AMD's Roadmap revealed

← Back to Stories (view on slashdot.org)

Posted by ryuzaki0 on Tuesday January 13, 2004 @02:27AM from the socket-to-me dept.

NoPants writes "It looks like the aces at Anandtech were able to get their hands on some of AMD's internal roadmaps. Anand has some interesting information including the new upcoming Socket 939 CPU standard as well as AMD's predicted release dates for Athlon 64 4000+ processors. Hopefully this will shed some light on what AMD is trying to do with all the different socket types..."

298 comments

offtopic.. by MindsEye · 2004-01-13 02:20 · Score: -1, Offtopic

I know this is off topic, but wasnt that plasma story posted before this one? now this one is supposidly posted before the plasma... Is this normal with slashdot? (I have never noticed before)
1. Re:offtopic.. by Trigun · 2004-01-13 02:23 · Score: 5, Funny
  
  The Slashdot staff created this story with a timestamp from a Mars watch. It's thirty nine minutes off.
2. Re:offtopic.. by Leffe · 2004-01-13 02:28 · Score: 0, Offtopic
  
  No, it accidentally showed up before the subscriber time went out... some glitch in the system.
  
  I think it's the real Saddam that is trying to hurt America(and of course the rest of the world) where it really hurts: Slashdot.
3. Re:offtopic.. by Anonymous Coward · 2004-01-13 02:31 · Score: 0
  
  "I think it's the real Saddam that is trying to hurt America(and of course the rest of the world) where it really hurts: Slashdot."
  
  Obligatory South Park reference:
  
  We're off to see the Prime Minister, the Prime Minister of Canada!
4. Re:offtopic.. by Anonymous Coward · 2004-01-13 02:33 · Score: -1, Troll
  
  It is because Slashdot is written in Pearl, which doesn't support 32-bit time stamps. Hence, the older article is showing up after this one.
5. Re:offtopic.. by Anonymous Coward · 2004-01-13 02:49 · Score: -1, Flamebait
  
  Perl, silly rabbit.
FP? by Anonymous Coward · 2004-01-13 02:20 · Score: -1, Offtopic

FP? What happened?
Maybe all of this... by BJZQ8 · 2004-01-13 02:20 · Score: 4, Funny

Maybe all of this preliminary information will help Intel markitecture their way to the Pentium 6!
1. Re:Maybe all of this... by somethinghollow · 2004-01-13 02:32 · Score: 4, Funny
  
  I think they wanted to call it Pentium !!!!!! after their last really successful processor, Pentium !!!.
2. Re:Maybe all of this... by JediDan · 2004-01-13 02:35 · Score: 3, Interesting
  
  Intel has said sometime in the past that their plans for the P4 core will last them until ~11 Ghz.
  
  --
  - Dan
3. Re:Maybe all of this... by CaptnMArk · 2004-01-13 02:58 · Score: 1
  
  and 1.1kW
4. Re:Maybe all of this... by smittyoneeach · 2004-01-13 02:58 · Score: 2, Funny
  
  Dunno. Pent- alludes to 5.
  Insert some joke about Sexium (at last?) here.
  
  --
  Get thee glass eyes, and, like a scurvy politician, seem to see things thou dost not.--King Lear
5. Re:Maybe all of this... by the_2nd_coming · 2004-01-13 03:04 · Score: 1
  
  at that point, the CPUs will need be be helium cooled in a graphite matrix to keep the system from going critical , causing a melt down.
  
  --
  
  I am the Alpha and the Omega-3
6. Re:Maybe all of this... by varslot · 2004-01-13 03:06 · Score: 3, Funny
  
  I think that should be "Pentium 3!" ...
  
  --
  There arises from a bad and unapt formation of words a wonderful obstruction to the mind. (Francis Bacon)
7. Re:Maybe all of this... by Anonymous Coward · 2004-01-13 04:01 · Score: 0
  
  Can someone explain these Intel heat-jokes to me? A number of fan failures on our Xeons were discovered only after the processors got too hot and self-disabled. After replacement of the fans they were fine. Athlons on the other hand don't seem to fair so well, I have seen the aftermath of a vertically mounted T-bird whose heat sink fell off - a partially melted socket! Maybe the average temps are higher on intels, but why would you not spend the extra 10% for the insurance of non-suicidal gear?
8. Re:Maybe all of this... by ArsonSmith · 2004-01-13 04:10 · Score: 1
  
  1.21GW using the flux cap core(TM)
  
  --
  Paying taxes to buy civilization is like paying a hooker to buy love.
9. Re:Maybe all of this... by BJZQ8 · 2004-01-13 04:17 · Score: 1
  
  It's because Intel, and AMD processors too, are getting hotter by the generation. Their heat density is rapidly approaching that of a nuclear reactor, literally! At the rate that Intel says it wants to ramp clock speeds, they will be much, much hotter.
10. Re:Maybe all of this... by red+floyd · 2004-01-13 04:20 · Score: 1
  
  Well, I don't think they can use "Octium", because it was used for a chip on "The Lone Gunmen".
  
  --
  The only reason we have the rights we have is that people just like us died to gain those rights. -- Cheerio Boy
11. Re:Maybe all of this... by at_18 · 2004-01-13 04:30 · Score: 1
  
  Shouldn't that be
  
  - Exium
  - Ettium
  - Optium (don't miss this!)
  - Ninium
  - Decanium (the old processor?)
12. Re:Maybe all of this... by Anonymous Coward · 2004-01-13 04:37 · Score: 0
  
  For those of you who don't know: the original Pentium was marketed with the exact phrase "Pentium !!!".
13. Re:Maybe all of this... by Anonymous Coward · 2004-01-13 04:47 · Score: 0
  
  Aargh. They have never said such a thing. They have talked 5 GHz, maybe a notch beyond. Never 11 GHz.
  
  Who modded this interesting? (Would "22 GHz" given a score of 4?)
14. Re:Maybe all of this... by MagPulse · 2004-01-13 05:00 · Score: 0, Flamebait
  
  With AMD making up numbers with every chip release to say how fast they think they are, they are clearly the ones to aim the markitecture label at.
15. Re:Maybe all of this... by Loki_1929 · 2004-01-13 05:07 · Score: 1
  
  " Intel has said sometime in the past that their plans for the P4 core will last them until ~11 Ghz."
  
  First of all, "P4" isn't a core, it's an architecture. Secondly, please cite your source for this "11GHz" remark. Thirdly, Prescott couldn't possibly ramp that high, so they'd have to go through at least two more generations of cores before even approaching that frequency. And lastly, getting to 11GHz on the P4 architecture would be both incredibly difficult and to an extent, pointless. Somewhere around 10GHz or so, core optimization and IPC are going to have to be raised substantially to make up for the horrible hits they'll take on latency, cache misses, branch mispredictions, etc. The P4 architecture simply is not designed for anything other than high frequencies. Besides, I'm betting that Tejas comes out labled as a Pentium 5, and with dual cores. At that point, I'm guessing that AMD will also begin to integrate the second core on their A64 chips for sampling, making them available some time in early '05.
  
  --
  -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
16. Re:Maybe all of this... by Hoser+McMoose · 2004-01-13 05:36 · Score: 1
  
  And the Pentium Pro core lasted them until 1.4GHz, but that didn't stop Intel from marketing it under the PII and later PIII brand names, not to mention the Xeons and Celerons.
  
  It's likely that the Netburst core of the P4 will be here for a while yet. I don't know about the 11GHz number, but I suspect that it Intel will continue to use the core until at least 2006 or 2007. However I also suspect that we'll see at least a "Pentium 5" in that time frame, and a "Pentium 6" is not out of the question. It's also likely (in fact, almost certain) that Intel will put two Netburst cores on a single chip in 2005 or 2006, at least for their Xeon line, and that may extend the basic Netburst architecture for a while longer.
17. Re:Maybe all of this... by jrockway · 2004-01-13 12:30 · Score: 1
  
  I haven't really liked AMD's practice of doing this, but it turns out that a 3200+ Athlon XP and a 3.2GHz P4 are quite comprable in benchmarks. AMD isn't pulling this stuff out of their asses as a marketing scam. They have good chips, but they just run slower. They do more work in one clock tick. Regular consumers don't understand this, hence the xxxx+ reatings. It's a necessary evil if they want people to take their processors serously.
  
  As for Apple, they need to start doing this too. They can call the G5 something like 4500+ and beat AMD and Intel :)
  
  --
  My other car is first.
First post by Anonymous Coward · 2004-01-13 02:21 · Score: -1, Offtopic

Mookore will fuck the GNAA!
1. Re:First post by Anonymous Coward · 2004-01-13 02:29 · Score: -1, Offtopic
  
  Did anyone see today's ASCII Art Fart? Ripping on the GNAA, it looks like.
Grhh... by Anonymous Coward · 2004-01-13 02:22 · Score: -1, Redundant

AMD's new stuff has been pretty impressive, but it really bothers me when they pull this type of stuff:

AMD Athlon 64 3700+ 2.4GHz 1MB Q2 '04
AMD Athlon 64 3400+ 2.4GHz 512KB Q2 '04
1. Re:Grhh... by BJZQ8 · 2004-01-13 02:24 · Score: 2, Interesting
  
  Ya, it bothers me too. But if Intel hadn't messed it all up by designing a "clock speed only" processor, then we wouldn't be in this situation. I definately agree that the Performance Ratings are a very poor way to describe a processor...
2. Re:Grhh... by binaryDigit · 2004-01-13 02:28 · Score: 5, Interesting
  
  AMD's new stuff has been pretty impressive, but it really bothers me when they pull this type of stuff: AMD Athlon 64 3700+ 2.4GHz 1MB Q2 '04 AMD Athlon 64 3400+ 2.4GHz 512KB Q2 '04
  
  What's the problem. They're saying that having the smaller cache gives you less performance. Are you upset that they happen to have the same clock speed? I assume you'd prefer nomenclature more on the order of "AMD Athlon 64 2.4/512 and 2.4/1024"? In many ways they way they are currently doing it is more descriptive to the average buyer. No guessing as to how much performance you're giving up by going with the smaller cache ,or how much you're gaining by going with the bigger (performance benchmark inflation not withstanding).
3. Re:Grhh... by TrueBuckeye · 2004-01-13 02:33 · Score: 5, Insightful
  
  Not to mention the fact that it lowers costs to them, and thus to the consumer, to do this. From what I've heard, they are able to take cpu's with some bad cache, which isn't uncommon, disable that non-functioning section, and then sell the cpu as a 512k cache cpu rather than wasting the entire chip. Lower performance, lower cost, but less waste. This is a far cry from the world of the Intel 486 sx vs dx with the math co-processor fiasco.
  
  --
  Was that night on the marge of Lake LaBarge I cremated Sam McGee...
4. Re:Grhh... by TheLink · 2004-01-13 02:49 · Score: 1
  
  Not a prob- the 3700 and 3400 are for the average Joe. As long as they are a fair indication of performance there's nothing wrong with it.
  
  The rest of us who cared about the details (which software, how fast) can and would find them out fairly easily.
  --
  
  Too many replies beneath your current threshold
5. Re:Grhh... by Zog+The+Undeniable · 2004-01-13 02:49 · Score: 1
  
  I thought Barton had more or less torpedoed the "more cache makes up for a lower clock speed" theory? The old Thoroughbred-B 2800+ was faster than the Barton 2800+ for most applications. No integrated L2 cache is undoubtedly a Very Bad Thing - see the original crippled Celeron for an example - but when you start increasing an already adequate cache, you're rapidly into diminishing returns and the core clock speed is more important.
  The lower clocked, bigger cache part does run a bit cooler though, so if a quiet fan is what pops your cork, go for it!
  
  --
  When I am king, you will be first against the wall.
6. Re:Grhh... by glsunder · 2004-01-13 03:14 · Score: 4, Insightful
  
  The ratings have been mostly accurate when comparing AMD cpus, and they're useful when talking to non-computer people rather than explaining things like cache size, locality, etc. With the Athlon64, it should be even more accurate since they now control the memory controller. If the performance rating can make it easier for the average person to compare systems accurately and pick the better value for them, then I'd say it's a good thing.
  
