming fabrications, expecte to hit .65 by next year, are supposedly dazzling. With massive heat/energy savings over Intel's competition. Not to mention the predictive gushing over the subsequent G6s, G7s, etc. (yeah, yeah, I know... believe it when it's in front of me).

Looks like the massive investment Big Blue made in their fab plant is going to be a wise and profitable one. Not only are they producing their own stellar chips, but they're producing for AMD, they just signed a huge deal to produce for Sony, and they're going to be supplying Microsoft.

My guess is that Intel is sweating.

right now vs later

[Neuroelectronic]

the point in buying amd64 (atleast for me) is that it's like a free upgrade later. best 32bit performance now, 64bit compatability later. I don't expect 64bit mode do be super fast but having access to 4 gigs plus of ram in C is pretty nice :) especialy for those monsterous neural nets

AMD64 Laptops

[NLG]

A friend and I were in Best Buy today and I gave the new AMD64 equipped emachines laptop the once over. Very nice, I nearly drooled. It was tagged at $1599, with some rebates knocking off 150 or 200(don't recall which). Seemed nice. But... comes with WinXP Home(if I have to have Win, let it be Pro). When some non-beta 64bit OS's are out I can see getting one of these to play with...also, the battery life on these things is only about 1 hour 20 minutes. Jeez, I can't even watch a dvd with that!...not that I would set it on my lap. When I first walked up to it I lifted the front up a bit and slid my hand along the bottom(get your mind out of the gutter!). It was very hot to the left of center. Much hotter than an idle laptop should ever be. AMD really needs to work on the power consumption and heat issues before I will shell out a grand plus for this tech, especially with no final stable 64bit OS here yet. Yeah, don't bother telling me "XYZ Linux distro is 64 ready.", 'cuz it ain't. Wait til June/July. That is about when some decent stable OS's should be available.

Re:AMD64 Laptops

[Lucretian]

This is odd. I too have this laptop and it's not hot at all, much cooler than my tibook even! It also lasts 2.5-3hours on battery. Maybe the powernow! drivers were not installed on the laptop you looked at. They are what allows it to clock down. Overall I like this notebook, and you can't beat the price.

Re:AMD64 Laptops

[Tassleman]

Keep in mind that laptop has probably been ON in the display at Best Buy since it was put up for sale, and if it's running the typical BUY THIS AWESOME COMPUTER~! promo package software it could be working at a pretty high load for days and days on end.

Re:How much?

[Lord Kestrel]

Sadly, I can see how that makes sense, in a roundabout way.

Finally

[Anonymous Coward]

Finally... A 64-bit operating system I can use on my K8W with 64-bit drivers for the Silicon Image 3114 Raid controller....

My gentoo install is crippled by having to use a slow old 20GB drive instead of the nice speedy pair of Raptors I bought for it... At least something 64-bit will be using them now.

Though I never thought I'd say it... Thank you microsoft for giving me something to play with for a couple of weeks until the linux support catches up.

64 bit computing?

[Anonymous Coward]

Whoa there captain! 64 bit computing is a SCO development. Expect SCO to sue Microsoft over stealing SCO code! After all SCO's story goes like this: "All of your 64 bit codes are belong to us!" If they can tag IBM for 3 billion, MSFT should go for 30 billion at least! Stay tuned Slashdot readers!

Comment removed

[account_deleted]

Comment removed based on user account deletion

Speculations...

[athlon02]

Intel goofed on Itanic? Nah, most of us already knew that, I'm not surprised by x86-64 CPUs from Intel. I just hope AMD is soaking them for the royalties :)

Re:Speculations...

[Anonymous Coward]

They cannot or should not.
If they did, Intel WILL roll out their own system and strangle AMD.
AMD is very interested (or should be, IMO) to get Intel to run x86-64 - they will have had time to mature the platform first.

gig of ram

[martin-boundary]

Since its not like any normal people have more than a gig of ram anyways.

I don't know about you, but I'm quite happy with my 640K.

Sincerely, Bill Gates.

Re:gig of ram

[The Patient]

Hey, Bill! Make up your mind, ferGawdsake.

http://www.wired.com/news/politics/0,1283,1484,00. html

Re:Free? Which kind of free?

[Anonymous Coward]

Yep. With windows it's much simplier.

With Linux is free as in free speach and sometimes it's free beer.

But with Microsoft Windows it's much simplier. It's just plain expensive.

With Linux you have to keep updating to get all the latest features, stability, and security.

With windows it's obsolete and insecure right out of the box and there is not much you can do about it.

I see how windows is much simplier.

