AMD Back in the Black

Profitable by 0mni · 2004-02-16 00:39 · Score: 5, Insightful

I guess its easy to understand that AMD would be running in the red, its prices are really quite low. Even with small production prices I couldnt imagine there would be too much profit for them.

Re:Profitable by Anonymous Coward · 2004-02-16 00:42 · Score: 5, Insightful

They haven't been that low for the last couple of years. I remember a time when every AMD CPU cost about half of what you paid for a comparable Intel.
Heavy investing and comparably small market share would have more to do with the losses.
Re:Profitable by betelgeuse-4 · 2004-02-16 00:50 · Score: 5, Informative

When I went to nanotech lab open day, one of the speakers said that 98%-99% of the chips on each wafer must work for the CPU company to make a profit.

--
Decode these
Re:Profitable by Anonymous Coward · 2004-02-16 01:14 · Score: 0

they're back in the black because of Me .. i've
had to buy three motherboards and four AMD procs
in the last six months because the crappy things
keep blowing up .. i finally switched over to an
intel rig this morning .. screw AMD .. i was loyal
to them for awhile but i really need something
stable that doesn't cut my hands open trying to get
the heat sinks on and off :p ( and no, i wasn't
overclocking any of it )
Re:Profitable by iezhy · 2004-02-16 01:20 · Score: 1, Informative

IMHO, these figures are a bit bloated According to this article in Toms hardware, prodution yield is about 30%, it it expected to rise up to 60% after two years of production CPU's are just too complicated to be produced with yield of 98%-99%. Maybe this spokesman was speaking about some other, simplier in design, chips?
Re:Profitable by Anonymous Coward · 2004-02-16 01:33 · Score: 0

You were probably using a shit power supply or something, especially considering what a high failure rate you had. CPU failures aren't always the fault of the CPU, you know.
Re:Profitable by Anonymous Coward · 2004-02-16 01:51 · Score: 0

You managed to blow up three motherboards and four CPUs and you never once stopped to think that maybe you were doing something wrong? Fuck, I still have a seven year old AMD K6-233 going strong and it's been moved between cases seven or eight times and the original heatsink removed & refitted I don't know how many times.
Re:Profitable by Anonymous Coward · 2004-02-16 02:02 · Score: 4, Informative

It depends on the chip and the market. Production yields for ARM CPUs would often be at 95%, a level undreamable by x86 chips.
Re:Profitable by DebianRcksLindowsLie · 2004-02-16 02:22 · Score: 2, Interesting

I'm guessing that you might have seen information on RAM rather than processors, but the numbers seem artificially inflated.

It's known that RAM that won't work at one level will work for another, all the way down to RAM used for storing voicemail in answering machines, which has failed at several levels above. Example - chips are supposed to work as 128M chips, fail the test, so they try them as 64M. If this fails, they go to 32, etc. /. had a story on this last year.

--
Sick of people trashing Debian? Me too! Check my sig. Want more info? Check my homepage.

--
Lindows Steals Copyrighted Art and Promotes Porn
Re:Profitable by Anonymous Coward · 2004-02-16 02:29 · Score: 0

Tom pulls his numbers out of his butt.
Re:Profitable by geordie_loz · 2004-02-16 03:01 · Score: 1

my understanding was it said OF CHIPS PRODUCED, not of wafer used.. so 99% is pretty possible, given the mental procedures and clean rooms in chip production. I visited a Fujitsu one, the slightest vibration would wreck a plate, so counter measures are used all over the place so that all vibrations are absorbed, at such microscopic levels its all or nothing.
Re:Profitable by dpilot · 2004-02-16 03:07 · Score: 2, Interesting

Intel's model for profitabilty is simple. They make their profit on Xeons, where until recently they have had no competition.

A friend once told me that the Celeron is priced, "one penny above variable cost," or essentially the lowest they could get away with without getting in dumping/antitrust problems. Note that a Celeron can only pay for its wafers and processing, not its own manufacturing line. Intel has managed to keep AMD pretty much in that market, except that AMD has to buy the manufacturing line at those prices, too.

In that respect, Intel is a lot like Microsoft. Microsoft makes so much money on Windows and Office that they can afford to lose it everywhere else. Intel makes that kind of money on Xeon, and gets the lion's share of its profit there.

People have criticized AMD for not going after IA-64 harder with Opteron/Athlon-64, or not flooding it into the mainstream market. But the IA-64 market is a hard nut to crack, and for a newcomer there's no money to be made there. AMD can't take on the mainstream market without at least a dozen fabs to handle the volume - which would just plummet prices through total Intel/AMD CPU overcapacity. Take a look at what they're doing - they're going after Xeon - and trying to get a piece of the profit in a market that's consistent with their fab capacity.

--
The living have better things to do than to continue hating the dead.
Re:Profitable by 4of12 · 2004-02-16 03:12 · Score: 2, Interesting

Probably both figures are right, just ripped out of context.

IIRC, there are 20-30 steps involved in the overall process.

Each individual step in the process absolutely must have 98-99% yield.

Meanwhile, the overall process has a yield more like (0.98)^20 = 0.66

Or something like that./p

--
"Provided by the management for your protection."
Re:Profitable by Loki_1929 · 2004-02-16 04:18 · Score: 5, Insightful

"According to this article in Toms hardware,"

I can't believe anyone still reads that rag. Let me give you a hint: Tom's was bought and sold about 3 years ago. Since that time, it has descended to the ranks of online propaganda host for Intel and a number of other companies. Tricks with driver versions and other such foolery causes them to get benchmark results drastically different from those of almost every other hardware site. No one's bias is more apparent than Tom's himself. Many of the conclusions to their own articles are non-sequitur, and the articles themselves are often little more than a press release for the company doing the most advertising at the time.

The few folks left defending Tom's tend to either be Intelbots or those who like to feel they know something after having read a few dumbed-down for-public-consumption articles from the site. To quote them is to invite laughted upon yourself. You would do well to visit other sites instead for your hardware news. Anandtech, Ace's Hardware, and plenty of other sites provide good, in-depth and trustworthy analysis, as opposed to operating a propaganda machine designed to rake in cash.

"prodution yield is about 30%, it it expected to rise up to 60% after two years of production CPU's are just too complicated to be produced with yield of 98%-99%."

But I say that production yield is about 80%, and is expected to rise up to about 95% after three months. And best of all, I can make up numbers and formulas to make it look very official and correct. When I see Tom in a 'bunny suit' on AMD's FAB floor, I'll believe their 'analysis' of production yields. Until then, he's making up numbers and statstics, adding to the other 73.4% of statistics that are already made up.

The quote from the article, which you have parroted here, is as follows: "However, we doubt that AMD's yield will be any more than 30% - this is based on information from other chip manufacturers that use similar processes."

Now, let's put a little bit of brain power into dissecting this, shall we? First of all, the whole thing is rather vague - using words and phrases like 'we doubt' and 'similar processes'. Secondly, these so-called 'other chip manufacturers' aren't even named. Are they talking about IBM? Or are they talking about 'Phil's CPU FAB', which is run out of a basement in a townhouse in Idaho? Just what are 'similar processes'? Is there someone else making Opteron and Athlon64 CPUs? Someone really ought to tell AMD about that. Or perhaps they're referring to the 130nm 'process', which describes almost nothing about the chips themselves? Maybe they're even talking about the 'process' of getting from wafer to die. Well, so far as I, or anyone I've ever talked to knows, AMD didn't go out and re-write the book on die construction with the K8. The 'process' of getting from wafer to die for K8 isn't that much different from that of K7. I would assume then that Tom's is also asserting that Barton and Thoroughbred yields are also a mere 30%. Or perhaps there's an entirely new made-up number for their yields.

It's amazing how you can throw a few numbers onto a website and everyone will believe you. It's almost as amazing that throwing a few numbers into a post will yield +4 Informative.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
Re:Profitable by Anonymous Coward · 2004-02-16 05:01 · Score: 0

i agree, i noticed that toms does too many sponsor supported reviews. it has fallen to the depthes of a corporate talk box. screw them.
Re:Profitable by slipgun · 2004-02-16 05:15 · Score: 1

can't take advantage of more than 4 megabytes of memory at a time.

Wow, looks as though 508 meg of my computer's memory is going to waste!

--
SpamNet - a spam blocker that really works
Re:Profitable by Hoser+McMoose · 2004-02-16 05:23 · Score: 2, Interesting

Intel's model for profitabilty is simple. They make their profit on Xeons, where until recently they have had no competition.

Xeon may be one of Intel's big cash-cows, but it's not their only one. The Pentium-M processor (part of the "Centrino" marketing package) is another good source of revenue, as are the high-end P4 chips. Intel sells a LOT of processors (10M+ every month), and a lot of their higher-end chips make over $100 in profit. That adds up REAL fast.

A friend once told me that the Celeron is priced, "one penny above variable cost,"
The Celeron doesn't make nearly the profit of the P4 and Xeons, but it does still make money. Variable cost for most processors is down in the $25-$50 range for commodity type chips. The bottom-end Celerons sell for not much more than that, but the top-end ones sell for over $100 (though they are definitely NOT worth that much, current Celerons are dog-slow, but that's another story).

In that respect, Intel is a lot like Microsoft. Microsoft makes so much money on Windows and Office that they can afford to lose it everywhere else

That much is definitely true, just have a look at Intel's balance sheet some time. The ONLY sector of the company that makes money is their PC processor division. They make roughly 75% of the companies revenue and about 150% of the profits.

But the IA-64 market is a hard nut to crack, and for a newcomer there's no money to be made there

Yeah, just ask Intel, they still haven't managed to crack that nut! The Itanium line is not making any money and hasn't really cracked into the high-end server market in a big way (Sun and IBM still own it). I haven't seen the numbers for Q4, but in Q3 of last year Intel managed to sell a grand total of 5000 Itanium servers. For comparison, AMD sold 10,000 Opteron servers while the Xeon found it's way into around a 1,000,000 servers (source here).
Re:Profitable by Anonymous Coward · 2004-02-16 06:14 · Score: 0

for example: they use some test that are fine-tuned for P4, like the MPEG4 encoding tests. Here we enter on a optimization of the used codec itself. It is known that DivX is optimized for P4 (divx folks say that), while XviD runs better on Athlon XP - I know it because of tons of user reports and because I tested it by myself (ok, it's not a deep test but I think it is enough for me): I have an Athlon XP 2100 (1743 MHz I think) and a P4 2,4 GHz. Both run on similar hardware, with DDR333 memory, similar MoBos and so (I know that this is not a good comparison because of differences on hardware and so, but it could be a bit indicative of what I am speaking about). Same original video files, same codec configuration, same avisynth scripts, same version of WinXP. That's the closest I can be on both computers. Numbers:
Test videos: 3'20" LOTR TTT extended (Helm's deep battle), 5'47" LOTR TTT extended (Ithilien stuff), from original DVD, encoded at 965 kbps 1 pass CBR (hey, after all that was a speed test, not a quality measurement - and XviD latest first pass has changed significantly) to MPEG4 at 512x208.
P4: DivX avg FPS: 52
XP: DivX avg FPS: 36
P4: XviD avg FPS: 16
XP: XviD avg FPS: 17
(XviD: B-Frames, QPEL, VHQ 4, no GMC on both AMD and INTEL).
Notice the HUGE boost on XviD on AMD. 1 fps more than Intel, but the AMD processor should be inferior overall.
Have in mind that the AMD CPU was about 90euro and the Intel one ~150euro when I bought'em. And there's 700 MHz in the middle of them (I know, I know, MHz are no good indicative of processor power, but it is still an indicative of something). So Mr Thomas Pabst tests are biased? IMHO yes, they're.

ps: I am not a hardware hacker, so plz don't expect the above to be the universal truth nor a professional thing. it is nothing but a comparison I did just to see what of both computers were faster for that task. Right now, I use the XP2100 machine for this task, when using XviD (almost all the time)
Re:Profitable by Anonymous Coward · 2004-02-16 07:30 · Score: 0

They make their profit on Xeons, where until recently they have had no competition.

This is silly. Xeon has been stealing business from RISC systems for years and years.
Re:Profitable by Veridium · 2004-02-16 08:45 · Score: 1

"I can't believe anyone still reads that rag. Let me give you a hint: Tom's was bought and sold about 3 years ago. Since that time, it has descended to the ranks of online propaganda host for Intel and a number of other companies. Tricks with driver versions and other such foolery causes them to get benchmark results drastically different from those of almost every other hardware site."

Case in point. When they compared the Athlon FX to the Pentium4 EE, the initial benchmarks they posted were the Athlon FX not overclocked, and the Penium4 EE overclocked. They did not mention this either in the article, until people on the forums started making a stink.

I still go there for the forums, as there are a few people there who have good insight. You do have to sort through an endless parade of Intel fanboys though(and a good dose of AMD fanboys as well). But the handful of objective people there make it worth it.

--
Think for yourself, destroy your television.
Re:Profitable by Loki_1929 · 2004-02-16 08:50 · Score: 3, Informative

"I still go there for the forums, as there are a few people there who have good insight."

I think you'd enjoy the forums at Ace's a lot more. The folks tend to be more intelligent, less 'fanboyish', and come out with insights you won't find anywhere else.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
Re:Profitable by Veridium · 2004-02-16 09:07 · Score: 1

Thanks! I'm looking around now...

--
Think for yourself, destroy your television.
Re:Profitable by Witsu · 2004-02-16 10:24 · Score: 0, Flamebait

AMD chips, especially the 64FX and Opterons are no longer much cheaper than Intel. I for one, purchased an AMD chip because it was cheaper than Intel. Given the choice, especially for the same price, consumers are likely to pick the brand that they know, being Intel, over AMD. I think it was a big mistake for AMD to raise prices. They think they are charging for 64 bitness, but most consumers are not using it, and even when Win64 comes out, they still won't buy more than 4 gigs of ram, so 64 bits really means nothing.
At least Intel's hyperthreading is actually useful to more people. More consumers multitask than use more than 4 gigs of ram
Re:Profitable by ElliotLee · 2004-02-16 17:34 · Score: 1

Tricks with driver versions and other such foolery
Ah, so THAT's where "tomfoolery" came from: Tom's hardware.
Re:Profitable by Anonymous Coward · 2004-02-16 19:32 · Score: 0

> The quote from the article, which you have
> parroted here, is as follows: "However, we
> doubt that AMD's yield will be any more than
> 30% - this is based on information from
> other chip manufacturers that use similar
> processes."

Another chip manufacturer who doesn't want to be named suggesting that AMD might have bad yeilds? Perhaps a chip manufacturer who got caught with their pants down by AMD? Perhaps one with a close relationship with the review site in question?

Intel, 32x64? by arivanov · 2004-02-16 00:40 · Score: 4, Informative

As far as I recall, Intel has not released anything yet. They put something on the roadmap, but they are still 100% behind Itanic. They released an improved 32bit emulation environment for the latter though

--
Baker's Law: Misery no longer loves company. Nowadays it insists on it
http://www.sigsegv.cx/

Re:Intel, 32x64? by sbennett · 2004-02-16 00:54 · Score: 5, Informative

See this. Of course, there were the standard rumours going around before Prescott's launch that it was going to have a 64-bit layer, but that didn't happen.

What I find interesting is that Intel said before Opteron's launch that they weren't going to make any form of 64-bit x86 processor, and now it's on the roadmap.

Earlier this week, Intel's President and COO, Paul Otellini, confirmed in a web-cast interview that a move into the 64-bit desktop market was certain, but that the company would nevertheless wait for the arrival of operating system and application support. "You can be fairly confident that when there is software from an application and operating system standpoint, we'll be there," he said.

You mean once the OS and application developers have started using AMD's 64-bit extensions, Intel will come up with something to compete?
Re:Intel, 32x64? by Anonymous Coward · 2004-02-16 01:01 · Score: 0

Intel will produce both Itanium and x86-64 in the future. They can afford to continue to invest in Itanium for many years.
Re:Intel, 32x64? by Anonymous Coward · 2004-02-16 01:16 · Score: 0

Intel has never said they will never make x86-64 CPUs. It has only been a question of when. They ofcourse try to talk down Opteron, but in their internal strategy x86-64 have been there for some years back.
Re:Intel, 32x64? by Anonymous Coward · 2004-02-16 01:28 · Score: 0

You mean once the OS and application developers have started using AMD's 64-bit extensions, Intel will come up with something to compete?
Why can't Intel just stick the Itanic's 64-bit instruction set onto a P4 like how AMD has stuck x86-64 onto the Athlon?
Re:Intel, 32x64? by mog007 · 2004-02-16 02:29 · Score: 1

The reason that Intel has decided to change their minds is simple. AMD is selling a shitload more Opterons and AMD64's than Intel is selling Itaniums. Intel is just afraid that they won't be the big bad wolf anymore. It's about time AMD upstaged Intel in the corporate sector.

--
Learn something new.
Re:Intel, 32x64? by Loki_1929 · 2004-02-16 04:34 · Score: 4, Insightful

"Of course, there were the standard rumours going around before Prescott's launch that it was going to have a 64-bit layer, but that didn't happen. "

It's entirely possible that 64-bit extensions are within Prescott, but disabled. Intel did this with the P4's SMT for quite a while. Xeons had SMT, and it was enabled, while desktop P4s had SMT, and it was disabled. The 64-bit instructions might not yet be finished, to be finalized and debugged in a later stepping of Prescott, or they simply remain dormant, used only as a preliminary testing grounds for Intel, while they're waiting for viable engineering samples of Tejas. To my knowledge, no one has completely accounted for all the new transistors inside the Prescott chips. The speculative execution enhancements, larger cache, longer pipeline, etc all provide for some of the extra transistors, but certainly not all. There's something about these chips that Intel's not telling us, and 64-bit extensions is as good a guess as anything else.

"You mean once the OS and application developers have started using AMD's 64-bit extensions, Intel will come up with something to compete?"

No, he means that when x86-64bit support is there in software, Intel will have a CPU at the ready to support it. Since AMD's 64-bit extensions are the only game in town, and Microsoft has told Intel to go stuff a second set of x86-64bit extensions, Intel will be forced to either emulate AMD64 (a thoroughly bad idea), or include the instructions as the core of any 64-bit x86 CPU they release. Intel has already licensed the AMD64 technology, and thus will be forced to use its 'little brother's' technology to stay ahead of the curve. The interesting thing about that is that AMD can then choose the direction for future instruction sets. So long as the industry is working off AMD's instruction set, AMD calls all the shots.

Intel's big mistake was continuing to behave like a monopoly, and ignoring the breakout CPUs of its chief rival. Intel was banking on a 64-bit nosedive on x86, choosing to all but ignore the concept until it was too late. Intel knew that x86-64 would force Itanium into a small niche at the upper end, and would send 10+ years of R&D down the drain. Now, even HP is getting over its sunken Itanic - choosing to sell Opteron machines in order to remain conpetitive.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
Re:Intel, 32x64? by Hoser+McMoose · 2004-02-16 05:41 · Score: 2, Interesting

Why can't Intel just stick the Itanic's 64-bit instruction set onto a P4 like how AMD has stuck x86-64 onto the Athlon?

The AMD64 (aka x86-64) instruction set is a natural continuation of the the old IA32 (aka 32-bit x86) instruction set. Pretty much the entire chip can be used for both, it's just a few tweaks here and there. The Itanium's instruction set (IA64, no connection to IA32 other than both came from Intel) is a TOTALLY different beast. It's not even remotely like x86 and would require a completely separate processor core. Now, that's not to say that Intel couldn't put two separate processor cores on the same chip, but then you get into the matter of cost.

Time to through a few numbers out here... The Opteron has a die size of 193mm^2 at a 130nm manufacturing process. This is considered VERY large, especially since the "Northwood" P4 was only 131mm^2 on a similar process. The Itanium2 has a die size that is 374mm^2, ie it's HUGE! If you were to combine a P4 and an Itanium on the same die, it would be well over 400mm^2. The cost for Intel to make such a chip would be VERY high, significantly more than 3 times the cost of making their P4 processors (a larger chip always results in lower yields in addition to taking up more die space). This would eat into their profits by an enormous amount.

Maybe if nothing changes in die sizes by the time Intel starts shipping chips made on a 65nm manufacturing process (late 2005/early 2006) it might be economically feasible. Of course, things have already changed, the new "Prescott" P4 built on a 90nm fab process uses a LOT more transistors (both logic and cache) than the "Northwood".
Re:Intel, 32x64? by Anonymous Coward · 2004-02-16 07:32 · Score: 0

The problem with big die sizes are two:

1) Yeald. The likeleyhood that something goes wrong on a large are is much bigger than on a small.

2) Waste. The smaller the chip size the more efficiently they can use the circular waffers (more percentage can be used).
Re:Intel, 32x64? by Jason+Hood · 2004-02-16 08:10 · Score: 1

but they are still 100% behind Itanic.

Actually their not. The IA64 has been a failure and the chip will not be supported once their new line of 64 bit processors come out.

The IA64 was too expensive, and did not perform as well as marketed. Most companies can go with Xeons/Opterons for a fraction of the price and a wider range of OSs.

--
Are you intolerant of intolerant people?

Does AMD have anything to compete with Centrino by MountainMan101 · 2004-02-16 00:43 · Score: 5, Interesting

They're chasing big boys market at the moment with 64-bit, but do they have something for the laptop market to match Centrino.

Re:Does AMD have anything to compete with Centrino by peragrin · 2004-02-16 00:51 · Score: 1

AMD doesn't Sun's sparc's line doesn't comes close to be good for laptops, the only mystery processor for 64 bit for laptops would seem to be the G5 hopefully with the new manufactoring process, the G5 laptop will be out soon.
Oh did you mean low power? sorry for the rant.