  Also, normal users don't care about 10% performance differences. I've found a good way to relate to this is to think about old computers. Do you really think of the difference between a P133 and a P166? No, they're both from the p5 generation, with a L2 caching up to 64MB or 128MB depending on chipset and the cpu performance is basically equal (slow). If a p166 will do the job you need nowdays, a p133 probably will too, and it's doubtful that you'll notice much difference.
7. Re:Grhh... by Anonymous Coward · 2004-01-13 03:23 · Score: 0
  
  > In many ways they way they are currently doing it is more descriptive to the average buyer.
  
  Maybe, but it's annoying to have to look up each time how fast an AMD processor is based on their goofy marketing numbers.
8. Re:Grhh... by mfago · 2004-01-13 03:25 · Score: 2, Informative
  
  the Performance Ratings are a very poor way to describe a processor...
  
  I agree it's all marketing, but ...
  
  As a data-point, I recently upgraded from an Athlon 2400 to the 3200 -- a 30% improvement in "PR," and saw my benchmarks go up almost exactly 30%. By benchmarks here I'm talking about a CPU bound computational mechanics code I wrote for my thesis. About as useful to everyone else as SPEC, but very relevant to me.
  
  As usual, YMMV.
9. Re:Grhh... by ndqc · 2004-01-13 03:48 · Score: 1
  
  there is big difference between p133 and p166mmx.
10. Re:Grhh... by Anonymous Coward · 2004-01-13 04:19 · Score: 0
  
  Yes, because AMD is sooooo tied to clockspeed like Intel.
11. Re:Grhh... by Anonymous Coward · 2004-01-13 04:24 · Score: 0
  
  Depends on the type of software you run.
  My 1.4 GHz Opteron with 1 MB cache kicks 2.8 GHz Pentium IV's ass when it comes to scientific computing.
12. Re:Grhh... by benzapp · 2004-01-13 04:25 · Score: 1
  
  more cache only matters when multitasking, not when running a single process. This is why Intel has always put larger caches on their Xeon line.
  
  --
  I don't read or respond to AC posts
13. Re:Grhh... by Anonymous Coward · 2004-01-13 04:26 · Score: 0
  
  Why do you need to do that? It's not like you have to set your motherboard clock & multiplier jumpers manually..
14. Re:Grhh... by Anonymous Coward · 2004-01-13 06:05 · Score: 0
  
  yeah the p166 mmx was a rip off.
15. Re:Grhh... by SacredNaCl · 2004-01-13 07:38 · Score: 1
  
  The P166MMX wasn't a rip off, it overclocked well.
  
  My P166MMX will happily do 266mhz @ 75mhz bus stable. Exactly the same as my P200MMX does in that board stably. It's still performing it's function happily running W2K server same as it has been for the past several years.
  
  The real problem back then was the OS it was running on. It's not easy to judge stability when you are running Windows 95/98. But put them with a decent OS & decent drive controller and they happily clock to the max your board allows in most cases.
  
  --
  Freedom is merely privilege extended unless enjoyed by one and all.
16. Re:Grhh... by Shokac · 2004-01-13 07:48 · Score: 1
  
  more cache only matters when multitasking, not when running a single process. This is why Intel has always put larger caches on their Xeon line. This is not TRUE !!! Use SETI as example. More cache is needed only when you do work on big data chunk. In SETI example 16 MB. So you need LESS requests to SLOW main memory. IT DOES NOT depend on MULTITASKING !!! Boy, 95% of posts and replays here are from ppl. who doesn't know Sh.t about computer technology and how CPU realy WORKS.
17. Re:Grhh... by benzapp · 2004-01-14 05:42 · Score: 1
  
  Oh yeah, the entire cache is flushed every time you switch processes.
  
  What was I thinking?
  
  The secondary cache is intended to prevent misses to the primary cache, that is going to be more likely the more processes you are running concurrently. SETI may be a great way for you to feel good about yourself, but that is NOT the kind of work 99% of servers out there are doing.
  
  Further, SETI is an example of something that WON'T at all benefit from a cache. Why? The data is unique! There is nothing to cache! Now, of course some of the analysis routines will be cached, but not the SETI data chunks themselves.
  
  You are right about the purpose of cache, but you are wrong about how it goes about decreasing the number of requests to main memory.
  
  Anyway, why I am responding to some fucking idiotic child with a warez site in his profile. He can't even write a sentence without ridiculous amounts of emphasis.
  
  --
  I don't read or respond to AC posts
well thats nice by ZenBased · 2004-01-13 02:22 · Score: 5, Insightful

but my amd 700mhz proc is still quite fast enough to give me debian, fluxbox, openoffice etc.. ah well there must be enough people out there who cant live without a fast proc

--
http://www.virtualconcepts.nl/
1. Re:well thats nice by TheViffer · 2004-01-13 02:38 · Score: 3, Insightful
  
  Unless you are a gamer or looking to compute Pi to the last digit, most of todays "out of production" (even lower then "budget") processors are fast enough for most of today's computing tasks. My cool running Duron 1000 still powers my file server like a champ.
  
  The more they release these fire breathing, heavy Watt using, frying pan of CPU's, the easier it gets on our pocket books.
  
  Wake me when a cheap "build your own system" RISC alternative hits the market.
  
  --
  -- Knowing too much can get you killed, but knowing who knows too much can make you rich.
2. Re:well thats nice by Anonymous Coward · 2004-01-13 02:39 · Score: -1, Flamebait
  
  then shut up bevis.
3. Re:well thats nice by Anonymous Coward · 2004-01-13 02:42 · Score: 0
  
  Sorry, I can only afford a 450 K6. I am in the
  dark ages. (Although I have 3 of them.)
4. Re:well thats nice by Anonymous Coward · 2004-01-13 02:47 · Score: 0
  
  a 1000 Mhz fileserver? sheesh, that sounds about as bad as my 650 Mhz firewall ;)
5. Re:well thats nice by Anonymous Coward · 2004-01-13 02:54 · Score: 0
  
  I run VMWare alot more now and L2 cache, FSB and memory are critical on that.
  
  2MB L2 cache with faster FSB should make VMWare run like the clappers and then some.
  
  Virtualisation is here on the desktop today with runable performance. What is the DRM and TCPA issue on this latest AMD cpu?
6. Re:well thats nice by TheLink · 2004-01-13 02:54 · Score: 1
  
  My Athlon 2000xp takes 60-90 minutes to gzip a 40GB HDD (for backup). 11MB/sec-7.4MB/sec.
  
  If it could do it four times faster at the max HDD throughput (40MB/sec) it'll be done in 17 minutes.
  
  In this case the bottleneck is the CPU or perhaps the software - anyone know of a faster gzip?
  
  HOWEVER, if a CPU is 4 times faster so as not to be a bottleneck for the HDD gzip, the HDD then quickly becomes a bottleneck for other scenarios ;).
  --
  
  Too many replies beneath your current threshold
7. Re:well thats nice by Zathrus · 2004-01-13 02:58 · Score: 5, Informative
  
  Unless you are a gamer or looking to compute Pi to the last digit
  
  Or are wanting to do things like rip MP3s (trivial) or burn DVDs (non-trivial; technically it's the MPEG2 mastering, not the burning, that takes the CPU time). Developers, graphics artists, and most engineering can also use as much CPU as is available. For just a plain old file server you do very well by using the cheapest (in terms of purchase and run cost) that you can get. A webserver probably needs more juice. A database server definitely does. Trivial home use excluded of course. I'm not talking about trivial usages -- they can always be solved easily.
  
  Wake me when a cheap "build your own system" RISC alternative hits the market.
  
  When you realize that the core ISA of all x86 chips is RISC let me know. Not to mention that most of the classic "RISC" designs have deviated far from the "reduced" portion of that moniker. Looked at the Power or PowerPC ISA recently? RISC was created not because a reduced instruction set is inherently better, but because it allowed for a number of technologies such as pipelining, branch prediction, caching, and so forth to be implemented. Every single one of those is in x86 architecture now. Sure, the ISA is still a mess, but it's a better price/performance than anything else out there. All the naysayers have been disproven, time and time again. And yes, when I was a little college student I was horrified at the design of x86. Then I grew up.
8. Re:well thats nice by dasmegabyte · 2004-01-13 03:03 · Score: 4, Interesting
  
  Except that programmers like myself write for the slowest currently marketted PC. We take advantage of the excess speed by increasing search capabilities, performing more intricate analysis, using higher quality fonts, sounds, graphics, etc.
  
  Yes, MOST of what people really need to do can be done on a 500 MHz machine. Shit, most of what people do -- search for information, write email, word process -- can be done on a goddamn Commodore.
  
  It is a fact of life that computers are going to get slowly faster, and people are going to expect these faster computers to have better software. Even if it's mostly superficial, we try to deliver that. Most of the time, though, a faster processor is a boon even to Joe Q. Homeuser. Consider a 3 megapixel camera, delivering photographs in excess of 1.5 megabytes. Time was we'd never THINK of doing graphical operations on that much information. Nowadays, it's so trivial that many photoalbums are processing 10 or more such pictures per second!
  
  Anyway, for easy operations like file serving, running a firewall, serving 100,000 or fewer web pages per day, etc...your best bet is a processor with a fast bus and a slow clockspeed. It'll be cooler and more reliable than some 64 bit god (honestly, who needs 64 bits to send packets?)
  
  --
  Hey freaks: now you're ju
9. Re:well thats nice by Billly+Gates · 2004-01-13 03:04 · Score: 3, Funny
  
  Run Gentoo or the FreeBSD ports sytem.
  
  Your mind will change quickly. :-)
  
  --
  http://saveie6.com/
10. Re:well thats nice by PhiltheeG · 2004-01-13 03:10 · Score: 1
  High-end CPU's aren't just for gamers. Personally, when I upgraded from a Athlon 800 to XP 1700 to now an XP Barton 2500 overclocked to think its a 3000 I benefited from:
  
  Faster compiles
  
  VM Ware virtual machine performance increased
  
  Better video captures and much faster compression (12 to 8 to 4.5 hours)
  
  Better grid.org scores
  
  The Barton was $90 retail shipped from Newegg and always at 50% CPU or above at around 50% on die. One of my motherboards is on the verge of flaking out, so I'll consider an Athlon 64 solution when that time comes.
  
  Upgrading my girlfriend's Duron 1.1ghz to an XP 1700 made her computer perform much smoother as a whole.
  
  You don't have to be a gamer to enjoy processing power, just buy when the time is right and enjoy. In fact, Quake2 is the only game I have installed.
  --
  -Phil
  Shoot questions, first ask later...
11. Re:well thats nice by krzysztof · 2004-01-13 03:10 · Score: 2, Funny
  
  I need the fastest computer possible. I helps me feel better about my personal shortcomings.
12. Re:well thats nice by secondsun · 2004-01-13 03:10 · Score: 1
  
  Yes, but does it have SSE, SSE2, 64 bit capability, 4+ GB ram addressability, Cool N Quiet support, a nice big L2 cache, and does your motherboard have DDR support or PCI-X support?
  
  I will guess not. My 1.4 Ghz TBird C may have the speed I need but there are new features I would like which is why the A64 is getting such a big push from me personally as my upgrade option. Plus it will hit the magic sub 150$ mark before the Prescott hand warmer.
  
  --
  There is nothing wrong with being gay. It's getting caught where the trouble lies.
13. Re:well thats nice by Anonymous Coward · 2004-01-13 03:11 · Score: 0
  
  I *do* want faster CPU, So that i can
  
  - ray-trace 3D images faster
  - compile Gnome/KDE or whatever faster
  - backup my dvd to divx faster ..
  
  There are lot of cpu intensive applications
14. Re:well thats nice by aliens · 2004-01-13 03:31 · Score: 1
  
  Every time there's a story about new CPU's or something speed related there are posts like this.
  
  What's your point? That we should stop making faster CPU's? Why do you care?
  
  Here's the post I want to see:
  
  Well that's nice, but my 286 that runs Minix is great! you don't really need that 700mhz proc, it's a total waste.
  
  --
  -- taking over the world, we are.
15. Re:well thats nice by yobbo · 2004-01-13 03:31 · Score: 1
  
  Doom 3 is gonna give you the shits.
16. Re:well thats nice by Anonymous Coward · 2004-01-13 03:34 · Score: 0
  
  The built-in ZIP support that comes with Windows XP is excellent.
17. Re:well thats nice by Atzanteol · 2004-01-13 03:38 · Score: 1
  
  Insightful my ass. This is a *classic* troll everytime a faster CPU comes out.
  
