Slashdot Mirror
Are We Not Ready For 64-Bit?
Q3vi1 writes "The Inquirer posted an intriguing article about how Intel doesn't think that we'll be ready for mainstream 64-bit computing until 2007. Coupled with the fact that MS isn't supporting the Opteron yet for their Windows 2003 Server, we may see a delay in consumer applications for 64-bit computing. However, as this article states, some people don't really care and will just go for Linux and AMD as a nice marriage."
Apple will come out with a 64-bit OS X sometime in the next year (with the 970). Critics will say "Wow!", and then ignore it. Apple sales won't change a bit and three years later MS will come out with 64-bit computing to universal acclaim and the market will buy it like hotcakes...
99.9% of the population do not use the currently level of computing power available. As a consultant I get the question all the time "Do I need to upgrade to a faster machine" when all the person is doing is a little word processing and surfing the net.
they're counting on $3000 IA-64 chips to preserve their profit margin, but if 64 bit catches on in the mainstream, they're going to have to follow AMD with x86-64 at much lower margins.
I think the problem is that if microsoft don't adopt opteron then AMD will not get the volumes needed to substantially undercut the price of itanium - if it isn't highly price/performance competitive with intel/sparc then your average linux shops simply won't adopt it.
.
:^)
So once again microsoft have the power to crush a fantastic new technology before it even gets off the ground
like a weight looming overhead - have to say i know that feeling
Before adopting WHATWG, read the moonlight.NET EULA [http://www.microsoft.com/interop/msnovellcollab/moonlight.mspx]
take off every sig for great justice
Just yesterday a few people suggested on apple.slashdot.org that the next release of OS X, code named 'Panther', may include 64-bit support. Apple may think we're ready.
But do we need it? Will the benefits outweigh the cost. I think Apple's offloading of CPU tasks to the graphics board for Quartz Extreme is an example of just one of the alternatives for speeding up machines. Offload more tasks to other intelligent subsystems.
I am ready, since when the 64-bit machines come out I can pick up a 32-bit on the cheap!
My user name was a mistake. Input wasn't restricted, my bad.
If this current situation shows anything, it is what happens to companies when they make deals with Microsoft. AMD's Chairman and former CEO Jerry Sanders agreed to testify on Bill G's behalf for the antitrust trial as long as MS ported windows to Opteron and Athlon 64.
As Apple has always been forward thinking to gain market share and attention, I think this will be yet another rush of sales for them, especially if Intel offerings start to have DRM built into the chips and continue to stretch processor pipelines to absurd stage numbers >20.
Yell & scream & rant & rave... it's no use... you need a shaaaave ~ Bugs Bunny
I'd be interested to know how many operations on today's computers actually even use up all 32 bits available to them. I'd expect those situations to be rare: Matrix math operations, some addressing.
How about every time you load a memory address or deference a pointer, since in 32-bit protected mode all you use is 32-bit addresses.
And oh, w/64-bit processors come 64-bit pipelines and the ability to use 64-bit instructions and data. The slowdown is nil.
Its really nice to break the two-gig barrier in program buffers. Sun-SPARC and SGI-MIPS have been 64-bit since 1994.
The Opteron will still run x86 code fine so a install that will work on any x86 system will still work on the Opteron (although wasting the 64bit capability).
Although there is a reason it's called Wintel.
Multimedia editing is a desktop app that can make good use of 64 bits. It isn't uncommon to to have uncompressed DV captures 17GB in size. Add effects and a few edits and the address space of a 32-bit machine can start to hurt in a hurry. The end result will have to be compressed as well. Yes there are ways to cope with it but it re-introduces the segment offset nightmares of old school x86 programming. Also memory sizes on end user desktops are increasing. Anything more than 2GB on an x86 box starts getting painful. Yes, I know they can `technically' handle 4GB but kludgery starts setting in at 2GB.
"Mom" is starting to use this "PC Thingy" to make home movies. I see "Mom" needing 64 bits before long.
64 bit server computing has been around for at least a decade. I was using a 64 bit DEC alpha
box back in 1994. Why is it that whenever middle aged or even old technology appears on in the PC
world its suddenly a Big Deal? I realise that Joe Sixpack won't have ever heard of 64bit (or probably even be able to spell it)
but surely the more technologically savvy types who read this site should know better?
Can you please explain to those of us who clearly don't know any better why certain PC applications are "dying" for 64-bit processors? Hint: they won't magically become faster.
Addressable memory. Right now the limit is 4GB. With Windows XP, the OS sets 2GB aside for the OS, so apps only get 2GB, and that's shared across all the apps.