"we will need MORE than 4 gigs of ram"

[rs79]

> "we will need MORE than 4 gigs of ram"

Absolutely. Just to be able to run a mail program.

Bloat on, you slacking fucks!

Looking for 64-bit OS? 64-bit Applications?

[MurrayTodd]

I'm not worried about Windows Media Player as much as I am drivers and compilers.

Will the 32-bit emulaton Windows-on-Windows stuff also cover device drivers or are like 2% of us going to be able to run this trial version because something like only 2 video cards are supported? I was under the impression moving 64-bit support to drivers was a majority of the workload. (I think I remember that being one of the slow points getting Linux to 64-bit five years ago.)

The other thing I want to know is this: when will there be a good compiler suite to make the first 64-bit applications? Did Micro$oft port their Visual Studio to 64-bit or are we going to have to use Cygwin. (And can cygwin make 64-bit Windows apps yet?)

If Solitare is the only 64-bit app that'll run on this thing, there's suddenly Not Much Point. I remember running Windows NT for Alpha and scratching my head because solitare was about the only app available to me.

Re:Looking for 64-bit OS? 64-bit Applications?

[Anonymous Coward]

If Solitare is the only 64-bit app that'll run on this thing, there's suddenly Not Much Point. I remember running Windows NT for Alpha and scratching my head because solitare was about the only app available to me.

Ooh, 64-bit Solitare! I gotta try that!

But will this run on Bochs? Cuz I don't have a 64-bit processor... (Windows-on-Windows indeed!)

Be still my heart

[rs79]

They've finally made a CPU that has more registers than a state of the 1973 art PDP-11.

Wow.

Any idea how many decades till we get a rational instruction set?

Ramdisk

[rs79]

> One word - Ramdisk.

Oh my. PC's catch up to CP/M circa '81 and AmigaDOS circa '86. Put your C compiler, sources and vi in ramdisk and things were just nice, even on a floppy based system. And oh yes your makefile did put a copy back on the floppy.

Ramdisks are utterly wonderous things, albeit, a little transient. When did you last check your UPS? :-)

Re:Ramdisk

[pla]

Oh my. PC's catch up to CP/M circa '81 and AmigaDOS circa '86. Put your C compiler, sources and vi in ramdisk and things were just nice, even on a floppy based system

Heh, I agree this seems like a throwback to an older generation of computer hardware, but one that works rather well.

Personally, I don't understand why we still have virtual memory - Another throwback to the days of now-obsolete hardware, when memory cost an arm and a leg yet programs started wanting tons of it.

The difference between the two, now that we have oodles of cheap RAM, involves performance. Disk paging (even totally idle) hurts performance, while a ramdisk improves it. Yet all modern Windows version force you to use the former (though you can technically disable it in XP, some programs simply will not work if you do so, regardless of how much physical RAM you have), and don't even include native support for the latter.

Re:Ramdisk

[Anonymous Coward]

> Disk paging (even totally idle) hurts performance,
Prove it.

> while a ramdisk improves it.
Prove it.

>Personally, I don't understand why we still have virtual memory

Maybe you shouldn't be making a fool of yourself then.

Re:Ramdisk

[pla]

Prove it.

Prove it? Um... huh?

Fine, here we go, embarking on an exercise in futility - educating the ignorant trolls of the world. Twit.

For paging to disk, which would you say takes more time: "hit the disk", or "nothing"? Even if only verifying the pagefile's integrity at boot (not currently the case on any OS I know of, though feel free to name a few, of which I can save you the trouble and tell you that you won't find either "Linux", "Windows", or "OS-X" as an example), that still comes out to T>0 vs T=0.

For a ramdisk... Wow, where to start?. Okay... Do you suppose loading file X from RAM, or from a set of glass disks with mechanical actuators moving across them, takes longer? Keep in mind those moving parts read bits off the glass plates, perform several layers of verification and error correction, place them in local RAM on the drive itself, and only then does the requested data make it to the CPU. So again, factoring out the "RAM" step common to both, this reduces to "something" vs "nothing".


Maybe you shouldn't be making a fool of yourself then.

I have enough confidence in my statements to post as myself, rather than AC. I occasionally make mistakes, and people call me on it, but really, I can't even imagine what you had in mind when you decided to post your comments...

However, feel free to vindicate yourself by proving the counterpoint to my assertions? I'd love to hear a bit about the world you live in, where a disk performs faster than RAM...

That's because the US dollar is trading low...

[rs79]

...against the bit.

"With an Intel-optimized Fortran compiler"

[rs79]

> With an Intel-optimized Fortran compiler,

Thanks. I'm gonna have to slaughter a pig to that THAT thought out of my head.

what you been smoking?