  100Mhz? Who needs it? My 486/66 can run Vi, gcc, and one or two other apps. What else do I need?
  
  --
  "Ignorance more frequently begets confidence than does knowledge"
  
  - Charles Darwin
18. Re:well thats nice by Cthefuture · 2004-01-13 03:42 · Score: 2, Interesting
  
  Or are wanting to do things like rip MP3s (trivial) or burn DVDs (non-trivial; technically it's the MPEG2 mastering, not the burning, that takes the CPU time). Developers, graphics artists, and most engineering can also use as much CPU as is available.
  
  Right on... Also, most developers need all the juice we can get. Faster compiles, better testing environment (more VMware sessions), etc, etc.
  
  All these people that say "nobody need anything more than X" are idiots. If a 700 Mhz proc works for you then fine (*). For the rest of us there is never enough computing power.
  
  Even if all you do is Office applications and web browsing, faster processors make the system more responive. Faster boot times, faster archive extracing, faster application start times. If you don't care about that stuff then fine, but I suggest you're not really using your computer anyway if you don't care.
  
  * By the way, just try a 3 Ghz processor for a while (maybe a week or two). Then go back your 700 Mhz system. You'll see the light.
  
  --
  The ratio of people to cake is too big
19. Re:well thats nice by Jeff+DeMaagd · 2004-01-13 03:46 · Score: 1
  
  It'll be cooler and more reliable than some 64 bit god
  
  While I agree that with a well-designed computer, 500MHz is very good for most people, I would bet that most of the 64 bit RISC systems are more reliable than most of the x86 systems, although I can't say much about Athlon 64 / Opteron, it hasn't been around for long enough. My daily-use Alpha built in 1997 ran Windows NT 4.0 to an uptime of 104 days. After that I quit just because it was a waste of power, although certainly more efficient than most of the P4 and Athlon systems sold in the last three years.
20. Re:well thats nice by MarcQuadra · 2004-01-13 03:59 · Score: 1
  
  You can knock that Duron MUCH lower in the clock and get comparable file server performance. I just underclocked my G3 file server from 450 to 300 Mhz and benchmarks are showing no difference in throughput or latency. Saves me a few cents in juice every month too, and runs much cooler than before (which was already cool enough to run fanless)
  
  --
  "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
21. Re:well thats nice by joib · 2004-01-13 04:00 · Score: 1
  
  ...compute Pi to the last digit...
  
  Hey, a C64 could finish that task as fast as the earth simulator! ;-)
  
  *hint* In case you didn't know, Pi has an infinite number of digits. Scary, huh?
22. Re:well thats nice by MarcQuadra · 2004-01-13 04:06 · Score: 2, Interesting
  
  But the PowerPC line has superior signal processing capabilities these days, is much easier for compilers to cater to, and runs cooler and more efficient than the X86 offerings.
  
  AFAIK, x86 units since the i686 have all used a RISC-like core that runs x86 ops by breaking them down into micro-ops and reconstituting them. It -works- but whay do that when the real thing is available?
  
  I think PowerPC would have a real future if MS lost full dominance of the PC market, it's a very short leap from Linux/OS X/BSD/whatever on x86 to the same on PPC. And now that IBM is making them tere seems t be a much more serious commitment to the architecture as a whole.
  
  --
  "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
23. Re:well thats nice by Rasta+Prefect · 2004-01-13 04:07 · Score: 1
  
  Sure, the ISA is still a mess, but it's a better price/performance than anything else out there.
  
  Unless you want to factor in things like power consumption....
  
  --
  Why?
24. Re:well thats nice by Anonymous Coward · 2004-01-13 04:17 · Score: 0
  
  And yes, when I was a little college student I was horrified at the design of x86. Then I grew up.
  
  Even Intel decided it was time to give up x86 to move ahead.
  Sure you can cram some pretty decent performance out of an x86 chip, but the overhead is insane.. Imagine all the resources spent on x86 used in a better way.
  
  Like the previous poster, i'd love to see an affordable RISC/FISC alternative. Load/store, enough registers and a decent vector unit, plus all the usual tricks. *drool*
25. Re:well thats nice by Dielectric · 2004-01-13 04:25 · Score: 1
  
  I take issue with your 500MHz limit. Gnome 2.0 runs like a pig in cement on my K6-III/500. Sure, we could have done all sorts of things on an Amiga, but the integration and features in newer desktop environments are slick. Take CD burning integrated into Nautilus (and Win Explorer on XP). I think that totally rules the school.
  
  OTOH, my firewall is a PentiumMMX/200 and it does just fine, thankyouverymuch.
26. Re:well thats nice by comedian23 · 2004-01-13 04:29 · Score: 2, Informative
  
  >* By the way, just try a 3 Ghz processor for a while (maybe a week or two). Then go back your 700 Mhz system. You'll see the light.
  
  Disagree. I use a 2.4Ghz at work and a 533Mhz at home and can't really tell a difference, except when (un)zipping files, or installing software(maybe 1% of my total use of the machine). My home machine can play music, games, surf the web, edit docs, etc. just fine.
  
  > Faster boot times, faster archive extracing, faster application start times.
  
  I think the faster disks in newer machines are probably the main reason this is faster, except the archive extraction, which is CPU intensive.
  
  >Also, most developers need all the juice we can get.
  
  You must be a Java programmer. :-)
  
  -Comedian
27. Re:well thats nice by LWATCDR · 2004-01-13 04:32 · Score: 1
  
  I have been wondering about underclocking a cpu. If one took 2.4 Ghz chip can clocked it down to say 1.2 could you run fanless? Use less power. Have the chip last longer???? With computers so bloody fast It might be me nice the make a cooler quiter system with out spending the money on a laptop stype chip set.
  
  --
  See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
28. Re:well thats nice by cbreaker · 2004-01-13 04:33 · Score: 1
  
  "Wake me when a cheap "build your own system" RISC alternative hits the market."
  
  I fear you may never awake from your slumber.
  
  --
  - It's not the Macs I hate. It's Digg users. -
29. Re:well thats nice by Zathrus · 2004-01-13 04:36 · Score: 2, Informative
  
  Unless you want to factor in things like power consumption....
  
  Feel free to. x86 is still cheaper. Equivalent speed systems don't use vastly less power. Best number I've seen is ~75W, which is 3/4 of what a P4 or Athlon64 uses. That's not an abundance in savings.
  
  To put it clearly -- 25W saves you 219 kWh/year (assuming it's on 24 hours a day year round (365.25 days/year)). If electricity costs $0.10 kWh then that's a savings of $22. Wow.
  
  And that, of course, is assuming that the CPU is fully loaded the entire year. If you aren't using 100% CPU power then the CPU will reduce its power draw -- not massively (these aren't laptop CPUs), but somewhat.
  
  You can point to other CPUs that draw less power than a P4/AMD64/970, but they cost vastly more to purchase. The PowerPC 970 is already overly expensive -- particularly given that AMD has already cut prices on the Athlon64 and Opteron lines since introduction.
30. Re:well thats nice by bluewee · 2004-01-13 04:46 · Score: 1
  
  untill you have to wait till your stage one system compiles... [but I still love you gentoo...]
  
  --
  [blue] - The Ministry of Information approved this message...
31. Re:well thats nice by Zathrus · 2004-01-13 04:46 · Score: 1
  
  It -works- but whay do that when the real thing is available?
  
  Uh, because it works well, is producing results that are better than "the real thing", and happens to run all those existing millions of programs out there without any problems?
  
  I think PowerPC would have a real future if MS lost full dominance of the PC market
  
  Yeah, and Segway might have a real future if it wasn't for all those pesky cars out there. (No, not a perfect analogy, but they're equally based in reality)
  
  This is exactly the kind of thing I'm talking about. Yes, the x86 ISA is crap. So what? Has it really caused any problems? Is it so incredibly bad that the competition is stomping it? No? Why hasn't that happened yet then? Why have Intel's own attempts failed so miserably?
  
  Why, exactly, has x86 been making more and more inroads into high-end markets if it's so godawful?
  
  The reality is that the market demands x86 compatibility. There are millions of apps out there that do their job perfectly, every day. Which couldn't be replaced without a lot of cost -- the source may not exist anymore, they may never have had the source, even if you have it the original requirements and domain knowledge is probably long gone, etc. And that's not going to change anytime soon, no matter how much you gripe about how bad x86 sucks on paper.
  
  And the point remains -- x86 may suck on paper, but it damn well flies in reality.
32. Re:well thats nice by Sloppy · 2004-01-13 04:52 · Score: 1
  
  That's why you should run Gentoo. It helps to combat the sense that you "wasted" money on hardware. ;-)
  
  --
  As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
33. Re:well thats nice by BOFHelsinki · 2004-01-13 04:54 · Score: 0
  
  Well put! Have you noticed how some people complain about x86, then say almost the same things about Perl but as praise? ;-)
34. Re:well thats nice by Jason+Hood · 2004-01-13 04:56 · Score: 0
  
  I think you answered your own "question".
  
  If you dont need a 3.0 Ghz proc, dont buy one. Those of use that do need one, will buy one and get our money's worth.
  
  --
  Are you intolerant of intolerant people?
35. Re:well thats nice by shachart · 2004-01-13 05:06 · Score: 1
  
  No, better scheduling makes the system more responsive. My AMD K2 233MHz running Linux kernel 2.6.x is more responsive than my P4 2.4GHz running XP, while compiling the same (platform-independent) code.
  
  --
  Those who can, do. Those who can't, consult.
36. Re:well thats nice by WNight · 2004-01-13 05:14 · Score: 1
  
  Zip up your 40GB C: drive with it. When that fails, examine your claim again.
  
  The built-in zip is handy, but it killed the explorer when I tried to use it, moments after first install, and that didn't make a good impression.
37. Re:well thats nice by kill-1 · 2004-01-13 05:19 · Score: 1
  
  You will NEVER get the maximum theoretical throughput of your hard disk on filesystem operations. Not even close. Try copying your 40GB to another disk and measure your real world fs throughput. It will be much closer to 10MB than 40MB.
38. Re:well thats nice by FuzzyBad-Mofo · 2004-01-13 05:24 · Score: 1
  
  bzip2
39. Re:well thats nice by Anonymous Coward · 2004-01-13 05:26 · Score: 0
  
  This is obviously an unfair comparison. Try doing your Linux tasks on the P4 2.4GHz machine, then come back with your results.
  
  (Tongue in cheek...)
40. Re:well thats nice by Hoser+McMoose · 2004-01-13 06:00 · Score: 2, Informative
  
  But the PowerPC line has superior signal processing capabilities these days
  
  According to who? And why? SSE2 provides plenty of instructions for signal processing, and SSE3/PNI will fill in a couple of the last remaining holes. AMD64 also doubles the number of registers for SSE2 as well as the general purpose registers.
  
  Exactly what advantage does the PowerPC have for signal processing? They do have a nifty multiply-add instruction that is missing on x86/SSE2, but on the flip side their vector processing engine (Altivec) seems to be limited to single precision floating point math unless I missed something.
  
  is much easier for compilers to cater to
  
  Ohh, so THAT'S why there are WAY more x86 compilers out there than PPC ones.
  
  And runs cooler and more efficient than the X86 offerings
  
  The PPC 970, used in Apple's Powermacs is listed at a "typical" power of ~48W at 1.8GHz. Maximum power is probably a good 20-40% higher. In other words, power consumption is pretty much identical to AMD's Athlon64/Opteron line and pretty darn close to Intel's P4 line. It also has 52 million transistors, nearly the same as the 55 million transistors of the P4. The IBM Power4+ consumes a ton of power, somewhere up around 100W.
  
  AFAIK, x86 units since the i686 have all used a RISC-like core that runs x86 ops by breaking them down into micro-ops and reconstituting them. It -works- but whay do that when the real thing is available?
  
  Why do it? Becuase hardware is cheap, software is expensive. They also do it because it doesn't really make a difference, ALL chips start by decoding their instructions, executing them and then putting it all back together again. It's not just an x86 thing.
  
