Slashdot Mirror

or read an actual overview of the spec

i guess that means it's Hammer Time!

An anonymous reader writes "AMD is expected to announce a new chip to compete with arch-rival Intel. An overview of the new CPU can be seen here, and some more information is available on Anandtech. Go AMD!" I just can't wait to see the prices on them! UPDATE: 08/11 17:00 GMT by T: This might be a re-post, as we have word that AMD working on a K8 processor, which will run at around 2 - 3GHZ.

AMD's ClawHammer is due the second half of this year. The Barton will (probably) be a scaled down 32 bit version of the ClawHammer. You can find the PR rating chart for the TB and Barton here. The Hammer may be released somewhere in the 3400+ range.

AMD's roadmap is here

The AMD Athlon "XP" modifier is designed to convey the extreme performance AMD Athlon XP processors deliver for the upcoming Microsoft Windows XP operating system.

Here is the Press Release from AMD.

Im afraid you're the one who's wrong.

I'll substantiate it with some links to the AMD webpage:

For example, they compare the XP2100 with The P4/2000 and the P4/2200 on their benchmarks page. And the XP2200 to the P4/2200 in their Software Performance Guide

The speed rating is what their marketing dept calls "Quantispeed Architecture": "*QuantiSpeed (TM) architecture operates at the following frequencies for these model numbers: 2200+operates at 1.8GHz,2000+operates at 1.67GHz.".

See also Introducing the AMD AthlonXP processor

Im afraid you're the one who's wrong.

I'll substantiate it with some links to the AMD webpage:

For example, they compare the XP2100 with The P4/2000 and the P4/2200 on their benchmarks page. And the XP2200 to the P4/2200 in their Software Performance Guide

The speed rating is what their marketing dept calls "Quantispeed Architecture": "*QuantiSpeed (TM) architecture operates at the following frequencies for these model numbers: 2200+operates at 1.8GHz,2000+operates at 1.67GHz.".

See also Introducing the AMD AthlonXP processor

Im afraid you're the one who's wrong.

I'll substantiate it with some links to the AMD webpage:

For example, they compare the XP2100 with The P4/2000 and the P4/2200 on their benchmarks page. And the XP2200 to the P4/2200 in their Software Performance Guide

The speed rating is what their marketing dept calls "Quantispeed Architecture": "*QuantiSpeed (TM) architecture operates at the following frequencies for these model numbers: 2200+operates at 1.8GHz,2000+operates at 1.67GHz.".

See also Introducing the AMD AthlonXP processor

Im afraid you're the one who's wrong.

I'll substantiate it with some links to the AMD webpage:

For example, they compare the XP2100 with The P4/2000 and the P4/2200 on their benchmarks page. And the XP2200 to the P4/2200 in their Software Performance Guide

The speed rating is what their marketing dept calls "Quantispeed Architecture": "*QuantiSpeed (TM) architecture operates at the following frequencies for these model numbers: 2200+operates at 1.8GHz,2000+operates at 1.67GHz.".

See also Introducing the AMD AthlonXP processor

We've been here before, when we all went from 16bit to 32bit CPUs, and sooner or later Intel's horse is going to win - it just depends on when Microsoft ships a 64 bit "desktop" version of Windows the consumers actually buy.

IIRC, Microsoft has already committed to x86-64. Intel has also been said to have a skunkworks project to develop an x86-compatible 64-bit processor, though whether this would be compatible with Hammer is unknown.

is "Opteron" (see http://www.amd.com/us-en/Processors/ProductInforma tion/0,,30_118_4699,00.html)

Here's the AMD pricelist for those of you who are interested.

That's a possibility I hadn't considered. I feel like defending myself, though: the advice on bottom-inlet fans comes straight from AMD's Builder's Guide:

With the vertical case, a power supply with ATX-style bottom air intake vents maintains
a better thermal environment than a power supply with only a front air intake vent.

Who is this Advanced Micro Designs company?