--
i thought once I was found, but it was only a dream.
Re:Does AMD have anything to compete with Centrino by phusnikn · 2004-02-16 00:57 · Score: 4, Informative

Humm I have an Athlon 64 mobility in my emachine and it rocks... I get about 3 hours of juice 2 1/2 w/wifi and this thing flys.

--
- I came I saw I Conquered
Re:Does AMD have anything to compete with Centrino by expro · 2004-02-16 01:01 · Score: 2, Interesting

Is it supported by Linux (unlike Centrino)?
Re:Does AMD have anything to compete with Centrino by bhtooefr · 2004-02-16 01:02 · Score: 1

Actually, the G5 is close competition for the Pentium M in both performance and efficiency.
Re:Does AMD have anything to compete with Centrino by dave420-2 · 2004-02-16 01:11 · Score: 1

strangely quiet around here...
Re:Does AMD have anything to compete with Centrino by Anonymous Coward · 2004-02-16 01:11 · Score: 0

Smells like an Intel monkey spweing FUD.
Re:Does AMD have anything to compete with Centrino by santiag0 · 2004-02-16 01:40 · Score: 1

Anyone ever run Linux on one of those eMachines M6805 or M6807s? Those are their two new AMD 64 mobile based notebooks.

I'd particularly like to try SuSE 9.0 for AMD 64.
Thinking about it as a desktop replacement, might use it for limited travel. Tried the linux on laptops page, nothing.

Nothing comes up on google either. Thinking about getting a recent version of knoppix and hitting Circuit City to try it out...
TIA
Re:Does AMD have anything to compete with Centrino by Glock27 · 2004-02-16 01:54 · Score: 1

Anyone ever run Linux on one of those eMachines M6805 or M6807s?
I'm wondering about this too. They use the nice ATI 9600 mobility graphics chipset, so I'm curious how close accelerated XFree86 drivers are (particularly ones supporting pixel shaders). ATI's website specifically states that mobile devices won't get generic drivers, and one doubts that E-machines will release Linux drivers. I hope I'm wrong about that. Is the DRI project still working on ATI drivers?
For everything you get with those laptops, though, I guess I could live with a simple framebuffer when I'm booted to Linux... ;-)
Anyone know about wi-fi support?

--
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
Re:Does AMD have anything to compete with Centrino by The-Perl-CD-Bookshel · 2004-02-16 02:48 · Score: 1

AMD would be smart to leave the high-end laptop market to intel and transmeta. AMD still has the sub-$1000 notebook market locked as far as I can see (I work at Circuit City and our best selling laptop is always the $899 after rebates offer). Also, I actually see Transmeta owning that market soon. As a side note, Transmeta stock went from about .70 a few months ago to 3.50 this week (on Astro high density server chips). Truly a company on the move with the resources to take their plans to the next level.
P.S. I'm not saying this to kiss Transmeta's butt because they have Linus on staff (do they even have him anymore?); rather I am doing this because i'm typing this on a Fujitsu Lifebook P-Series with a Crusoe chip and I've been on battery since 8:00am (pushing 2 hours and 40% battery left).

--
I don't keep a lid on my coffee so when I walk around I look busy -me
Re:Does AMD have anything to compete with Centrino by JPriest · 2004-02-16 02:54 · Score: 1

The fact that prescott has 122 million transistors, requires so much power, and runs an average 30 degrees (F) hotter than Northwood means they won't be using that technology on the mobile front for a while (it will improve). Intels M is a much different animal than the prescott, but the celeron is usually based on the desktop line of processors and is used in many low end lap tops. The current Prescott core is just not an option for the celeron right now. It does not let AMD take over this market by a long shot, but it does put them in a slightly better position.

--
Saying Java is nice because it works on all OS's is like saying that anal sex is nice because it works on all genders.
Re:Does AMD have anything to compete with Centrino by Brian+Stretch · 2004-02-16 03:04 · Score: 4, Interesting

Centrino: marketing-speak for a Pentium-M CPU (Pentium 3 on steroids), Intel chipset, obsolete Intel 802.11b WiFi chip, and $300 million ad campaign.

AMD: Mobile Athlon 64, variety of chipset vendors, variety of 802.11g chip vendors, no Centrino marketing tax. Thus you can buy eMachines Athlon 64 3000+ widescreen notebooks with high-end video chips from Best Buy for $1300 after the usual rebates. If you're reading Slashdot you'll get great battery life; if you're playing UT2004 you won't, but you'll get better performence than the Pentium-M can deliver.
Re:Does AMD have anything to compete with Centrino by addaon · 2004-02-16 03:31 · Score: 1

i think you just inspired the next ad campaign for mobile athlon's. "It flies, but not for as long as the plane you're on."

--

I've had this sig for three days.
Re:Does AMD have anything to compete with Centrino by bhtooefr · 2004-02-16 04:31 · Score: 1

What time did you post this? I've got 9:48AM as your post time (but the time zone is often off), giving you until 11:48, or 3:48 battery life. 3:48 isn't that good, unless it's a very small subnotebook.

By the way, Linus is now with OSDL.
Re:Does AMD have anything to compete with Centrino by charnov · 2004-02-16 05:35 · Score: 1

I have one of the M6805 eMachines, too (my God this thing is fast). The WiFi chip is a Broadcom, so it doesn't look like Linux will recognise it. Hello, Broadcom, we need info to write drivers...

--
[RIAA] says its concern is artists. That's true, in just the sense that a cattle rancher is concerned about its cattle.
Re:Does AMD have anything to compete with Centrino by Hoser+McMoose · 2004-02-16 05:59 · Score: 1

The AthlonXP-M actually doesn't do too bad compared to the Pentium-M ("Centrino" is purely a marketing campaign to sell a Pentium-M processor combined with an Intel chipset and an Intel WiFi chip).

AMD sells a line of AthlonXP-M processors with a TDP (Thermal Design Power, ie kinda-almost maximum power) of 25W, basically the same as the mainstream Pentium-M chips (Intel also sells some ULV Pentium-M chips with a TDP of only 7W). The performance is pretty good in comparison too, especially if you compare the AthlonXP-M 2000+ to the Pentium-M 1.7GHz (top-end of either line). Perhaps even more importantly though, the AthlonXP-M is MUCH cheaper.

The real downside for AMD is that the Pentium-M has slightly better dynamic power management features, so in normal use it consumes more power on average (maybe 20% more, or about a 5-10% difference in battery life).

In the end, the AthlonXP-M can compete VERY effectively with the new Celeron-M. The two chips will be priced similarly but the AMD will offer much better performance and better power consumption (Intel disables the dynamic power management features of the Celeron-M, so AMD comes out on top here). Not quite the high-end market of the Pentium-M, but then again, not everyone wants to spend $1500-$3000 on a notebook.

One word of warning though, AMD also sells an AthlonXP-M with a TDP of 45W as well as "Desktop Replacement" AthlonXP-M chips, and they don't really make much of an effort to differentiate between the three chips. They will all perform the same at the same clock speed, but they'll have different power consumption figures, so you really have to check just WHAT chip you're actually getting. And just so that Intel doesn't feel left out, they do damn-near the exact same thing with their "Mobile Pentium4-M" and "Mobile Pentium4" processors, which have drastically different power consumption figures.
Re:Does AMD have anything to compete with Centrino by Hoser+McMoose · 2004-02-16 06:03 · Score: 1

Transmeta? HIGH-END?!?! What the heck have you been smoking? Their Crusoe chips get absolutely owned by the ULV Celeron processors with similar power consumption and lower prices! They are pure bargain-basement stuff! Even their upcoming "Efficeon" chip is only promising 50-80% better performance, which might make them competitive with the bottom-end of the Celeron line in terms of performance, but not much else.

Good power consumption, sure, but at the cost of much lower performance than anything Intel and AMD are designing. Transmeta just has to look out that the world doesn't discover VIA chips, which offer better performance with the same power consumption and they offer it for dirt-cheap!
Re:Does AMD have anything to compete with Centrino by Hoser+McMoose · 2004-02-16 06:06 · Score: 1

Intel just recently introduce the "Celeron-M" processor for laptops. It's a cheaped-down version of the "Pentium-M" processor used as part of the Centrino marketing campaign.

Unfortunately Intel disabled many of the most important dynamic power saving features of the Pentium-M when they released the Celeron-M, so it's not as interesting of a chip as it might be.
Re:Does AMD have anything to compete with Centrino by speck · 2004-02-16 10:31 · Score: 1

I've got one of these too (an eMachines m6805). It's a great little machine, but not the most compatible with linux out of the box - at least, not if you want to run a kernel in 64-bit mode.

The main problem is with the hardware manufacturers. At least three devices in the notebook (the ATI Mobility 9600 video card, the Broadcom-based 802.11g built-in wifi, and the SmartLink internal modem) have only binary drivers available for Linux. The binaries are invariably 32-bit 1386 ones, meaning that they can't be linked into a 64-bit kernel.

This is annoying - especially the wifi - but the machine still runs a mean gentoo, as long as you're willing to run mostly the latest and greatest versions of, say, XFree86 (which currently supports 2D acceleration in the video card, but no 3D). It's my hope that as 64-bit Windows looms on the horizon, hardware vendors will realize that two sets of binary drivers no longer cover all the bases.

Alternatively, I'm told, one can run Linux in 32-bit emulation mode (this is how Windows runs on the box right now). No doubt this would net one greater binary compatibility, but it still chaps my hide that companies produce binary-only drivers for linux at all.

Anyways, short answer, the CPU itself is fairly well-supported, but the drivers for accessing devices from a 64-bit OS are not all there yet.
Re:Does AMD have anything to compete with Centrino by santiag0 · 2004-02-16 11:08 · Score: 1

Found this, if this is the same broadcom wifi setup on the lower end eMachines laptop:
http://users.zoominternet.net/~wally001/M 5312.html

To quote:

Broadcom 54 MBs Works fine using "Linuxant driverloader" w/ Windows Broadcom drivers

Uses windows driver, but author claims it works.
So, if the ATI graphics chip works, the rest will probably be a no brainer. I checked and Best Buy here in Austin is going to have some of the M6805 eMachines in stock later this week. Just ordered latest knoppix CD (I don't have a CD burner, or have easy access to one) for 5 bucks. I'll try it out this week at Best Buy with the knoppix CD.

Will be running in 32 bit mode, so won't be a good test of the processor, but will suffice to see if the other hardware is recognized under Linux.
Re:Does AMD have anything to compete with Centrino by Trepalium · 2004-02-17 08:12 · Score: 1

You might be able to get the smartlink modem to work in 64-bit mode. You need the latest version of Alsa (1.0.2, I think), and compile in the i810 modem support, and use the ALSA support of the latest (beta) SmartLink binary drivers. This new version runs all in userspace (except for the Open Source ALSA driver), so as long as you can run 32-bit binaries, you should be fine. IA64 users are still out of luck, though.

--
I used up all my sick days, so I'm calling in dead.

You can't compete if you're bleeding by ObviousGuy · 2004-02-16 00:43 · Score: 5, Insightful

I'm glad to hear this kind of recovery by AMD. Not only for the employees of AMD who won't have their lives disrupted by layoffs, but also for the stockholders who can reap the benefits of a company that is now making money.

What's more, it forces Intel to compete against a competitor that can actually put extra top line money towards research and development. Everyone wins when companies can compete.

--
I have been pwned because my /. password was too easy to guess.

Re:You can't compete if you're bleeding by CTho9305 · 2004-02-16 02:24 · Score: 1

Fear of layoffs? Far from it!

AMD to expand, add Austin jobs
Chip maker leases additional office space in Northwest Austin.

By Kirk Ladendorf

AMERICAN-STATESMAN STAFF

Wednesday, February 11, 2004

Chip maker Advanced Micro Devices Inc. has leased additional office space in Northwest Austin and plans to add more engineers there this year, a spokesman said Wednesday.

It will be the company's first expansion in several years.

AMD has leased an additional 36,000 square feet at 9500 Arboretum Blvd., which houses the company's Personal Connectivity Solutions division. The company previously had 56,000 square feet there.

The operation, which employs a few hundred people in Austin, designs low-power chips for Internet appliances, television set-top control boxes and Internet access devices.

AMD spokesman Drew Prairie said the company expects to complete construction of the new space this spring and begin phasing in new workers, with a focus on design engineers.

The company employs about 3,000 people in Austin.

CB Richard Ellis represented the landlord, Pac Trust, in the transaction.

--
My server
Re:You can't compete if you're bleeding by BoneFlower · 2004-02-16 05:50 · Score: 1

They probably had the money troubles because they put so much into R&D and marketing. Short term risk(running red) for long term benefit against Intel. They probably knew there was no way they could be profitable in the short term and be anything but a bit player, and intentionally ran red so they could get to a better position.

Go, Go AMD by JamesP · 2004-02-16 00:44 · Score: 5, Interesting

Way to go AMD. Intel is eating dust on this one...

The problem is, Intel went from an Engineering company to a marketing company. Let's just hope it doesnt became a lawsuit comapny...

--
how long until /. fixes commenting on Chrome?

Re:Go, Go AMD by AndroidCat · 2004-02-16 00:57 · Score: 5, Insightful

AMD won't have won until Intel starts rating its processors in "equivalent Athlon64 performance". ;)

--
One line blog. I hear that they're called Twitters now.
Re:Go, Go AMD by Anonymous Coward · 2004-02-16 01:04 · Score: 0

Typical black and white thinking. Intel is still the king in engineering and invest vast amount in money on research and development. This does not mean that AMD is bad though.
Re:Go, Go AMD by Short+Circuit · 2004-02-16 01:55 · Score: 2, Informative

The whole stigma about "equivalent performance" is really unwarranted. Cyrix used to name their processors things like "P-100" or "P-120" to rate them as equivalent with the Pentium 100MHz or Pentium 120MHz. And they did perform to those standards.

In a logical sense, there shouldn't be any problem with AMD using numbers like "3200+" ...Of course, nobody ever said the Megahertz Myth was logical. It only seems to be.

--
tasks(723) drafts(105) languages(484) examples(29106)
Re:Go, Go AMD by anno1a · 2004-02-16 02:49 · Score: 1

AMD didn't rate their processors as equivalent to Intel Pentiums, but as equivalent to AMD T-birds.

--
------- I fumbled my registration and I now must suffer
Re:Go, Go AMD by Zak3056 · 2004-02-16 02:50 · Score: 4, Informative

AMD won't have won until Intel starts rating its processors in "equivalent Athlon64 performance". ;)

I'm assuming you're referring to AMD's "Performance Rating." If you are, you might be interested to know that AMD compares their CPUs to a 1Ghz Duron, and NOT any sort of intel chip.

PR3200+ would be 3.2x faster than a 1Ghz Duron.

--
What part of "shall not be infringed" is so hard to understand?
Re:Go, Go AMD by Anonymous Coward · 2004-02-16 04:37 · Score: 0

Intel is eating dust on this one...

Intel Financial Results
AMD Financial Results

Gross Profit:
Intel: $13,320,000,000
AMD: $591,370,000
(Intel is 22x Higher)

Operating Margin:
Intel: 24.99%
AMD: -6.63%
(Intel is 30% higher)

Fiscal Year Earnings Growth
Intel: 141.4%
AMD: N/A

Free Cash Flow
Intel: $6,920,000,000
AMD: -$736,570,000
(Intel has $7.5B more free cash flow)

Market Cap:
Intel: $196,870,000,000
AMD: $5,210,000,000
(Intel is 37x higher)

So, basically, the profit AMD made over last year, Intel makes every 2 weeks. Yup. Looks like they are really eating dust.
Re:Go, Go AMD by Deliveranc3 · 2004-02-16 04:48 · Score: 1

A nasty article was posted receently outlining AMD's x86 instruction set which they got from Intel. Intel in exchange has the right to all the plans for AMD cpu's. In other words they can copy AMD's cpu's!

Lawsuits would be ugly :)

AMD shares most of it's really low level research with IBM and Sun, this combination allows them to produce chips increadibly cheaply while still maintaining decent profit margins. They are a few months from opening a new fab in Germany which should dramatically increase yield and processor availablility.
Re:Go, Go AMD by Anonymous Coward · 2004-02-16 05:20 · Score: 0

Uh, no. That won't happen. Rating a processor according to its competitor is not a sign of market inferiority. If AMD released a 10ghz chip that ran at PIV 1.0ghz speeds, or something and Intel had a smaller ghz number yet better performance.
Re:Go, Go AMD by Loki_1929 · 2004-02-16 05:32 · Score: 1

"I'm assuming you're referring to AMD's "Performance Rating." If you are, you might be interested to know that AMD compares their CPUs to a 1Ghz Duron, and NOT any sort of intel chip."

I'm still not quite sure where this rumour started, but as I recall, AMD stated specifically that the rating system was relative to Thunderbird core Athlon performance, as it was the last Athlon produced prior to the introduction of the model number system. Thus, an AthlonXP 2600+ should perform as well or better, on average, than a Thunderbird core Athlon running at 2.6GHz.

This whole thing about it being relative to the Durons appears to have cropped up some time in the past 6 months or so. I suppose it's possible it could be correct, but I've never seen an AMD whitepaper stating as much. If you, or someone else, could point me in the direction of an AMD page to clear this up for good, it would be appreciated.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
Re:Go, Go AMD by Anonymous Coward · 2004-02-16 05:49 · Score: 0

And an Athlon 64 FX-53 compares to a 1Ghz Duron... how?
Re:Go, Go AMD by CodeRx · 2004-02-16 06:06 · Score: 1

... AMD compares their CPUs to a 1Ghz Duron ...

Yeah, right. That might be what AMD says, but everyone knows the PR is supposed to compare to an equivalent p4. IE, PR3200 is supposed to be roughly equivalent to a 3.2Ghz p4.

Your average IT manager or consumer thinks that Mhz are everything and thus a 3200Mhz p4 must be way faster than an Athlon 64 running at a puny 2000Mhz.

32, 64,... by Anonymous Coward · 2004-02-16 00:44 · Score: 4, Funny

What I want to know is, where are the 128bit CPUs?

Re:32, 64,... by Anonymous Coward · 2004-02-16 00:53 · Score: 0

be thankful the AMD64 is 64bit. The were going to make it 48bit, can you imagine how unmarketable an AMD48 would've been?
Re:32, 64,... by moro_666 · 2004-02-16 00:59 · Score: 2, Informative

check out the playstation2 from sony, there you have the 128bit cpu, wonder what does the pc market take so long
here are the ps2 specs (a bit long but still) :

CPU : 128-bit CPU
System Clock Frequency: 294.912 MHz
Cache Memory : Instruction: 16KB, Data: 8KB + 16 K(ScrP)
Main Memory : Direct Rambus (Direct RDRAM)
Memory Size : 32MB
Memory Bus Bandwidth : 3.2GB per second
Co-processor : FPU (Floating Point Unit) Floating Point Multiply Accumulator x 1 Floating Point Divider x 1
Vector Units : VU0 and VU1 Floating Point Multiply Accumulator x 9 Floating Point Divider x 3 Floating Point Performance : 6.2 GFLOPS 3D CG Geometric Transformation: 66 million Polygons per Second Compressed Image Decoder : MPEG2
GRAPHICS- Clock Frequency : 147.456MHz Embedded DRAM : 4MB DRAM Bus Bandwidth : 48GB per second DRAM Bus Width : 2,560 bits Pixel Configuration : RGB:Alpha:Z Buffer (24:8:32) Polygon Drawing Rate: 75 million Polygons per second Screen Resolution : Variable from 256 x 224 to 1280 x 1024

now go and compare it to your pc and get stunned

--

I'd tell you the chances of this story being a dupe, but you wouldn't like it.
Re:32, 64,... by Anonymous Coward · 2004-02-16 01:08 · Score: 3, Informative

The 128 bits there are referring to the size of the data bus and registers, not the address bus. With only 32MB of memory, the PS2 doesn't need more than 25 bits to address it (it does however use a 32 bit address bus.)

So really, it is a 32bit/128bit hybrid.
Re:32, 64,... by turgid · 2004-02-16 01:22 · Score: 1

What I want to know is, where are the 128bit CPUs?
In Jesus' flying saucer that we captured from the aliens, in Area 51.

--
Stick Men
Re:32, 64,... by pesc · 2004-02-16 01:45 · Score: 4, Informative

It really isn't a FULL 64 bit implementation. In it's current incarnation it supports 40 bit physical and 48 bit virtual address spaces, as I recall. Even the Itanium has only a 44 bit address bus.

Please don't propagate this kind of FUD.

The ISA (Instruction Set Architecture) is fully 64 bits. The pointers really are 64 bits wide. The programs you compile now will be able to fully use a 64-bit wide virtual and physical (will we ever see one?) memory architecture.

This is similar to nearly all previous 64 bit architectures such as Alpha and Sparc (and maybe Power and HP-PA and MIPS?). Most of the actual machines used don't really have 64 bit physical adresses.

You have to distinguish between a ISA and a physical implementation of it. Most motherboards can't host more than a couple of GB memory anyway. But the ISA of the processor is still a true 64 bit architecture.

--

)9TSS
Re:32, 64,... by Anonymous Coward · 2004-02-16 01:52 · Score: 0

...where are the 128bit CPUs?
In the playstation 2
Re:32, 64,... by dreamchaser · 2004-02-16 01:58 · Score: 2, Informative

How is it FUD? I pointed out that neither the Athlon 64 NOR Itanium is a FULL 64 bit implementation. Internally yes. ISA wise, yes. Address bus wise, no.

Stop the knee jerk reactions. You sound like a zealot :)
Re:32, 64,... by MasTRE · 2004-02-16 02:07 · Score: 4, Funny

> What I want to know is, where are the 128bit CPUs?

Which will be able to address..... [zoom in on Dr. Evil's face] 1 MILLION MEGABYTES!!!

--
Must-not-watch TV!
Re:32, 64,... by d_strand · 2004-02-16 02:20 · Score: 2, Interesting

Really?

