Intel Begins Shipping 64-bit Prescotts 411
Rucas writes "With a minimum of fanfare, Intel has begun shipping a version of the Pentium 4 with 64-bit instruction set extensions. The news came to light not via an Intel press release, but rather through the spec sheet for a new server from IBM. In the midst of the new IBM eServer xSeries servers based on the recently released 64-bit Xeon is a blade server powered by the 64-bit Prescott. This marks the first product appearance of the new CPU."
plagiarism (Score:2, Informative)
Original Article (Score:5, Informative)
http://arstechnica.com/news/posts/20040804-4070.h
Xeon-Nocona no faster on 64-bit code? (Score:5, Informative)
Though Xeon-Nocona has been available for more than a month [intel.com] it seems there there are no substantial reports on 64-bit performance of Nocona. Is there anyone here who can report anything about the 64-bit performance of Nocona?
That write up looks familar ... (Score:4, Informative)
Re:Where are the 64 bit apps? (Score:5, Informative)
Among other things, it should let the OS map more than a few gigabytes of memory into the address space at one time. A 32-bit application will only be able to see 4 gigabytes (or 2, or whatever the limit ends up being after tag bits and OS space are reserved), but the total amount in use can be more, without an application rewrite needed. This is already done to some extent (my understanding is that the 32-bit processors have 36 bits of address space in total, with a 32-bit per process maximum), but moving to 64 bits gives a lot more headroom.
I see a lot of people upgrading to 64 bit chips, but what good does it do if there's nothing to utilize them? Is it just for bragging rights or what?
I'm a programmer and I have yet to see a need to get a 64 bit chip.
It's handy to have native handling of things like 64-bit integers, but addressable memory space is the most pressing reason right now. You'll be able to mmap() a file larger than 2 gigabytes on x86-64 machines (where up to now you had to use a non-x86 platform). You'll be able to hold more than 2 gigabytes of working data in RAM, which is significant if you're doing video editing (or heavy rendering or really heavy image processing).
Consumer apps and games will move into this niche in a few years (there are algorithms that let you trade off memory footprint and speed, and memory is cheap). But there are several places where the ability to address more memory is important _now_, even for user workstations.
Re:Quick! (Score:1, Informative)
A Note on memory addressing (Score:5, Informative)
Thats right, the same 36 bits that intel has supported via PXE for years...
Thus, total system memory size for these processors is limited to 64GB, meanwhile the per-processor limit for AMD chips is 1TB, 256TB total in a system (max 256 CPUs, if anyone ever makes a board and Hypertransport bridges capable of supporting such a large number of chips).
Anyway, it is a big difference, and it hints that the actual implementation may be the same old slow PXE implementation intel has had for years (since the pentium pro, if I remember correctly).
------------ This post was made while on percocet and no spell checking has been done. deal.
Re:Disabled 64 bit extensions on first chips shipp (Score:3, Informative)
My guess is that it would work, but they've been fine-tuning it the whole time and so if you could enable an old one, a new chip (pre-enabled) would be faster than an old one, as they were using the extra time MS gave them (intentionally or not) to make things better.
Re:A few months late to the party... (Score:2, Informative)
http://www.nationmaster.com/encyclopedia/DEC-Alpha [nationmaster.com]
Re:Amazing (Score:1, Informative)
Think you mean the 186 don't you as that controls traffic lights.
286 was pre 386
The 186 was pre 286 as well.
I think he means the 8088 is a stripped down 8086, or that the 386sx is a stripped down 386dx, or the 486sx, or the celeron...
Re:Quick! (Score:4, Informative)
There are also the "intangibles". For example right now software can only use about 3 gigs of memory without hacks (PAE and such). This is because there is only 4 gigs of address space and the OS and libraries must be in there somewhere, so most OSes give the OS 1 or 2 gigs of that address space. And you must map a library into each program's view of the address space, possibly into different areas. With a 64-bit address space, you could give a full 4 gigs to tons of programs, all while having lots of libraries loaded and have a simple linear addressing space for everyone. This simplifies things quite a bit. And when you need to use more than 4 gigs of data, you'll be able to without any performance hit.
The biggest difference you'll see are the registers. While it won't help you type faster into a word processor, it could very well help a game out.
Re:A Note on memory addressing (Score:2, Informative)
I know it's the percocet talking, but I think you mean PAE [thefreedictionary.com] not PXE [pxe.ca]...