All of the Durons I've seen were made by Advanced Micro Devices.

Sorry to cut this post short, but my 1993-vintage post-American Telegraph and Telephone buyout National Cash Register-manufactured laptop is in need of a nap.

• Intel x86 P3 - 29W
  
• Motorola PowerPC G4 MPC7455 (p15) - 30W
  
• AMD Athlon Model 4 - 55.1W
  

"Microsoft spokesman Jim Desler said Kempin's memo was "irrelevant" because the company never acted on his ideas."

Not entirely true, it turns out. See what AMD has to say about this (source at bottom):

" Tailored for Compatibility with Microsoft® Windows® XP

The AMD Athlon(TM) XP processor offers compelling performance for running Microsoft® Windows® XP operating system, as well as outstanding performance on previous versions of Windows. The raw power and robust features of the AMD Athlon XP processor help enable users to make the most of multitasking and user switching capabilities offered in Windows XP. Microsoft optimized the DirectX 8.0 interface for Windows XP specifically for the AMD Athlon XP processor.

AMD processors were used for the design, development, and testing of Windows XP. AMD processors are designed to deliver high levels of performance with this latest version of the Microsoft Windows operating system.

The AMD Athlon XP processor allows you to take full advantage of the power of Windows XP in multiple ways.

• High quality digital media, such as audio, video, and photos from digital devices benefit from the advanced capabilities of AMD processors and the integrated features of Windows XP.
• The AMD/Windows combination provides an enhanced Internet experience with smoother streaming audio and video.
• Communication with family and friends via video, voice, and instant messaging is quick and easy when powered by the next-generation features found in AMD processors.
• AMD processor-based Windows XP workstations running financial. modeling, scientific, engineering, or graphic design applications have the sheer computing power to handle highly demanding applications.
• AMD processors are designed for the multi-threaded and mission-critical applications of cutting-edge Windows XP Professional software applications.

Through this collaboration, AMD can offer you excellent integration and compatibility in your computer's functioning, resulting in outstanding computing performance across a broad spectrum of applications."

Source:
http://athlonxp.amd.com/overview/microsoftWindowsX P.jspa

For the most part, remember, CPU speed isn't the big bottleneck that it used to be

That's true on a big fat GameCube, PortBox, or Athlon PC with 1000 Mflops, but on a 16.78 MHz ARM7TDMI processor, you really need to make every cycle count if you want to keep up with the 59.7 Hz retrace. Most of the tricks that applied on the 486 still apply on the Game Boy Advance.

Well, i've been working at the ACCRC For over a year and a half now. It's a terrific place. Most of our volunteers come from the homeless shelter next to our building. It's amazing how much people can leanr when they're immersed in technology so completely.

A couple of answers to previously proposed questions. The Athlon 850's and motherboards for them were graciously donated by AMD for use in our cluster. They also gave us a good deal of PC100 dimms to help us expand the cluster. 3Com donated all of our switches and ethernet cards.

Microsoft has never contacted us, nor are they likely to. I find it highly unlikely that they would attempt to shut us down because we distribute Linux. SuSe Gave us 30,000 boxed copies of 7.0 in its various incarnations, and this is the OS we distribute. We'd love to get any other distributions we could, but for now, we will use SuSe because we have a buttload of it.

Now, some related links! Webcams In the Ministry of Truth, AKA the media lab at the ACCRC.

Buy Shit from the ACCRC here. Extremely disorganized, just like the warehouse is.

Anyone in the bay area is invited to come by and check us out. We are open from 10-5 weekdays and 12-5 saturdays. We invite anyone to volunteer, no matter what your skill level is. Also, if you would like to send us your equipment for a donation and a tax write-off, send it to our street address, not our post office box.

Thank you ve5ry much for all your enthusiasm. We need volunteers badly! Volunteers get digging rights!!!!

A webcast of today's conference call announcing Opteron is available here

-Mark

I can't believe the USPTO actually let them trademark the letter I when used in relation to computers and such.