[Penguinoflight]

Come on man drop the Mary Jane and listen up!
Apple hardware isn't superior, it's a known fact that it's not even Apple Hardware! You've got IBM and Motorola processors on a system with nvidia or ati video. The MB's are as proprietary as microsoft and sun. People don't use mac's because they're faster, more reliable, or not even primarily because they're cases look like strawberry vinella; People use macs because they like MacOS, and they don't care about games, or windows (how do you figure they'd run windows with only 1 stupid mouse button anyway?)

Hey man, don't take it too hard, you might be right too, but I think that your angle is probably going to be broke. Microsoft isn't trying to keep it's hold, they're "running like a constipated weener dog" to keep up with Linus, who had AMD64 for 1 1/2 years already.

Fast download mirror.

[Anonymous Coward]

http://premierdownload.microsoft.com/download/7/a/ f/7af62a47-5020-42ec-9eb3-0b146bfd7501/srv03sp1_us a_1069_amd64fre_pro.iso

About twice as fast as the normal mirror for me.

he did say he was talking mathematical computing

[Anonymous Coward]

And Fortran is still heavily used there. Oh, and vodka will get rid of the image cleaner and quicker.

I've got one

[atrader42]

Right now, I'm lying on my couch with it comfortably on my lap. It's not cold, but I'm certainly not scorching myself. I've also been on battery power for over an hour now and have an hour left. Mind, I have yet to run a 64 bit OS on it (dling the windows version, but it's awfully slow. Is Microsoft getting slashdotted?), but it's quite nice. I also installed fedora core 1 on it and that runs pretty well although there are naturally issues (ethernet, wireless needs NDISwrapper, need to upgrade XFree to recognize video card). For 1300, it's well worth it

Torrent Anyone?

[atrader42]

Seems that Microsoft is feeling the Slashdot/mydoom effect and this is pretty slow. Anyone have a full version they could share? If not, I'll have one in a few hours.

Alpha Technology Lives on in Opteron

[ayden]

My brother-in-law is a chip engineer for Sun. Coincidentally, his next door neighbor does a very similar job at HP. We had a very interesting conversation last spring about the latest - last generation of Alpha processors. According the HP engineer, HP sold much of the Alpha technology to AMD for use in the Opteron.

HP will continue to support this last Alpha generation until 2011.

Re:Alpha Technology Lives on in Opteron

[John Courtland]

The guy who designed the first Athlon was a former DEC engineer (Dirk something-or-another). Also, the original Athlon bus was almost identical to the EV-6 Alpha bus, minus the SMP stuff. The Athlon has taken quite a few pages from the DEC handbook it would seem.

Re: Quick notes on the install

[Lucretian]

One note about win64 before you install it. There are no current drivers for the integrated wireless card. Just thought I'd warn you. If you're using an external card with it, enjoy.

Also, with the install, there was a tendency for the installer to sort of "freeze" near the later steps of the install, a quick wiggle of the touchpad seemed to clear that up.

There were a few other components that lacked drivers but I can't recall which exactly.

Other than those issues, good luck!

Re: Quick notes on the install

[atrader42]

Figures. Thanks for the warning. Naturally, I'm in a wireless-only situation. I guess I'll see if anything comes out.

really?

[Anonymous Coward]

ive never heard that expression living in many canadian provinces.

maybe your over 30 or something

Re:really?

[Darken_Everseek]

nope; 22. My dad's fond of it though; and he's over 50 .. maybe thats it?

Depends

[Sycraft-fu]

64-bit means about jack and shit on the desktop these days. The increased memory pool (the main reason to want 64-bit) is meaningless for the general desktop at this point, and 64-bit integer calculations are not needed by much. Most large calculations desktop PCs need are for games and are FP, which are already over 64-bit.

Sooooo, the Itainum pitches to the market for which there is the most intrest: high end servers. Now, as time goes on, the following iterations will doubtless get cheaper, as has already been demonstrated with the 1->2 generation. It is likely that by the time 64-bit on the desktop IS something important, the Itanium X will be availabe at a desktop price.

Now if this works out remains to be seen, could trun out that x86-64 is where evreone goes and that is that. However, just because AMD has consumer level 64-bit chips now doesn't mean they are going to win the 64-bit war. Most consumers are going to sitck with 32-bits for some time to come since it currently offers a cost advantage and there is no real advantage for them to move to 64-bit.

Re:Depends

[pla]

Most consumers are going to sitck with 32-bits for some time to come since it currently offers a cost advantage and there is no real advantage for them to move to 64-bit.