  The main downsides to x86 are as follows:
  
  - Too few general purpose registers and restrictions on what registers can be used for which instructions
  
  - 32-bit pointers
  
  - Stack based FPU
  
  - Somewhat more complex instruction decoder
  
  AMD has addressed the first two points with AMD64. They've extended the general purpose and FPU (SSE) registers from 8 to 16 and removed the restrictions on what registers can be used for which instruction. Not quite the 32 registers of some other architectures, but still pretty good.
  
  The stack-based FPU is in the process of being replaced by SSE2. While SSE may have started out just as a vector SIMD engine, with SSE2 it's really a full fledged floating point unit to replace the old x87 unit.
  
  The more complex decoder has also been largely addressed by Intel in their P4 design with their trace cache. This stores already decoded instructions, so about 90% of the time the decoder is not needed (and therefore can be made much simpler).
41. Re:well thats nice by Anonymous Coward · 2004-01-13 06:29 · Score: 0
  
  Actually your comment about Image Processing reminded me of that weird '80s Kevin Costner movie called "No Way Out" where the plot hinged on it taking forever to image enhance a photograph on a Government computer. The photo, when finally enhanced, gave away the big secret. Its really funny to think that the movie could not be made today because computers have gotten that much faster.
42. Re:well thats nice by dave1g · 2004-01-13 07:44 · Score: 1
  
  "And that, of course, is assuming that the CPU is fully loaded the entire year. If you aren't using 100% CPU power then the CPU will reduce its power draw -- not massively (these aren't laptop CPUs), but somewhat."
  
  Actually, with AMD's "cool and quiet" the athlon 64's act much like laptop processors, they will underclock themselves down to 800 MHz when not in use, and once the load is at 100% the processor scales up the clock until its not 100%.
  
  This is assuming that you have a motherboard that supports it, and according to Toms Hardware, there are only a few that give it good support.
  
  So actually the power savings are pretty big with AMD 64, so the grandparent is even more wrong lol.
43. Re:well thats nice by Anonymous Coward · 2004-01-13 07:50 · Score: 0
  The TDP of most highend x86's isn't particularly bad when compared against other highend CPU's.
  
  IBM Power4 1.3GHz = 135W
  
  IBM PPC970 1.8GHz = 42W
  
  Alpha EV6 575MHz = 90W
  
  Alpha EV7 1GHz (predicted/planned) = 100W
  
  Alpha EV8 1GHz-2GHz (planned) = 150W
  
  Intel Xeon 2M L3 2.8GHz = 85W
  
  Intel Pentium-M (banias) 1.7GHz = 24.8W
  
  Intel Itanium2 6M L3 1.5GHz = 107W
  
  Intel Itanium2 1.5M L3 1.0GHz = 55W
  
  AMD Opteron (all current models) = 89W
  
  AMD Opteron (low power/planned) = sub 50W
44. Re:well thats nice by Anonymous Coward · 2004-01-13 08:13 · Score: 0
  
  You're probably thinking of MPC74xx chips. Those weren't originally PowerPC. They're PPC compatible, but designed by Motorola.
  
  True PPC chips like the PPC750 run much faster and cooler than anything Motorola ever cranked out. And remember, with all but the MPC74xx's, IBM *did* help design them.
  
  Oh, and the PPC750FX dissipates about 6W total at a clock speed of 900MHz. (Source: IBM) That's gonna save you a bit more.
  
  And that's not to mention that it doesn't downclock itself when it needs to reduce power consumption. IIRC, it actually just shuts segments of the chip off, making the clock blips do *nothing* in entire areas of the die.
  
  And the PPC750FX isn't that expensive. Add to that IBM's efforts to add the Altivec SIMD unit to it, and you have a low-power, low-cost, low-heat chip that can run circles around Centrinos.
  
  X86 isn't as good as you think it is.
45. Re:well thats nice by vandan · 2004-01-13 08:16 · Score: 1
  
  I would have believed you until I read the 'openoffice' bit. Don't get me wrong, I love openoffice, and am pushing hard to move the other 50% of our office onto it, but it needs a fast processor ... no, no ... a very fast processor.
  
  Also you are discounting the effect of games. I only play about 3 hours per week, but it is nice to be able to play something other than Warcraft or Tuxracer.
46. Re:well thats nice by Anonymous Coward · 2004-01-13 08:33 · Score: 0
  
  sigh, every time a story involving new processors/video cards/whatever gets posted, someone makes a retarded "i don't need it" post like the parent and it always gets modded up
  
  gg fucking useless mods
47. Re:well thats nice by Datafage · 2004-01-13 08:49 · Score: 1
  
  That of course was the point of the parent. Someone attempting to calculate all of Pi will have an infinite amount of calculation to do and thus never be done and want the fastest possible to get as much of it done as possible.
  
  --
  Nicotine free Amish .sig.
48. Re:well thats nice by TeknoHog · 2004-01-13 08:53 · Score: 2, Funny
  
  By the way, just try a 3 Ghz processor for a while (maybe a week or two). Then go back your 700 Mhz system. You'll see the light.
  I saw the light, it was the glowing heatsink.
  
  --
  Escher was the first MC and Giger invented the HR department.
49. Re:well thats nice by Zathrus · 2004-01-13 09:01 · Score: 1
  
  No, I'm thinking of PowerPC 970, which has a "typical" dissapation of ~50W and maximum of ~75W. That's the only PowerPC chip that's even vaguely close in computing power to x86 chips.
  
  If you want to start talking about lower powered chips (as in computational capacity), then I'll happily bring up Via's line of x86 CPUs, which have extremely low power dissapation. Performance is roughly that of a P3, which is about the same as the 750FX. And they're really, insanely inexpensive.
50. Re:well thats nice by Predius · 2004-01-13 11:19 · Score: 1
  
  Best I can offer is my Cyrix 486 DRx2-66 running FreeBSD 4.9p1... See link above. : )
51. Re:well thats nice by Anonymous Coward · 2004-01-13 12:11 · Score: 0
  
  a 1000 Mhz fileserver? sheesh, that sounds about as bad as my 650 Mhz firewall ;)
  
  No kidding... I've got a 166MHz Pentium MMX that handles both jobs (with software RAID), and it's still almost completely idle. This is on OpenBSD too, which isn't exactly known for high performance.
52. Re:well thats nice by TheLink · 2004-01-13 15:08 · Score: 1
  
  I get 40MB/sec for a 7200rpm drive.
  
  Method:
  hdparm -d1 /dev/hda
  dd if=/dev/hda bs=131072 of=/mnt/backup/hdimage.img
  
  With compression:
  hdparm -d1 /dev/hda
  dd if=/dev/hda bs=131072 | gzip -c > /mnt/backup/hdimage.gz
  
  I find gzip -4 not significantly faster than the default -6. The default seems to be a decent balance between speed and compression ratio.
  --
  
  Too many replies beneath your current threshold
53. Re:well thats nice by TheLink · 2004-01-13 15:11 · Score: 1
  
  I said faster gzip.
  
  bzip2 is not faster, in my experience it is much slower.
  --
  
  Too many replies beneath your current threshold
54. Re:well thats nice by evilviper · 2004-01-13 16:39 · Score: 1
  
  Nope... I was using OpenBSD on a 233MHz system. I'd just let several of the ports build over-night, and come back.
  
  And BTW, the only program that didn't run more than fast-enough, was Mozilla... If mozilla was (significantly) faster, or if the faster web-browsers were more mature, I wouldn't have ever upgraded from my old 233.
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
55. Re:well thats nice by evilviper · 2004-01-13 16:44 · Score: 1
  
  your best bet is a processor with a fast bus and a slow clockspeed. It'll be cooler and more reliable than some 64 bit god
  
  A fast bus is good advice, but a slow clock isn't. Faster processors will run nice and cool assuming they don't have a high workload. Lets also not forget that newer processors are more energy-effecient than older processors anyhow.
  
  (honestly, who needs 64 bits to send packets?)
  
  For one thing, AMD64 are the systems with the fastest buses, so there's one reason.
  
  Secondly, encapsulation, encryption, and all that, are still done by the processor, so performance is an issue. Put a gigabit NIC in a slow machine, and watch it come to a grinding halt during the first interrupt storm. This could be resolved by NIC manufacturers putting more smarts in the NICs, but until then...
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
56. Re:well thats nice by evilviper · 2004-01-13 16:50 · Score: 1
  
  When you realize that the core ISA of all x86 chips is RISC let me know.
  
  A core does not make a chip. Nobody will claim that x86 is RISC. You might as well say that your truck gets good gas-mileage because you are towing a Geo Metro.
  
  Sure, the ISA is still a mess, but it's a better price/performance than anything else out there. All the naysayers have been disproven, time and time again.
  
  Well, while x86 processors may be nominally faster than the G5 and the like, the G5 does it at about half the wattage, so it's not like they are on remotely equal ground.
  
  You're definition of price/performance is only to apply it to the purchase price, no matter if the power usage costs many times that.
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
57. Re:well thats nice by superyooser · 2004-01-13 16:54 · Score: 1
  
  Unless you are a gamer or looking to compute Pi to the last digit, ...
  Or unless you plan on using Longhorn.
58. Re:well thats nice by evilviper · 2004-01-13 16:56 · Score: 1
  
  Sorry, buth the performance speil about VIA processors is bull. They perform at about half their rated speeds (eg. my 800MHz C3 performed like a 400MHz Intel/AMD proc), and the power consumption is a no-brainer... They have the same power consumption as old half-the-MHz Intel/AMD processors as well.
  
  I had this arguement with someone else on slashdot before... He continued to say that his 1GHz VIA performed like a 1GHz AMD/Intel processor, but he also said that playing a simple DVD used up 80% of his processor :-). Some people just have perception problems.
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
59. Re:well thats nice by FuzzyBad-Mofo · 2004-01-13 17:05 · Score: 1
  
  bzip2 is more processor intensive, however it will create smaller files. Therefore less disk activity. I guess there's a cpu threshold to overcome for bzip2 before you could realize an overall speed increase for archiving your data.
  
  Another thought that comes to mind is to gzip data from one disk to another (especially on SCSI drives or on independant IDE channels).
60. Re:well thats nice by Zathrus · 2004-01-14 02:36 · Score: 1
  
  You're definition of price/performance is only to apply it to the purchase price, no matter if the power usage costs many times that.
  
  You saw my post regarding this, so why bring it up again? The additional power usage is deeply unlikely to exceed the amount saved on the purchase price... even if it's only $100 (which, btw, it isn't... not even close).
  
  My definition of price/performance did not include "only" the purchase price... it also takes into account operation costs (electricity and cooling). If you'd like, I can throw in software availability... but that's not necessary.
61. Re:well thats nice by kill-1 · 2004-01-14 02:55 · Score: 1
  
  If you use dd you bypass the filesystem. Try cp.
62. Re:well thats nice by aliens · 2004-01-14 03:08 · Score: 1
  
  hehehe, that is pretty sweet, nerd kudos goes out to you and the 386!
  
  --
  -- taking over the world, we are.
63. Re:well thats nice by TheLink · 2004-01-14 03:12 · Score: 1
  
  Well I use dd for copying hard disks. cp sucks at that.
  --
  
  Too many replies beneath your current threshold
64. Re:well thats nice by Billly+Gates · 2004-01-14 03:38 · Score: 1
  
  Took almost a week on my athlonXP 1700 to install gnome, kde, openoffice, jdk1.4, emacs/xemacs,vim. loads of apps, php, etc.
  
  You have to admit a smp athlonMP +2700, would be quite nice for a clean ports install of 2.5 gigs worth of apps. That is what df reports on my FreeBSD box.
  
  --
  http://saveie6.com/
65. Re:well thats nice by evilviper · 2004-01-14 15:00 · Score: 1
  
  Took almost a week on my athlonXP 1700 to install gnome, kde, openoffice, jdk1.4, emacs/xemacs,vim. loads of apps, php, etc.
  
  Well, if it really did take that long, it certainly wasn't CPU-bound. Most likely that you either have a very slow hard drive, a slow net connection, or some other reason things weren't progressing.
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
66. Re:well thats nice by Anonymous Coward · 2004-01-19 07:02 · Score: 0
  
  You must be a Java programmer.
  