By now, the "I" trademark has little if any legal force left. Unlike with copyrights and patents, if you don't enforce a trademark by suing or licensing, you lose exclusive rights in the mark.

ObDuron: On the other hand, a paint manufacturer doesn't generally have the right to prevent a semiconductor maker from using a similar or identical trademark because paint and semiconductors are considered separate domains, even though the first hard drives' platters were essentially coated with paint.

Athlon? ... BTW it's trademarked by AMD...
Thunderbird? ... sound's like a Ford ...
Clawhammer? ... a few pounds ...
Sledgehammer? ... about 22 pounds ...

Now ... CODE NAMES for the CPUs are a different matter ... AMD shows us what the codenames are ... in italics. These are the cores that make up the CPU. So, what's the difference between Thoroughbread and Barton? Cache size for one ... but probably slightly different architecture for performance.

One thing to note ... Clawhammer and Sledgehammer ARE the codenames ... but probably be the product names when they come out.

AMD pricing for Athlons is much higher than Durons. All the Durons are under $100, and all the Athlons are higher. Presumably AMD will drop the price on Athlons when the Durons go away. I can't see them abandoning the low end.

Everyone's favourite? Intel's not inside my computer.

AMD rules!

umm AMD's said it all along right here.

why the hell is everybody so intent on making some sort of BE/Linux hybrid?

Not to "save" the BeOS legacy/religion/apps obiously, but to save the linux kernel with all its drivers/features/fans/developers/sponsors/bouty from becoming a platform used for running nothing but posix webservers on headless pc hardware while it can be better (in design) then OSX for (even old) pc hardware.

This BefrankensteinAtOS is just a step toward what is my dreamworld:

- a cheap Nforce like mainbord with onboard graphics(nvidia, nuff said),audio(dolby 5.1 encoder),network(100mbit is 100mbit) and firewire (usb is now a "legacy connector" ;-))

- A dvb-c card

- two or four Clawhammer cpu`s

- Cooling that makes sense, not noise

- a linux-based kernel that loads directly from eeprom instead of an ugly old bios that doesn`t even understand todays harddrives. but still load ms-dos 3.00

- no more X, just every bit of experiance nvidia has with performace drivers

- A really fast gui, just try going back from Be`s Beos to windows

- a simple gui and cli shell that doesn`t eat more reasorces then it offers functinality but has a noice look and feel

- configurable translators

A filesystem that is fast, doen`t need complex journaling couse the oswrites metadata in a recoverable order and the hardware is fast enough to offer reasonable fast recovery anyway and has optional metadata (like the BeFS mime filetype)

I think this is really close to what others on slashdot want, note the lack of "evil" technology (except for perhaps nvidia).
After reading it back I found it also lacks girls and a social life but then again you can`t have it all ;-)
I guess for now I will have to do with the dano leak....

IC speed is generally a part selection - all the parts are made the same, then tested and sorted by how fast they'll go. The slowest gate on the chip determines the speed limit. That's why testing matters; you may have 20 million gates that work at a high speed, and one that doesn't.

AMD's own CPU price list is interesting. The fastest MP is the 2000+, while the fastest XP is the 2100. Does this indicate a speed penalty for enabling multiprocessor mode? It may.

The faster processors cost far more than the slower ones, and it's unlikely that they really have a severe yield problem that requires this. It's unusual today for a fab to produce large numbers of substandard parts. Today, yields below 80% indicate serious problems in the fab. Some fabs report 99.5% yields. A decade ago, variability in the fab was much higher; a whole range of speeds came out, along with a sizable percentage of rejects. Today, the processes are much more uniform.

(Think about what this means. Sizable wafers are being produced with almost all the atoms where the design says they're supposed to be. That's an achievement. And then these bozos slap conductive paint on the pins and think they've done something cool.)