I really don't understand why so many people have decided to speak poorly of 64b CPUs... Sure, not all that many programs will benefit from them right at the moment. But some will. And if we really want to take the "we don't need more bits", why not go back to 16b? or even 8b? Hell, let's just use bitslicers - We could probably clock one of those puppies well into the hundreds of gigahertz, due to the design simplicity.


The mathematical hobbyists (such as myself) will switch first, for the obvious number-crunching advantages. I already look forward to getting my hands on an Athlon64, to port a few of my projects to. Even better than the machine word length, though, I look forward to having a decent number of registers. Yum.

Then the gamers, as soon as they realize that 64b->64b->256b (CPU to AGP to GPU) performs quite a lot better than 32b->64b->256b...

Next will come either another boon to the gamers, or to the artists, depending on whether "killer game 2005" or "Photoshop 2005" comes out first with x86-64 optimizations.

Last will come the casual users, but they will only buy in when they have no choice (really, although 8b doesn't suffice, 16b works just fine for 99% of what a PC does.. So why do they even use 32b?).

Overall, I agree with you - you don't need 64b to browse the web and email grandma. For anything that either pushes the CPU to its limits, or improves linearly with the addition of more RAM, 64b has an obvious advantage.

As an aside, I already mentioned the increased number of registers in AMD's 64b offerings... While a lot of people have debated this issue only on the merits of "why do I need 64b?", the x86 line has always had a SEVERE shortage of GPRs. Doubling that number will (not just "could") boost performance immensely.

Re:Depends

[Sycraft-fu]

Registers are not as important as you may think. Remember that the x86 ISA no longer has anything to do with how a chip actually operates. ISA registers are remapped to the real registers, of which there are a great deal more of. So while there is a benefit of exposing more registers in the ISA (which I would note IA64 has more of), it is not as large as you might imagine.

Re:Depends

[pla]

Registers are not as important as you may think.

Above some "decent" number, I'd tend to agree with you. Standard IA32 does not, however, have anywhere near enough.

"Enough" means not needing to use registers with clear designated purposes (such as ESI, EDI, and yes, even EBP) just to keep a triply nested loop (that actually does something) from hitting memory.

"Enough" means not needing to remember if CX gets clobbered on a given shift-like operation, so we need to preserve it temporarily.

"Enough" means having the ability, on performing a set of similar operations on a vector (not talking about using SSE or the like here), to interleave enough groups of operations to prevent a register dependancy stall...

Enough already. <G>. "Enough" means "more than 8" (of which you can only ever use at most seven, and even that with some difficulty).

Re:Depends

[ProtonMotiveForce]

What's funny is when people buy thse 64-bit chips and realize they aren't any faster on even the things they _thought_ they would be faster on. Gamers won't be helped much at all - the performance increases due to more registers are no better than you'd expect from any of a number of other changes.

Meaning more registers is no better than more cache, more GHz, more IPC, etc... And it will not boos importance Immensely - it'll be some number less than 10% most of the time.

Windows XP 64-bit close to release?

[MtViewGuy]

I personally think that Windows XP Home/Professional for the AMD x86-64 CPU architecture is closer to release than people think.

They're probably right now redoing much of the OS code so it does take full advantage of x86-64 registers, and is waiting for other Microsoft departments to complete their work so an improved version of Internet Explorer 6.01 (Service Pack 2?) and all the Windows XP Service Pack 2 improvements are incorporated into the final version. Don't be surprised that when Windows XP SP2 ships some time this summer we'll see both 32-bit and the x86-64 64-bit version come out at the same time.

My condolences

[rs79]

I grew up on FORTRAN II on punched card, Later WATFOR and WATFIV.

I'd like to say those were the happiest days of my life.

I'd like to say the prospects for world peace are good, too.

Re:It's not that great.

[lowe0]

Your machine's fucked. Whoever gave it to you, give it right back and tell them to set it up for you, and to do it right this time.

Sorry, but no modern system should take that long to copy a file. Mine can move around 60 megs in about 20 seconds. This isn't a "My B0x0rz R0x0rz" brag here; it's just that your machine shouldn't be that slow.

One possible issue: if you're getting IDE corruption, XP will degrade your performance (down to PIO, if necessary) in order to preserve data integrity. Check your IDE controller settings to find out if this is the case.

Anyway, the major reason why Opteron owners want XP 64 is to be able to use the extra registers on their CPUs. They're not available in 32-bit mode.

Hi, you are a fucking retard

[Anonymous Coward]

That is all.