What makes a cpu xx-bits?
Answer: how big numbers it can deal with in a single instruction. So a 64-bit cpu can handle 64-bit floats natively without splitting the operations into 32-bit chunks.

I have no idea if the Sony emotion engine or whatever it's called can handle 128-bit floats/longlonglongs natively (Quad precision?) but I doubt it since it's utterly unnecesary for the software it uses. If it's able to utilize it's 128-bit registers fully with some kind of 4-unit-SIMD instructions, it still isn't a real 128-bit processor, just a vectorproc.
Re:32, 64,... by pesc · 2004-02-16 02:22 · Score: 1

Sorry about the knee-jerk! ;-)

But I have seen several discussions about how the Opteron is not REALLY a 64-bit architecture (while Itanium or Alpha supposedly are), and a lot of confusion amongst people around the fact that the chip only exhibits 40-something address bits.

So I tend to react against people that starts to talk about how many adress bits a particular chip has. It is not an interesting fact and it confuses most people.

Regards /Per

--

)9TSS
Re:32, 64,... by sloptaco · 2004-02-16 04:22 · Score: 1

Funny joke, but a 128 bit processor would be able to address much more than that.

Ok, 2^32 is 4GBytes (or precicely 4,294,967,296 addresses). 2^64 is 18,446,744,073,709,551,616 addresses (18 pentabytes?).

2^128 = 3.4028236692093846346337460743177e+38

Umm... 3 yowserbytes? Holy crap!, no wonder there's no rush to go to 128. (I think we run out of latin words at this point.)
-sloppy
Re:32, 64,... by sloptaco · 2004-02-16 04:57 · Score: 1

Sorry, 2^64 = 18,446,744,073,709,551,616 (or 16 exabytes =~ 17 billion GB.)
-sloppy
Re:32, 64,... by Hoser+McMoose · 2004-02-16 06:22 · Score: 4, Informative

The Playstation2 does NOT use a 128-bit CPU!!!

The PS2 has a 32-bit CPU core with 128-bit vector units. The Pentium3 also uses a 32-bit CPU core with 128-bit vector units (SSE), as does the Apple/Motorola G4 chip (with Altivec). There has never been a 128-bit CPU used in ANY gaming console, and I'm only aware of 1 64-bit CPU ever used (Nintendo64).

Of course, the reason for this is that going to more bits makes a CPU SLOWER! All else being equal, a 64-bit is 5-10% slower than a 32-bit CPU, and a 128-bit CPU is 10-20% slower than a 64-bit one. Since games don't need to address more than 4GB of memory, it's totally pointless to use a 64-bit CPU in a gaming console. The only other thing that a 64-bit CPU buys you is an integer range of more than 4 billion, and that's RARELY used outside of cryptopgraphy (how often do you do cryptography on your gaming console?).

Of course, all else usually isn't equal (eg AMD64 adds 8 more general purpose registers and cleans up some cruft when compared to IA32). Also PCs often do need to address more than 4GB of memory (virtual + physical).

PCs do not, however, need to address more than 10^19 bytes of memory, and they definitely don't need more than 10^19 integer range for much of anything, so 128-bit CPUs get you absolutely NO positives but you still would have to deal with the 10-20% performance loss.
Re:32, 64,... by caseih · 2004-02-16 06:36 · Score: 1

Well, the Saturn RISC processor that powers the venerable HP 48 Calulculator line has 64-bit registers but only a 4-bit data bus. The address bus is 20-bit, however. I have no idea what this processor is considered to be. I doubt they call it a 64-bit processor. Maybe they call it a 4-bit? Anyway, sometimes this whole "x-bit" thing is confusing. Reminds me of the old video game console days when they were all 8-bit processors but the games were considered advertized using the megabits they took up on the cartridge.
Re:32, 64,... by Anonymous Coward · 2004-02-16 07:34 · Score: 0

No one needs more then 640k... sound familer? If not re-read your post.
Re:32, 64,... by Anonymous Coward · 2004-02-16 07:48 · Score: 0

Another example of cowardly mods on crack using 'underrated' for something that wasn't rated in the first place, AND was spot on!

This overrated/underrated crap has to go. There is no meta-moderation oversight and it is being widely abused!
Re:32, 64,... by Hoser+McMoose · 2004-02-16 08:06 · Score: 1

Fine, write back to me in 50-70 years when someone might actually need more than 10^19 bytes of memory (and that's assuming we continue with the current rate of doubling memory usage). If we're still using PCs that in any way, shape or form resemble today's PCs, then maybe I'll grant that a 128-bit desktop CPU might have some reason to exist.

Until that time, stick with 64-bit chips.
Re:32, 64,... by stfvon007 · 2004-02-16 09:26 · Score: 1

2^128 = 3.4028236692093846346337460743177e+38 Umm... 3 yowserbytes? Actually its only 2. (the larger the number the greater discrepancy between the 1k=1000 number system and the 1k=1024 that computers use at this size number there is nearly a 75% discrepancy between the two)

--
All misspellings and grammatical errors in the above post are intentional and part of my artistic expression.
Re:32, 64,... by Anonymous Coward · 2004-02-16 16:18 · Score: 0

So what about the n64? Did that really have a 64bit cpu?

Why 64-bit is better by Decaff · 2004-02-16 00:46 · Score: 2, Informative

64-bit processors are better than 32-bit ones because 32-bit processors 'can't take advantage of more than 4 megabytes (sic) of memory at a time'.

Well, yes, but the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.

Re:Why 64-bit is better by pesc · 2004-02-16 00:58 · Score: 4, Informative

the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.

No.

You can move data around fast if you have a good memory architecture. A wide data bus to external memory. And a bus clocked at high speed. And larger caches.

You can have all of that with both 32-bit and 64-bit processors. The 64-bittness doesn't help here. If everything else is equal (in the memory architecture), I would expect the 64-bit processor to lose slightly since it has wider pointers. That puts more pressure on the caches and uses more memory bandwidth.

64 bit processors are good because they can easily adress more than 4GB virtual memory.

--

)9TSS
Re:Why 64-bit is better by Anonymous Coward · 2004-02-16 01:29 · Score: 1, Informative

Well, yes, but the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.

No, as such there is no guarantee that 64-bit means a 64-bit data bus (e.g. Amiga had 16 bit data bus but 32-bit (well 24-bit on A500) address space). It means the amount of address space you can offset using one segment register. It's really just the same segment:offset pair as with the "640 kB" crowd, it's just that the offset is so much bigger nowadays: 32-bit addresses 4 GB and 64-bit a lot more.

Also, the 64-bitness implies pointers are double size, 64-bit. So moving a pointer can be just as fast versus the 32-bit chip even though you have a 64-bit bus. But I do agree that in principle you have a possibility of doing more work in one cycle (e.g. copying strings), and the speed increase will also work out in practice.
Re:Why 64-bit is better by dnoyeb · 2004-02-16 01:46 · Score: 2, Insightful

But 32-bit processors can, using the exact same tricks to pass around 64-bit data, address more than 4GB of memory.

Both are legitimate enhancements that a 64-bit processor has over a 32-bit one.

More address space, wider data path.

My personal opinion is the end result of 64-bits will be an efficiency improvement, but not a performance one. So once again AMD favors performance over clock speeds. Probably another reason intel is weak on putting out 64-bit CPUs because they know the clock speeds will be lower.
Re:Why 64-bit is better by Anonymous Coward · 2004-02-16 01:57 · Score: 0

The real reason why the Athlon64 is faster is because of the abundant internal registers. In native 64bit code the compiler can directly make far more efficient use of the available register space. In 32bit mode the cpu can utilise its clever register renaming scheme.

This also partly the reason why the PowerPC series has such good performance, when compared clock for clock with previous x86 implementations. They (PPC) waste less time storing and restoring register values and spend more time getting on with useful work.
Re:Why 64-bit is better by ncc74656 · 2004-02-16 04:37 · Score: 1

But 32-bit processors can, using the exact same tricks to pass around 64-bit data, address more than 4GB of memory.

At best, they can only see a 4GB "window" into memory. In the end, it's not too different than the bank-switching my Apple IIe used to access more than 64K (it started with 128K and was expanded to 1MB), and it'll impose many of the same limitations. If you need to work with >4GB of code and/or data, the flat address space a 64-bit processor offers is far preferable to trying to shoehorn everything into running on a 32-bit processor.
My personal opinion is the end result of 64-bits will be an efficiency improvement, but not a performance one.

There can't help but be a performance improvement, even if it's just a small one. Being able to just load a register from any memory location has to be faster than making sure you're looking in the right place first and then calculating an offset into the currently-active chunk of memory. It's one operation vs. more than one operation.

--
20 January 2017: the End of an Error.
Re:Why 64-bit is better by ikewillis · 2004-02-16 07:23 · Score: 1

Well, yes, but the real reason...
"Well, no!" is the proper response. I'm sure most of us have been using > 4MB RAM on 32-bit architectures for years.
The real limitation is 4GB of total VM space (2^32 = 4294967296 bytes) for operating systems running on 32-bit architectures. This can be very disadvantageous, especially on architectures such as OS X which prebind applications to increase performance. When prebinding is utilized, each library and executable is pre-assigned a portion of the VM space to run in, which means that if you install too many programs you may run out of available VM space. This problem is remedied on the G5, which uses the G5's 64-bit functionality to manage a 64-bit VM space (2^64 = 18,446,744,073,709,551,616 bytes, or 18 exabytes) however no one process can utilize more than 4GB at a time due to the use of 32-bit pointers. This is where a real 64-bit operating system like Solaris, Irix, Tru64, etc. is handy, at least for databases and other applications which need to crunch large data sets in memory.
There are other areas where having a 64-bit VM space alone is a major boon, one of the most notable being memory-mapped I/O. On a 32-bit architecture, processes typically can't memory map a >2GB file, but on a 64-bit architecture, with 18 exabytes of VM space to blow, processes can mmap to their heart's desire without worry.

Yeah ! AMD64 rulez ! Now if the could just... by Brane2 · 2004-02-16 00:46 · Score: 3, Insightful

...stop being such assholes and decide to use Socket 940 for all the models, stop charging insane amounts for those extra two HT links on Opterons 8xx and use some smart diferentiating qualities between subfamilies (like amount of L2 cache, for example) instead of number of HT links, Socket models etc crap, this 64-bit idea would have a whole lot more appeal...

4gigs of ram by phreak03 · 2004-02-16 00:47 · Score: 4, Informative

you can adress more than 4 gigs of ram with a 32bit prossessor You just need a cludge (kinda expensive/slow) but itspossible speaking of lots of ram, anyone seen those Ram Harddrives they had at CES a couple years ago

--
come comment on the madness at http://slashdot.org/~phreak03/journal/

Re:4gigs of ram by AndroidCat · 2004-02-16 01:05 · Score: 5, Insightful

You can address more than 4 gigs of ram with an 8 bit processor. That doesn't mean that the result is pretty or that you should do it.

--
One line blog. I hear that they're called Twitters now.
Re:4gigs of ram by Anonymous Coward · 2004-02-16 01:07 · Score: 0

Like OS X's 64 bit memory support?
Re:4gigs of ram by Anonymous Coward · 2004-02-16 01:14 · Score: 0

The 8bits are already stretching it with the high, low memory pointers.
Re:4gigs of ram by wowbagger · 2004-02-16 02:34 · Score: 1

I could make a 6502 address more than 4G of memory. Of course, it would spend all of its time paging in paging tables to figure out what to page in, but it could be done.

However, writing 6502 code to access that memory would be a nightmare.

Simillarly, writing ia32 code to access more than 4G of memory per thread is a nightmare of paging - instead of simply mmap'ing a file and moving a pointer, I now have to bring the paging logic into my program, and make my code all the more complicated. And complicated code tends to be buggier than simple code.

--
www.eFax.com are spammers
Re:4gigs of ram by Anonymous Coward · 2004-02-16 03:43 · Score: 0

I could

Alright kiddo, alright... we know sweetie.
Re:4gigs of ram by hackstraw · 2004-02-16 04:52 · Score: 1

you can adress more than 4 gigs of ram with a 32bit prossessor You just need a cludge (kinda expensive/slow) but itspossible speaking of lots of ram, anyone seen those Ram Harddrives they had at CES a couple years ago

Bullshit. On 32bit systems, when you ask the OS for memory, it returns a 32bit pointer that cannot be incremented beyond 4gigs for one contiguous chunk of memory. There is a hack in x86 systems to put more RAM available to the whole machine, but not to one app for one chunk of memory.

This is why 64bit machines have been out for over 10 years now, some people need more than a cheap PC to get their work done.
Re:4gigs of ram by FooAtWFU · 2004-02-16 04:56 · Score: 1

4 megabytes of memory should be enough for anyone!!!

err... wait a moment :)

--
The World Wide Web is dying. Soon, we shall have only the Internet.
Re:4gigs of ram by Anonymous Coward · 2004-02-16 05:27 · Score: 0

Boy, that'd be one bitchin' bank switch scheme on my Atari 800!
Re:4gigs of ram by glitch! · 2004-02-16 05:45 · Score: 1

I could make a 6502 address more than 4G of memory. Of course, it would spend all of its time paging in paging tables to figure out what to page in, but it could be done.

However, writing 6502 code to access that memory would be a nightmare.

It's funny that you should pick the 6502 for your example. If I remember correctly, all memory references in the 6502 have to use pointers in "zero page", as either [ptr+x] or [ptr]+y addressing. With a little hardware support, it might be straightforward to implement a useful VM by latching the zero page reference as an index into some context specific translation lookaside table. :-)

--
A dingo ate my sig...
Re:4gigs of ram by BoneFlower · 2004-02-16 05:47 · Score: 1

You could do it. That would be a nightmare of a program to code, but you could write an OS that makes programs think they have only 4GB of memory available.

You would need a rather complicated API for memory management, and to take advantage of it you'd have to use that API for all your memory needs... but it could be done.

Is it a good idea? Probably not. But it could be done.
Re:4gigs of ram by diegocgteleline.es · 2004-02-16 06:04 · Score: 2, Insightful

You can get 64 GB with a modern 32 bit processor with PAE (physical address extension; which extends some register up to 36 bits - but not the whole processor)
Re:4gigs of ram by AndroidCat · 2004-02-16 07:48 · Score: 1

However, writing 6502 code to access that memory would be a nightmare.
Piece of cake! Remember how the Apple ][ had Woz's Sweet16 virtual machine in ROM to do 16 bit operations without so much fiddling around?
A little tinkering and .. The Sweet64! :)

--
One line blog. I hear that they're called Twitters now.

Thanks for clearing that up by Anonymous Coward · 2004-02-16 00:48 · Score: 5, Funny

Do you also explain jokes to people after you tell them?

Re:Thanks for clearing that up by Anonymous Coward · 2004-02-16 01:02 · Score: 0

Notice he put the smiley face in there to illustrate he'd made a "clever" comment?
Re:Thanks for clearing that up by Anonymous Coward · 2004-02-16 01:05 · Score: 0

except... it's not clever. (sic) is put in when the quote has an error, and you want to point out that you are not the one to introduce that error

Congrats by Killjoy_NL · 2004-02-16 00:48 · Score: 5, Insightful

Congratulations to AMD, they've been more innovative in the CPU market than Intel (which is a big feat in my book)
They've also setup a big solid state memcard department (I'm dutch and can't remember the correct name for it right now) which is running along nicely as well.

I hope they can continue keeping up the good work, they deserve it.

--
This is the sig that says NI (again)

Re:Congrats by Plammox · 2004-02-16 00:57 · Score: 5, Insightful

Face it. AMD and Intel need eachother. For me it's a sign of health that Intel's roadmaps are affected by AMD's moves and vice versa.

It's easy to imagine how Intel or AMD products would be more inferior due to lack of competition.
Re:Congrats by dave420-2 · 2004-02-16 01:03 · Score: 2, Insightful

You say that, but Intel are doing so much more... Centrino, celerons, mobile chips, etc. AMD just has 32-bit desktops and 64-bit desktops. Their mobile chips are just desktop chips in funky packaging.
I'm all for giving credit where credit's due, but they don't get a +1000, Innovative just because they're AMD...
Re:Congrats by Killjoy_NL · 2004-02-16 01:06 · Score: 5, Insightful

I don't mean to give them a +1000, Innovative.
+500, sure :D

They designed a cpu that's a much better workhorse than that of their competitor (Athlon), then they did it again (AthlonXP) and again (Opteron/AMD64)

That's innovation from where I'm standing.
I know Intel has a lot more different products, but they use those products more as cashcows, trying to milk as much money from it as possible before the market demands something new.

--
This is the sig that says NI (again)
Re:Congrats by ELiTeUI · 2004-02-16 01:12 · Score: 1

Centrino is intel's only real mobile chip designed for low-power mobile use. Props to them for that.
PIII-M and P4-M (intel's "mobile" chips) are simply standard pIII and p4 cores, which have been cherry-picked for their ability to run at a given speed at a super-low voltage. Other than that, they are no different than desktop chips aside from the packaging. Sounds a lot like AMD.
Celerons are simply defective p4's (or not defective, but crippled nonetheless) with most of the cache disabled. They are NOT a seperate core. This sounds a lot like AMD's Duron.
ELiTeUI
Re:Congrats by dave420-2 · 2004-02-16 01:21 · Score: 1

Celerons aren't "defective" P4s - that's highly emotive language :) They're P4 chips with reduced on-board cache (the expensive part, as I'm sure you know). I don't remember anyone complaining when they realised you could run a $180 300MHz chip at nearly 1GHZ a few years ago :)
Re:Congrats by dave420-2 · 2004-02-16 01:26 · Score: 0, Flamebait

hehehe :)
"Much better workhorse" is a very subjective definition... Some would claim that durability was the essential factor in proclaiming something a better workhorse, which the Athlon definitely didn't have. Remember the cooling rigs that rivalled icebergs? Which if fell off, let all the magic smoke out of the CPU?
I'm not bashing AMD - far from it - they've injected so much life into the CPU industry it's great - but people saying their chips have no down-sides is siding in zealotry :) AMD chips run hotter than their intel equivalents. The Intel chips have always had better survival rates from failed cooling - even a P4 with no cooling (yes, NO cooling) will work.
AMD chips are cheaper in every essence. The low price is only possible because they're not fabricated to as high standards as Intel. I've got no problem with this - it makes cheap chips for us, but when people gloss over this fact it promotes a skewed (and down-and-out untrue) view of the marketplace.
I hope I'm not coming off as pro-Intel/Microsoft nutcase (I'm not). I just wanted to air what is an oft-missed point. :)
Re:Congrats by tomstdenis · 2004-02-16 01:35 · Score: 1

Not to get picky but the AthlonXP and Athon are essentially the same core [all the way up through Barton].

The only real diffs are the cache size [but even the manual notes the limitations of the core with TLB entries], transistor size and addition of SSE. The actual execution engine is the same design [hence the same cycle counts].

Not saying the Athlon isn't a good core. I've had about five diff athlons [and I made sure my laptop would have one] but it isn't as if they jump leap and bounds with their newer processors.

They've always lacked in certain areas. For instance, the cache bus is 64-bits which kills some load times [17 cycle latency to L2 cache according to cpuid from cpuid.com] and SSE load/stores take two load/store buffers.

Also the decode engine still is the same in terms of window size [eight bytes]. So if you can't pack three instructions per window you lose. The only way to get a 3IPC then is if previously decoded instructions stall and one of the three schedulers is free.

They still have a six cycle multiply [I dunno if they can make this faster...] for the ALU. Even if they dropped this to 4 it would rock.

They still don't have good idle support [e.g. Barton 3000+ always runs at 2.1Ghz regardless of what it is doing], etc..

Intel has changed in many respects. While I hate the P4 pipeline they have kept a huge cache bus, their cpus can scale nicely [re: you can remove the heatsink of a P4] in terms of heat, etc. Their cache also have low latency and their decode engine now uses a trace.

If they only made their core slightly more efficient [re: not rely on Mhz myth] we might see an Intel core that competes on the MIPS level with a comparable clock rate AMD core.

Tom

--
Someday, I'll have a real sig.
Re:Congrats by tornado2258 · 2004-02-16 01:35 · Score: 1

Have you ever had a cooler fall off?
I don't mean to be getting at you it's just that this isn't the first time that I've heard mention of what cooler failures do to computers and I was wondering if you'd evr seen it happen. I've been using computers for quite a few years and have been using the cheapest coolers and m-boards I can get my hands on (for myself and other people) and have yet to have a cooler fail or fall off.
I just wondered if it does actually happen or is it just one of those nighmares that system builders have akin to water cooling springing a leak...
Re:Congrats by Sique · 2004-02-16 01:55 · Score: 1

As far as I know, AMD has also much more than desktop CPUs. They have flash RAM, they have embedded controllers (anyone remember the AMD29K series?). Without those other product lines they wouldn't have survived the times when they were struggling to get the new desktop processors out.

--
.sig: Sique *sigh*
Re:Congrats by Killjoy_NL · 2004-02-16 01:56 · Score: 1

"you can remove the heatsink of a P4"

Same goes for the Athlon, the computer shuts itself down.

I believe you were refering to the Tom's Hardware movie where the AMD heatsink was removed and the cpu turned itself into the useful sidekick of Powdered Toast MAN!! (from Ren & Stimpy).
But the cause of that problem was the mainboard, it had no overheating protection, so the cpu is not to blame.

--
This is the sig that says NI (again)
Re:Congrats by Anonymous Coward · 2004-02-16 02:01 · Score: 0

>Celerons aren't "defective" P4s - that's highly emotive language :) They're P4 chips with reduced on-board cache...

No, the parent post was right - intel isn't disabling the cache on purpose, these really ARE defective P4s (some of its on-board cache is defective).

Intel didn't invent Celeron, they simply gave a name to defective P4s and sold them anyway as lower-class parts instead of throwing them in the trash.