WITHOUT the ability to reverse engineer ... You wouldn't have two chipmakers competing in the x86 market

I'm all in favor of competition, naturally. I applaud IBM's continuing effort to market the obsolete and discredited PowerPC architecture. That, however, has nothing to do with, for example, AMD's ongoing criminal violation of intellectual property rights. Intel has made a massive investment in research and development. They have advanced the state of the art by decades, and all computer users benefit. It is right that Intel should reap the rewards for their work. It is not right that AMD should traipse in late in the game, with no R&D department of their own, manufacture cheap knockoffs in Taiwan, and make a fortune exploiting somebody else's innovations. This is called "dumping" and it is, under the wise and just laws of our nation, a criminal act.

As for "open source", there again we have poorly-paid (or entirely unpaid!) workers producing cheap imitative knockoffs of innovative products. This serves only to reduce the market value of real software, thereby snatching food from the stomachs of those who create real software. The avowed intent of the "free software" pirates is to reduce the market value of software.

...WINE is wrong, Bleem is wrong, hell, VMware is wrong.

That is correct. All of those are, in effect, criminal conspiracies to damage the economy by reducing or eliminating the natural rewards given by the free market to innovative and effective competitors.

...reverse engineering is legal...

WRONG. Intellectual property law has reached maturity in this country. Those who create valuable ideas are now guaranteed their right to retain full ownership and control of their own property under the terms of the Digital Millennium Copyright Act.

Thanks for playing.

Does the same rule apply to any form of IP? (patents, copyrights, etc.). It would be hypocrisy if it didn't. This would basically destroy the chip making (i.e. AMD, which is fabless), or any other advanced engineering, firm immediately.

(I'm assuming you copied the wrong paragraph and were continuing the "exceptional market" discussion that started your reply.)

AMD has multiple fabs. It's Rambus that was fabless, and I, for one, have no problem with their going under.

You're ignoring the fact that hardware has much more normal supply dynamics than software. Marginal costs per chip are much larger than pressing CDs or net distribution, both in absolute terms and percentagewise. It's these minimal marginal costs that make free software possible. Given that the supply dynamic for software is completely different from hardware and other physical goods, expecting the software market to behave the same as the market for physical goods is really absurd.

Finally, what rule are you referring to that would apply to these goods?

In your own article you commented that Linux, if it was developed with paid labour (instead of sweatshop freebies), would cost $1.9 billion, so stating that there is not a cost ... per copy distributed is greatly simplifying ...

1. Volunteer labor is not sweatshop labor, and comparing the two is nothing but slander to all the people who have worked on free software. You owe an apology to a hell of a lot of people.

2. Huh? The fact that Linux would have required a couple billion in fixed costs means that software has significant marginal costs? Why? Software does have minimal marginal costs compared to the majority of goods; this is fact and can't be denied. Large or small, fixed costs don't affect marginal costs, and have nothing to do with Bruce's point.

(is there a cost if I sneak into a movie theater in a half-full audience? If you see it in a selfish, individual way then no, but if you see it as a whole then of course there is: What if everyone snuck in?)

That's true. However, it doesn't relate in any way to the sentence you're responding to. Bruce is not talking about the cost to society; he never mentioned it. He is referring to the marginal cost, the cost to produce and distribute one item of product. That cost, for software, is near-zero. That is what is why Bruce believes that software markets cannot be treated the same as hardware markets.

If you /really/ want to be like that, then the rest of the world will just ignore you - you can go back to being the isolationist state that you were for many years, and the rest of the world will be happy to avoid you.

Interestingly enough, I believe most of AMD's processors are actually fabbed in Europe - Dresden, in fact.

Take a look at this and do the sums - most of AMD's fab's are outside the US.

The US really isn't the centre of the world, you know . . .

himi

I found it dissapointing that these limits were in the design up front without apparent room for expansion (free bits to be used in the future) This means that when they do decide to expand the addressing range, they will have to redisign the page table layout and force OS writers to change their code to use it. It would have been nicer to have expansion room built in to the page table design and simply have the CPU implementation have limited pinouts.