Apart from that - absolutely correct.
Re:Fan Boy Alert (Score:2, Informative)
The USB 2 didn't work and they had to bundle a sepearte card and turn off all the onboard USB.
That sucked
Dell is shipping 64-bit Pentium 4 workstations. (Score:5, Informative)
Also, Anandtech just posted a new roadmap [anandtech.com] with some info on upcoming 64-bit Pentium 4 CPU/chipsets for the desktop. The Intel 925XE chipset (with 1066MHz FSB) will ship in October along with 64-bit Pentium 4 "F" processors. "F" supposedly means it's a 64-bit Prescott.
Re:Opteron Still Better (Score:3, Informative)
But the major reason to do it (at least in the server space) is because it's not shared. So if you have a 4 processor Intel server (which has a shared memory bus through the northbridge), and you have 1 GB/s of memory bandwidth (way to low, just an example), then if all processors are accessing memory they each get about 250 MB/s of data. If you go up to 8 processors the total memory bandwidth is the same, so now each processor would only get 125 MB/s (if they were all asking of memory at once). As you add processors, that situation becomes more and more common, meaning that your chips spend more and more time waiting on memory. So while adding a second CPU may boost performance 90%, the 8th may only boost it 10% or less (depends on the work your doing, etc.).
Now the Opteron each has it's own memory bus. That means that when you have 4 CPUs each with 1 GB/s of memory bandwidth (fictional number, again) there is a total of 4 GB/s of bandwidth. Each chip can work in it's own memory at 1 GB/s. When you go up to 8, or 16, or 32, or whatever it still works. So with a 8 processor server, each CPU still gets 1 GB/s. So when you add a second CPU to an Opteron system, it might boost performance 90% (again). But when you add the 8th, it will scale much better, so you might get an 80 or 85% boost.
So while putting 32 Intel chips on one motherboard would be basically pointless in many situations (because they processors would be stuck wating on memory), with an Opteron it would work pretty well.
And even if you only have 2 gigs of RAM, all that extra address space can really make things easier on the OS.
Re:Figures (Score:5, Informative)
Re:Figures (Score:4, Informative)
IT'S NOT A PROBLEM ANYMORE, NVIDIA AND SIS BOTH HAVE QUALITY CHIPSETS FOR AMD AND VIA HAS CLEANED UP IT'S ACT.
I'm sorry for shouting but damn, this hasn't been a valid argument for years and intel zealots are still spouting off about it.
Re:Figures (Score:3, Informative)
At least with AMD we can say they moved to 64 bit, Intel hasnt really done anything.
Re:AMD welcomes Intel to the world of AMD64 (Score:3, Informative)
The Itanium series does have a few high-availability features nonexistent in Xeon or Opteron, and is a heavy-iron type chip. Unfortunately, the market for those are slim at best compared to the desktop and small server market. It doesn't help that there is something of a backlash against high-watt computers, for example, a lot of blade systems have stuck to PIIIs then replaced by Pentium Ms.
Re:Amazing (Score:3, Informative)
Son, what are you talking about? Zillions of 16-bit apps use numbers bigger than 65336 (2^16). "16-bit" does not mean the biggest number you can store is 2^16. By that logic, how could Microsoft accountants ever keep track of their billions when 2^32 is only around 4.2 billion?
As it happens, my 32-bit Linux system's C library understands some numbers into the quintillions (ULLONG_MAX is 18,446,744,073,709,551,615, for example) and the MySQL library can deal with numbers up to 1.79769313486231470e+308. If that wasn't enough, I could code up my own libraries to deal with longer numbers.
Read an intelligent book like "The New Thought Police" or "The War Against Boys", and learn the TRUTH.
You might also want to try one or two on computer science.
Re:Figures (Score:3, Informative)
It's not an old bug, I have an Nforce2-based motherboard and have that zzzzzzzzz always present in my speakers, and it even varies the pitch depending on CPU load.. imagine the annoyance. I can't beleive things like that still shows up in modern systems, but they do, in fact, I'm not really mad since the board didn't cost me 500$. Of course this isn't related to AMD directly but it's still something that, in the real world, would be associated to AMD easily since you don't see that kind of issues with intel-based systems.
On the other end, AMD's dual chipset is really a good platform (getting old but still good) I used it in a production environment, 7 renderfarms were made with those, only one failed in 2 years, and while I didn't have time to check it yet, I'm sure it's something other than the board/CPU.