Also helps to put more "intel inside" into a lot more boxes (because the Celeron costs a lot less than a P4).
Re:Congrats by Anonymous Coward · 2004-02-16 02:04 · Score: 0

Remember the cooling rigs that rivalled icebergs?

You mean the Pentium IV heatsinks which weighed nearly 1lb and required a reinfoced motherboard and case to support it properly?

The low price is only possible because they're not fabricated to as high standards as Intel.

Well now you really need to define this, because when you're dealing with chips it isn't as though you can employ a factory of immigrant labour to assemble them by hand. If AMD wern't producing their CPU's to a high standard they'd have a very high failure rate, which would cost them a lot of money. One can assume from the fact that they are turning a profit and keeping the channels filled with chips probably means that they do not have a failure rate any higher than Intel does, so they must be manufactured to an equally high standard.

About the only thing I can think that you might possibly mean is that AMD chips do not carry a thermal diode to protect them in the case that they would overheat. If you think a component which would cost a couple of cents per CPU and which actually has dubious advantages means that AMD are not manufacturing their components to a high standard then you should study the differences more closely.

Notice that I didn't even bring up FAB 36 Oh, whoops.
Re:Congrats by dave420-2 · 2004-02-16 02:12 · Score: 1

Well, seeing as people mention it I'm sure it has been known to happen.
I don't think people are scared of how frequently it happens, but rather the fact that if it does, it could destroy their whole computer (and if they're not in front of the PC at the time, their whole house). That fact alone is enough for a lot of people to stay away from AMD. I know I'd be pretty bummed if I came back from the pub and my PC was reduced to a grey-ish puddle and intriguing scorch-marks in the corner of my room, all because I saved 100 on buying an AMD processor :)
Re:Congrats by dave420-2 · 2004-02-16 02:17 · Score: 1

You mean the Pentium IV heatsinks which weighed nearly 1lb and required a reinfoced motherboard and case to support it properly?
No, I'm talking about the heatsink/fan combos on every Athlon since the early days, which if it fell off, results in the CPU bursting into flames. Intel chips can go through a lot more than Athlon chips. Think of them like horses. The AMD is the racehorse, and the Intel is the mule (sure, if this was real the Mule would run at a similar speed as the racehorse). You can load a mule up with a bunch of wood, and it'll totter on. Try that with a racehorse, and you'll be having Shergar sausages by dinnertime. The AMD chips are good, when they work, but vary their operating conditions too much (like removal of heatsink, etc) and you run an increased risk of screwing something.
I'm not slighting AMD here, I'm just pointing out a major difference between the chips' designs.
Re:Congrats by thelasttemptation · 2004-02-16 02:40 · Score: 1

It's a nightmare for sure, as my brother's cpu water block sprung a leak and well, it happens. A friend of mine once put the clip on wrong and his heatsink did fall off when he moved the comp, so it does happen from time to time, but it's not often.
Re:Congrats by paitre · 2004-02-16 02:42 · Score: 1

Also, re: Opteron, they've apparently "gotten it", and you -should- be able to run at least some of the models with just a heatsink...not even a fan.

I want to say the rig I've got (dual 244, 6G RAM, 1U rackmount) is fanless, but I'd have to go crack the case and look.
Re:Congrats by thelasttemptation · 2004-02-16 02:45 · Score: 1

well at the time there were no mobos that had the overheating problem, and no intel boards do as well, the intel cpu clocks itself down, while amd's, even with no mobo support, just dies. I think it was saing that while AMD's works fine, they don't have all the lil extras ondie that intel does.
Re:Congrats by ckaminski · 2004-02-16 02:53 · Score: 1

yes yes yes, the lack of a thermal diode on early Athlons was indeed a fatal flaw...

Since that problem has been fixed, and no recent stories about Athlon 64's and Athlon 3200+'s going up in heat-smoke seem to be filling the airwaves, I can only conclude that you are trolling, and with a 3 year old troll at that.
Re:Congrats by Slugworth01 · 2004-02-16 03:11 · Score: 1

Well, seeing as people mention it I'm sure it has been known to happen.
Are we talking Bigfoot sightings?
Might be a problem, but without anything to back this claim up, it looks like a troll to me.
Re:Congrats by Slugworth01 · 2004-02-16 03:14 · Score: 1

The low price is only possible because they're not fabricated to as high standards as Intel.
Thermal diodes in Athlons, math errors in Pentiums. Beyond those two items, you might want to substantiate this claim.
Re:Congrats by tomstdenis · 2004-02-16 04:50 · Score: 1

The P4 won't shut down though. It clocks down to cool off. The AMD Athlons will either die, die horribly or power down.

All of which are annoying if you're say an hour from home and your server goes down. Hence I either leave my box in the cold basement or I have a huge desk fan blowing in it [case walls removed]. Keeps it nice and cool.

Tom

--
Someday, I'll have a real sig.
Re:Congrats by hackstraw · 2004-02-16 04:56 · Score: 1

Congratulations to AMD, they've been more innovative in the CPU market than Intel (which is a big feat in my book)

Hmm, I don't consider adding 64bit extensions to a 30 year old 16bit processor that was created by another company as "innovative". Wake me up when they have a wide memory bus, flat 64bit archetecture with a low voltage CPU. This is where innovation is going.
Re:Congrats by denobug · 2004-02-16 04:58 · Score: 1

I don't usually post here but base on the experience the cooling fans do fail from time to time. The probability of failure increase greatly by the life of a particular machine.

While I'm sure the chance of the CUP cooling fan (motor) failure is rare, it does happened. It happened to once of my older computer (PII machine, kinda old, I know). My sister's P4 just had one of the cooling fan failed NOT b/c of the fan is bad but the motherboard is not supplying any power (through the existing pins). I had to use a power adaptor for the workaround.

I myself is using an Athlon and the motherboard does have the setup to detect the temperatures of the computer at serveral point (including the CPU temp.)

In general in a safety related design there are more than one check point. For example, if the CPU fan failed and the CPU temp. failed to pickup the uncontrolled temp. increase, the m-board temp. indicator will also shows an increase. Also you can tell from the electricity usage to determine the abnormal computer conditions. The power controller should pick up the unusually serge in power usage if any circuits are shorted inside the computer (possibly a melt down on insolation material external of the chips).

The worst case scenario that I can think of on my computer is if there IS a small fire ( not very likely since the processor should have been self-destruct even before that point). The m-board and the power supply shold catch it and shut the power off meediately. The Processor may be hot the the amount of energy is not enough to even harm my harddrive. I may hae some problem w/ my data integrity if my harddrive is running when the power is cut, but the physical damage is limited to the processor and the m-board, at most the RAM near the processor and possible damage to one side of the video card. The IDE cable is far enough not too pose a significant issue.

But above all else, given the redundent level of protection (however small), I don't think I will be worry about my house being burned down by my computer an more than other appliances. To be real, a short circuit in compressor of the fridge has more power to short out your electricity (i.e. causing problems) than the comptuer. If that is not a problem, why should my computer be?
Re:Congrats by ivan256 · 2004-02-16 06:39 · Score: 1

but even the manual notes the limitations of the core with TLB entries

When you dug that out of the manual, did you understand what it meant?

Pick a processor, and then show me a programmer that has done virtual memory subsystem level optimization for said processor for applications with large datasets, and I'll show you a programmer that thinks there aren't enough TLB entries on said processor.

Until there is a processor that has a TLB entry for every page in the system, there aren't enough to satisfy the types of people who's performance is signifigantly degraded by a lack of TLB entries. 99% of people (probably more) don't run the types of programs that would see more than a 1% boost in performance from additional TLB slots.
Re:Congrats by Hoser+McMoose · 2004-02-16 07:01 · Score: 1

The P4 will shut down as well or it will die, die horribly. Tom's video was faked, go read Intel's thermal design guidelines sometime. Hell, you don't even need to do any research to see it was faked, just watch the video and notice how the processor stays at less than 30C when "throttled", even though thermal throttling doesn't kick in until the processor hits 65-70C.

Even if fully throttled a P4 will still consume at least 20-30W of power, and that is WAY more power than a die with no heatsink can dissipate. Ever try running a PentiumMMX processor without a heatsink? They consume only about 10W of power and would overheat in under a minute without a heatsink.
Re:Congrats by Hoser+McMoose · 2004-02-16 07:39 · Score: 1

Not to get picky but the AthlonXP and Athon are essentially the same core [all the way up through Barton].
And by the same token, the PentiumPro, PII and PIII were all the same core as well.
The only real diffs are the cache size [but even the manual notes the limitations of the core with TLB entries]
Err, do you even know what that means? Because ALL processors will have some limitations caused by the TLB, and all should note them if they're doing a decent job of documenting the chip!
They've always lacked in certain areas. For instance, the cache bus is 64-bits which kills some load times
With it's 128KB of L1 cache the Athlon has always been much less dependant on the L2 cache when compared to the P4. Sure, a 128-bit wide L2 cache bus might help a bit, but it's going to make a big difference most of the time, given the chips design. The latency isn't really bad either. Again, lower latency would help a bit, but not much. Both AMD and Intel need to trade off speed for cost in their designs, but since their chips are VERY different they often end up requiring different trade-offs.
The only way to get a 3IPC then is if previously decoded instructions stall and one of the three schedulers is free.
Yeah, and we hardly ever see x86 instructions stall in a 10 stage pipeline... Ohh wait, that happens damn near all the time!
They still have a six cycle multiply [I dunno if they can make this faster...] for the ALU. Even if they dropped this to 4 it would rock.
I don't know the multiply latency of the Athlon off-hand, but the Athlon64 and Opteron have 3-cycle latency in 32-bit mode and 5-cycle latency in 64-bit mode. Of course, instruction latency usually isn't that big of a deal with an out-of-order processor like the Athlon or Pentium4. It's a damn good thing that it isn't for the P4 though, because it has a HUGE latency on integer multiplies (or at least it did until the new Prescott P4s).
They still don't have good idle support [e.g. Barton 3000+ always runs at 2.1Ghz regardless of what it is doing], etc..
At this time, the Athlon64 is the ONLY desktop processor that I'm aware of that runs at different speeds while idle. Intel's P4 doesn't, IBM's PPC 970 (aka Apple G5) doesn't, Sun's UltraSparcs don't, Alphas don't, Itaniumss don't. Before AMD brought their "Cool 'n Quiet" to the desktop this was an almost unheard of solution outside of laptops. I saw "almost" because AMD actually DID implement this technology with some of their desktop AthlonXP chips, but they were only sold in south-east Asia, and mostly just as a test-market kind of thing.
As I'm sure you know, this technology originated in laptops. In fact, not just any laptops, it originated in AMD laptops! AMD is the one that STARTED this whole thing of having the chips run at different speeds while idle as comapred to when they're running full-out (err, actually it was probably started in some embedded chips, but I'm talking about main-stream consumer-grade CPUs here). The K6-2+ was the first chip to support "PowerNow!" as AMD called it. Intel followed up a bit later with "SpeedStep", and then Transmeta came along later still with their "Longrun" technology. In short, dynamic processor speeds is an area where AMD clearly IS being innovative, first in laptops and now on the desktop.
While I hate the P4 pipeline they have kept a huge cache bus
That is true. As mentioned above, the P4 is more dependant on it's L2 cache than the AthlonXP or Athlon64 are, so it's not suprising that the P4 has a 256-bit wide L2 cache bus running at full core clock speed.
their cpus can scale nicely in terms of heat, etc
Not with the Prescott revision of the P4. At 3.2GHz they're already consuming over 100W of power.
[re: you can remove the heatsink of a P4]
Sure, as long as you don't mind your computer freezing up. You can NOT run a P4 without a
Re:Congrats by Anonymous Coward · 2004-02-16 09:10 · Score: 0

Actually, based on what I've been reading, the IBM 970FX is capable of something they call PowerSlewing. I'm no engineer, but it comes across to me as a power stepping implementation that runs all the time.

It's what's inside those brand new Apple Xserve G5s, too. There's no clear indication of whether or not they actually take advantage of the capability, or if it would derade performance in a server implementation.

Take it for what it's worth.
Re:Congrats by dcam · 2004-02-16 10:07 · Score: 1

No, but it is good engineering.

I learnt early on that there are two approaches to making changes (whether coding or in my training, mechanical engineering). One says throw everything out and rebuild. The other says extend and work what we have now.

The second option, while it isn't as pretty and leaves with the nasty hacks of the past, is the best way forward 90% of the time.

--
meh
Re:Congrats by True+Grit · 2004-02-16 13:05 · Score: 1

Arggh! Somebody please mod the parent up!

I knew the previous post was wrong about the AMD CPU idling. An Athlon64 will go anywhere from 10% over rated clock speed (10% overclock - rated clock on the 3000+ and 3200+ is 2Ghz) down to 800Mhz (less than half of normal speed). If you use a motherboard with the right support, like an MSI K8Txxx "Neo", CPU speed can be automatically controlled by the motherboard based on current load. Not bad for a *desktop* PC.
Re:Congrats by True+Grit · 2004-02-16 13:42 · Score: 1
1. Wake me up when they have a wide memory bus, flat 64bit archetecture with a low voltage CPU. This is where innovation is going
Is it really? For which market? The Itanium is so expensive it hasn't and probably never will make it to the desktop. For the *desktop* CPU, where is the innovation happening? Intel keeps speeding up their CPUs, for sure, but how about adding registers, adding bigger cache, dynamic clock speed control? AMD does that in their AMD64 architecture, and by the way, AMD64 isn't a "copy" of IA32 as you imply, otherwise their CPU would have the same performance as Intel's chips at the same clock speed. The fact a 2Ghz Athlon64 performs roughly as well as a 3Ghz P4 tells me that AMD has been doing a little bit of innovating with Intel's original design. And why in the world didn't Intel add new general-purpose registers to IA32 in the last 10 years or so? I still remember the RISC folks making fun of our measly 8 registers (and early on most of them were special-purpose, not general-purpose), yet we had to wait for a *competitor* to Intel to bump them up to a whopping 16! So let me get this straight: AMD improved the CPU core to the point they get Intel-like performance at a much lower clock speed, they doubled the number of gp and math registers, bigger L1 and L2 cache (except for the P4EE's L1, IIRC), dynamic, motherboard-based CPU clock control, and it costs about *half* the price of a Xeon, and you're telling me this isn't innovation?

Finally, Intel's idea for the desktop future never took off. The Itanium is still so expensive its only used in servers. AMD's idea for the desktop future (AMD64) is here, now, getting good reviews, and at about $250 a pop, is seriously undercutting Intel's P4 pricing, and now we hear that AMD64 is about to be adopted by Intel! And you claim Intel is still doing the innovating?!?

Look, even if you never buy an AMD chip in your life, you should still thank them for keeping that fire under Intel's backside nice and warm. If AMD wasn't in the picture, how long would desktop users have to wait for affordable 64 bit CPUs?
Re:Congrats by Via_Patrino · 2004-02-16 16:27 · Score: 1

Not to get picky but the AthlonXP and Athon are essentially the same core

IIRC AthlonXP has pre-fetch, Athlon doesn't
Re:Congrats by jp10558 · 2004-02-16 17:43 · Score: 1

I've had 2 CPU fan's fail on AMD AthlonXP cpu's (oddly enough both in my sister's computer - and within a month of each other). I've never had the heatsink itself fall off though. The fan failing did not damage the chip - though the computer would lock up totally in about 5 min of run time. We did get it to run by opening the window and blowing 20 degree farenheit air at it with big fans so my sis could finish a paper(in her parka lol) I offered to let her use my computer which worked fine and was in the next room, but she wouldn't ...

--
Opera, Proxomitron-Grypen,GPG 0x0A1C6EE3
Re:Congrats by dave420-2 · 2004-02-16 23:26 · Score: 0

The lack of thermal diodes is due to bad physical design, the maths error was a logical flaw. The P4s can do maths fine now, but you can still use an athlon to cook your dinner :-P
Re:Congrats by Slugworth01 · 2004-02-17 11:09 · Score: 1

You make a good point, I agree with you on this issue.
However, when you think about it, is there any difference in a semiconductor between a logic flaw and a bad physical design? They're both instantiations of the photolith masks by the time the chips are actually being made. Granted - in the end, the P4 math error could be fixed in software, while the overlooked thermal diode in the deisgn has no real fix other than a measure of care.

Re:hmm. by Anonymous Coward · 2004-02-16 00:49 · Score: 0

Wow, you think so?

Re:32 bit only access 4MB of RAM at a time????? by 0mni · 2004-02-16 00:49 · Score: 1

Well it all really depends how long "at a time" last, if its a millisecond between each swap of data it may well be 4MB, on the other hand if its a second it could be 4GB. Could someone elaborate on this somewhat?

In related news by Anonymous Coward · 2004-02-16 00:51 · Score: 5, Interesting

AMD has made deep cuts in their CPU prices, probably pre-emptively.

Re:hmm. by Anonymous Coward · 2004-02-16 00:51 · Score: 0

I assume you're right. That seems to be what I've read in the past. And if it is, then it's a dubious reason for big sales differences. I'd love to have just 1Gig of RAM, but for the last two years or so RAM prices have more or less sucked. If I could get a Gig for fifty bucks, this might be a factor. But with a mere Gig running at over a hundred bucks, more than four Gigs is kinda off the map.

AMD HEAT PROBLEM by Anonymous Coward · 2004-02-16 00:51 · Score: 1, Informative

The heating problem with AMD processors is a BIG MYTH! It' is simple not TRUE. I can attest to this.

3 of my 4 computers at home, run on AMD processors. My File Server runs on an AMD K6-2+ 500Mhz and Win2000 Pro, and has never flickered. Never crashed. Never hot. After 4yrs of faithful service. I keep it on most of the time... all day, all night...

I just retired my Original AMD Athlon 800 slot A workstation. I bought this when they first came out... and believe me, it is still good to go. I has never failed me... for the last 4yrs...

My next box will definately be an AMD OPTERON. If i'm paying for a computer, I like to know that I am getting the most performance for my money... and that the product is simply RIGID and VERY STURDY... and that is AMD.

You can't go wrong with AMD.

Re:AMD HEAT PROBLEM by dave-tx · 2004-02-16 01:02 · Score: 5, Interesting

The K6-II+ and K6-III+ are fantastic processors for low-heat applications, because they were intended to be used in notebooks. I ran my email/web/firewall on a K6-III+, overclocked to 550MHz, for years. It was cool, quiet, and so freakin' stable that I would reboot it every couple of months just for kicks.
On the other hand, I had a dual Athlon-MP machine that was like an oven. Really nice computer, but it had to go, because it made my computer room too hot.
I, too, am looking forward to an Opteron-based system in the future. As a former AMD employee, they'll always have my financial support as long as they continue to produce innovative products.

--
>> "What would the robut do? Frame someone!"
Re:AMD HEAT PROBLEM by rale,+the · 2004-02-16 01:14 · Score: 3, Informative

I just finished a game of UT2K4 on my Athlon64 3000 (2000mhz, currently overclocked to 2150mhz). Processor temp reads a cool 34.6'C - and thats air-cooled. Compare that to the new Prescott P4's that are setting records for hottest running cpu's... The Athlon64 is an amazing piece of hardware.
Re:AMD HEAT PROBLEM by mech_knight · 2004-02-17 11:00 · Score: 1

I still have a K6-2 450 MHz which I bought in 1999 for my main home computer. I use it as a file server and I agree that it's very stable. I leave it on all the time and it never ever needs rebooting --except of course after I've installed the latest Windows updates...

--
"Size matters not. Look at me. Judge me by my size, do you?" --Yoda {whips out green light saber}

The metric system can only simplify things so much by MukiMuki · 2004-02-16 00:51 · Score: 5, Funny

In other news, the DVD consortium has finally approved a standard of blue ray disc drive, which allows optical media to break DVD's 18 megabyte barrier, finally allowing for movies times exceeding 10 seconds.

Re:32 bit only access 4MB of RAM at a time????? by CdBee · 2004-02-16 00:51 · Score: 1, Funny

"4mb ought to be enough for anybody!" Bill Gates, c. 1993 ? (/humour)

--
I have been a user for about 10 years. This ends Feb 2014. The site's been ruined. I'm off. Dice, FU

AMD have been better than Intel for some time... by mu-sly · 2004-02-16 00:52 · Score: 5, Insightful

...however, it's not about better products, it's about mindshare of the buyers.

I've been building PCs for quite a few years now, and have nearly always used and recommended AMD processors over Intel. In my opinion, AMDs cost less, often outperform their Intel equivalents, and lead the way when it comes to new innovations.

I guess the reason they don't have a bigger market share is because a lot of the OEM companies only sell Intel, and because Joe Public only knows about MHz as a measure of speed.

--
Organic free-range music... yum!

Re:Yeah ! AMD64 rulez ! Now if the could just... by Barbarian · 2004-02-16 00:52 · Score: 4, Insightful

You know the reason for the product differentiation they have chosen is based on what is most likely to fail in fabrication--so for example if some of the HT links are bad, you can turn them off and call it an Athlon 64.

AC/DC by Anonymous Coward · 2004-02-16 00:53 · Score: 1, Funny

This just in, AMD also has cat's eyes, and possibly nine lives.
-Stu

or they could give them away for free... by Anonymous Coward · 2004-02-16 00:54 · Score: 1, Insightful

curious that you would critisize AMD's pricing structure in the context of an article reporting that AMD had finally returned to the black.

Re:hmm. by nazh · 2004-02-16 00:54 · Score: 1

Dunno, like I read the article. ;)

Re:hmm. by Anonymous Coward · 2004-02-16 00:54 · Score: 1, Informative

No, it should be (for newer Pentiums at least) be 64GB.