While I'm griping, I'll also mention that the X86-16 (Virtual real mode) support has been dropped when in 64 bit mode. I know that noone uses it much anymore, but there are still old legacy games that I have that run in DOS mode and it would be nice to be able to support them.

Isn't that:

mov ah, #1
mov ax, #1
mov eax, #1
mov rax, #1

Feel free to read the specs.

The site also has a 64-bit simulator for you favorite 32-bit processor based Linux system.

I was just thinking the same thing I googlized my thought and found this a AMD Whitepaper. Looks like its ah, ax, eax, and rax.

If you compare the intel parts to other alternatives, you're already getting half the processor, and for twice the price as well!

ARM != StrongARM.

This is very similar to how Athlon != IA-32. Don't confuse an architecture with an implementation of that architecture.

Speculation: Intel gets Hammered in the second half of this year.

Note to self: remember quote, and read AMD's whitepapers and documentation when i'm done with my CSE project tonight...

I'm new, i know, i'm learning architecture as a sophomore so this stuff is fun to me...

Speculation: Intel gets Hammered in the second half of this year.

Note to self: remember quote, and read AMD's whitepapers and documentation when i'm done with my CSE project tonight...

I'm new, i know, i'm learning architecture as a sophomore so this stuff is fun to me...

Watch out for the power supply. The only 250 watt psu AMD recommends is aopen's FSP250-60GTA. All the others power supplies are 300 watts, or more. I think you're asking for trouble going for a bottom of the line psu on an Athlon, especially one as fast as the 1.4.

AMD

All right, I'll concede on the gate count issue. I'd be interested to see how many are dedicated to cache as opposed to processor logic.

Athlon, for instance, is already copper and is moving to SOI by 2004. I think Intel is already SOI, but is slower moving to copper. I guess what I'm saying is that neither of those two factors are likely to be an issue going forward.

The G5 is an upcoming 32-bit embedded chip made by Motorola (like the G4 and G4+), and does not resemble the (64-bit) Power4's internal architecture in the slightest. Whether this chip will be the basis of the next generation of Macs is of course not yet known.

According to the Motorola PowerPC roadmap, the G5 will be available in both 32 and 64 bit versions. How much it resembles Power4 isn't clear, but it's supposed to debut at up to 2 GHz. Are you still so confident it won't have world-class performance?

Because Apple does not have the integrity (nor, according to the oft-repeated excuse, the FORTRAN compiler) to submit SPEC runs for a G4-based computer, there are no official SPEC scores for the G4. However, we do have Motorola's *estimated* *SPEC95* scores for the 7450 (a.k.a. G4+) at 733MHz. (Here [motorola.com], second page, on the left.)

For what it's worth, I agree that Apple should do SPEC benchmarking itself. Especially now that MacOS is Unix.

On the compiler front, I did find a seemingly decent FORTRAN compiler for MacOS X, so that issue is addressed at least. ;-) (Absoft is a respected compiler company.)

I must say I'm surprised at how low that 'estimated SPECfp95 score' is. I'd really like to see more information on G4 fp capabilities. The Absoft compiler claims to have auto-vectorizing capabilities using Altivec, which might have considerable impact on some of the benchmarks. (The new dual-processor 1 GHz G4 is claimed to have 15+ GFlops of computing power, using Altivec I presume.) I guess my next step should be to actually purchase a Mac and get busy benchmarking. ;-)

As to your estimated SPEC scores, I appreciate the effort but I doubt those are worth much.

Power4 is simply not a desktop chip design. Even using one of the 4 dies in the MCM as the basis for a desktop CPU is a shakey proposition, since they're too big (again, 400mm^2 on .18um), and include a bunch of integrated I/O stuff and the L3 TLBs, all stuff which would be worthless in a desktop machine. The actual datapaths are quite simple, and indeed are optimized to work in an 8-way MCM, not as the sole CPU of a desktop machine.