64-bit Windows

[kylef]

Of course windows likely will run slower since it's so optimized for the older 32bit platform.

The last time I checked, NT is built on something called a "Hardware Abstraction Layer" that made it relatively painless to port NT from MIPS to x86 and then to PowerPC. (NT was designed on MIPS R4000 machines which themselves were completely designed internally by Microsoft. This effort was deemed necessary to keep the codebase free of x86-specific assumptions and optimizations since portability was a key NT goal.) The hardest part about getting your system to run on a new 64-bit platform is getting drivers to work; generally you need lots of support from hardware vendors to accomplish this feat. Getting the OS itself to compile is the easy part.

But I doubt seriously that Windows NT is "so optimized for the older 32bit platform." The kernel is clearly portable to other architectures, and was in fact developed FIRST on a non-x86 architecture with different properties (page size, Endian-ness, etc). This leads me to believe that it is emphatically not "optimized" specifically for 32-bit x86. If you have evidence otherwise, I would like to see it.

Linux is just a much more mature platform for 64bit computers.

Much more mature? Perhaps you were unaware of Windows XP 64-bit Edition? Sure, it only runs on Itanium, but do you not honestly think that for Microsoft to have released it in early 2003 that they would probably have been working on it and testing it for at least a couple years prior to that? Also, from Microsoft's website, I notice that they have also implemented a 32-bit emulation layer for Itanium called "Windows On Windows 64" (WOW64) that lets the OS run 32-bit X86 code. Does Suse have this capability built-in?

The other issue which I pointed out earlier is the driver situation. You can't really call a product "much more mature" unless its drivers are more mature. I don't see a clear win either way at the moment.

Re:64-bit Windows

[joib]

> Linux is just a much more mature platform for 64bit computers.

Much more mature? Perhaps you were unaware of Windows XP 64-bit Edition? Sure, it only runs on Itanium, but do you not honestly think that for Microsoft to have released it in early 2003 that they would probably have been working on it and testing it for at least a couple years prior to that?



Linux was ported to the alpha about a decade ago (this was still a 32-bit kernel, just like NT on alpha AFAIK), sometime in 1996 a real 64-bit version was released (2.0). Despite MS market share, I'd guess that there are a lot more 64-bit linux installations around than 64-bit windows.

Another important things is that since most linux software is open source and designed for portability from the start, a 64-bit kernel with a 64-bit userspace is as easy as a recompile (well, almost). MS has a big disadvantage here, because they need to wait for their ISV:s to produce 64-bit programs as well as drivers.

Re:64-bit Windows

[kylef]

Despite MS market share, I'd guess that there are a lot more 64-bit linux installations around than 64-bit windows.

You might be correct, but honestly both of us are just speculating. To be honest, I think neither Linux nor Windows can match the number of Solaris 64-bit installations there are in the world. But again, it would be interesting to see some data on the matter. My point was only that one can't call Linux "a much more mature platform," as the previous poster did.

I do know that HP and one or two others are shipping Itanium2 servers full-steam at the moment, despite Intel's recent 64-bit malaise. It's almost a given that all of those will be running 64-bit Windows. I've seen a demo of a HP 64-bit workstation running 64-bit Windows, and it was really nice. It even had accelerated video drivers, but I don't know what video hardware.

MS has a big disadvantage here, because they need to wait for their ISV's to produce 64-bit programs as well as drivers.

This is absolutely correct. If you have source code, you can (usually) just recompile for 64-bit user-mode applications. Otherwise you wait for an ISV to produce a binary for you. But Linux64 is in the same boat with Windows64 as far as drivers go. Arguably worse, since manufacturers have been (until now) unwilling to make their drivers open source and generally produce Linux drivers only after Windows drivers are already complete. And as we all know, the KEY to PC users' hearts is seamless hardware support!

Re:64-bit Windows

[Xabraxas]

The last time I checked, NT is built on something called a "Hardware Abstraction Layer" that made it relatively painless to port NT from MIPS to x86 and then to PowerPC

I guess the last time you checked was a long time ago. Originally NT was built on top of a microkernel, and that is what was supposed to make it portable. Unfortunately it was dog slow and it is no longer a real microkernel. The microkernel is what you are referring to when you say "Hardware Abstraction Layer". It's safe to say that Windows was pretty much x86-centric until this release.

Re:64-bit Windows

[Xabraxas]

Correction. Winodows still useses what they call HAL (Hardware Abstraction Layer), although it is not the same as the microkernel approach they once tried. HAL is basically what became of the NT microkernel. That makes it easier to port but probably not as easy as a microkernel would be. It all depends on how big HAL actually is.