Main Reason for profitability by MadX · 2004-02-16 00:54 · Score: 5, Insightful

As long as they have a product that their rivals cannot compete with, they can keep the prices at a premium.
Hence, until such time as Intel release a competitive product, AMD can enjoy high profit margins.
This will change once Intel do release their competitive product though.

BTW: As was said in the article, the other arm of AMD's fabrication was also responsible for their profits ie: flash memory for cellphones. It's only because they have a majority stake in the joint venture with fujitsu, that they are able to declare the income as part of their overall turnover.

Re:32 bit only access 4MB of RAM at a time????? by TrancePhreak · 2004-02-16 00:55 · Score: 0, Troll

--

-]Phreak Out[-

Irony by Killjoy_NL · 2004-02-16 00:57 · Score: 5, Funny

"and Intel releasing chips mimicking the 32/64-bit behaviour of the Opteron"

Does anybody else see the irony in this ?

--
This is the sig that says NI (again)

Re:Irony by Anonymous Coward · 2004-02-16 01:02 · Score: 0

"and Intel releasing chips mimicking the 32/64-bit behaviour of the Opteron"

Does anybody else see the irony in this ?
Yeah, Opterons are big iron alright!

Does AMD have anything to compete with Centrino? by skreet · 2004-02-16 00:57 · Score: 2, Insightful

Just ran a centrino sys. the other day. This thing started-up just like a calculator should. In about a nanosecond it booted and was ready to run. Multiple apps. open on the fly in the same manner. I had about 15 major memory intensive programs open at one time and this chip handled everything. Also, someone told me that the new AMD chipsets have a default lockout to prevent over-clocking? Has anyone heard anything about this?

--
www.linuxfree.net Quality linux distributions on cd/dvd

Wow by Anonymous Coward · 2004-02-16 00:57 · Score: 0

That a pretty impressive figure. It must be an immensely reliable production proccess then.
Must be pushing the envelope quite a bit.

I don't think intel has to worry. by SmallFurryCreature · 2004-02-16 01:00 · Score: 4, Interesting

I am currently installing gentoo on a dual opteron server as well as a 1u celeron machine that will contain backups. No suprise that there is a performance difference but the gap is gigantic. Same with better specced dual P3 and P4 machines. Even the dual Xeon P4 is left behind easily.

HOWEVER, the dual opteron contains an intel raid and soon an intel network card. And I must say that installing the pentiums in the past was an awfull lot easier.

Price/performance opteron is currently the clear winner, its giganctic cache and better memory structure heads above the same price Xeons. As far as support and quality of the hardware goes. Intel all the way. Sadly for intel the bubble has burst and web companies cannot afford the Itanium. So Opteron it is.

But AMD has been on top before and they always managed to screw up. Intel screws up to but somehow manages to keep making money during the down times. AMD is not so lucky.

--

MMO Quests are like orgasms:

You may solo them, I prefer them in a group.

Re:I don't think intel has to worry. by Anonymous Coward · 2004-02-16 01:17 · Score: 1, Interesting

Curious to know how you've concluded such a performance disparity between the various machines strictly through installing. Do you honestly believe the speed of the processor controls the install process?
Re:I don't think intel has to worry. by dreamchaser · 2004-02-16 01:20 · Score: 3, Insightful

For Gentoo it does, since everything is compiled during install. I'd expect AMD's to do better here since they generally exectue integer code faster.
Re:I don't think intel has to worry. by Anonymous Coward · 2004-02-16 05:49 · Score: 0

You don't really think luck has anything to do with it do you? $9B cash reserves to fund R&D and manufacturing expansion during downturns, Captive Fab capacity adequate to cover 90% of the potential martket during upturns, and 80,000 engieneers and technicians to make it all happen. Yes, and a pile of marketers to make sure that Intel builds the stuff the people with money actually want.
Re:I don't think intel has to worry. by GSloop · 2004-02-16 06:16 · Score: 1

But AMD has been on top before and they always managed to screw up. Intel screws up to but somehow manages to keep making money during the down times. AMD is not so lucky

AMD? How about Intel!
P3 1.13Ghz
Pretty miserable P4 performance early on.
Rambus/RIMM, thus no Mainboards for early P4's that would use decent price memory.
bad ACTH translator hubs resulting in huge costs from recalls etc.
Total confusion on the chipset market till recently (last 2 years or so)

Intel, if it had the reserves and market share/sales etc of AMD would have imploded and turned into dust a long time ago!

AMD isn't doing so fabulously itself, but Intel seems to be most capable of pointing a very large gun at its head and pulling the trigger repeatedly!

Cheers,
Greg

Re:hmm. by Anonymous Coward · 2004-02-16 01:00 · Score: 0

To the original poster:

Good troll! You got a lot of biters.

To everyone else:

You have been trolled, suckers!! Haha!

Re:AMD have been better than Intel for some time.. by auric_dude · 2004-02-16 01:02 · Score: 1, Insightful

I suppose that Joe public recogonise big brandnames like Microsoft and Intel and this will hold sway their purchasing habits. The "Intel Inside" advertising efforts did reach a lot of people, I just can't seem to remember and AMD reaching out to as many with their advertising spend. If you are buying on technical grounds then you are correct but how many of Joe public think like you?

Re:Yeah ! AMD64 rulez ! Now if the could just... by da'covale · 2004-02-16 01:03 · Score: 1

On the same note, would they please stop calling one model 2600 and another 3000+, even though there's only a difference of 0.03 GHz (2.13 -> 2.16)
It's fooling customers.

--
da'covale d'Rie Bolmdahl

Re:hmm. by Anonymous Coward · 2004-02-16 01:04 · Score: 0

Are you foreign?

Also, please stop winking and smiling at me. It's turning me on a bit too much. Thanks.

The reason you don't want socket 940 by ColourlessGreenIdeas · 2004-02-16 01:06 · Score: 5, Informative

Socket 940 arranges the pins so that it's easy to lay out multiprocessor systems with a 6 layer motherboard (expensive, but you'll want it in a server anyway for reliability reasons). Sockey 939 (real soon now) will work with 4-layer motherboards and so will result in cheaper systems. Both the Athalon 64 and Athalon FX will soon be socket 939, differentiated by the ammount of cache. Opteron will remain as it is, as otherwise your 4 and 8 way boxes won't work. Given that Opteron 8xx is absurdly cheap compared to any other 64 bit 8-way server, I can't see why AMD would want to lower prices.

--
In soviet russia stale jokes recycle you!

Re:The reason you don't want socket 940 by Anonymous Coward · 2004-02-16 01:56 · Score: 0

> Both the Athalon 64 and Athalon FX will soon be socket 939...

What the hell is an "Athalon"? And don't tell me it's a typo, you made the same mistake twice in the same sentence...
Re:The reason you don't want socket 940 by Anonymous Coward · 2004-02-16 02:45 · Score: 0

You sound as if by removing one pin, the board layout becomes so much easier that they can do with almost half the number of layers....
Re:The reason you don't want socket 940 by Brane2 · 2004-02-16 03:11 · Score: 1

I thought that whole difference between S939 and S949 was that one pin that is needed for 8xx. After looking at pinout, there seems no reason for rearrangements. HTs get premiere position at the edges, convieninently arranged so they can be routed without fuss and everything else seems to be adapted to this.

I really don't see the issue of having extra 2 layers on board. Since NorthBridge is in the CPU, that should outweight the price difference of the board.

Besides, when one pays quite a price for Opteron, why should extra few bucks for more layers in board make such a difference ?

IMHO no board should have less than 6 layers anyway. Server MBs need them for stability and overclocker MBs need them for speed...
Re:The reason you don't want socket 940 by Paul+Rutland · 2004-02-16 03:29 · Score: 1

As I understand it the 939 pinouts have a memory channel on either side of the socket while the 940 pinout has both memory channels on one side. 940 is better if you want 2 or 4 sockets on a motherboard. 939 is better if you only have one socket.
Re:The reason you don't want socket 940 by Hoser+McMoose · 2004-02-16 06:38 · Score: 1

Socket 939 has really no relation at all to socket 940. AMD did did not just remove 1 pin, they completely redesigned the socket, it's only by sheer co-incidence that they ended up being nearly identical in terms of pin-count (ok, maybe not sheer coincidence, they needed to use a socket that is physically the same size).

The socket has been re-layed out for a different purpose, so yet it WILL be so much easier to design boards that you can do it with almost half the number of layers. On the flip-side though, it won't be possible to use more than one processor with this socket type.
Re:The reason you don't want socket 940 by Viceice · 2004-02-16 06:40 · Score: 1

First time i ever hear the Opteron 8xx labled "absurdly cheap" :)

--
Sometimes I wish I was a plumber, then I'd know how to deal with other people's shit.
Re:The reason you don't want socket 940 by Chris+Burke · 2004-02-16 12:30 · Score: 1

I thought that whole difference between S939 and S949 was that one pin that is needed for 8xx. After looking at pinout, there seems no reason for rearrangements. HTs get premiere position at the edges, convieninently arranged so they can be routed without fuss and everything else seems to be adapted to this.

The problem is the DRAM channels.

Notice how all S940 processors require buffered memory. Granted, in a server you would want buffered memory anyway, but for the Athlon FX this is a big problem. An FX-based workstation/gaming rig actually does worse than A64 on some things, due to the increased memory latency. The reason for this requirement is that the signal integrity of the DDR channels is simply not good enough to support non-buffered DIMMS. So, they are making S939 which will optimize the DRAM channel pinouts, allowing unbuffered DIMMS and finally making the FX chips the top performers they should be.

Sounds like a good reason to re-do the pinout, no?

I really don't see the issue of having extra 2 layers on board. Since NorthBridge is in the CPU, that should outweight the price difference of the board.

But why settle for no change in cost when you can go to a 4-layer board and have a net decrease in cost? You cannot underestimate how cost-conscious motherboard makers can be.

Besides, when one pays quite a price for Opteron, why should extra few bucks for more layers in board make such a difference ?

It's not, yet. But consider how the price of the lower-end FX chips will drop between now and the introduction of S939-based motherboards. Being able to fit an FX-based system into the upper-mid level market segments will be a good thing.

Also, I think AMD is planning to eventually EOL the 734-pin package, and put all K8-based chips in S939. I'm sure system builders would be very happy about that (er, at least once they forget about the R&D cost of making the S734 boards...). If I'm right, then the ability to make 4-layer boards will be absolutely crucial once A64 works its way into the segments currently occupied by Barton/Thoroughbred.

IMHO no board should have less than 6 layers anyway. Server MBs need them for stability and overclocker MBs need them for speed...

If you're not an overclocker, or running a server, then the savings for a 4 layer board are worth it, IMO. Regardless, the motherboard makers are demanding it, and thusly AMD will deliver.

--

The enemies of Democracy are

Re:AMD have been better than Intel for some time.. by dave420-2 · 2004-02-16 01:09 · Score: 0, Insightful

They don't have a bigger marketshare because even though the chips perform well, their construction hasn't (in the past) been up to that of Intel. Take, for example, the cooling required for AMD chips. Compare it to that of their pentium equivalents. When said cooling falls off (or stops working) - the pentiums don't burst into flames. That's the difference - higher manufacturing quality.

AMD did a great thing - they've pushed CPU development and innovation forward, but let's not pretend they're something they're not. They make cheap chips that run just as well as the intel equivalents. Just like how a souped-up Honda Civic can go just as fast as an Aston Martin... That said, I know which one I'd prefer to drive ;)

Carma whore by da'covale · 2004-02-16 01:09 · Score: 1

The "Mod parent up!" comment by AC-ploy is "#""#!!! Links like that in the sig isn't good.

--
da'covale d'Rie Bolmdahl

No. by Anonymous Coward · 2004-02-16 01:14 · Score: 1, Informative

Irony, as in an "incongruity between the actual result of a sequence of events and the normal or expected result"? I see no irony in that all.

As far as I know, this claim is premature as well. Intel is clearly preparing itself to respond to 64 bit x86 when it feels compelled to but that hasn't happened yet. If and when it does, it will not be "ironic".

Re:No. by Anonymous Coward · 2004-02-16 05:50 · Score: 1, Insightful

I'll explain the joke for you, just in case you really didn't get it and aren't just another pompous, pedantic windbag:

AMD started out as a manufacturer of Intel clones. The expected result of this sequence of events is: Intel makes a new chip, and AMD clones it. The actual result is shaping up to be: AMD makes a new chip, and Intel is scrambling to clone it.

AMD back in black... by Markos · 2004-02-16 01:15 · Score: 0, Flamebait

Today AMD has achieved something that their processors have been able to do, quite easily, for quite a while now. Don't belive me? Take off the heatsink and find out.

*RIMSHOT*

I'm not a hater though. My thunderbird is serving as a space heater; keeping me warm on those cold Canadian nights.

Cheers AMD!

Re:hmm. by Anonymous Coward · 2004-02-16 01:19 · Score: 0

Actually that would be quite flattering.

this isn't exactly correct.... by leehwtsohg · 2004-02-16 01:22 · Score: 1, Insightful

The right statement would be that in order to make a profit, the percentage of duds have to be equal or less to those that your competition makes.
A rate of 10% failure can not raise the price of the chips by more than 10%.

Re:this isn't exactly correct.... by croddy · 2004-02-16 01:32 · Score: 2, Insightful

...unless your competitor spends gazillions of dollars on advertising.
Re:this isn't exactly correct.... by Slugworth01 · 2004-02-16 03:01 · Score: 5, Informative

Neither statement is exactly correct. The economics of semiconductor manufacturing are pretty complex. You typically have a certain set of variables to work with. You can invest in line yield, process quality, new processes, automation, capacity, marketing, new device design, retooling, and any number of other areas. You can build cheaper, less complex fabs, build in locations with cheaper labor rates or lower startup costs. You can outsource some or all your manufacturing to a foundry who can make your designs for a contracted price.
AMD has an approach that says they will "build smarter" than their competition. Their flagship fabs (Fab 30 in Dresden, for example) are highly automated with very tight process control, ensuring the right work gets done at the right time. The focus is on equipment utilization; reduction of tool idle time. Further, they focus on minimizing the number of non-product wafers in the line, which take tool time but don't directly produce any chips that can be sold. The management of all this is done through software.
They also have to focus on fab uptime ... since they don't necessarily have the back up manufacturing capability to allow them to recover if their fab is down. For example, AMD makes about two-thirds their revenue from processor sales according to a recent 10-Q filing. Most recent quarter for which there is data (for the period ending 12/28/2003) shows $1,205M in quarterly revenue. You can estimate around $800M in revenue from their processor lines. Fab 30 make nearly all their processors. If Fab 30 were to go down for one hour, that's one hour in the 730 hours in a quarter that they can't make chips. If they have demand that is greater than or equal to capacity, and they're running at full capacity, they would loose roughly $1M due to potential finished goods that could not be made. A cost of $1M per hour of fab down time is pretty typical in the market where AMD competes and for fabs that compare to Fab 30.
A single tool going down is a problem. The entire fab going down is a huge problem. Things that can bring an entire fab down include utilities (electricity, water, gasses, etc.) contamination of facility-wide services like vacuum line, DI water, and various gasses, labor strikes, natural disasters, fires, and plant-wide software.
When you rely on software to manage your manufacturing to the degree that AMD and other high-end semiconductor manufacturers do, you tend to pay a lot of attention to the software.
Re:this isn't exactly correct.... by nelsonal · 2004-02-16 03:53 · Score: 1

Good points, but AMD's revenue mix is just over 50/50 processors (580 million) to flash (560 million) revenue in the last quarter. On the operating profit side, processors turned positive for the first time in several quarters in Sept. While flash has had small operating losses over the past year, they have been more moderate than the huge losses processors racked up from about mid 2002. The joint venture with Fujitsu (or Toshiba) should result in considerable cost savings for both companies.
One other point is that almost all of the cost in semicondutor manufacturing is fixed, AMD's processors begin to break even at about 2 billion/yr (anything over that usually brings between 60%-80% in incremental profit margins).

--
Degaussing scares the bad magnetism out of the monitor and fills it with good karma.
Re:this isn't exactly correct.... by Slugworth01 · 2004-02-16 06:40 · Score: 1

The 10-Q I used was for the period ending June 29, 2003, so yeah, the numbers might be off. memory products revenue going from $211M to $560M is a huge quarterly jump, and might account for their profitable bottom line more so than processors. Still $800K in lost revenue for an hour of fab downtime is huge, you can't make it up; it's not so easy crank up the factory to make more chips to cover for the loss when you're running at capacity. In reality, AMD has outsourcing agreemtns that could ehlp mitigate this, but even foundries have finite capacity that might not be available when you need it.
And you're right about the fixed costs. Operations budgets for fabs are tiny when compared to the capital costs to build the plant in the first place. In classic fab economics you only have a fixed amount of time to recover your capital investment before a fab is obsolete. If all goes well, you recover the capital investment before you have to replace the fab to keep up with your competition. Typically this cycle is 3 to 6 years, depending on the market in which you are competing.
Re:this isn't exactly correct.... by Anonymous Coward · 2004-02-16 07:44 · Score: 0

The entire fab going down is a huge problem. Things that can bring an entire fab down include utilities (electricity, water, gasses, etc.) contamination of facility-wide services like vacuum line, DI water, and various gasses, labor strikes, natural disasters, fires, and plant-wide software.

You're telling me. For the short time I worked at MSAI in Durham, NC (before it shut down for good), half of all that stuff in your list happened.

Re:AMD have been better than Intel for some time.. by Anonymous Coward · 2004-02-16 01:25 · Score: 1, Insightful

How so? The AMD chip is more versatile, more nimble; meanwhile, all the intel does is go fast in a straight line. The P4's pipelines just keep getting longer to facillitate higher clock speeds (to keep pace with AMD, as it were), as opposed to AMD who puts out a new design that focuses more on efficiency per clock and adds something completely new to the CPU market. So you can take your souped up ricer chip, I'll stick with the chip that actually has some engineering and innovation.

Re:AMD have been better than Intel for some time.. by madprof · 2004-02-16 01:25 · Score: 1

Except they don't.

Re:AMD have been better than Intel for some time.. by Associate · 2004-02-16 01:26 · Score: 1

And we all know someone who has a render farm in their basement.

--
Someone hates these cans.

4 megs... by Spacejock · 2004-02-16 01:28 · Score: 1

I wrote them about the 4 megs/gigs error the day their article came out. Must be real busy over there.

--
Hal Spacejock: Science Fiction with Nuts

Re:AMD have been better than Intel for some time.. by dave420-2 · 2004-02-16 01:30 · Score: 5, Funny

Using terms like "versatile" and "nimble" to describe a CPU makes me slightly wary of the rest of your point ;) What's next, "majestic" RAM? "enigmatic" GPUs? :-P

Re:LOL by Anonymous Coward · 2004-02-16 01:31 · Score: 1, Funny

Reminds me of the days when my Commodore ran on 0.064 megs of ram that cost me 0.6k

Re:AMD have been better than Intel for some time.. by Haeleth · 2004-02-16 01:35 · Score: 2, Interesting

Bob renderfarm knows low clocked P4's out render high clocked AMD's.

Figures, please. Assertions like that without any evidence to support them are what we normally call "trolls".

A Centrino system is nothing special... by cnelzie · 2004-02-16 01:37 · Score: 3, Informative

...all you need to slap 'Centrino' onto a laptop is the following...

A Pentium IV Mobility Processor

A Particular Intel Mainboard Chipset

Intel's WiFi Internal Card

I also believe that it needs a certain Graphics processor, also from Intel.

The 'Centrino' label is nothing spectacular. It is just another marketing line that 'creates' a new Intel Line without really engineering a whole new line. The whole 'Centrino' line is a marketing thing to get people excited about mobile computing and is designed to get people out and buying laptop computers. It gives people a sense of having 'teh' best laptop, even if they really don't have the best laptop.

Really, which would you rather have...

An HP Laptop with a Mobil Pentium IV, Wireless Access and a 3D Graphics Chip?

or...

An HP Laptop Equipped with Centrino Technology?

They are both basically the same thing, one just has a shorter 'catchy' name attached to it, nothing more, nothing less.

--
If you ignore the other uses of a tool, does that make the tool less useful, or you less useful?

Re:A Centrino system is nothing special... by Anonymous Coward · 2004-02-16 01:57 · Score: 0

Centrinos have a pentium M, not p4 mobility. Huge difference in clock-for-clock performance and power consumption.
Re:A Centrino system is nothing special... by phrasebook · 2004-02-16 01:59 · Score: 1

Pentium IV Mobility Processor

To be pedantic, I think the term for it is just 'Pentium M'. The Pentium 4 Mobile is the version with speeds around 2-2.2 GHz, and most of those systems get about 2.5-3 hours battery life.

I swapped my Thinkpad R32 (P4-M 1.6) to a R50 (P-M 1.4) and the battery life is about 4.5 hours. So if that is due to the new Pentium, it's pretty good for me.

I also believe that it needs a certain Graphics processor, also from Intel.

Nah I think you can use others, mine has an ATI Radeon 7500 but I've got 'Centrino' plastered all over it.

What the parent was saying about starting up like a calculator, though, is rubbish.
Re:A Centrino system is nothing special... by Anonymous Coward · 2004-02-16 02:07 · Score: 0

You can NOT have a Centrino system with a Pentium 4M processor. A centrino system includes:

A Pentium-M cpu
The intel 855PM or 855GM chipset
and the intel wireless chipset

You need all three to have it be centrino.
Re:A Centrino system is nothing special... by Anonymous Coward · 2004-02-16 02:12 · Score: 0

oh and dont forget that 32% premium thats in the pricetag too!
Re:A Centrino system is nothing special... by Anonymous Coward · 2004-02-16 02:44 · Score: 0

And soon they will upgrade to a 64% premium. Er... wait...
Re:A Centrino system is nothing special... by Umbriel · 2004-02-16 08:34 · Score: 1

The processor of a Centrino laptop is NOT a Pentium 4 Mobility, it's a Pentium M that is nearer a Pentium 3 with enhanced processing capabilities at the same time as very low power comsumption. In fact at the same MHz is quite faster than a Pentium 4, yet my laptop can reach 6 hours of battery.