The integrated I/O might or might not be worthwhile, but Apple's current pro machines use L3 cache. What would really be of interest on the desktop, of course, is the execution efficiency that manages to retire so many instructions per clock. If that single Power4 CPU was really "optimized to work in an 8-way MCM", it truly did a stellar job as a uni-processor.

Rumor also has it, BTW, that the G5 will include an on-chip memory controller allowing memory bandwidth to scale in SMP systems, similar to the scheme used in Hammer. I wonder when Apple will release SMP boxes with more than two CPUs...

At any rate, thanks for a more interesting discussion than usual. :-)

299,792,458 m/s...not just a good idea, its the law!

This seems to be a completely different bug than the previous article. That bug was about the virtual memory translation table. It's in the AMD processor revision guide as errata #16. It's a processor bug. That bug seems fixable with the mem=nopentium flag. The bug mentioned in the latest article (Tracking Down, etc...) is about cache coherency semantics, which is a completely different beast.

Actually Appaloosa is the next core in the Duron line of CPU's from AMD. The next Athlon core, due in the 1st half of this year (so by the end of June) is Thoroughbred, which will be a 0.13 micron process, basically a die shrink from 0.18 micron for the current crop of Athlon's. This will allow AMD to again ramp up clock speeds because of the reduction in heat/power consumption. Appaloosa is also a 0.13 micron process btw.

The roadmap further indicates that in the second half of this year, another incarnation of Athlon will appear using a 0.13 micron Silicon-On-Insulator (SOI) process.

AMD Processor Roadmap

-Sokie

Apparently, if you'd believe the Linux community, you'd be hard-pressed upon where to place the blame. You see, the Linuxist Manifesto's number one rule is to lie to protect the best interests of Linux. No self-respectable Linux zealot would insult or place blame upon AMD, because AMD's philosophy centers around tackling American Corporations with their Asian sweatshops, selling their chips at bargain-basement prices like the Red Menace Commies do with their Wal-Mart shit.

So, right about now, you're probably thinking that the zealots are clearly in a dilemma. Who are they going to blame? If you have a prediction before I tell you, the poll is on the right. Or maybe the left. Either way, take your pick.

You'd think that the parasitic community would place blame upon Microsoft, right? Alas, Microsoft has had the bug patched since September 2000. Not only that, Windows XP , the latest in the suite of high-powered, stable operating systems from Microsoft Corp., has this patch built in. That's right, built in. Keep in mind that Windows XP was released in October 2001, over three months ago. Meanwhile, no one knows what the hell Alan Cocks has been doing since then, since he hides under the cloak of secrecy. nVidia has been informing users via tech support, even to the Linux community, how to fix the problem for months now. Clearly the blame is upon Alan Cocks's shoulder, but to place the blame where it is rightfully justified is inexcusable in the Linux community. The drones are in disarray.

The actual bug occurs when Linux users contract the Tux Racer virus via KEmail. When first run, Tux Racer enables a feature in your third-world sweatshop AMD processor called "extended paging." Now, I know you're probably thinking that this sounds like some sort of Nokia feature. Well, you're wrong. It's yet another feature that AMD illegally hacked from Intel. It allows your browser to seamlessly view pages up to 4Mb in size. Before its introduction in the early days of the Intel Pentium processor, web pages were broken up into 4K segments, because any pages larger would freeze the computer. That's why Microsoft didn't invent Javascript until after the Pentium, every time they went to use it, their pages exceeded 4K, and henceforth froze the computer. Intel came to the rescue with the Pentium line of chips, and, as usual, AMD got out their super high tech Asian hacking tools and "reverse-engineered" (code-name for 'illegally hacked') Intel's technology. Thus, users of the inferior AMD Cyrix Kx86-2 Now! processor could also view large web pages without crashing. So why did no one notice that pages larger than 4K would crash AMD processors? Well, Microsoft has had a fix for 16 months, like we mentioned earlier. But why did no one from the Linux community notice? Well, apparently, there does not exist a page devoted to Linux that is more than 4K in size. Since most of the Linux installations out there denounce color as 'feature bloat,' all Linux pages follow an unwritten oath to suck. Believe me, they all do.