  Actually, I program mostly in C with some C++. I do high performance stuff though (3D applications and such). The machines are never fast enough.
Still not convinced by LookSharp · 2004-01-13 02:24 · Score: 4, Insightful

There's no question Athlon 64 and AthlonFX are great products. That being said:

*Do they really need to be different products? Opteron is your product for server/high-end workstations, Duron (and now Athlon XP) is low-end... you want Athlon64 to be mainstream, right?

*Is it really a good idea to have the memory controller on the CPU? OK, I buy that it increases performance, but it hasn't lowered mainboard costs and all I've seen it doing is causing a rift between the A64 and AFX product lines, since Athlon64 doesn't have a dual-channel memory controller.

*Why in the world introduce an AthlonFX based on Socket 940, especially at the outrageous price, when you're moving to socket 939 imminently?

I think it would have been more of a slam-dunk as a platform and a "brand" to release Athlon64 as all dual-channel, all Socket 939 (or some standard), and left Opteron as the high-end platform. Any other takers?
1. Re:Still not convinced by lwells-au · 2004-01-13 02:36 · Score: 3, Informative
  
  "Why in the world introduce an AthlonFX based on Socket 940, especially at the outrageous price, when you're moving to socket 939 imminently?"
  
  Simple really. AMD feared that Intel was about to release the next revision of the P4 aka. Prescott. The 940-pin FX was an attempt to get something out the door ASAP.
  
  Unfortunately that means that some people might be caught at a loose end when it comes to upgrade time, but that is not clear cut at this stage to my knowledge.
2. Re:Still not convinced by Firehawke · 2004-01-13 02:41 · Score: 1
  
  Well, the Athlon FX line seems to have been aborted shortly after birth-- I'm glad I didn't choose to buy right from the starting line, since this could have potentially costed me in a pretty large way.
  
  As for the A64, that's pretty much going to be the going line at this rate, it looks like. We'll see if there are any more changes in the next few months, but by summer we should be seeing good indications of where AMD will REALLY be going with this-- roadmap aside, reality doesn't always map out well.
  
  Socket 940.. well, covered that with Athlon FX. Really bad move, and it's one some people will definitely not be happy with.
3. Re:Still not convinced by diablobynight · 2004-01-13 02:42 · Score: 1
  
  OK, the first thing is that they released their outrageous priced processor to compete with Intel's Extreme edition of the Pentium. They knew it was outrageous, they just wanted to be competitive in all aspects of the market.
  
  On the other hand, your question about having the memory processor directly on the processor. It is the best idea ever, and you may not understand this, being a desktop user, but being in IT when I was young, and now in the money end of IS, I understand the value of the system amd is implementing, for instance sometimes I would purchase a quad Xeon system but it irritated me to do so, because I knew that because of the bottleneck to the memmory, my fourth processor was almost worthless. But with the memory controller on the proc, you amazingly reduce latency, and every time you add another processor you add more memory bandwidth, as apposed to each processor having to share a limited amount of memmory bandwidth on the board.
  
  AMD is on track for the future, even though it seems they are not doing what's best for your current desktop needs.
  
  --
  Anonymous Cowards - Oh God, How I hate you
4. Re:Still not convinced by LookSharp · 2004-01-13 02:50 · Score: 2, Interesting
  
  On the other hand, your question about having the memory processor directly on the processor. It is the best idea ever, and you may not understand this, being a desktop user, but being in IT when I was young, and now in the money end of IS, I understand the value of the system amd is implementing, for instance sometimes I would purchase a quad Xeon system but it irritated me to do so, because I knew that because of the bottleneck to the memmory, my fourth processor was almost worthless. But with the memory controller on the proc, you amazingly reduce latency, and every time you add another processor you add more memory bandwidth, as apposed to each processor having to share a limited amount of memmory bandwidth on the board.
  
  That argument makes sense for Opteron, but not Athlon 64/FX. OK, you want your cores as similar as possible to reduce costs, so you can argue that point... and I did acknowledge the performance increase; but does it make sense for the mainstream product line at this point, especially if it's not reducing the costs of mainboards?
5. Re:Still not convinced by LookSharp · 2004-01-13 03:00 · Score: 2, Informative
  
  Well, the Athlon FX line seems to have been aborted shortly after birth...
  
  Actually, read the roadmap. AthlonFX and Athlon64 will both be Socket939 and dual-channel memory controller products by the end of 2004. The chips will be the same, except A64 will have 512k cache and AFX will have a full meg.
  
  This actually makes a lot of sense, and should have been the way it was done from the start. No socket 754, no socket 940 (except Opterons), just a "mainstream" and a "performance" product.
6. Re:Still not convinced by Anonymous Coward · 2004-01-13 03:00 · Score: 0
  
  You have it all backwards. Intel released the P4EE last minute to try to spoil AMDs FX series. This is why you still can't buy the fantom P4EE... it isn't really a product! And, FYI AMD has made it public all a long that the Athlon 64 and 64 FX will be chaning sockets in 2004.
7. Re:Still not convinced by Anonymous Coward · 2004-01-13 03:07 · Score: 0
  
  1. The Althon 64 FX is for enthusiasts only. It is fully unlocked so you are free to overclock it however you like. It will have more cache than the regular Athlon 64 (see the roadmap) and it will potentially contain other Opteron specific enhancements over time.
  
  2. On-die memory controllers do increase performance buy quite a big margin because they decrease the response time (latency) of accessing memory. If you read the roadmap and analysis posted you will see that after the socket changes occur both the Athlon 64 and Athlon 64 FX will have dual channel memory controllers on a faster hypertransport bus.
  
  3. I don't know why, maybe because they don't want people trying to use the Athlon 64 FX as an Opteron replacement. As for the Athlon 64 socket switch I assume it is to account for the "upgrade" in the memory controller.
8. Re:Still not convinced by Anonymous Coward · 2004-01-13 03:16 · Score: 0
  
  phantom along changing
9. Re:Still not convinced by CaptnMArk · 2004-01-13 03:22 · Score: 1
  
  FX = relabeled Opteron
10. Re:Still not convinced by hirschma · 2004-01-13 03:37 · Score: 1
  
  Sorry about the formatting, Slashdot wouldn't let me make nice tables :(
  Your point is? Class Intel AMD Server(hi-end) Itanium Opteron Server(low-end) Xeon Opteron Workstation(hi) Xeon Opteron Workstation(lo) P4 A64FX MainstreamPC P4 A64 CheapPC Celeron AthlonXP Seems like they're rationalizing things at last, no?
11. Re:Still not convinced by nelsonal · 2004-01-13 03:37 · Score: 1
  
  The athlon 64 is just a way to keep costs reasonable on the Opteron, this was a chip designed from the start to get the server world's attention. There is no money in the PC business for AMD, they can't match Intel's huge operations, and R&D budget. The company bet the farm on building a server chip, but has to keep selling them to consumers because there are a ton of fixed costs, and even if you sell them at breakeven, you lower your average chip cost and stay competitive. If you changed the consumer part, you can not take advantage of the huge unit demand (AMD sells 20 million dice a year) to keep you costs low in the server market.
  The two noteworthy items so far have been Dell's continued refusal of the part, and SUNs acceptance. IBM still seems pretty agnostic about the whole thing, likely covering their bases, SUN will be promoting the daylights out of the thing in the coming months.
  
  --
  Degaussing scares the bad magnetism out of the monitor and fills it with good karma.
12. Re:Still not convinced by Anonymous Coward · 2004-01-13 03:55 · Score: 0
  
  This is why you still can't buy the fantom P4EE
  
  Um, You can't? You fanboys never stop talking out of your butts.
13. Re:Still not convinced by bogie · 2004-01-13 03:57 · Score: 1
  
  The AC has it right. Intel's outrageously overpriced Emergency Edition was a direct response to AMD's chip, Not the other way around. Do some googling if you still think your version of what happened is right.
  
  --
  If you wanna get rich, you know that payback is a bitch
14. Re:Still not convinced by Hoser+McMoose · 2004-01-13 06:25 · Score: 4, Informative
  
  The marketing of the Athlon64 FX has become a bit confusing. It kind of made sense for the initial launch to combat a precieved weakness of the design compared to Intel's P4 though. With the P4 you get up to 6.4GB/s of memory bandwidth, while the first Athlon64 would only have 3.2GB/s of memory bandwidth. Now, it turns out that the extra bandwidth doesn't actually buy you much on most applications, but this was seen as a weakness, hence the Athlon64 FX. With Intel bringing out the P4EE to compete with the FX, now AMD might need to keep the chip, even if it isn't a worthwhile product (The P4EE isn't a worthwhile product either).
  
  *Is it really a good idea to have the memory controller on the CPU?
  Yes, yes it is a good idea. A VERY good idea in fact. Memory latency has only improved by about one order of magnitude in the past 15 years. Meanwhile everything else in the system has gone up by at least two orders of magnitude. Virtually everything that is being done in CPU design these days is to hide memory latency (larger caches, out-of-order executation, branch prediction, even SMT).
  Integrating the memory controller reduces latency by 20-30%. At 2.0GHz this makes a BIG difference (this is the main reason why a 2.0GHz Athlon64 is faster than a 2.2GHz AthlonXP), at 4 or 5GHz the difference will be huge.
  
  but it hasn't lowered mainboard costs
  
  You can buy new Athlon64 motherboards for only $100, only 3 months after the chips release. It took ages for Athlon or P4 motherboards to reach that price point. What's perhaps even more impressive is the dual-processor boards that are only $200. In short, it HAS reduced motherboard costs, whether you've noticed or not. It also means that ALL Athlon64's support ECC, chipkill and a few other nifty reliability features, regardless of how badly VIA screws up their chipset design.
  
  *Why in the world introduce an AthlonFX based on Socket 940, especially at the outrageous price, when you're moving to socket 939 imminently?
  
  The Athlon64 FX was a bit of a last minute decision I believe. They found a marketing weakness and wanted the quickest and easiest solution they could find. The answer? Sell your server chip as an "enthusiast" chip. Intel did exactly the same thing for the same reason with the P4EE.
  
  Also, it's actually VERY normal to switch sockets soon after releasing a new processor. Intel's upcoming Prescott will use Socket 478 for only about 6 months before switching to socket 775. The original P4 used Socket 423 for a very short time before switching to socket 478. The original Athlon used Slot A for a year or so before switching to Socket A. The PIII came out in Slot 1 form but then switched to Socket 370 about a year later. The Celeron followed the same path a couple years before.
  
  I think it would have been more of a slam-dunk as a platform and a "brand" to release Athlon64 as all dual-channel, all Socket 939 (or some standard), and left Opteron as the high-end platform. Any other takers?
  
  In retrospec that might seem like a good idea, hindsight is 20-20 after all. However the original split of ALL Athlon64 chips being socket 754 and ALL Opteron's being socket 940 seemed to make the most sense when AMD was desigining them. It wasn't until market conditions changed and a new perceived weakness was discovered that AMD felt they need a consumer chip with a 128-bit wide memory bus. By that time the chip was already late to market and designing a new socket would have added more delay to the equation.
  
  There's also the question of budget chips. AMD hopes to move their entire product line to the Athlon64/Opteron platform by the end of 2004. That means they need a budget chip, and socket 939 with it's 128-bit wide memory bus is problematic for that. Hence the continued existance of Socket 754 and the AthlonXP for that platform.
15. Re:Still not convinced by Clay+Pigeon+-TPF-VS- · 2004-01-13 08:00 · Score: 1
  
  You forgot to include the p4 emergency edition.
  
  --
  Viral software licensing is not freedom, it is in fact GNU/Socialism.
16. Re:Still not convinced by Groo+Wanderer · 2004-01-13 08:00 · Score: 1
  
  "*Why in the world introduce an AthlonFX based on Socket 940, especially at the outrageous price, when you're moving to socket 939 imminently?"
  
  S939 was designed for 2 purposes, to allow for 4 layer mobos and to use non-registered DDR400. This saves you money, and gives you better performance. I don't tend to complain about either scenario much.
  
  -Charlie
17. Re:Still not convinced by evilviper · 2004-01-13 16:36 · Score: 1
  
  Unfortunately that means that some people might be caught at a loose end when it comes to upgrade time,
  
  I really don't understand this sentiment at all.
  