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 01:37 · Score: 4, Insightful

Overall system/platform stability also matters a lot.

In my experience (repairing computers at a 'white box' shop), AMD has still way more 'oddball' problems with it's chipsets and motherboards.

If you build an Intel box, generally it Just Works. If you build an AMD AthlonXP box, it generally probably works, if you are lucky and you are using just the right brand of memory.

Part of the problem is the HAREBRAINED idea of AMD; 'we are not a chipset company'. They gave keys to their kingdom to VIA, and VIA promptly keeps churning out crap. Only the latest chipsets (KT400A etc) are in my opinion any good, and even there you can find big differences with the quality of the implementation between mobo makers.

Granted - motherboard and chipset maturity seems MUCH better with Athlon64 and Opteron, but I've seen too few systems so far to be sure if the status quo is maintaned when Athlon64 goes mainstream and motherboards get cheaper.

But in any case - if I'd have to build a new high-end gaming rig today, I'd still choose Intel, even with the penalty of higher price. I agree that _right now_ is a stupid time to do so, as AMD is rapidly moving to 940pin, while Intel is going to the new 775(?) pin thingy. So basically everything out there today will be obsolete within 6 months. Of course this doesn't really differ from the norm in reality, but at least you can *hope* that if you go for the first 940pin Athlon64 board, it might be upgradeable with just a CPU swap down the road. No such luck for 745 pin mobos.

I really hope Athlon64 motherboard stability and quality is better in the long run than with AthlonXP.

My amps go up to 11 !!!! by gelfling · 2004-02-16 01:39 · Score: 3, Insightful

That would be one than 10, wouldn't it?

No, actually it should be 4 gibibytes... by blorg · 2004-02-16 01:39 · Score: 2, Informative

shouldn't that be 4 gigabyte ;)

...Seriously, I wasn't paying attention and until I saw this post thought that the SI vs IEC prefix thing was the reason for the (sic) in the story. Talk about missing the wood for the trees ;-)

(-1, Pedantic)

Re:No, actually it should be 4 gibibytes... by Anonymous Coward · 2004-02-16 01:58 · Score: 1, Interesting

I was reading Slashdot for the first time to figure out what it is all about and for a novice you have to agree that it might get a trifle confusing when a discussion starts off on an incorrect note. I do not know what (sic) means and as I come up to speed with Slashdot lingo and accepted levels of casualness of this community I am sure I can get the joke better.

Re:hmm. by Anonymous Coward · 2004-02-16 01:40 · Score: 0

Thats confirmed it, Slashdot is now officially "News for idiots who managed to click on a link, Stuff that would matter if only you could understand it"

Seriously, you would assume they mean 4Gb, and seems to be what you read in the past? It's common fucking sense and basic computer science. They teach this sort of stuff in higher level High School maths classes!

Oh good lord, I give up. Say "Hi!" to AOL support next time you call them.

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 01:41 · Score: 1

... and I obiviously meant that AMD is rapidly moving to the new *939* pin setup... 939.. 940... bah humbug.. :)

Re:AMD have been better than Intel for some time.. by Anonymous Coward · 2004-02-16 01:43 · Score: 0

Now that would be the software recompliled using intel compiling software suing SSE3/2/MMX?

Mod parent up! by Anonymous Coward · 2004-02-16 01:44 · Score: 1, Funny

The "Mod parent up!" comment by AC-ploy is "#""#!!! Links like that in the sig isn't good.

Yeah, but it's easy to tell it's a fake - everyone knows that February 30 isn't a Monday.

Do the math... by sultanoslack · 2004-02-16 01:44 · Score: 3, Informative

2^32 bit = 4294967296 bytes of address space

Converting to gigabytes...

4294967296 / 1024 = 4194304 (kb)
419304 / 1024 = 4096 (mb)
4096 / 1024 = 4 (gb)

Of course there's a much easier way of doing that by figuring out that 1024 = 2^10, so you could just do:

2^32 / 2^10 / 2^10 / 2^10 = 2^(32 - 30) = 2^2 = 4

You can't address more than 4 GB of virtual memory with a 32 bit address. So regardless of how much memory you can afford that means that you can't have more than 4 GB of physical memory plus swap. Even then you typically allocate at least 1 GB of address space to the kernel leaving you with 3 GB of addressable space for applications. Now add up your swap and physical memory and you realize that we're getting pretty close to that limit on newer desktops.

Re:Do the math... by Dr.+Evil · 2004-02-16 02:05 · Score: 3, Informative

Sort-of. There are four more addressing lines giving you up to 64GB, internally, the kernel can address up to 64TB virtual memory with segment/offset stuff, and of course the 64GB physical memory.
It's similar to the 8088/8086 with a 16 bit cpu, and 1MB of addressable RAM.
Time to dust off the far pointers!
http://www.prism.gatech.edu/~gte213x/LinuxMM/rpt.h tml
Re:Do the math... by timjdot · 2004-02-16 04:41 · Score: 1

The Linux Kernel for one takes up far less than 1GB. The "spare" room in the Kernel space is given over to caching functions.

--
Expect Freedom.
Re:Do the math... by ca1v1n · 2004-02-16 05:16 · Score: 1

Virtual memory spaces are specific to processes. The significance of the 4GB memory barrier is that while I can have a 64 GB RAM, 128 GB swap box running 48 processes that each use 4 GB, I can't have any one process that uses that much.

There are advantages to having a large virtual memory space even on a machine without so much RAM. I recall a recent benchmark that showed 64-bit binaries took a slight performance hit, except with applications like MySQL that address memory spaces far larger than the amount of memory they actually allocate, because it saves index lookups on large data sets.

I expect techniques like that will become more popular as 64-bit computers become more prevalent. We're not anywhere close to actually implementing memory systems that large. IIRC, the G5's MMU is only designed for 48-bit physical memory spaces. A 2^64-byte memory bank would have mass on the order of a kilogram times the number of atoms in each transistor, to say nothing of the power consumption.

--
WARNING: there is a trojan on your
Re:Do the math... by Anonymous Coward · 2004-02-16 05:35 · Score: 0

You can't address more than 4 GB of virtual memory with a 32 bit address. So regardless of how much memory you can afford that means that you can't have more than 4 GB of physical memory plus swap.

Yeah, but that's per task and (with ia32 at least) per segment.

Granted, it would be hard to use "per task" with physical memory unless you have some sort of hardware paging (seg regs should work, if you're not using them elsewhere), but you can easily use different swap space.

And for those places where you really need more than 4GB in a single task, segmentation is a horrible solution.

closing arguments... by twoslice · 2004-02-16 01:47 · Score: 1

This is probably AMD's make-or-break year. I hope they make it. For all Intel's wondrous abilities, it's nice to see a two-horse race.

are also fitting if one replaces AMD with Linux and Microsoft where it says Intel...

--

From excellent karma to terible karma with a single +5 funny post...

Honda -vs- Aston Martin by Anonymous Coward · 2004-02-16 01:51 · Score: 0

That's a good analogy. Because it shows you're just concerned about brands image. For a performance enthusiast, it's not the name but rather the soup that goes into the souping up that matters.

AMD Athlon Processor Build & Installation Guid by Futurepower(R) · 2004-02-16 01:56 · Score: 5, Informative

Haven't seen any problem with AMD processors. It's necessary to follow the Cooling Guidelines, of course.

Make sure you have a good power supply. We use KingWin 350 Watt supplies that have two fans. (Ignore the language, "Extreme Series". That's there just to appeal to gamers, who expect every product to include some reference to violence or games. There is nothing extreme about them, and they are reasonably priced.)

Note that power supply manufacturers sell power supplies that have 100 Watts more rated power for sometimes close to twice the price. That's to take advantage of the "more is better" people.

Re:LOL by Anonymous Coward · 2004-02-16 01:56 · Score: 1, Funny

There is a fighting version of the G5?!? Fantastic! (duel)

Re:Yeah ! AMD64 rulez ! Now if the could just... by Fweeky · 2004-02-16 01:56 · Score: 2, Insightful

Performance isn't just a factor of clockrate. The latest Barton chips have twice as much cache as previous models, so they typically perform better than older models at the same clockrate. That's the entire point of the rating system!

There's an AC/DC joke in here somewhere... by drfishy · 2004-02-16 01:57 · Score: 1, Offtopic

Check the lyrics, they're rather fitting... I'll just post the whole thing since I'm not funny enough to edit it well... AC/DC Back in Black (1980) Back In Black Back in black I hit the sack I've been too long I'm glad to be back Yes, I'm let loose From the noose That's kept me hanging about I've been looking at the sky 'Cause it's gettin' me high Forget the hearse 'cause I never die I got nine lives Cat's eyes Abusin' every one of them and running wild CHORUS: 'Cause I'm back Yes, I'm back Well, I'm back Yes, I'm back Well, I'm back, back I'm back in black Yes, I'm back in black Back in the back Of a Cadillac Number one with a bullet, I'm a power pack I'm in a bang With a gang They've got to catch me if they want me to hang Cause I'm back on the track And I'm beatin' the flack Nobody's gonna get me on another rap So look at me now I'm just makin' my play Don't try to push your luck, just get out of my way

Re:There's an AC/DC joke in here somewhere... by Darth23 · 2004-02-16 03:52 · Score: 1

From this crowd I expected altered lyrics to fit the topic. Off Topic, I always thought Back in Black would make a great Rap song. The original is barely sung, ans the whole attitude of the lyrics sounds like they're straight from the boastful 'G' side of hip-hop.

--
-------- In Soviet Russia, "Soviet Russia" sigs hate Slashdot.

Re:AMD have been better than Intel for some time.. by Anonymous Coward · 2004-02-16 02:02 · Score: 0

Just like how a souped-up Honda Civic can go just as fast as an Aston Martin... That said, I know which one I'd prefer to drive ;)

Meaning you and every other small dicked individual will choose the Aston Martin. Every level headed individual who has better things to judge people on than the car they drive will probably choose the Civic. If you replace Aston Martin with Intel and Civic with AMD the metaphor works just as well :)

Glad to see it by n00b_101 · 2004-02-16 02:05 · Score: 1

I for one am glad to see this news. As an amd reseller I have dealt with their customer service department and IMO they are one of the best in the biz. A great company, they make a great product, they should be profitable. Contracting with IBM may well be one of the best decisions they made and probably contributed to this news.

Re:AMD have been better than Intel for some time.. by vanillacoke · 2004-02-16 02:08 · Score: 1

And that is why i turned my back on the CRAP that is VIA and embraced NVIDIA (chipsets, not videocards).

Emphasis is added by everyone burned by shitty via chipsets.

--
The secret to getting modded up is to allways say i've got karma to burn in your sig..

Thanks for your constructive comment. by Futurepower(R) · 2004-02-16 02:11 · Score: 1

Mod parent up.

Thanks for your constructive comment. I get tired of reading hostile, immature, "I'm better than you" comments like some of those posted before yours. Not everyone can know everything, especially about computers.

Back In Black ... by Anonymous Coward · 2004-02-16 02:12 · Score: 0

Cranking up some AC/DC right now!

Re:Back In Black ... by MrPink2U · 2004-02-16 05:19 · Score: 1

The devil's kept me hangin' around!

Re:AMD have been better than Intel for some time.. by Shadow99_1 · 2004-02-16 02:13 · Score: 1

You mean burst into flames like this?:
http://reviews.zdnet.co.uk/hardware/proces sorsmemo ry/0,39024015,39145079-2,00.htm

Even back then I had my 1.33 Ghz Athlon (first gen socket A, which is when this load of crap started) cpu fan die and it ran on just the heatsink for quite awhile before I noticed... In fact if games hadn't kept locking up after a short time I would probably never have noticed...

--
we are all invisible unless we choose otherwise

There are a lot of people like you. by Futurepower(R) · 2004-02-16 02:14 · Score: 1

Good point. There are a lot of people like you, and they are welcome to Slashdot. Ignore those with an anger problem.

Re:Pentium-M by Slack3r78 · 2004-02-16 02:15 · Score: 2, Insightful

The Pentium M and the P-4 Mobile actually have little in common. The Pentium M is much closer to a PIII in design, borrowing some elements of the P4 such as SSE2 support, adding in some power saving functions of its own, and adding a ton of cache. Clock-for-clock the Pentium M eats the P4 alive, and it's really a shame that we'll probably never see a desktop version of this chip made available as Intel has invested far too much marketing money into the ridiculous scaling of the MHz with the P4.

No - it's the physical memory that's key. by Anonymous Coward · 2004-02-16 02:16 · Score: 2, Informative

64 bit processors are good because they can easily adress more than 4GB virtual memory.

NO!

The bottleneck on all modern [isolated, not networked] computer systems, which dwarfs all other bottlenecks, is precisely virtual memory. Calls to the hardrive are many, many orders of magnitude slower than calls to any other system.

Now while it's generally true that you can't have more than 2^32 bytes of total [physical + virtual] memory on a 32-bit machine, 64-bit machines are faster than 32-bit machines precisely because they allow for more than 4GB of true, physical memory.

Calls to virtual memory are so slow that you can practically beat them by hand - if, for instance, you have a big database of phone numbers and addresses, so big that it bleeds over into virtual memory, then you can just about find a phone number by hand from The Real Yellow Pages themselves faster than your computer can retrieve it for you from virtual memory.

A 64-bit platform with less than or equal to 4GB of physical memory is utterly worthless: As you yourself have pointed out, it's almost certainly slower than an equivalent 32-bit system.

Re:No - it's the physical memory that's key. by Hoser+McMoose · 2004-02-16 06:32 · Score: 1

No, the previous poster was right, the issue is virtual memory.

You can easily hack more than 4GB of physical memory onto a 32-bit processor, just increase it's address lines, this much isn't even that ugly of a hack (more on that later) and shouldn't hurt performance much. The problem is that you still only get 2 or 3GB of virtual address space (1 or 2GB reserved for the OS). Even if all that space is in physical memory it's still limited to just that much space.

There are some REALLY ugly hacks that let you use more than 3GB of virtual address space on 32-bit processors though, and THATS where things get messy. This gets back into the same sort of segmentation mess that we had back in the 16-bit DOS days, and it's just UGLY! Even when it doesn't hurt your performance by too much, it's still an unnecessary mess that will drive up development and testing costs.

'sic' Latin for 'thus' - indicates error in quote by blorg · 2004-02-16 02:17 · Score: 4, Informative

Dictionary.com. It is used when quoting, to indicate that the transcriber has faithfully reproduced a possible mistake in the source. This is because it is considered bad form to modify a quote, at least without indication through square parantheses, which are generally used for explanatory additions due to loss of context, not corrections. And if 'sic' wasn't put in, it would likely look like an error on the transcriber's part. It's certainly not a /. thing ;-)

Re:AMD have been better than Intel for some time.. by grondu · 2004-02-16 02:17 · Score: 4, Informative

Yeah, that Prescott is a cool running chip.

--

I'm the urban spaceman babe, but here comes the twist... I don't exist

Re:LOL by Vargasan · 2004-02-16 02:19 · Score: 1

Yes, duel processor. It's kind of like "Dueling Banjos", only it's for nerds.

--
Putting the romance back into necromancer.

Re:LOL by 10Ghz · 2004-02-16 02:24 · Score: 1

G5 does not have L3-cache. And besides, it was just a typo, no need to cream your pants because of it.

--
Lesbian Nazi Hookers Abducted by UFOs and Forced Into Weight Loss Programs - -all next week on Town Talk.

Re:32 bit only access 4MB of RAM at a time????? by LA_Samurai · 2004-02-16 02:26 · Score: 1

Actually, Sir Bill said 640 KB was enough for anybody--this was back in the days of DOS somewhere around late 80's.

--
They die so well...

You cannot have an external fire. by Futurepower(R) · 2004-02-16 02:26 · Score: 1

No matter what happens inside your computer (that has a metal case), you cannot have an external fire.

Even with serious component burning, you do not get a fire, because of fire-retardant materials. The smoke smells horrible, of course.

At present, AMD and Intel processors are about equal in power use. With a proper heat sink, they will both last for years, with no problems.

Re:You cannot have an external fire. by dave420-2 · 2004-02-16 02:42 · Score: 1

It's very possible to have an external fire in a case. Sure, everything's fireproofed, but all it takes is something hotter than normal to come out of the case. Cases are riddled with ventilation, and also plastic. If some of that plastic melted and caught fire, it could feasibly run out of the box and cause a fire.
Power supply fires are pretty cool. They have more magic smoke than most components :-P
The thing about AMD chips is, they don't know when they're running ridiculously hot, as that video on Toms Hardware showed. With the cooling removed. a P4 slows down and runs as fast as it can without being too hot. The AMD simply doesn't realise, and promptly bursts into flames.
Re:You cannot have an external fire. by ckaminski · 2004-02-16 03:54 · Score: 1

That video is over two years old. You think AMD hasn't gotten around to putting on a simple thermal diode?
Re:You cannot have an external fire. by dave420-2 · 2004-02-16 23:32 · Score: 0

It wasn't just the thermal diode. It's the whole system of slowing the processor down to acceptable levels.
Oh, and the AMD chips do have thermal diodes, they're just not quick enough to tell when the cooling's failing. I think they sample the temperature every second or so, which is long enough to let the magic smoke run wild

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 02:28 · Score: 1

Sadly Nvidia came *very* late to the AthlonXP party, and the first nForce was overpriced piece of shit. nForce2 is quite ok, but even it is very picky with the memory modules - especially in dual channel configurations.

Which results in lots of unneccessary fiddling and tweaking to hunt down the culprit in a misbehaving AthlonXP setup. With Intel, It Just Works. When you people get bit older, you are willing to pay couple of hundred extra for a system that Just Works, while still retaining the benefits of a homebuilt system (expandability, knowledge that none of the components suck... the things that make overpriced brand name setups blow chunks)

Another note: by Futurepower(R) · 2004-02-16 02:30 · Score: 1

Another note: We just had the power supply in our voicemail computer go out. It had been running continuously for 13 years. It burned extensively, but was certainly not a fire risk.

Re:AMD have been better than Intel for some time.. by Shadow99_1 · 2004-02-16 02:33 · Score: 1

Maybe it's just because I see so many systems that just don't work in my job, but I wouldn't pay more for Intel... They don't "Just work" anymore than Athlon's do...

--
we are all invisible unless we choose otherwise

640K by flafish · 2004-02-16 02:35 · Score: 1

Not according to this: excerpt.

AMD should make chipsets. by Futurepower(R) · 2004-02-16 02:38 · Score: 1

I agree. It's crazy that AMD does not make their own chipsets.

Old news! by CTho9305 · 2004-02-16 02:38 · Score: 2, Informative

This was announced on January 20th.

--
My server

Re:Yeah ! AMD64 rulez ! Now if the could just... by CTho9305 · 2004-02-16 02:40 · Score: 1

This is especially good, when you look at Pentium 4 processors with Northwood cores vs Prescott cores - at the same clock speeds, the Prescott is generally slower, but you don't see that in just the GHz.

--
My server

Re:Pentium-M by LankyBoycie · 2004-02-16 02:42 · Score: 1

The Pentium-M does indeed sound like a great chip but you are wrong in one respect - there is going to be a desktop centrino. See the inquirer Also you can already get desktop Pentium M/Centrino thingies for use in embedded systems, they're a bit pricey though.

Re:AMD have been better than Intel for some time.. by Glock27 · 2004-02-16 02:49 · Score: 5, Informative

They don't have a bigger marketshare because even though the chips perform well, their construction hasn't (in the past) been up to that of Intel. Take, for example, the cooling required for AMD chips. Compare it to that of their pentium equivalents. When said cooling falls off (or stops working) - the pentiums don't burst into flames. That's the difference - higher manufacturing quality.

Modded +5 Insightful? Now that shows the weakness of the Slashdot moderation system...

Athlon, Athlon 64 and Opteron all have thermal protection, just like the P4s...and have had it for some time.

Further, current P4s dissipate more power than the AMD solutions, due to high clockspeeds that don't equate to better performance except for a slight edge in multimedia codec performance.

In short, at this point AMD is flat out better - and a much better deal to boot. You can pick up an Athlon 64 3000+ for about $210...that's a steal!

--
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait

Burst into flames by dpilot · 2004-02-16 02:53 · Score: 3, Insightful

Bursting into flames has everything to do with one specific feature, and nothing to do with overall design quality. Specifically, the Pentia you're talking about has a fast-acting, sensitive temperature sensor connected to clock-throttling circuitry. When the chip gets too hot, the clocking is cut back to reduce power. FWIU, AMD has merely an on-chip temperature sensing diode.

AMD would do well to pick up Intel's design on this feature, but I'll bet it's patented.

But it is a single, specific feature. Other than that it's a very nice feature to have, it says *nothing* about other measures of quality in either CPU.

If you want to talk about other measures of quality, ask which CPU just plain runs well with today's compiler output, and which CPU requires new compiler generations in order to get decent performance.

--
The living have better things to do than to continue hating the dead.

Re:Burst into flames by Anonymous Coward · 2004-02-16 03:45 · Score: 0

Athlon 64 and Opteron have that feature. It is very simple to implement.

There are software programs that do the same thing with older Athlons.
Re:Burst into flames by Anonymous Coward · 2004-02-16 06:57 · Score: 0

i believe athlons have had this feature since the thunderbird.. prior to thunderbird was when you had athlons "bursting into flames"

Re:AMD have been better than Intel for some time.. by Jonathan+Platt · 2004-02-16 02:54 · Score: 2, Insightful

I think it's the other way:

The souped up cars are for the dudes with somthing to make up for, while the Aston Martin, a relatively unflashy car, is for people who like luxury and/or prestigue. AM's are a great example of enginreering master peices.