Re:The last thread on Xeons... (Score:3, Informative)
But rumor has it that Intel's 64-bit performance is no faster than its 32-bit performance, and slower than AMD's 64-bit performance.
Welcome to Trusted Computing. (Score:4, Informative)
Prescott is also Intel's first processor to support a security technology code-named Le Grande. While Intel has not yet detailed the technology, it is believed to provide a protected space in main memory for a secure execution mode required as part of Palladium, a new PC security scheme being developed by Microsoft Corp.
Le Grande is Intel's codename for Trusted Computing. HP's codename is ProtectTools, Cisco's codename appears to be either NetworkAdmissionControl or SelfDefendingNetwork, Phoenix BIOS code name is CoreManagedEnvironment, and of course we all know Microsoft's codename was Palladium and now is NaGSCaB and is slated to appear in Longhorn.
If you scroll down near the bottom of this page [chip-architect.com] you can catch a look at a micrograph of the Prescott from about a year ago. Note that the Trusted Computing core is it's own an entire CPU and memory and support structures, and eats up about 20% of the chip. In other words Trusted Computing core ties up around 25 million transistors of real-estate, or about half of a Pentium 4.
It will support encrypted code (to secure it against you, the owner), it will encrypt RAM access (again, secure against you) and take over a portion of your cache. It will carry a unique key to identify you and your machine, but far more powerful than the old CPU serial numbers. It will forbid you to know your own encryption keys and prohibit you from decrypting your own data. I know it's designed to work with a "secure clock" (wouldn't want you the owner to be able to "tamper" with the time, now would they?), but I'm not sure if the secure clock is inside the CPU or planned to be external.
AMD has their own Trusted Computing project, but I have been having trouble digging out any hard info. It *may* be incorporated into the Opteron processor.
Transmeta has a trusted Computing project too, the TSX system - Transmeta Security eXtensions. I beleive initially appearing in the Caruso5800.
Welcome to tomorrow. Resistance is futile, all your base already belong to us, Slavery is Freedom, and always remember The Computer Is Your Friend.
-
Re:Figures (Score:3, Informative)
I'm using the Asus A7N8X, not the deluxe, and have no sound problems. The on board is better than my old SB16. The white box store that I deal with had serious trouble with the SB live Audigy in the deluxe version of the same Mobo. It was Creatives drivers and never did work right. The on board, through a 2 year old set of Klipch 5.1s sounded better than the Audigy did in any box with the same speakers. I don't really think sound cards are worth it any more.
Re:My Question... (Score:1, Informative)
Adding 64-bit datapaths to a 32-bit processor typically increases its circuit complexity (transistor count) less than 10%. This obviously varies with the processor, and power depends on more than the transistor count, but it certainly isn't going to be twice as much as an equivalent 32-bit processor.
thefreedictionary.com (Score:5, Informative)
Please do not post links to thefreedictionary.com - they are a dodgy site which repackages Wikipedia [wikipedia.org] content, with ads, for profit, whilst stretching the GFDL [wikipedia.org] as far as they possibly can.
Look at that link you posted - you'll see a credit to Wikipedia at the bottom. Now disable javascript in your browser and refresh - ooh, the credit is gone! They insert it in with javascript rather than putting it in the body of the page to ensure that Google doesn't pick it up. Why? Because a link to Wikipedia's article would help lift Wikipedia's pagerank above that of thefreedictionary.com.
Just say no, and if you want to read about PAE, read the original [wikipedia.org] Wikipedia article.
Re:AMD welcomes Intel to the world of AMD64 (Score:3, Informative)
No, I'm sure that internally at least they know only too well that they stuffed up big time. That's got nothing to do with not calling these chips "AMD compatible". They don't want to do that because in the public's eye, that would make AMD chips the real deal, and Intel's ones a copy. If they're the same speed (all most people care about) and about the same price, then people will buy the "genuine" ones, not the Intel "copies".
It's marketing, pure and simple.
Re:A few months late to the party... (Score:2, Informative)
As for the other 64 bit machines; Yes, yes, we know they've been out for ages. They weren't, however, ever remotely targeted for consumers, and therefore largely in a different class ($5k machines and up). (Its just like how there's Sun, SGI, and all of the other flavors, but when Apple started shipping OS X as the standard install, it became the "largest vendor of Unix in the world" overnight.)