  Tell me something... When was the last time that you upgraded your processor, but not your motherboard with it? I certainly can't remember the last time I did so (maybe an old 48633 to 486/66). I rarely see that happening... For the extra few dollars you spend on a mobo, you now have 2 working systems, instead of only 1 (and something to drill a hole into, and put on your keychain).
  
  --
  Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
18. Re:Still not convinced by akuma(x86) · 2004-01-25 21:39 · Score: 1
  
  Integrating the memory controller reduces latency by 20-30%. At 2.0GHz this makes a BIG difference (this is the main reason why a 2.0GHz Athlon64 is faster than a 2.2GHz AthlonXP), at 4 or 5GHz the difference will be huge.
  
  So reducing latency by 20-30% is "huge", but only having half of the bandwidth (3.2 vs 6.4) is no biggie? Many memory accesses can get prefetched so latency isn't as big a deal as you make it out to be. Of course, if you're prefetching, more bandwidth will help you out considerably.
  
  I guess you don't encode DVDs to DIVX or do any high performance floating point work?
Learn Moocais! by Anonymous Coward · 2004-01-13 02:27 · Score: -1, Offtopic

Mooscais (Pronounched Moosay) is the offical language of the Mookore trolling group. The language is still in beta stages (like most open sores projects) and will probably not be intelligable to 90% of the non trolling population. But we are working on it, and here is a word from are sponsors, in moocais of course.

Moocoro iz eno ojanicayono mit nigo gai de veldo fon eno purpo. Jent nigo gai!

Ma Nigo?
Ma Gai?
Ma Nigo Gai?

vaj lo Nigo Gai Abocayono Ameriko (NGAA).

iso, abtaino lo moewei "Gay niggers from outer space" ond cejen ne.
zvie, wecit irc.efnet.net $NGAA ond abko vuer iso applicayono form.
vienal, obtayno iso "First Post" lo Slashdot
Quat, vindo Cowboyneal ond kallo Obeco!

Lo proyto provia MooCoro (Mookore 2004), en hapze momo do NGAA!
1. Re:Learn Moocais! by Anonymous Coward · 2004-01-13 04:33 · Score: -1, Troll
  
  ..here is a word from are sponsors..
  
  Maybe you should work on English before you start inventing new languages, you herpes riden cum-bucket.
Roadmap? by Brian+Dennehy · 2004-01-13 02:29 · Score: -1, Offtopic

I can see my house!
Global Warming by Anonymous Coward · 2004-01-13 02:30 · Score: 4, Funny

Wow if these new chips radiate at a proportionate level to AMDs current offering we could all be wearing shorts in Antartica by new year 05.

Seriously tho. I think AMD ought to work some better thermal performance into its cpu range. A low cost, low temperature, high performance CPU is what is required in the market.
1. Re:Global Warming by Anonymous Coward · 2004-01-13 02:38 · Score: 1, Funny
  
  Ladies and gentlemen of slashdot, this troll is starving. Will someone please feed the troll? Think of the children.
2. Re:Global Warming by Anonymous Coward · 2004-01-13 02:49 · Score: 0
  
  Please remember that Intel is not to be left behind here. Perhaps you haven't noticed by P4s at high clock speeds radiate quite a bit. In fact, remember the die shrink to the P4 that was supposed to be out now? Yah, they're having a problem getting heat out of the core due to the smaller surface area to contact the heatsink.
3. Re:Global Warming by Anonymous Coward · 2004-01-13 02:54 · Score: 1, Informative
  
  i dunno whart you're talking about, most AMD chips put out between 60-75 watts, and the intels are running up to 90-100 watts. people must drop the misconception that amd runs hotter because they really dont.
4. Re:Global Warming by JamesP · 2004-01-13 04:04 · Score: 0
  
  A low cost, low temperature, high performance CPU is what is required
  
  Yadaa, yadda, yadda...
  
  As if Intel is Low cost, high performance, low temperature...
  
  Wanna low temp and "acceptable" performance? Try VIA and Transmeta...
  
  --
  how long until /. fixes commenting on Chrome?
5. Re:Global Warming by hattig · 2004-01-13 06:06 · Score: 4, Interesting
  
  This whole AMD is hotter than Intel thing was true when Intel's flagship processor was the cool (relatively) PIII.
  
  The P4 generates more heat than the Athlon (any variant) for the same performance.
  
  It is such an old, and incorrect joke it isn't even funny anymore.
6. Re:Global Warming by CmdrTHAC0 · 2004-01-13 06:17 · Score: 1
  
  Required in what market? I should think that if there was such a demand, instead of chips putting out 70W, we would see VIA C3 or Transmeta-based offerings taking over the world.
  
  --
  __CmdrTHAC0__
  In Soviet Russia, Spanish Inquisition doesn't expect YOU!!
7. Re:Global Warming by VoraciousGorak · 2004-01-13 14:11 · Score: 1
  
  If I may expand on this, the Pentium 4 also has two thermal diodes. The first, which is placed in the center of the core, is what the CPU uses for its own measurements for throttling. The second, placed near the edge of the die in a cooler zone, reports temperatures to the end user... and in addition to being in a relatively cool part of the CPU, it reports temps at least 10 degrees centigrade below what it actually registers.
MOD PARENT DOWN! IS KARMA WHORE! by Anonymous Coward · 2004-01-13 02:32 · Score: -1

EVERY time a story about fast processors, over clocking or fast computers come out, Some karma whore says some crap like this! It is redundant! Please mod it down, as he is abusing the Moderation system at Slashdot for his own personal gain! To help with stopping abuse of karma, visit http://anti-slash.org/. Keep your smelly old computer you smelly troll!
1. Re:MOD PARENT DOWN! IS KARMA WHORE! by Anonymous Coward · 2004-01-13 02:52 · Score: 0
  
  Yes indeed, the AC you replied to will collect loads of karma so that he won't have to post at 0 anymore.
  
  retard!
2. Re:MOD PARENT DOWN! IS KARMA WHORE! by LookSharp · 2004-01-13 02:55 · Score: 1
  
  Nice response, anonymous coward. First of all, I wasn't karma-whoring, I was making three (in my opinion) logical points about what I dislike in AMD's processor architecture choices.
  
  If you don't like reading informative remarks, well-reasoned opinons, or getting factual link, I guess you can go somewhere else.
3. Re:MOD PARENT DOWN! IS KARMA WHORE! by Anonymous Coward · 2004-01-13 03:14 · Score: 0
  
  EVERY time a story about fast processors, over clocking or fast computers come out, Some karma whore says some crap like this! It is redundant! Please mod it down, as he is abusing the Moderation system at Slashdot for his own personal gain! To help with stopping abuse of karma, visit http://anti-slash.org/. Keep your smelly old computer you smelly troll!
  
  Moocoro, lero moocais zemero!
4. Re:MOD PARENT DOWN! IS KARMA WHORE! by vida · 2004-01-13 03:57 · Score: 1
  
  If you don't like reading informative remarks, well-reasoned opinons, or getting factual link, I guess you can go somewhere else. and where would we find these again?
Socket, shmocket ... I want RAM! by ackthpt · 2004-01-13 02:35 · Score: 5, Insightful

The only reason I'm even considering one of these gems is so I can cram more memory into a system for video work. All the boards I've seen for Athlon 64 max at 3Gb. The SK8* boards for the Athlon FX will take, IIRC 8Gb. Where's the boards I can cram 32 or more into?

--

A feeling of having made the same mistake before: Deja Foobar
1. Re:Socket, shmocket ... I want RAM! by BigDumbAnimal · 2004-01-13 02:46 · Score: 5, Funny
  
  Call Sun.
2. Re:Socket, shmocket ... I want RAM! by Duncan3 · 2004-01-13 02:50 · Score: 1
  
  That is a "server" part. You can get those boards a variety of places for about $25,000 each.
  
  After all, only the fotune 500 buy "servers", they can afford it ;)
  
  --
  - Adam L. Beberg - The Cosm Project - http://www.mithral.com/
3. Re:Socket, shmocket ... I want RAM! by ackthpt · 2004-01-13 02:58 · Score: 1
  
  That is a "server" part. You can get those boards a variety of places for about $25,000 each.
  Bah!
  What we're seeing is the same old motherboards Taiwan, Inc. has been cranking out for 32bit CPU's for ages, no real redesign to take advantage of that 64 bit architecture. I can understand it to a small degree, but honestly, isn't the real reason for getting an Athnlon 64 so you can go beyond 4 Gb? Otherwise, it's just an Athlon on steroids, as far as I'm concerned.
  Maybe when they have on of those big tech shows in Taiwan in the near future, they'll unveil something.
  I waited all this time for the 64b CPU's to hit the shelves now I'm waiting on mobos... foo.
  "3 Gigabytes should be enough for anybody."
  
  --
  
  A feeling of having made the same mistake before: Deja Foobar
4. Re:Socket, shmocket ... I want RAM! by Eric+Sharkey · 2004-01-13 02:59 · Score: 3, Informative
  
  Where's the boards I can cram 32 or more into?
  
  Here.
5. Re:Socket, shmocket ... I want RAM! by __aahlyu4518 · 2004-01-13 03:00 · Score: 1
  
  32Gb Memory for video-editing??? Jeezzz... that 61 inch plasma screen only has a 1365x768 resolution !
6. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 03:13 · Score: 0
  
  He's future-proofing his video editing operation for the next generation of resolution-enhanced breast implants ;-)
7. Re:Socket, shmocket ... I want RAM! by Jeff+DeMaagd · 2004-01-13 03:15 · Score: 1
  
  32GB is clear into the heavier iron territory and not for toys.
  
  I think the Tyan K8W Thunder may be your best bet, but I'm not sure it can do 32GB. It is Opteron-only. If you need it that sort of power, it is well worth it.
8. Re:Socket, shmocket ... I want RAM! by __aahlyu4518 · 2004-01-13 03:19 · Score: 1
  
  With breast-implants that take full advantage of such amount of RAM.... I'd need bigger hands as well !
9. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 03:22 · Score: 0
  
  I've got a hard-on, already.
  
  Seriously, though, I really do.
10. Re:Socket, shmocket ... I want RAM! by DarkSarin · 2004-01-13 03:22 · Score: 1
  
  16GB for the dual proc, 20 for the quad..which isn't available yet
  
  --
  "We don't know what we are doing, but we are doing it very carefully,..." Wherry, R.J. Personnel Psychology (1995)
11. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 03:27 · Score: 0
  
  Not if you run VMWare or host a server for gaming etc..
  
  Maybe web server with the DB cached into memory for performance?
  
  32GB != Big Iron, its server/workstation territory. Big iron is mind boggling.
12. Re:Socket, shmocket ... I want RAM! by Slack3r78 · 2004-01-13 04:09 · Score: 1
  
  Have you considered the fact that the cost of that much RAM is prohibitive to 95%+ of the population? At 3GB, you're already talking around $600 in cost just for memory. The poster asserting that this qualifies as a server part in today's terms is correct - for the most part only corporations are going to need/be able to afford that much memory at this time.
13. Re:Socket, shmocket ... I want RAM! by TobySmurf · 2004-01-13 04:57 · Score: 1
  
  Indeed, I have a server here at work (HP 9000) with 128GB of memory, and it can hold a *lot* more than that. Go HP-UX!
14. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 05:06 · Score: 0
  
  The current Athlon64/Opteron line is limited to 8G per CPU using 4x2G DIMM's. If you want 32G, then you need a quad or higher system and shell out the bucks ($1000+ per cpu alone). Go look at the specs on 4 and 8 processor systems for your requirements.
15. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 06:45 · Score: 0
  
  It's called the Tyan K8W. It will go to 16GB dual-channel. The Tyan K8S may be able to go higher, but I don't recall.
16. Re:Socket, shmocket ... I want RAM! by Groo+Wanderer · 2004-01-13 08:07 · Score: 1
  
  Actually, you can get 32 into any dualy board, 64 into the one you linked. I was asking some of the AMD memory people at the Opteron launch some questions, and one thing they said was it supports 4GB dimms. They don't promote this fact because there is no standard 4GB dimm out. That said, any decent dualy board will support 32GB.
  
  -Charlie
17. Re:Socket, shmocket ... I want RAM! by Gramberto · 2004-01-13 09:08 · Score: 1
  
  At work we have 8GB of RAM, but those are Solaris boxes that cost $70,000. I was on another project with a $250,000 server that had 16 GB of RAM.
  