Re:64-bit Windows

[Bert64]

Windows NT has always been a 32bit platform however, even the version for the alpha processor used hacks to make the processor appear to be a 32bit one, the alpha, like the itanium, is a 64bit design from the ground up and has no 32bit compatibility mode atall, however it can emulate 32bit x86 and 32bit vax in software.
Linux on amd64 doesn`t need to emulate 32bit x86, since the amd64 architecture can execute 32bit x86 code natively. However alpha linux can emulate 32bit x86 code with a tool called em86
Aside from that, the grandparent poster is correct, linux is far more mature as a 64bit platform... linux has been 64bit on the alpha for years, ultrasparc too but not quite so long, and i believe there are 64bit mips and ppc ports too.

Re:64-bit Windows

[Bert64]

What`s more, 64bit windows is something new, so your far more likely to encounter non 64bit clean code in windows apps, Contrast this to unix apps.. where 64bit systems have been available for years and so a majority of programs can already compile cleanly on a 64bit platform.

Re:64-bit Windows

[Bert64]

However a lot of linux drivers are 64bit clean, and have long worked on 64bit Alpha, PPC and Sparc machines running Linux.. Many PCI nic and scsidrivers for instance work flawlessly across different architectures including 64bit ones.
I myself have an Alphastation with a number of pci cards using drivers intended for 32bit x86 machines, which work perfectly well.

Re:64-bit Windows

[inquisitor]

I do know that HP and one or two others are shipping Itanium2 servers full-steam at the moment, despite Intel's recent 64-bit malaise. It's almost a given that all of those will be running 64-bit Windows. I've seen a demo of a HP 64-bit workstation running 64-bit Windows, and it was really nice. It even had accelerated video drivers, but I don't know what video hardware.

Almost certainly either NVIDIA or ATI; probably NVIDIA, since only a couple of ATI cards are supported on Itanium. NVIDIA also already have an accelerated AMD64-Windows driver, and accelerated Itanium and AMD64 Linux drivers available from their web site. They are much further ahead on 64-bit than ATI are, and that could be to their great advantage.

Re:64-bit Windows

[Torne]

The HAL is not anything to do with the microkernel (the executive). The HAL sits outside the executive and is responsible for managing things like the current interrupt level, and other things which can differ wildly between architectures. Windows NT is not x86-centric and never really has been; the codebase has contained PPC/ARM/Alpha code for a while (though the ARM port was never released).

Re:64-bit Windows

[tc]

There is still such a thing as the Hardware Abstraction Layer. It's not the same thing as the now defunct microkernel.

hum no

[Anonymous Coward]

clueless moron.

Re:hum no

[Penguinoflight]

double clueless moron, now what!?!

M$ better fix the 32bit first

[Anonymous Coward]

XP crashes just left and right on the 32 bit version.
Fix that M$ u piece of shit software company.

This has been around for a *long* time

[zrail]

I have a relative that works at Microsoft, and as part of an internal promotion thing she has a bunch of three-disk sets. 1st disk is WinXP Home, 2nd is Pro, and the 3rd is XP 64bit. This has to have been at least a year ago.

Well then what the fuck am I running?

[blair1q]

I just bought an eMachines m6807 notebook with an Athlon64 3000+ cpu (512MB/60GB/802.11g/DVDRW/Radeon9600/etc/etc/etc) and...yeah...probably a 32-bit version of XP Home. Pro woulda been nice but it wasn't an option; as a compensation, all the "free" bundled software uninstalled almost cleanly, and I was able to get a nifty new 802.11g WAP/switch/router/VPN with the savings vs. a comparably equipped Dell...

When I feel more confident (and get a couple of blank DVDs to use for backups) I may snarf down winxp64...

Some notes and thoughts...

[89cents]

1. Nice to see an AMD64 directory on the CD instead of the old I386. There still is an I386.

2. EXE files seem to still start with the MZ initials and contain the text "This program cannot be run in DOS mode."???

3. Click on a .exe file on a P4 produces filename.exe is not a valid Win32 application - expected

4. Docs/XP_AMD64.TXT, system requirements contains:

* 1.5 Ghz Opteron(TM) or Athlon(TM) processor

* 512 megabytes (MB) of RAM (minimum)

See how many people try to install on their 32 bit
Athlon. Suprised to see 512MB minimum.

5. Suprised to see this bit about the relatively new .NET framework:

Applications dependent on Microsoft .NET Framework version 1.1 are not
compatible with Windows Server 2003, Standard Edition;
Windows Server 2003, Enterprise Edition; or Windows XP 64-Bit Edition
releases for AMD Opteron and AMD Athlon 64 systems.