For word processing and surfing the net as it currently is now, none of this matters.
But if you want rich multimedia content, the ability to do serious 3D imaging on the fly (think 3D operating systems) and the like, you're going to need more RAM. The only way to get that is with a 64-bit chip.
The AutoCAD and 3D Studio and Photoshop apps the parent poster mentioned *are* dying for more RAM. I have 3D models that are pushing that 2GB limit.
My journal has hot
Yeah, but we'll see just how long Microsoft ignores Opteron when everyone starts buying low-cost servers based on Linux and Opteron. They will have no choice but to adopt it. Even then, it will be growing on the desktop.
Keep in mind that these processors are going to be *replacements* for the current line of consumer-grade AMD stuff... Not Intel server chips. Not SPARC. As long as AMD continues to beat Intel to the punch in terms of performance and features at a low price, I don't think it will be a problem... And that's exactly what they have in mind.
The 80386 processor introduced more than just 32-bit register addressing. It was also the first processor to support the protected mode interface to the processor and not to mention the ability to "virtualize" memory by paging to another medium. Windows 3.0 took advantage of the new features of the processor while still being a 16-bit operating system.
Nonetheless, I think the basics of 64-bit computing are solid for the server arena, but when you examine the Opteron processor (and the x86-64 architecture), AMD offers alot of simple performance benefits by simply assisting problems associated with register starvation (the more the merrier, right?) When you take this into consideration, any application that works with large chunks of data (be it 32-bit for Opteron's legacy mode, or native 64-bit) - it results in faster processing time. Compiling the Linux kernel should be faster with all those handy dandy general purpose registers that come with the Opteron.
I believe Intel understands what it is talking about, however - Intel has done an extraordinary job in predicting the market and following demand. However, in the case, I think Intel is purposefully leaving out the x86-64 implementation in their consideration. Early Itanium benchmarks (even the Itanium 2) show that the processor isn't up to snuff in most instances, and to compensate, Intel simply throws 2M (or even more) worth of cache to help the little guy out.
AMD, on the other hand, is not waiting for a certain time to flip the big switch for the consumers. By incorporating native support for all legacy 32-bit application code in the processor, mainstream consumers will be adopting 64-bit computing without necessarily utilizing it for what it was intended for, BUT they will enjoying the architectural benefits as a result.
Ayup
Are we ready for 64-bit on the desktop? yes. Do we need it? No, but that isn't the point of a lot of computer hobbyists. Most of us don't really need the latest video card from ATi or nVidia. Mose of us don't need the latest processor from AMD or Intel. But we still buy the latest and the greatest. Why? Could be a matter of manhood, or for the woman, womanhood. Whatever reason it is for this phenomenon, there is no doubt that it happens. Yes, we are ready, and no, we don't need it, but the hobbyist will still buy them if the average computer consumer won't.
---Baseball is not right, a man can not walk with four balls. mike9010
Correct me if I'm wrong, but isn't the PowerPC/G4 based off of the POWER4 architecture... but with all the 64-bit (as well as several other "high-end" features) stripped out?
You're wrong. The G4 is basically a PowerPC G3 with an 'Altivec' vector unit.
Come on guys.... you know I'm right. Unless you're in the scientific fields that use huge numbers and insane gobs of memory, 64-bit data paths will be wasted cpu-real-estate.
And 640K of RAM should be enough for everybody.
What Intel is really saying here is that INTEL isn't ready for mainstream 64-bit computing.
Both AMD (Hammer) & IBM (PPC970) 64-bit processors will run 32-bit applications with no modification, and at more than full speed, unlike Intel's Itanium processors. By the time Intel gets around to a 'mainstream' 64-bit processor, both AMD & IBM will have years of experience with mainstream 64-bit CPUs, and in the CPU game, experience is invaluable. Then again, watching someone else make the mistakes often has an advantage, too, and I doubt Intel is going out of business anytime soon.
Intel has worked out that their Itantium/Pentium performance/cost manufacturing curves cross in 2007.
Also, asking the question presupposes there's an answer. "Mom, are you ready for 64-bit computing?" "64 what?" Most people don't know or care what their system architecture is, they just want their apps to work.
Which is why 2007 is really too late - we need a 64-bit time_t in production by 2007 so that 30-year mortgages can be properly calculated. (32-bit time_t values run out in 2038) Remember, that's how the Y2K problem was 'discovered'. If Y2K is any gauge, 4 years is about how long people will need to get all the systems fixed, so we ought to be getting started just about now.
Thanks, Apple.
My God, it's Full of Source!
OUTSIDE_IP=$(dig +short my.ip @outsideip.net)