So, for the good of Linux, you may now disperse. Head off to various tech sites and continue blaming Microsoft for not telling you sooner. Your community will thank you.

Apparently, if you'd believe the Linux community, you'd be hard-pressed upon where to place the blame. You see, the Linuxist Manifesto's number one rule is to lie to protect the best interests of Linux. No self-respectable Linux zealot would insult or place blame upon AMD, because AMD's philosophy centers around tackling American Corporations with their Asian sweatshops, selling their chips at bargain-basement prices like the Red Menace Commies do with their Wal-Mart shit.

So, right about now, you're probably thinking that the zealots are clearly in a dilemma. Who are they going to blame? If you have a prediction before I tell you, the poll is on the right. Or maybe the left. Either way, take your pick.

You'd think that the parasitic community would place blame upon Microsoft, right? Alas, Microsoft has had the bug patched since September 2000. Not only that, Windows XP , the latest in the suite of high-powered, stable operating systems from Microsoft Corp., has this patch built in. That's right, built in. Keep in mind that Windows XP was released in October 2001, over three months ago. Meanwhile, no one knows what the hell Alan Cocks has been doing since then, since he hides under the cloak of secrecy. nVidia has been informing users via tech support, even to the Linux community, how to fix the problem for months now. Clearly the blame is upon Alan Cocks's shoulder, but to place the blame where it is rightfully justified is inexcusable in the Linux community. The drones are in disarray.

The actual bug occurs when Linux users contract the Tux Racer virus via KEmail. When first run, Tux Racer enables a feature in your third-world sweatshop AMD processor called "extended paging." Now, I know you're probably thinking that this sounds like some sort of Nokia feature. Well, you're wrong. It's yet another feature that AMD illegally hacked from Intel. It allows your browser to seamlessly view pages up to 4Mb in size. Before its introduction in the early days of the Intel Pentium processor, web pages were broken up into 4K segments, because any pages larger would freeze the computer. That's why Microsoft didn't invent Javascript until after the Pentium, every time they went to use it, their pages exceeded 4K, and henceforth froze the computer. Intel came to the rescue with the Pentium line of chips, and, as usual, AMD got out their super high tech Asian hacking tools and "reverse-engineered" (code-name for 'illegally hacked') Intel's technology. Thus, users of the inferior AMD Cyrix Kx86-2 Now! processor could also view large web pages without crashing. So why did no one notice that pages larger than 4K would crash AMD processors? Well, Microsoft has had a fix for 16 months, like we mentioned earlier. But why did no one from the Linux community notice? Well, apparently, there does not exist a page devoted to Linux that is more than 4K in size. Since most of the Linux installations out there denounce color as 'feature bloat,' all Linux pages follow an unwritten oath to suck. Believe me, they all do.

So, for the good of Linux, you may now disperse. Head off to various tech sites and continue blaming Microsoft for not telling you sooner. Your community will thank you.

Using the model number as comparison to older Athlons doesn't make sense, anyway. An AthlonXP 1600+ running at 1.4GHz doesn't perform like a TBird running at 1.6GHz, it performs like a TBird running at 1.4GHz.

If you mean the Athlon Classic, rather than the TBird, there has never been an Athlon Classic that ran at 1.6GHz and it doesn't make sense to compare your product to one that doesn't exist.

Alan Cox and other kernel hackers do read these documents. The question is if AMD documented this bug in their errata, or just fixed for Windows 2000 and figured that was good enough.

Bug #16 in AMD's Errata list for the AMD Athlon Model 6 processor (ie the AthlonXP/MP) lists the following:

(Begin quoting)

16 INVLPG Instruction Does Not Flush Entire Four-Megabyte Page Properly with Certain Linear Addresses

Products Affected. A0, A2

Normal Specified Operation. After executing an INVLPG instruction the TLB should not contain any translations for any part of the page frame associated with the designated logical address.