  Those prices will drop in time. By 2005 you will probably see 6-8GB boards for less than $2000. So very high end gamers will buy it.
  
  Then in 2006, they will become affordable. That is pretty fast. Games won't be developed that need that much RAM for a while anyway. The only reason you need tons of RAM this day is if you run a server.
18. Re:Socket, shmocket ... I want RAM! by Eric+Sharkey · 2004-01-13 10:45 · Score: 1
  
  there is no standard 4GB dimm out
  
  Actually there is. You can get them from Crucial, but so far they're only available in PC2100 speeds, while many boards require PC2700. Not to mention the fact that they're rediculously expensive.
19. Re:Socket, shmocket ... I want RAM! by coopaq · 2004-01-13 11:54 · Score: 1
  
  I love you. Can you send me some money?
  The following is actually cheaper than your 32GB of memory:
  Seriously just pay me and I'll outsource your video
  processing needs to India for manual
  calculation and have them back to you in no time.
  What do you say?
  (note: 1 stick 1GB DDR400 = $375 )
20. Re:Socket, shmocket ... I want RAM! by AMDude · 2004-01-13 13:18 · Score: 1
  
  Well than you certinly wouldn't buy Windows XP! Or maybe I'm just prejudice :)
  
  --
  Game Maker Community
21. Re:Socket, shmocket ... I want RAM! by Anonymous Coward · 2004-01-13 13:24 · Score: 0
  
  I can understand it to a small degree, but honestly, isn't the real reason for getting an Athnlon 64 so you can go beyond 4 Gb? Otherwise, it's just an Athlon on steroids, as far as I'm concerned.
  
  That's *exactly* what the Athlon64 is aimed at - it's the successor to the AthlonXP series. To the market it's targeted at, the reason to buy one is that it performs better than other desktop chips, and the ability to handle larger amounts of memory is merely a bonus that no-one's really taking advantage of yet.
  
  If you want to put 12Gb of memory into a desktop, that's what your Opteron-based workstation boards are for...
22. Re:Socket, shmocket ... I want RAM! by Groo+Wanderer · 2004-01-13 15:52 · Score: 1
  
  There are lots of 4GB Dimms floating, but as of yet, no standards body has approved them, and probably none will, they will be supplanted by DDR2 before they are needed by the mainstream.
  
  -Charlie
MOD PARENT DOWN! IS KARMA WHORE! by Anonymous Coward · 2004-01-13 02:38 · Score: -1, Offtopic

EVERY time a story about fast processors, over clocking or fast computers come out, Some karma whore says some crap like this! It is redundant! Please mod it down, as he is abusing the Moderation system at Slashdot for his own personal gain! To help with stopping abuse of karma, visit http://anti-slash.org/. Keep your smelly old computer you smelly troll!

Moocoro, lero moocais zemero!
socket types by ynohoo · 2004-01-13 02:40 · Score: 5, Funny

Hopefully this will shed some light on what AMD is trying to do with all the different socket types..

Making us buy more motherboards, of course!

--
need a free COBOL editor for Windows?
1. Re:socket types by Anonymous Coward · 2004-01-13 02:52 · Score: 0
  
  What i want is dual cores, stacked N way CPUs and optical hypertransport. All these are a reality, just not on the desktop yet.
2. Re:socket types by Peldor · 2004-01-13 06:53 · Score: 0
  
  Making us buy more motherboards, of course!
  The funny (not ha-ha funny) part is, they don't make the motherboards. Really I think AMD is hurting themselves with the extra confusion. People have been waiting on the whole socket plan to shake out instead of buying.
MOD PARENT DOWN! IS KARMA WHORE! by Anonymous Coward · 2004-01-13 02:40 · Score: -1, Troll

EVERY time a story about fast processors, over clocking or fast computers come out, Some karma whore says some crap like this! It is redundant! Please mod it down, as he is abusing the Moderation system at Slashdot for his own personal gain! To help with stopping abuse of karma, visit http://anti-slash.org/. Keep your smelly old computer you smelly troll!

Moocai, becozo ingliz sukz NGAA kocz
Dual Processors? by Krieger · 2004-01-13 02:45 · Score: 5, Interesting

What the article does not cover, is when we will be able to purchase non-Opteron Dual processors. Since they are inherently capable, it would be nice to know when we'll be able to build a performance (non-ECC) dual desktop.
1. Re:Dual Processors? by Anonymous Coward · 2004-01-13 03:51 · Score: 0
  
  ECC hardly makes a dent in performance or cost.
  
  Props to AMD to marketing their dual systems to professionals and not riceboys like the above poster.
2. Re:Dual Processors? by Jeff+DeMaagd · 2004-01-13 03:54 · Score: 1
  
  I thought like AFX, Opteron supports ECC, not requires it. IIRC it does require registered memory though.
  
  Not that it matters to me, I just stick ECC into everything I can, it really isn't that much more expensive. While it might slow performance a tad, ECC becomes even more necessary if you need to use multiple gigabytes of RAM.
3. Re:Dual Processors? by brucmack · 2004-01-13 04:30 · Score: 1
  
  The Athlon64 FX51 supports dual processors and non-ECC memory. It requires registered memory, however. That's what makes the memory expensive, not the fact that it's got ECC (I've seen lots of OEM machines at work that have ECC SDRAM in them).
4. Re:Dual Processors? by Krieger · 2004-01-13 05:21 · Score: 1
  
  Ah, yes. My bad. Registered memory and ECC, both are performance hits. And from the reviews I've seen relatively significant performance hits (5-10% potentially). Didn't know the A64FX supported dualie. Wishful thinking to hope for a A64 3x00+ that supports dualie without the requirement for registered memory, or are they fixing that in the newer A64FXs?
5. Re:Dual Processors? by Wesley+Felter · 2004-01-13 05:28 · Score: 1
  
  What the article does not cover, is when we will be able to purchase non-Opteron Dual processors.
  
  Because the answer is never.
6. Re:Dual Processors? by Visaris · 2004-01-13 07:40 · Score: 1
  
  You cannon purchase non-Opteron AMD64 processors that are capable of running dual. The reason is simple. The Athlon 64 line does not have enough hyper-transport links to connect to both another CPU and to the motherboard. The Opterons however, have more HT links. If you want to go dual, buy a couple Opteron.... That's what I did.
  
  --
  
  I am a viral sig. Please help me spread.
7. Re:Dual Processors? by Bedouin+X · 2004-01-13 08:20 · Score: 1
  
  Opterons require registered RAM. They won't even boot up without it.
  
  --
  Dissolve... Resolve... Evolve...
What roadmap, where are the Opterons ? by Erik_ · 2004-01-13 02:46 · Score: 0

I see the slashdot title AMD Roadmap reveal and I say Yah!!! what's my dream Opteron cpu for 2004 ? and ... nothing...
A prayer for the return of Camelot in 2004 by Anonymous Coward · 2004-01-13 02:50 · Score: 0

What kind of peace do I mean?

What kind of peace do we seek?

Not a Pax Americana enforced on the world by American weapons of war.

Not the peace of the grave or the security of the slave.

I am talking about genuine peace, the kind of peace that makes life on earth worth living, the kind that enables men and nations to grow and to hope and to build a better life for their children--not merely peace for Americans but peace for all men and women--not merely peace in our time but peace for all time.
1. Re:A prayer for the return of Camelot in 2004 by Anonymous Coward · 2004-01-13 02:53 · Score: -1, Troll
  
  Go and practise your kumbaya-singing commie-peacenik crap somewhere else.
Real Mhz on the 4000 chip? by MongooseCN · 2004-01-13 02:54 · Score: -1, Flamebait

What's the real Mhz on the 4000+ chip? I'm sick of AMDs false advertising. The benchmarks on Toms Hardware constantly shows AMDs false cpu rate underperforming Intels real CPU rate.

Looking at Toms now, AMDs 3200+ chip benches slower than Intels P4 2.8.

--

Outdoor digital photography, mostly in New Engl
1. Re:Real Mhz on the 4000 chip? by Anonymous Coward · 2004-01-13 03:02 · Score: 0
  
  Huh?
  
  Are you only looking at the one page on video encoding and ignoring every
  other benchmark on that hardware site and all the others???
2. Re:Real Mhz on the 4000 chip? by DanglingPointer2004 · 2004-01-13 03:17 · Score: 5, Insightful
  
  False advertising? It's called marketing. They never said "Our 3200+ is equivalent to Intel's P4 3.2C". Find that on the AMD site and you are making sense. Also, compare a duron chip to a celeron chip that are "rated the same". There is no comparison, but then, neither company specifically said "these two chips are the same speed", so you can't really complain. You can't blindly trust a number to tell you how well a processor will perform, there's a lot more to it than MHz and GHz. As for Tom's Hardware, I would look at who pays their bills before counting on their "benchmarks" too closely.
3. Re:Real Mhz on the 4000 chip? by nelsonal · 2004-01-13 03:40 · Score: 1
  
  I'd guess it would be in the 2.5-2.6 GHz range, the fastest 64 bit stuff is in the low 2 Ghz range now.
  
  --
  Degaussing scares the bad magnetism out of the monitor and fills it with good karma.
4. Re:Real Mhz on the 4000 chip? by Loki_1929 · 2004-01-13 05:23 · Score: 1
  
  "As for Tom's Hardware,"
  
  Anyone waving Tom's Hardware in your face is part of the "Knows Just Enough to be Dangerous" crowd anyway. These are the folks who think that reading a dumbed-down article or review makes them knowledgable enough to render a viable opinion.
  
  They're also the people who burn up their mainboard and CPU trying some voltage mod they read about, then want to return everything for a refund because it no longer works.
  
  --
  -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
5. Re:Real Mhz on the 4000 chip? by philminatz · 2004-01-13 07:05 · Score: 1
  
  "They're also the people who burn up their mainboard and CPU trying some voltage mod they read about, then want to return everything for a refund because it no longer works."
  You say that like it's a bad thing
6. Re:Real Mhz on the 4000 chip? by Anonymous Coward · 2004-01-20 23:53 · Score: 0
  
  You say that like it's a bad thing
  
  It is if you shop at Fry's. It's customers like that who keep me from finding an unopened product there.
G5 looks like ramping up faster by beelsebob · 2004-01-13 02:55 · Score: 5, Interesting

By the look of the figures the Athlon 64 is margionally faster than the G5 clock for clock... (the 2.2 Ghz beating the 2 Ghz G5 convinvingly and the 2Ghz ones locked in a tight battle). It looks a lot like AMD are gonna have to ramp up faster though, because IBM are gonna have 3Ghz G5s by Q3 this year, and AMD are only saying 2.6Ghz by Q4. Bob
1. Re:G5 looks like ramping up faster by Junks+Jerzey · 2004-01-13 03:23 · Score: 4, Interesting
  
  IBM hasn't hit the power/heat problems that Intel has, primarily because the PPC is a more streamlined processor. It's still very complex, mind you, but the x86 line is so complex, with all of the legacy support and CISC to RISC conversion and wacky nonsense like MMX *and* SSE *and* SSE2 all at the same time. Intel is already talking 150 watts for processors to be released this year. It is quite likely that the PowerPC line is going to pass Intel in the next 8 to 12 months.
2. Re:G5 looks like ramping up faster by Anonymous Coward · 2004-01-13 03:51 · Score: 0
  
  Meh, so far Intel always comes up with something to fix everything. They have always done this.
  
  They keep pushing current technology until it becomes unwieldy (like 150W processors) then they miraculously introduce some new technology (smaller fab techniques, etc; all of this is planned, I'm sure). Then all is well and they keep the top spot.
  