Because Microsoft .NET Framework 1.1 is not supported by any 64-bit
products, .NET Framework is not included on the 64-bit CDs.

The 32-bit version of .NET Framework is also not supported by these
64-bit products and cannot be installed on 32-bit applications running
on 64-bit Windows operating systems (WOW64). This restriction applies
to the current and previous versions of .NET Framework.

6. Now I just need an Athlon 64 :)

Advantage: No more files!

[Cardbox]

I don't care about 64-bit arithmetic. 64-bit pointers on the other hand... they give you enough memory that ANY hard disk can be memory-mapped. For database applications that's a big win. At present you can only memory map small files (1GB) and still need to keep the apparatus for file I/O in case people want to create something larger. But with around 8EB of virtual memory you can keep the whole DB in memory and let the OS deal with *all* the physical details. Anyone know a good Linux to start developing on, now?

Re:It's not that great.

[Anonymous Coward]

YHBT, YHL, HAND

parent is a small-minded tool

[Anonymous Coward]

and there are so few of them on /.

need a preserve

This story has been out for more than 10 minutes

[waspleg]

i bet there is a hack

download here - url

[Anonymous Coward]

http://download.microsoft.com/download/7/a/f/7af62 a47-5020-42ec-9eb3-0b146bfd7501/srv03sp1_usa_1069_ amd64fre_pro.iso

Still no SATA driver :(

[Frodo420024]

Gave it a spin on my shiny new box :)

No fun, the SATA driver is not included, it doesn't see my hard drive. Guess I'll have to do it the tricky way, modifying the install CD.

Any Linux's out there in 64 bit versions with a SATA driver out of the box?

Re:Still no SATA driver :(

[Anonymous Coward]

Yep, Gentoo :-)

http://dev.gentoo.org/~brad_mssw/amd64-tech-note s. html

Re:Still no SATA driver :(

[Anonymous Coward]

Mandrake and FreeBSD (64 bit versions for both) are the only ones which worked with my gigabyte onboard sata...

unfortunately a lot of good distros like Debian don't have a release yet... :(

Suse sux don't try it, didn't recognize my sata...

Re:Still no SATA driver :(

[Frodo420024]

Yep, Gentoo :-)

Gentoo AMD64

Whoa, a Live-CD :)

Trouble, though:

... Silicon Image 3112 driver [..], this does work on some boxes, but NO SUCCESSFUL REPORTS on AMD64!

Damn...

Also I do like X and KDE (or Gnome for that matter) - being dropped to a raw shell is not tops. With the SI 3112 issues, I guess I'll have to add patience :)

Donald Duck

[Anonymous Coward]

Donald Duck will have a SCREAMING ORGASM when the 256-bit DRMed Winblows Lowerhorn comes out.

Confusion

[nmg196]

I don't understand.

In the Top 5 Reasons to move to Windows XP 64 page it says things like, "Windows XP 64-Bit Edition has been optimized specifically for the Intel Itanium processor" and many other similar comments. It mentions nothing about any Athlon 64bit processors. Yet on the download page it says it only supports the Athlon 64 and Opteron.

Why the massive discrepancy? If the whole thing is optimised for the Itanium, then why isn't the Itanium even supported by the demo version?!

It doesn't even boot after install?!

[Anonymous Coward]

I was happy when I saw this message because from my understanding there is only an OEM version of WinXP64 - (hey I run linux too this is not trolling and my hw only takes xp). No Retail? So what the heck is this release then anyways? Is there no OEM version at all? I thought it was vaper-ware but jeesh... maybe it was the IA64 (?!)

Anyways... however, after backing up my drive, downloading the ISO, and installing, very bad things happened...

The system would hang on boot and the printer starting spewing out f*ct up screen shots... ???

Thankfully NTI Backup was able to provide an excellent recover (albiet slooowwwww).... I even got my lilo back so I could boot mandrake if I wanted. So please I BEG you, if you feel the need to install this then back up your HDD first! *shouldn't even have to say this, but hey...*

Also, the ISO starts with "srv03", whats up with that? And links from the site point to Server 2003 website after you, uhm, 'register'. And no reg code like for Server 2003 either...?

I told my brother I would go rip out Bill Gate's heart Indiana Jones style if this didn't work...

see ya l8r!

Who cares???

[pillendraaier]

not me

64 is about marketing, and about selling boxes.