Non-conformance. When the logical address designated by the INVLPG instruction is mapped by a 4-MB page mapping and LA[21] is equal to one it is possible that the TLB will still retain translations after the instruction has finished executing.

Potential Effect on System. The residual data in the TLB can result in unexpected data access to stale or invalid pages of memory.

Suggested Workaround. When using the INVLPG instruction in association with a page that is mapped via a 4-MB page translation, always clear bit 21.

(end quoting)

It's there. It's been listed there for quite some time. No one read the errata and/or no one bothered to check to see if this one affected Linux systems. I hate to break it to the Linux boys, but they kinda missed the boat on this one. Normally Linux kernal hackers seem pretty good at staying on top of processor bugs, but it looks like this one slipped through the cracks.

FWIW, anyone looking for this errata list can find it here. As a bit of an aside, none of AMD's PDF documents will load for me in Mozilla/Netscape 6 with Acrobat 5, but they all work fine with IE/Acrobat 5. Wierd.

Are you sure? The list of AMD identifications is in the AMD Processor recognition application note. See pages 20-21 of the PDF.

Apparently, if you'd believe the Linux community, you'd be hard-pressed upon where to place the blame. You see, the Linuxist Manifesto's number one rule is to lie to protect the best interests of Linux. No self-respectable Linux zealot would insult or place blame upon AMD, because AMD's philosophy centers around tackling American Corporations with their Asian sweatshops, selling their chips at bargain-basement prices like the Red Menace Commies do with their Wal-Mart shit.

So, right about now, you're probably thinking that the zealots are clearly in a dilemma. Who are they going to blame? If you have a prediction before I tell you, the poll is on the right. Or maybe the left. Either way, take your pick.

You'd think that the parasitic community would place blame upon Microsoft, right? Alas, Microsoft has had the bug patched since September 2000. Not only that, Windows XP , the latest in the suite of high-powered, stable operating systems from Microsoft Corp., has this patch built in. That's right, built in. Keep in mind that Windows XP was released in October 2001, over three months ago. Meanwhile, no one knows what the hell Alan Cocks has been doing since then, since he hides under the cloak of secrecy. nVidia has been informing users via tech support, even to the Linux community, how to fix the problem for months now. Clearly the blame is upon Alan Cocks's shoulder, but to place the blame where it is rightfully justified is inexcusable in the Linux community. The drones are in disarray.

The actual bug occurs when Linux users contract the Tux Racer virus via KEmail. When first run, Tux Racer enables a feature in your third-world sweatshop AMD processor called "extended paging." Now, I know you're probably thinking that this sounds like some sort of Nokia feature. Well, you're wrong. It's yet another feature that AMD illegally hacked from Intel. It allows your browser to seamlessly view pages up to 4Mb in size. Before its introduction in the early days of the Intel Pentium processor, web pages were broken up into 4K segments, because any pages larger would freeze the computer. That's why Microsoft didn't invent Javascript until after the Pentium, every time they went to use it, their pages exceeded 4K, and henceforth froze the computer. Intel came to the rescue with the Pentium line of chips, and, as usual, AMD got out their super high tech Asian hacking tools and "reverse-engineered" (code-name for 'illegally hacked') Intel's technology. Thus, users of the inferior AMD Cyrix Kx86-2 Now! processor could also view large web pages without crashing. So why did no one notice that pages larger than 4K would crash AMD processors? Well, Microsoft has had a fix for 16 months, like we mentioned earlier. But why did no one from the Linux community notice? Well, apparently, there does not exist a page devoted to Linux that is more than 4K in size. Since most of the Linux installations out there denounce color as 'feature bloat,' all Linux pages follow an unwritten oath to suck. Believe me, they all do.

So, for the good of Linux, you may now disperse. Head off to various tech sites and continue blaming Microsoft for not telling you sooner. Your community will thank you.