The AM is a plain Lian-Li case with a solid system underneith, while the souped up Honda, is a stock IBM with heaps of mods and neon lights. While the AM is more expencive it is a much more solid, and valuble car, also from a logical point of view, it will have a much longer life and a comparitively much higher re-sale value.

--

VENI, VIDI, VICI, DIXI

Re:AMD have been better than Intel for some time.. by Jonathan+Platt · 2004-02-16 02:56 · Score: 1

Unless you install a rocket in the back of the Honda it will never break the 4 seccond mark. Plus the AM will be much nicer to drive, and and have a much higher top speed.

Now I dont compleatly disagree with your argmuent, but the analogy was a bad one.

--

VENI, VIDI, VICI, DIXI

Re:AMD have been better than Intel for some time.. by Jeff+DeMaagd · 2004-02-16 02:57 · Score: 1

I've stuck with Intel because of the IMO Athlon's poorer heatsink mounting mechanism and the exposed core. I've known people that cracked a core trying to mount the heatsink.

IMO, it wasn't until the A64 line when AMD really could compete well against Intel on performance, before then it was mostly just price.

Also, too many of the Athlon chipsets had IMO poor PCI implementations, particularly at busmastering. AMD's own chipsets were better at this, I have a few pieces of hardware that required workarounds for Via and SIS compatibility. Even if the performance lagged, I'd prefer Intel's or AMD's chipsets rather than other chips that might be incompatible with boards I might buy in the future.

Megabytes (sic) ? by FuzzyBad-Mofo · 2004-02-16 02:58 · Score: 1

There's nothing wrong with that spelling . Maybe Mr. XaXXon prefers the obnoxious Mebibytes?

Re:Megabytes (sic) ? by Alex_Ionescu · 2004-02-16 03:27 · Score: 1

Sic means it was a mistake in the article. It's GIGAbytes. Not Megabytes.
Re:Megabytes (sic) ? by mrscorpio · 2004-02-16 03:33 · Score: 1

Nothing wrong with the spelling, everything wrong with the terminology use.

Chris
Re:Megabytes (sic) ? by FuzzyBad-Mofo · 2004-02-16 03:41 · Score: 1

Thanks, it wasn't clear from the context what the mistake was. My fault for only skimming the article, I guess. :)
Re:Megabytes (sic) ? by Anonymous Coward · 2004-02-16 04:36 · Score: 0

SIC = Spelt In- Correctly. So O.P. was correct in saying it was spelt incorrectly, however wrong the meaning was technically.
Re:Megabytes (sic) ? by toggleflipflop · 2004-02-16 05:22 · Score: 1

Where do you get that "SIC = Spelt In- Correctly" idea? "sic": Latin: thus; so (not a mistake and is to be read as it stands)
Re:Megabytes (sic) ? by multipartmixed · 2004-02-16 07:01 · Score: 1

> OPEN15,8,15,"N0:XYZZY,04":CLOSE15

Oh, man, I typed that in and formatted my Zork floppy! ;)

--

Do daemons dream of electric sleep()?
Re:Megabytes (sic) ? by FuzzyBad-Mofo · 2004-02-16 07:29 · Score: 1

Tragic! But at least you can get another copy. ;)

4 megabytes? by Mr+Pippin · 2004-02-16 03:00 · Score: 1, Redundant

I assume you meant 4 gigabytes. A 32-bit address space is limited to 4gig, not 4meg.

Re:hmm. by DarkDust · 2004-02-16 03:04 · Score: 2, Interesting

4 megabytes (sic) of memory at a time

shouldn't that be 4 gigabyte ;)

Actually, the 4 megabytes is correct: x86 processors handles memory in pages. They normally are 4kB in size (thanks to the 8086 or propably even the 8080). The Pentium then introduced an extension called Page Size Extension (PSE, see /proc/cpuinfo if that flag is present ;-). The PSE allows the use of 4 megabyte pages. And the processor can only access one page at a time, which makes the original statement correct... more or less ;-)

I would help .... by Ozric · 2004-02-16 03:06 · Score: 1

When socket 939 comes out with PCI-X. I will help them by buying some nuw CPU's. So it look like they can count on my money in March.

Mod the parent up! by axxackall · 2004-02-16 03:11 · Score: 1

I cannot believe the parent is not modded up as informative yet AND no one else noticed such a huge typo.

--

Less is more !

Re:Mod the parent up! by Anonymous Coward · 2004-02-16 03:31 · Score: 0

There's no point in modding the parent up for not RTFA + short synopsis. It clearly says megabytes(sic) which means it's a spelling error in the article. Article which, by the way, came out on the 20th of January, so I doubt they will change it now.
Re:Mod the parent up! by Skater · 2004-02-16 03:59 · Score: 1

Everyone noticed it. That's why there's a "(sic)" after the word "megabytes" in the article summary...

--RJ
Re:Mod the parent up! by axxackall · 2004-02-16 05:06 · Score: 1

what is "(sic)"?

--

Less is more !
Re:Mod the parent up! by HTH+NE1 · 2004-02-16 05:40 · Score: 1

Do people not know about dictionary.com?
sic adv. (sik)

Thus; so. Used to indicate that a quoted passage, especially one containing an error or unconventional spelling, has been retained in its original form or written intentionally.

[Latin sic. See so- in Indo-European Roots.]

Source: The American Heritage(R) Dictionary of the English Language, Fourth Edition
Copyright (C) 2000 by Houghton Mifflin Company.
Published by Houghton Mifflin Company. All rights reserved.
Note it is not an abbreviation for "Spelt In-Correctly" nor "Seen In Copy".

Much like people think "Re:" is an abbreviation for "in REference to" when it too is a Latin word merely meaning "in reference to" and thus should not be translated into regional equivalents like "Aw:" as certain Microsoft software did (does?) causing some modicum of havoc in Usenet.

--
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?

So... by MoneyT · 2004-02-16 03:13 · Score: 1

Does having been in teh red these past few years make them beleaguered yet?

--
T Money
World Domination with a plastic spoon since 1984

Re:AMD Athlon Processor Build & Installation G by Anonymous Coward · 2004-02-16 03:13 · Score: 0

Are you trying to sell these things or something?

Where's Opteron 250, 450, 850? by 4of12 · 2004-02-16 03:26 · Score: 1

Every buyer likes prices cuts. Me, too.

But I was hoping to see a little more information about availability of the next performance jump of the Opteron to 2.40 GHz, apart from this old rumour.

It's "early 2004". I'm ready to buy a dual Opteron, but I want the best performance I can get.

--
"Provided by the management for your protection."

Oh no. by Carl+T · 2004-02-16 03:37 · Score: 3, Informative

Virtual memory is not the same thing as swapped out memory.
There are a couple of points here:

Even a 32-bit machine may have more than 4 GB of physical RAM, just as a 16-bit machine may have more than 64 kB. It's just that it cannot be mapped into a single block of virtual memory, so without ugly workarounds there's no way a process can address more than 4 GB.
It's not uncommon to (for various reasons) allocate more memory than needed, and never touch part of it. These allocations don't consume physical memory, but they dos count towards the 4 GB virtual memory limit for the process. Since the kernel must be able to produce the memory when asked for it, the amount of available swap space may decrease, but that doesn't mean that anything is actually written to the swap.

--

This signature is not in the public domain.

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 03:38 · Score: 1

Well, I'd say we sell roughly 70% AMD and 30% Intel (whitebox builder, small company, 80%+ to consumers, built out of OEM components at the back room).

Out of the computers that return for a repair under warranty due to failures in the mobo-cpu-memory, 95%+ is AMD. Last time I had to swap out a motherboard for an Intel setup is *weeks* ago. Last time I saw 'dead out of the box' Intel CPU is *months* ago. Heck, if you get a dead Intel box, you can be almost certain that the videocard or the PSU is bust (or it's just a stupid user error and there is no hardware failure)

Now I do admit that it's a rare case when AMD *cpu* is faulty. Almost as rare as with Intel, if we count out the selfbuilt setups with broken AMD CPU cores due to stupid builder error. However, AMD *motherboards* (VIA, nVidia, SIS) ... I get to RMA dozens every month.

Re:hmm. by TheLink · 2004-02-16 03:51 · Score: 1

It's kinda funny actually. While AMD is trying to push a potential future for the x86, Intel is going back to their past - the way the P4s are kludged to address 64GB reminds me a lot of the 8088, 80*86 segment addressing and similar crap. Or the Apple II bank switching stuff.

Don't forget expanded memory and the good old EMM386 stuff.

--

Too many replies beneath your current threshold

Re:AMD Athlon Processor Build & Installation G by drakaan · 2004-02-16 04:07 · Score: 1

Note that power supply manufacturers sell power supplies that have 100 Watts more rated power for sometimes close to twice the price. That's to take advantage of the "more is better" people.

Or, maybe they make them for those people that have more than 4 hard drives/CD-ROM's/DVD-RW's in their system...try running a decent (say 5 SCSI drives) RAID-5 setup on that 350W P/S, and see how fast you run out of juice, nevermind molex connectors.

--
"Murphy was an optimist" - O'Toole's commentary on Murphy's Law

0.70 - 3.50? wrong. by Anonymous Coward · 2004-02-16 04:18 · Score: 0

http://finance.yahoo.com/q/bc?s=TMTA&t=1y

that's the last YEAR...

Re:32 bit only access 4MB of RAM at a time????? by CdBee · 2004-02-16 04:19 · Score: 1

lol, actually I knew that, I was hoping that by putting a wrong date in there people would realise that I was updating his comment for the Windows 3.1 era

--
I have been a user for about 10 years. This ends Feb 2014. The site's been ruined. I'm off. Dice, FU

Yeah, but these are hacks. by Anonymous Coward · 2004-02-16 04:23 · Score: 0

It's just that it cannot be mapped into a single block of virtual memory, so without ugly workarounds there's no way a process can address more than 4 GB.

Right, I understand that there are hacks, like Intel's so-called 36-bit extensions of 32-bit platforms.

But these are hacks. Serious people don't base enterprise solutions on hacks.

Besides, at this point we're arguing semantics. If by "virtual memory" you mean "a hack," then we're talking about two different things. Most people, however, use "virtually memory" to mean precisely "swapped memory."

Re:AMD have been better than Intel for some time.. by gratefully+dead · 2004-02-16 04:29 · Score: 1

I answer your FUD from my (Athlon) workstation at AMD...

Actually, this "feature" that Intel has installed on their chips allows the P4 to run as fast as it can until it heats up to a certain temperature, then the clock is scaled back. As a result, unless you have optimum cooling (unlikely), you are not getting the best performance out of your computer.

AMD chose to design the Athlon to run at optimum speed under normal conditions. That is why they (we) have a thermal design guide for the heatsink. There is nothing lower quality about this solution. Furthermore, I believe that with Athlon 64, Intel is now the one trying to create equivalents...

Re:AMD have been better than Intel for some time.. by Darren+Winsper · 2004-02-16 04:34 · Score: 1

Err...AMD were destroying Intel back when the Athlon first came out. They beat Intel to 1GHz and Intel never really recovered until Northwood came out.

Re:Profitable (WTF?!?!?!) by hackstraw · 2004-02-16 04:44 · Score: 3, Informative

I don't know what bothers me more. People stating their uninformed opinion as fact, or people actually buying it and modding it up.

They make their profit on Xeons, where until recently they have had no competition.

Huh? Intel is the largest manufacturere of CPUs in the world. They have had a net income of about $1b per quarter for the last 4 quarters, they have $16b in the bank. Thier stock has remained pretty stable (aside from the .bomb inflation), etc.

Being that were I work (a university) and there are THOUSANDS of p3, p4, etc chips and way less than 100 zeons, if they are making all of their profits on those 100 chips that only cost a few dollars more than the other thousands of chips.... Whatever, obviously your wrong.

Take a look at what they're doing - they're going after Xeon - and trying to get a piece of the profit in a market that's consistent with their fab capacity.

They are going after the HPC market, because that is the only market for cheap 64bit CPUs. You don't need a 1.457THz 128bit processor to check passwords on your domain. Sorry all of you Windows admins, being a domain controller is not that big of a deal.

Crunching numbers across 20 processors for 5 days at a time is a big deal. Being able to do that in 2.5 days is a real big deal. Not being able to do that because you can't address more than 4Gigs of memory at a time is a show stopper.

Think before you mod people.

Re:Go GENTOO by GoneGaryT · 2004-02-16 04:45 · Score: 1

Well funny you should say that, as the only 64-bit 2.6 kernel offering from Gentoo that I can find is experimental and they don't seem to be recommending 2.4 kernel 64-bit compiles.

I have 2.6.2 x86_64 compiled and running in SuSE 9 AMD64, the full works; I run the Gentoo exp 2.6 AMD64 as well, but there's not a lot there yet.

So your comment could do with fleshing out in detail a little, that's all.

Re:hmm. by timjdot · 2004-02-16 04:46 · Score: 1

I can't believe those dunces at the U. taught me it was 128 bytes at a time!!! I knew that instruction re-ordering was B.S.

--
Expect Freedom.

Re:AMD Athlon Processor Build & Installation G by toddestan · 2004-02-16 04:46 · Score: 1

Note that power supply manufacturers sell power supplies that have 100 Watts more rated power for sometimes close to twice the price. That's to take advantage of the "more is better" people.

If you run a power supply at near capacity, it will run hot, noiser (if it has variable fan speed, which many supplies do now), and likely have a shorter life, than if you had used a higher capacity power supply. Though granted, for a typical computer (1 CPU, 1-2 HDD's, 1-2 optical drives) 350W is more than plenty.

Re:AMD have been better than Intel for some time.. by Loki_1929 · 2004-02-16 04:54 · Score: 2, Informative

"Take, for example, the cooling required for AMD chips. Compare it to that of their pentium equivalents. When said cooling falls off (or stops working) - the pentiums don't burst into flames."

Wow, another TomBot, I see. Listen, reading dumbed-down consumer grade articles from a propaganda rag like Tom's makes you neither smart, nor informed. First of all, the problem was NOT with the AMD CPUs, but rather with the mainboard's non-spec design. Had the manufacturer designed the board to AMD's specifications, this would not have been a problem at all. The computer would have locked up, just like the Pentium 3 did. Why does it act like a Pentium 3? Because the K7 came out about the same time the P3 did. AMD's board specs called for specific thermal protection circutry on the board itself to help protect the board and the CPU. Arguably, AMD should have put all the thermal protection circutry inside the CPU itself, but the fact remains that Tom's took a board that was not built correctly, and used it to make an example out of AMD. In journalism, the technical term for doing this is, "bullshit".

Secondly, the chances of a heatsink falling off are virtually nil. Your statement is the equivelent of saying, "When the radiator falls off my Chevy, it still works semi ok - not like those Fords". Yeah, I sure do hate it when the radiator falls off my car. Happens what, 'bout once a week at least?

"their construction hasn't (in the past) been up to that of Intel." .. "That's the difference - higher manufacturing quality." ... "They make cheap [quality] chips"

This just shows your complete lack of knowledge of the CPU industry's past. Or perhaps you're actually 10-second Tom from 50 First Dates, and you've forgotten all the many, many problems and recalls Intel has had over the years. That being said, I don't remember a single recall of AMD's Athlon chips. Let's see if I can remind you of Intel's shady past, shall we? Go read this from last year. I actually did my homework before opening my mouth - as opposed to reading some sellout's online rag (Tom's).

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

Athlon! ATHLON! Only one "A." by Anonymous Coward · 2004-02-16 04:57 · Score: 0

Why is is so difficult? Sheesh.

Re:AMD have been better than Intel for some time.. by Cecil · 2004-02-16 05:01 · Score: 1

I've been building AMD systems since the Athlon 700MHz was top-of-the-line. And when I say "systems", I'm talking around 15.

And I've never had a memory problem, or indeed any problem that could be blamed on AMD, except for running too hot due to the cheap, crappy heatsinks/thermal pads that come with AMD CPUs. The few problems that I have had have been solved, without exception, by moving from a cheapass OEM 300W powersupply to an Antec 380W.

--
Random and weird software I've written.

Wrong. by Jahf · 2004-02-16 05:12 · Score: 2, Insightful

Even with "mega" corrected to be "giga", the statement 'can't take advantage of more than 4 megabytes (sic) of memory at a time.' is a fallacy.

Ever since the Pentium Pro the Intel line has been capable of 64GB of RAM due to it's 36bit memory path.

Can you make use of over 4GB without some ugly extensions that are reminiscent of using 2MB on a 286? No. Is that anywhere near the memory capacity of a 64bit path? No. Do either of those problems justify continuing the false statements about 4GB memory limits? No.

the 4GB limitation is as much a problem with the OS (in other words, without paging tricks you -are- limited to 4GB of RAM per process, but that's not a function of the CPU it is a programming item).

I'm all for Opterons and Athlons, but if they are superior tech, then they shouldn't need falsehoods to win, especially when the real truth is -almost- as bad as the FUD.

--
It is more productive to voice thoughtful opinions (reply) than to judge (moderate) others.

Upgrading is Dead by Vagary · 2004-02-16 05:12 · Score: 1

It's so cute that people still believe they'll be able to upgrade their processor. Just reading the front-page of /. right now, not only are CPU sockets changing rapidly, but so are video card slots. You're also unlikely to be able to use your slow RAM after any upgrade and even power supplies are rapidly increasing in wattage.

Storage devices are just about the only thing that motherboards maintain backwards compatibility with. So sure you can use your old HD and case after you upgrade every other component!

Re:Upgrading is Dead by Jarnis · 2004-02-16 05:55 · Score: 1

And storage devices are moving over to Serial-ATA...

I know very well that in *reality* you most likely will have to buy a new mobo next time you upgrade anyway. Doesn't take the sting out of buying a motherboard you _already know_ will never ever take faster than 3700+ Athlon64, as it's designed to become obsolete in less than 6 months.

Also the upgrade cycles differ. You might upgrade once in 2-3 years, in which case you get to buy new motherboard anyways. I personally upgarde once a year or so, and right now I'm looking at Athlon 64 with a simple problem;

If I buy right now (3200+ or 3400+ if I feel rich), I know full well that in one year I cannot upgrade without swapping the mobo once again.

If I buy in 6 months, getting the very first 939pin mobo + whatever CPU is 'fastest' at that point (3600+? something like that), I might be able to stick 4500-5000+ CPU in an year later without swapping the motherboard. Yeah, most likely I swap the motherboard anyway, but it's still not *certain* :)

And yeah, PCI-E throws it's own wrench in. I know full well my next videocard is PCI-E one (I currently have Radeon 9800 Pro), and that dictates my next motherboard/CPU upgrade - whoever puts the first stable and fast PCI-E-compatible platform after the first juicy super-fast PCI-E vidcard is released :)

I might consider getting a motherboard with both AGP and PCI Express-16 slots, and upgrade the videocard later, but in any case since I'm waiting due to PCI-E anyway, Athlon 64 with 754pins is even *worse* deal when considering the future :)

And no, I don't need to upgrade my 465W Enermax PSU just yet... tho I know I'll be pushing the limits when I add my 7th HDD... Of course when I run out, I have the option of just finally retiring the smallest (40GB) drive to get the power consumption back down :) (joys of four IDE connectors + SCSI for the speed-critical OS files...)

Re:AMD have been better than Intel for some time.. by Loki_1929 · 2004-02-16 05:17 · Score: 2, Insightful

"If you build an AMD AthlonXP box, it generally probably works, if you are lucky and you are using just the right brand of memory."

Quit using ECS and no-name memory and you won't have problems. I've been building AMD systems almost exclusively for about 3 years now, and I've had about the same number of AMD and Intel-based computers come back, nearly all for mainboard problems. Trying everything from ECS (crap) to FIC (almost as bad) to MSI, Gigabyte, and finally, Asus, I pretty much have run the gambit on different combinations. I've been using Asus boards exclusively for about a year now, and I haven't had a single one come back for any hardware or driver related problems. It doesn't take expensive memory or an expensive board to make it work - just decent quality stuff. The Asus A7V8X-MX is a good, inexpensive, entry-level board, which works very well with the Kingston value RAM. There's nothing about 'luck', merely doing a little bit of research ahead of time. I had tons and tons of problems with Intel CPUs on ECS boards, which is why I quickly learned my lesson not to trust that cheap garbage ever again. I've had similar problems with Intel brand mainboards, which seem to have quarky memory problems, especially with Rdram.

"If you build an Intel box, generally it Just Works."

This is such an amusing statement to me. It just reminds me of how, with sufficient marketing, you can cover up all the garbage being pushed out the door with little to no real effort. Take a look over here and let me know what you think about Intel 'just works'. How many times does Intel need to recall defective CPUs before you, and those like you, figure out that they're not the clean 'n pretty CPU maker their marketing droids have programmed you to believe they are?

What's next? Microsoft products as the pinnacle of security and stability?

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

Nice to see them doing better. by BoneFlower · 2004-02-16 05:25 · Score: 2, Insightful

AMD. Going from simply fabbing chips for Intel, to making simple clones(cheaper and lower performing than the intels) to dead even performance with their own designs, to actually pushing around the direction of the industry a bit(though not quite as much as intel). Without AMD, computers would probably be much more expensive. Even when they just fabed chips for intel, rather than compete head on like they do now, that got more chips onto the market keeping prices from getting too out of hand. And now with them being a viable competitor, and even leading in some areas(it seems every six months the one with the fastest chip flip flops)... Even Intel fans benefit from AMD forcing Intel to keep prices somewhat reasonable.

If either Intel or AMD slacked on advancing their designs, or decided to get too greedy with pricing, the other would eat them alive. They push each other to put out better products at lower prices, and the consumer wins.