[nikster]

that is the beginning and the end of the argument for 64 bit. who cares if it's faster? of course it will be, for some things, and it will be on par for others.

but the big thing is selling a box. this is where the $ is. and this is where i can say: i will sell you double for almost the same price! 64 instead of 32 for just a small premium. it's justifiably "more advanced" technology. and that will sell it.

who needs 64? servers and large apps may or may not need it. marketing most definitely needs it.

Microsoft, Intel, and AMD do not care about making ssl faster, or mp3 encoding. they couldn't care less. what they do care about is selling boxes. that is what it's all about. who will benefit the most if everybody upgrades to 64? games have been the sole reason to upgrade your system for the last couple of years, and that is just a pretty weak argument (e.g. capturing only a very small portion of the market). 64, on the other hand, could be huge.

Re:64 is about marketing, and about selling boxes.

[inkless1]

after all, who needs more than 640k of memory?

Seriously, if you justify technology by what you -need-, you'd have an ARM processor, 16MB of RAM, some form of portable media, a touchscreen and a keyboard. Add an ethernet if you want to get fancy and call it a day.

Yamhill, It's Intel's Opteron clone***

[DABANSHEE]

designed as a backup & hopefully just shelved away.............well unless AMD's Hammer developed mommentum

Many years ago AMD managed to get a license to Intel's patents, however it was a cross license agreement, meaning Intel can make X86-64 CPUs.

This seems to suggest that maybe Intel's Yamhill is a clone of AMD'S Hammer. Now whether it's a straight clone, IE electrically compatible as in chipset/socket compatible (like the Cyrix 686 & the P5 or dare I say the old AMD 486s & the Intel 486s), is another question altogether.

MOD PARENT UP

[Anonymous Coward]

Insightful. :-)

Dammit... where are my mod points when I need them?

I apologize in advance...

[denlin]

"What are you doing, Dave?"

Expiration

[Orlando]

It's a pre-release copy that will expire in 360 days

That's funny, in my experience release copies of Windows usually 'expire' much sooner than 360 days.

someone set us up teh bomb

[lamer]

its noticeD not notice

dont leave your education to chance.

I missed somthing...

[Maljin Jolt]

Why should I use a preview of future 64-bit Windows when I can use current 64-bit Linux just now?

To hell with 64 bits..!

[dustinbarbour]

What we need is a tertiary computer. We've been using the same lame-ass binary system forever and it has its limits. It seems to me that, instead of developing better PCs, we just make them all faster. Bleh! You know the old addage (sp?).. work smarter, not harder.

Offtopic: White vs. mirror

[Sique]

I've never been blinded by the sun glinting off a pile of sugar, but I sure have when it glinted off the bumper of my '84 Buick tank.

Go to White Sands, NM ;)

It's a gypsum desert, purely white (ok, ok. It's calcium sulfate, so it's not as bright as titanium dioxide, but there are no titanium dioxide deserts I am aware of).

When I was there in summer (115 F/46C in the non existant shadows!) I had to actually hold my hand below my eyes to see anything, and usual sunglasses wouldn't have helped because they don't shadow the eyes from light coming in from below.

The main difference between white and mirror is that the mirror reflects the sunlight beam in a single direction, and if the mirror has an optical albedo of 0,9 (90% of the visual light gets reflected), you look at 90% of the full sunlight if the reflection of the sunlight hits your eye (which is quite bright), but you get barely anything at other angles (just the reflection of the general brightness of the surroundings).

A white surface doesn't necessarily keep the light beam parallel, so you see a bright surface from a very large angle. A white surface with an optical albedo of 0,99 (only 1% of the visual light gets sucked in and turned into infrared) can be calculated as a new light source, which emits nearly all of the incoming light according to its own characteristics. That means that the light you receive from it depends on the angle you look at it and the distance you have from it. But because the white surface emits the light in different directions, you will never get the full intensity of 99% at a single point, and the intensity decreases further with the square of the distance (if you double your distance to the surface you get a quarter of the intensity).

So even if a white surface may be 10 times more effective as a mirror (with 1% light loss in reflection vs. 10% light loss in reflection), from a certain point the mirror will look brighter: If you stand directly in the reflected light beam.

(Those different properties of reemitting received light are wellknown to the computer graphic specialists, because both effects they get handled differently: For mostly reflecting surfaces like mirrors and polished things ray tracing is a quite good model to calculate the light impression, for matte surfaces like stones, wood and walls radiosity yields better results.)

(PS: Those albedo numbers are made up, but they shouldn't be far away from reality).

MS follows the leaders again

[Warlock7]

Now that Apple had laid down the gauntlet and Linux works that way too, MS is again following the rest of the industry...

really?

[cyberbob2010]

thanx for the link to microsoft.com lol, like there arent enough out there