If only the consumer OS market was this competetive. Linux is rapidly rising in the consumer space, so perhaps things will start looking up even there.

Re:Profitable (WTF?!?!?!) by Anonymous Coward · 2004-02-16 05:29 · Score: 0

If you're doing number crunching on 'regular' p4's I pity you. in your own words, doing 20 processors x ~1-2Gig for 5 days stuff like ECC memory is a must (and larger cache/extra stability/multiprocessor systems a nice bonus).

btw, ~2G should be per processor (let aside the fact that 20-way xeons aren't that common) - any sane number-crunching proggie would use 20 processes, each with its own address space - and communicate through something like mpi.

finally, they're NOT going solely after HPC. that's actually what Intel's doing with Itanium - now that's a FP monster aimed squarely at HPC and using it for anything else is a waste of money. There are other things where a hard limit of 2 (say 3 with tweaks, or more and a lot slower with PAE) Gigs per process is a real showstopper - thing (medium-sized) databases. number crunching is not the only game in town - it's just the one that would benefit most from doubling the number of SSE2 registers ;-)

Re: sic by curtoid · 2004-02-16 05:30 · Score: 1

http://en.wikipedia.org/wiki/Sic

"sic" is Latin for "thus" by Ernest · 2004-02-16 05:32 · Score: 1

In context it usualy means "He did it!" (or "they" or whoever). Sometimes used next to a literal quote.

Ouside of official documents (lawmaker lingo), it is often used to demontrate a brown bag oops.

--
Ernest J.W. ter Kuile

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 05:47 · Score: 1

Okay. Tell me which nForce2 boards take in Kingston HyperX memory in dualchannel config without manual 'downtweaking' of memory settings?

I know A7N8X Deluxe/Gold does not.

How bout why the heck does A7N8X Deluxe bork out with CL3 DDR400 Kingston modules? CL2.5 works just fine.

Then tell me why Asus A7600 fails to boot/crashes with numerous memory brands as soon as you stick in 2nd RAM module? Yes, there are brands and types that work, but you have to select the used RAM carefully.

Crappy chipsets with way too finicky memory handling. Pure and simple.

Then lets talk about the gooood old A7V333 and the great design decision of putting surface mounted components right under the plastic 'hooks' of the heatsink. Guess how many (homebuilt) mobos came back with components missing due to user not noticing that you can trash your mobo while installing a heatsink?

And lets not forget the great decision of having ceramic cores without heat spreaders protecting the core. Sure sells more CPUs to stupid end users building the computers. And for the record - I've broken zero AMD cores installing the heatsink (with several thousands installed), but I also get to tell the happy news at least once a week to a stupid user who has broken his CPU core by skipping the Fine Manual (and lacking common sense).

And you just can't deny it - motherboards and chipsets for AMD CPUs are just generally way less robust than ones made for Intel CPUs. Sure, once that AMD system is purring and working fine, there is no difference, but sometimes getting there takes considerable amount of extra work, and there seems to be a lot more faulty motherboards being pushed down the channel with VIA/nVidia/SiS chipsets. Granted - SiS on the intel side also has it's share of Quality Control issues.

AMD should offer it's own chipsets (at a premium) to those who are willing to pay extra for *stability*. With P4, you can pay extra for stability (Intel chipset) or go cheapo and get SiS or VIA. With AMD you either go cheapo with SiS or VIA, or pay extra for few bells and whistles with nVidia. The 'rock stable' option is not there.

Now I admit - most of the problems are not due to AMD *CPU*s. AMD makes fine CPUs. It's just that the whole *platform* of AthlonXP is less robust than comparable Intel setup. Thankfully Athlon64 looks way better so far, but my experiences are too limited to form a solid opinion either way yet. I keep my fingers crossed and hope that the 'massmarket' mobos for Athlon64s will keep the quality up. Of course the fact that the northbridge is on the CPU helps out...

Re:Pentium-M by frank_adrian314159 · 2004-02-16 05:53 · Score: 1

Clock-for-clock the Pentium M eats the P4 alive, and it's really a shame that we'll probably never see a desktop version of this chip made available...

Sorry to dispute this, but I'm happy to let you know that your wishes may come true, as per this story in The Inquirer. Obligatory quote:

CHIP FIRM Intel will this week announce details about a new wave in desktop computing using the Centrino bundle.
The wonder is it didn't do it earlier, we ran a crusade for this.
The chip firm is likely to announce it this week.

And Overclockers.com speculates that the whole thing basically means putting the M into desktops without all of the other Centrino crud.

--
That is all.

Re:Profitable (WTF?!?!?!) by dpilot · 2004-02-16 05:55 · Score: 2, Insightful

I didn't say the other chips weren't profitable. They are. They just aren't *obscenely* profitable. The Xeons aren't 'just a few dollars more', a quick check on pricewatch (for lack of a quickly accessible better source) shows a 3.0GHz P4 at $214 and the Xeon 3.0GHz, 'slow' fsb, for $440.

They make money on your thousands of garden-variety Pentia, but they *mint* money on the hundred Xeons.

As for the HPC market... Yes, AMD is going after that. Opteron is a natural for NUMA. But that wasn't what I said about going after the Xeon market. The HPC market may be spectacular, but it isn't big. The Xeon market may not be spectacular from a computing standpoint, but it is for profits. They can sell into the HPC market as an aside to the Xeon market. Besides, the price gap between X86 and X86-64 isn't anything like the gap between X86 and IA-64. It isn't stupid to buy X86-64 as a fast X86, even if you don't use 64-bitness.

--
The living have better things to do than to continue hating the dead.

Centrino by dpilot · 2004-02-16 05:57 · Score: 1

I'll grant your point on Centrino, and then some. IMHO, Centrino is a big problem for Intel, because it exposes the mess they've made of P4 by chasing clock speed above all else. Clock for clock, watt for watt, Centrino is the best thing Intel makes, and if they didn't watch it, it would take over the X86 server market.

--
The living have better things to do than to continue hating the dead.

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 06:05 · Score: 1

We junked the ECS from our lineup over an year ago. FIC and Gigabyte were dropped in testing before even taken into selection due to total suckage. Currently our lineup is MSI, Asus and AsRock for the penny pinchers. Abit and Epox are provided as options via special order to end users that know what they are doing (or at least claim so) - we usually don't recommend them due to variety of 'funny' probs here and there...

The problem is with the chipsets. Even the 'best' Asus boards (A7V600, A7N8X Deluxe) have their share of problems with *Brand name* modules. Kingston, for example has several different DDR400 modules. Some work, some don't. You need to pick the right ones. Funnily HyperX uber-RAMs are ones that most often have timing issues when running more than one stick.

And note that lots of these memory problems are *not* an issue with 1x512MB. Put that 2nd one in, and you may find out that in order to reach stability, you get to replace even the first one. HAPPY JOY JOY for the end user that bought his setup with one module, and plans to add 2nd later when he finds out he needs 1GB. Those boxes will come and haunt you in about an year when 'normal users' go beyond 512MB...

Due to finnish consumer protection laws, at that point the store I work in would be in deep doodoo. If customer can prove the initial module and/or the motherboard does not work as advertised when he sticks in 2nd module, we get to replace the first module (or the motherboard) for free. So we have to go and test this stuff. Some lowend systems we sell *telling the customer* that due to the (cheaper) parts used, upgrading to 1GB won't probably work. Some agree that it's a fair tradeoff. Most don't.

It's also funny how just about ever Athlon motherboard has 3 ram module connectors. Once you go thru the 'fine print', you find out that the chipset won't work with 3x DDR400 module at full speed. And this is with single-channel VIA chipsets. Guess what a customer *expects* from a motherboard with 3 memory module slots...

Just pure chipset crappiness. AMD should get into chipset business and make a good one at a premium.

Re:AMD have been better than Intel for some time.. by Loki_1929 · 2004-02-16 06:12 · Score: 1

"Once you go thru the 'fine print', you find out that the chipset won't work with 3x DDR400 module at full speed. "

Asus lists exactly what they've tested each board with right on their site. For the low-end offerings, this generally isn't an issue at all. For higher end offerings, simply following the memory guide listed on Asus's page for the particular board yields zero problems, in my experience. The only boards I've had odd timing issues with were the nForce 2 boards. Those absolutely are picky as hell about memory.

By the way, just how much pinching are your penny pinching customers doing that they don't want to pay for a ~$60 board? (Asus A7V8X-MX) Heh.

I agree that it would be nice if AMD got into making their own chipsets and boards, but I also think it would put them back in the red - at least for a while. For the time being, I'm content to simply do a little bit of homework ahead of time to save both time and money getting the best performance per dollar.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

blimey.. what a lot of debate! by snellgrove2 · 2004-02-16 07:06 · Score: 1

lots of arguing here, over a simple thing that we should all be happy with.

all be happy you say? huh?! Yes, all of us should be happy about this because competition is good, in general

and being an AMD user, of late, its good to see them doing well and personally, I think they make 'fab' chips ;)

Re:hmm. by toddestan · 2004-02-16 07:13 · Score: 1

What do you mean Ram prices have sucked? I guess you never spent $350 for an 8MB upgrade at one time. And I know people here have spent much more for less. All my systems have atleast 512MB of ram just because I can.

Eh? by jo42 · 2004-02-16 07:15 · Score: 1

> Back in the Black

Isn't that racist?

My AMD's are in beige (cases)...

Intels 64bit plans. by Xzisted · 2004-02-16 07:19 · Score: 1

Intel will be announcing Yamhill at IDF this week. The funny thing about this subject is that you have a whole lot of people who have no idea what they are talking about posting about facts they cant back up.

I got a look at Intels NDA ppt that they have been handing out to sales folks at different companies (ASUS, Abit, etc.) and it clearly states the areas where they are making money and the markets they are going after. Right now AMD is squarely centered in the $10,000 and under market with the Opteron. This shows that their main market penetration is against the Xeon and the P4. However, this is NOT where their main focus is. The problem with AMD right now is that all the main tier1 manufacturers have not put forward servers that fully support the AMD64 platform. Most of them are 2cpu systems or workstations.

For AMD to clearly move ahead, they need the backing of IBM, Sun, and HP in the 4+ cpu market to really make a dent in Intel or even have a possibility at Itanium. Word on the street is that Sun and HP/Compaq will be putting forward 8-way systems in the near future. The problem is that if they do not get on the ball, Yamhill will be out and could steal much of the thunder away from such a release.

--

Honesty may be the best policy, but apparently by elimination, dishonesty is the second best policy.

Re:AMD have been better than Intel for some time.. by vicotnik · 2004-02-16 07:30 · Score: 1

Since you got +5 informative I just have to comment on one thing that makes you sound like an AMD fanboy. I think it can be accurate to say that high clock speed means higher performace and higher dissipation OR that it doesn't equate to either performance or high dissipation because BOTH these things depend on the architecture. You make it sound like high clock speed sucks, or at least only gives a "slight edge in multimedia performance". I agree that the Athlon64 3000+ is a good buy though.

Gawd - you're dumb. by 0x1337 · 2004-02-16 07:30 · Score: 1

Take a good look at any Multi-Processor IA-32 server system these days - oh wait, is that 8 GB per CPU? Is that the PAE flag enabled in CR0 on each cpu? 36-bit physical address bus, eh?

Its not a hack - its CPU design. And the corporate, enterprise world sure loves having servers that don't choke on memory. Not everyone can run all their webservers off of VMs on a zSeries.

Yes - you're dealign with a 4 GB window that can sit anywhere from 0 MB to 64GB, through the sheer wonders of Paging with PSE and PAE.

Not from CPUs by MarcQuadra · 2004-02-16 07:40 · Score: 1

I'd think that AMD's real moneymaker isn't selling CPUs to people, but the HUGE embedded and ASIC market. Hell, I've got radios, televisions, keyboards, PDAs, and network equipment with AMD ASICs in them. Sure, the price might be only a few cents for those chips, but there's so freaking many of them.

--
"Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails

Long Live Upgrading! by Vagary · 2004-02-16 07:42 · Score: 1

Okay, you may still be the exception: upgrading every year might just be frequent enough to work. But most people might as well save the money of sockets and slots and solder the components to the motherboard.

I guess it's just because Moore's law has ramped up the speed of development, but it used to be that hardware designers had to try and eke out the best performance from the old infrastructure for each development, now they redesign the infrastructure to support the development. I guess it's kind of like the difference between console developers making games a few years after a console has been released and PC game developers pushing the limits of graphic card features.

Re:Profitable (WTF?!?!?!) by NoodleSlayer · 2004-02-16 07:52 · Score: 1

You need to take a look at Pricewatch my friend:

http://www.pricewatch.com/menus/m3.htm

Your average Xeon costs about three times more then your average P4 at the same clockspeed, with the exception of the Extreme Editions, which by and large are just remarketed Xeons. This is hardly just a "few more dollars." Although "just a few dollars more" may be accurate on describing the production cost between your average P4 and Xeon.

Re:AMD have been better than Intel for some time.. by Anonymous Coward · 2004-02-16 07:52 · Score: 0

Thunderbird and I think Athlon XP did not have any "thermal protection", they relied on the motherboard to look out for high temperatures and know what to do.

Re:AMD have been better than Intel for some time.. by Hoser+McMoose · 2004-02-16 07:54 · Score: 1

Err, I've got one of hte first generation nForce boards, and it's performance is every bit as good as any competitors at the time whiel it offered decent integrated graphics (great for 2D stuff, acceptable for limited 3D gaming at the time) and excellent integrated sound. Add to that the fact that even the version 1.0 drivers worked better than ANY drivers I've ever used for a VIA motherboard and I'm happy.

As for Intel "just working", you obviously never suffered through the hell of early revisions of Intel drivers. There were occasions when they were worse than VIA, the only difference being that at least Intel fixed their problems while VIA didn't. I'm thinking specifically of the first set of drivers for the i810 and i820 motherboards as well as the first drivers for the PIIX4 southbridge (430TX and 440LX chipsets). Those were CRAP! Things definitely did NOT "just work", they just didn't work! If you installed the PIIX4 drivers in the wrong order or with the wrong combination of Windows service packs you had to format the drive to get things working properly again.

Intel's motherboard drivers have been generally ok, but they have are hardly a pinnacle of proper functioning. VIA, on the other hand, has been generally bad and always problematic.

All in all, having used all kinds of different systems over the years, I feel quite confident in saying that nVidia has the best drivers of ANY motherboard chipset maker, including Intel.

Of course, if you REALLY want something that "Just Works", buy a Mac.

Re:AMD have been better than Intel for some time.. by Anonymous Coward · 2004-02-16 08:24 · Score: 0

I went with the car theme that he started ;)

Re:AMD Athlon Processor Build & Installation G by Vancorps · 2004-02-16 09:18 · Score: 1

hmmm, those numbers still don't add up. I personally had a RAID 5 array with 10 10k rpm drives in it and the psu was rated at 145 watts. Granted this was about five years ago but the 8 dvd-rw tower I built last week still only had a 200 watt psu in it and that includes powering the motherboard and pci cards with the exception of my management card which has an independent power source so I can turn the machine on remotely from a web browser.

Here is some figures on a typical scsi drive

It requires 6.7 watts idle and 8.1 watts full power. Types 5 drives and you are not talking about needing anything close to 350 watts.

For cross reference sake another manufacturer also uses 8 watts. You can find the info here

peak power dissipation by Anonymous Coward · 2004-02-16 10:17 · Score: 0

Current Intel CPUs have higher peak power dissipation than AMD CPUs, but they also perform better also.

Furthermore, when not pushed to the limits, the Intel CPUs drop low a much lower power consumption rate than the AMDs.

For example, my Intel P4 3.0GHz is rated at 100 Watts dissipation. But when plugged into a device that measures the power usage, my entire system uses less than 100 Watts in normal use. It doesn't even break 100 Watts when playing a movie. And this includes HD and video card power use and power supply inefficiency! It does not include my display.

Now, my 1700+ Athlon XP computer uses 160 Watts when just idle. I can feel the heat coming out of the back of the unit.

And then there's Pentium M, which is far more power efficient than either of them.

Re:AMD have been better than Intel for some time.. by Jarnis · 2004-02-16 10:20 · Score: 1

KT400 and KT400A were pretty indifferent about memory, but the new KT600 chipset is showing some odd behaviour with some modules that work just fine on KT400/400A. And then there is nForce2, which should probably come with it's own 'nVidia' branded RAM that is tested to work :p

Penny pinchers go for AsRock K7S8X 3.0E. Something like 40 euros... For normal setups we currently recommend A7V8X-X (as long as they are still made), or A7V600-X (the new replacement). Sadly A7V8X-X has about 3-5% 'dud rate' out of the box, and A7V600-X has the KT600 memory iffyness problem with multiple sticks.

The new A7N8X Deluxe-E is pretty spiffy and seems to have something 'cured' in the memory timings dept, but I didn't expect anything less from a 'late revision' board.

But all this is pretty poor when you can pick almost any 865 or 875-based intel board, and you can throw almost any memory (preferrably branded) at it, and It Just Works(tm). I do admit intel has had it's own share of mobo/chipset issues back in the early days of P4, but the platform has matured a lot, while AthlonXP platform *still* has some issues, and it's almost end-of-life!

Thankfully, like I said, Athlon64 looks like it's 'born mature' due to the lateness of the CPU. At least once the chipset/mobo makers had plenty of time to finish their products :)

Re:Pentium-M by Slack3r78 · 2004-02-16 12:18 · Score: 1

That really is great news, even if I am 12 hours late on it. :) Between this and the fact that Intel has finally admitted that they'll eventually have to move to an x86-64 architechture, it looks like they're finally starting to get their act together and leave the Megahertz Marketeering behind. I'm an admitted AMD fanboy, but I've always really liked the Pentium M, and it irked me that it wasn't essentially being left to itself in the notebook segment rather than leveraged in the desktop market as well because Intel was too busy ramping up clock speed with the comparitively hugely inefficient P4. This is one of the better pieces of news I've heard today, thanks. :)

AMD Back in the Black? by Anonymous Coward · 2004-02-16 12:50 · Score: 0

Did they hit the sack?

Are they gettin' loose, from the noose, that's kept them hangin' around?

reference by sewagemaster · 2004-02-16 13:36 · Score: 1

AMD back in the black
because 32-bit processors 'can't take advantage of more than 4 megabytes (sic) of memory at a time.'

sounds like a gang bang reference to me... once you go black, you never go back.

--
my blog

Re:AMD have been better than Intel for some time.. by RdsArts · 2004-02-16 13:52 · Score: 1

"It also has a beautiful frontside bus, and huge tracts... of LAN."

Re:AMD have been better than Intel for some time.. by Via_Patrino · 2004-02-16 16:58 · Score: 1

the chances of a heatsink falling off are virtually nil

Don't know about the heatsink falling but I have a computer that works 24/7 and exactly every year I need to change the heatsink fan.
And there's also bad installation, like a space between the heatsink an the processor.

It stays idle most of the time, so that's not a big thing (it don't heat very much), but it would be a big problem if it was a very used server.

Re:AMD have been better than Intel for some time.. by Loki_1929 · 2004-02-17 03:59 · Score: 1

"Don't know about the heatsink falling but I have a computer that works 24/7 and exactly every year I need to change the heatsink fan."

Are you using the stock cooling? I've been running my AthlonXP 1700+ 24/7 since the 1700+ was about the fastest chip available, and I've never had to change out the stock cooler. I can certainly see where some third party coolers could fail, and I have seen where AMD used pretty cheap quality HSFs on some of the Durons around the time of the 1.1s. Other than that, I've always been pretty happy with the quality of the stock HSFs coming out of AMD. My only complaint for the Athlon coolers is that they occassionally pack some fairly loud fans with the higher end models.

"And there's also bad installation, like a space between the heatsink an the processor."

The installation complaints that many have raised are addressed in the new Athlon64 CPUs. The exposed die has been covered with a heat spreader (much like the P4s), and the HSF (at least for the AthlonFX, not sure about the others) is also a bit like the P4 stock HSF.

What many people don't really realize or think about is that the Athlons were not designed to compete against the Pentium 4s. If you remember way back when, the Pentium IIIs were basically brand new when the Athlon was introduced. All the sockets, HSF designs, chip packaging designs were done basically 5 years ago. Changing all of those things requires nothing less than a complete break of backward compatibility with older boards. While Intel has always been more than happy to do this (socket 423 was around for what, a year?), AMD has always worked hard to make certain that existing designs would last as long as possible. Socket 7 is a perfect example of this. While Intel was content to let socket 7 die with the 233MHz Pentium MMX, AMD continued with socket 7 (re-labled 'Super' Socket 7) all the way into the ~450MHz area. Thus, board makers didn't have to make huge changes to their manufacturing, nor toss out their older stock to continue supplies for AMD CPUs. This is why so many Super socket 7 boards ended up being used. AMD made one major split with the Athlon CPUs, which occurred when they went from Slot A to Socket A, about the same time the Thunderbird core was introduced. This was a rough change for AMD, and something its longtime customers weren't used to at all. That being said, it was both necessary and smart for them to dump the good-on-paper slot-style CPUs. What is truly impressive is that the Athlon family hasn't changed all that much in terms of board design from the 700MHz CPU that was competing against the PIII, to the AthlonXP 3200+ that now competes with the P4s. K7 has taken on two families of Intel's CPUs, and that's impressive by anyone's standards.

"It stays idle most of the time, so that's not a big thing (it don't heat very much), but it would be a big problem if it was a very used server."

If it were a very used server, it would be using a Xeon or an Opteron. Using anything else for a server merely invites trouble. If it's a low-end deal, I'd recommend either the AthlonMP, or the PIII Tualatin. Both are relatively inexpensive, and both are pretty reliable.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

Any thoughts on a Apple by Anonymous Coward · 2004-02-27 06:34 · Score: 0

any thoughts on apple over AMD

359 comments