  AMD still has compatibility problems, motherboard chipset issues, heat problems, and all sorts of things that keep them off the top spot.
3. Re:G5 looks like ramping up faster by Slack3r78 · 2004-01-13 04:13 · Score: 1
  
  AMD still has compatibility problems, motherboard chipset issues, heat problems, and all sorts of things that keep them off the top spot.
  1. Name one. 2. NForce2 3. P4's heat dissipation is higher. Nice try at a troll though.
4. Re:G5 looks like ramping up faster by brokenbeaker · 2004-01-13 06:07 · Score: 2, Informative
  
  I don't know much about processor design, but one problem of the IBM POWER series is that they are NOT very streamlined. They in fact use more transistors to do the same job as other designs (I think the Alpha is a good counter example). This is because IBM uses automated design techniques. The tradeoff for the less efficiency is faster development. see for example,
  
  http://www.research.ibm.com/journal/rd/461/warno ck .html
  
  http://pix.cs.olemiss.edu/csci523/64bit.html
  
  http://www.research.ibm.com/compsci/spotlight/de si gn_automation/ddh.pdf
  
  I'm sorry i can't relocate the original article, but maybe this helps.
5. Re:G5 looks like ramping up faster by Hoser+McMoose · 2004-01-13 06:41 · Score: 1
  
  IBM seems ot be well ahead of AMD in moving towards a 90nm manufacturing process. The new Xserve G5's have already been announced with 90nm PPC970 chips and they should ship in 6-8 weeks, making it a close second to Intel's 90nm chips (which should actually be available in two to three weeks time). AMD is going to be a little bit late to the show (not surprising, they don't have the financial resources of Intel or IBM, so they're always ~6 months behind in bringing out a new process generation).
  
  Of course, I wouldn't hold my breath for 3GHz G5's by Q3. 2.5GHz PPC 970 processors by mid-summer sure, no problem. But 3.0GHz? It's possible, but certainly not a sure thing. I fully expect the clock speeds of these two chips to remain pretty comperable for some time to come.
6. Re:G5 looks like ramping up faster by Junks+Jerzey · 2004-01-13 08:58 · Score: 1
  
  I don't know much about processor design, but one problem of the IBM POWER series is that they are NOT very streamlined.
  
  They are FUNCTIONALLY streamlined. Just look at the PowerPC instruction set and architecture as compared with the x86.
  
  That IBM is using automated design is a good thing, because it means that any improvements they make to their design tools will be felt across the board.
7. Re:G5 looks like ramping up faster by StarCat76 · 2004-01-13 09:51 · Score: 1
  
  Intel is already talking 150 watts for processors to be released this year.
  
  Initially people thought this was the case, but it seems to be clear as of late that Intel's Prescott will use about as much power clock for clock as Northwood, due to the smaller procwss used (90nm).
  
  It is quite likely that the PowerPC line is going to pass Intel in the next 8 to 12 months.
  
  Regardless of what you think about Intel's products, they have a good sized market share, which is not the kind of thing that will change within a year. Customers want high clockspeeds, regardless of performance, and vendors are only happy to oblige. However, even if the everyone in the market all decided simultaneosly that they should switch to a different architecture, that would not be enough to put PPC in front of Intel within a year; All the applications would have to be recompiled and such. Or perhaps I misinterpreted what you said. In my opinion, Intel will remain the company with the largest CPU market share for at least three more years. Their most dangerous competitor is AMD, because the CPU's of each run the same code.
8. Re:G5 looks like ramping up faster by beelsebob · 2004-01-14 04:48 · Score: 1
  Two reasons why I expect 3Ghz G5s by Q3:
  
  Steve Jobs announced that that was the plan last year and IBM seem to be sticking to the plan pretty closely.
  
  2.4 or even 2.6 Ghz G5s are widely rumoured to be announced on the 24th (20th anniversary of mac).
  
  Bob
9. Re:G5 looks like ramping up faster by htacoma · 2004-01-14 06:24 · Score: 1
  
  ...rather strange all that is happening!
  
  IBM Sells Computer Using AMD Chip to Bristol-Myers
  Wed January 14, 2004 01:02 AM ET
  
  Cheers!
  
  --
  ~ Artificial Intelligence is better than none! ~
10. Re:G5 looks like ramping up faster by brokenbeaker · 2004-01-15 18:18 · Score: 1
  
  I see what you mean. How about the comments flying around that ever since the pentium days, and with modern compilers, the x86 chips are very much like the RISC architectures? Is it possible that the busy instruction sets boil down to a serius of micro-ops?
Top 5 things you will do with your Athlon64... by Realistic_Dragon · 2004-01-13 03:00 · Score: 4, Funny

Run Doom 3.
Compute Pi to 5.497558e+11 bit precision during your lunchbreak.
Store this value of Pi in RAM.
Install Kazaa and not notice the spyware slowdown.
Use the faster page loading times to get FP more often.

--
Beep beep.
1. Re:Top 5 things you will do with your Athlon64... by Billly+Gates · 2004-01-13 03:07 · Score: 1
  
  hate to say it but a 4000mhz system will be the bare minium like a 486dx2/66 was in its day to play doom1/doom2 fluidly. Expensive yes but nice for such an app.
  
  I would not want to run doom3 on my athlonXP 1700 with a limited geforce4TI. That is for usre.
  
  --
  http://saveie6.com/
2. Re:Top 5 things you will do with your Athlon64... by LDoggg_ · 2004-01-13 03:35 · Score: 2, Insightful
  
  I would not want to run doom3 on my athlonXP 1700 with a limited geforce4TI. That is for usre.
  
  I seem to remeber the leaked demo running playably on a 1Gig celery and geforce2 MX.
  You'd think they've had plenty of time to optimize code since then.
  
  --
  
  "If they have both, tell them we use Linux. And if they have that, tell them the computers are down." -Dave Chapelle
3. Re:Top 5 things you will do with your Athlon64... by Anonymous Coward · 2004-01-13 05:11 · Score: 0
  
  So basically you're saying that the guys at ID have been testing a slide show? Your "bare minimum" doesn't exist yet.
  
  I don't agree with you. It must be running very nicely on say, an Athlon XP 2600+ and a Radeon 9800 pro.
4. Re:Top 5 things you will do with your Athlon64... by Anonymous Coward · 2004-01-13 06:09 · Score: 0
  
  I think you forgot "???" and "Profit!!" //FFT
5. Re:Top 5 things you will do with your Athlon64... by Peldor · 2004-01-13 06:56 · Score: 0
  
  Plan my real estate purchases by figuring out how much global warming and coastal flooding we'll have in 2050.
6. Re:Top 5 things you will do with your Athlon64... by Billly+Gates · 2004-01-14 03:40 · Score: 1
  
  I run an athlonXP 1700 with a geforce2MX. Doom3 is unplayable. My guess is because the video ram is underclocked and only sdram on my geforce.
  
  --
  http://saveie6.com/
Socket hell by freidog · 2004-01-13 03:03 · Score: 4, Insightful

So 940 gets moved to opteron only
939 encompasses both Athlon64/FX chips, starting in Q2.
754 is relegated to the next gen AthlonXPs (with the on die memory controller, but only 32 bit)
462 dies a slow death.

Why can't every CPU made just fit on Socket 7... :)
1. Re:Socket hell by scharkalvin · 2004-01-13 04:49 · Score: 1
  
  Looks like 3 different athlon 64's.
  socket 754 is single channel memory.
  socket 939 (won't fit opteron) with dual channel
  ram. 1m cashe = FX, 1m is athlon 64.
  
  Will socket 939 chips work in socket 940 mb?
  current athlon64fx chips will work in opteron mbs.
2. Re:Socket hell by Cyno · 2004-01-13 05:08 · Score: 1
  
  Or if you must build a new socket call it socket 8, design it the right way, and attempt to build backwards capatibility into some sort of bridges or something.
3. Re:Socket hell by addaon · 2004-01-13 06:08 · Score: 1
  
  This is a wretched idea. Lets assume for a moment you could do the backwards compatibility, which means changing what pins mean, changing bus widths, and changing voltages... you still run into the problem that pin numbers only go up (from 32 on my first computer to over 4000 on the Power4 I play with now)... which means you'd have to supply more pins than you need. Even if you only supply twice as many pins as needed today... the socket is the most expensive component on most motherboards, and making it more expensive would be deeply silly.
  
  --
  
  I've had this sig for three days.
4. Re:Socket hell by Cyno · 2004-01-13 06:23 · Score: 1
  
  How did they get those Pentium chips to run in 486 motherboards? Wasn't that some sort of socket bridge they built between the CPU and the board? At least until they started making pin-compatible 586 class CPUs for the old 486 motherboards as options to upgrade to people who already purchased the old hardware. I see no reason why they couldn't do this same thing between low and high end 32-bit chips, and eventually 64-bit or whatever the future holds if they planned for it ahead of time.
  
  BTW, why do you think they keep increasing pin count? Do you think a 10000 pin chip would be faster than a 4000 pin chip or something? I bet only about half the pins are actually needed to make the system operational. 800 pins is probably more than enough for this generation of technology. So why not standardize the socket type?
5. Re:Socket hell by addaon · 2004-01-13 06:42 · Score: 1
  
  Do you think a 10000 pin chip would be faster than a 4000 pin chip or something?
  
  Not to put too fine a point on it, yes. Let's pretend there are only two things going over all those pins: access to main memory, and power.
  
  How many power pins do we need? On modern (Pentium and further) processors, a good guideline is that half of the pins are power pins, although sometimes its as low as a third. Todays processors use at least 400 power pins. Why so many? Because it takes really low resistance to get 60A across a wire effectively... this includes the pins themselves, but also inside the chip the distance power can travel is limitted. Can you reduce this number of pins? Well, yes, if you're willing to reduce the quality of your power supply... which means decreasing the clock speed to keep reliability.
  
  How many memory pins do we need? It depends. If we just want to be able to read and write a 32-bit bus, we can probably pull it off "efficiently" with 33 pins or so. We can use even less pins, of course, if we take multiple bus cycles to read and write memory. But what if we want a wider memory bus? Todays systems use 64 and 128 bit memory busses... many of tomorrows will use 256 bit ones. This takes pins, honestly. A 486 package just can't support a 128 bit memory bus. Can you reduce this number of pins? Well, yes. Either reduce the bus width, or use a narrow serial bus width (rambus style) and do and on-chip memory controller.
  
  Not even getting into IO... why do you think they keep increasing pin count? Do you think a 10000 pin chip can really be trimmed to a 4000 pin chip without making huge compromises?
  
  --
  
  I've had this sig for three days.
6. Re:Socket hell by Hoser+McMoose · 2004-01-13 06:44 · Score: 1
  
  Been there, done that, but the PPro didn't sell.
  
  Actually I'm not sure how much backwards compatibility there was in the PPro socket, but it WAS called "Socket 8".
7. Re:Socket hell by Hoser+McMoose · 2004-01-13 06:49 · Score: 2, Interesting
  
  Socket 7?!?! Good &deity no! Talk about a TERRIBLE design!
  
  If we kept socket 7 we would: a.) still be stuck at ~1GHz processors because the socket did not provide enough power or grounding pins for todays faster processors. b.) would have TERRIBLE memory throughput, the real-world performance of this socket was terrible even if when the theoretical numbers were ok.
  
  Perhaps most importantly though, it wouldn't help anything. You would STILL need to buy new motherboards to support new chips. In fact, it would probably be a LOT worse because you wouldn't know just what processor your particular version of socket 7 board supported! So instead of having 4 sockets to worry about you would have THOUSANDS of different motherboards, all with a lists of dozens of processors that they do and do not support.
  
  There's MUCH more to making a chip compatible with a motherboard than just the socket. In fact, the physical socket is a rather trivial part of it.
8. Re:Socket hell by Cyno · 2004-01-13 07:09 · Score: 2, Interesting
  
  Do you think a 10000 pin chip can really be trimmed to a 4000 pin chip without making huge compromises?
  
  Yes.
  
  Like you said some pins are used for memory bus bandwidth and power. Build a generic configuration that supports enough power and bus pins for all your average 256-bit wide buses. So each generic socket would have like 1000 pins. Enough to have direct CPU-CPU, CPU-Memory, and CPU-IO buses and power.
  
  I don't design hardware, but if I did I wouldn't waste so much time redesigning it every year.
9. Re:Socket hell by addaon · 2004-01-13 07:24 · Score: 1
  
  Okay... but what about when I come up with a chip that uses 500W per package, uses quad 256-bit busses, uses 0.7V instead of 1.3V (higher amperage means even less resistance allowed)?
  
  Okay, fine, we saw that far ahead, so our generic package had 5000 pins (about what you'd need for the above, judging by the Power series).
  
  Let's ignore that that package will cost 10x more than current cpu packages, and that the motherboard will cost $10 more, too. Let's explain that away by "economy of scale."
  
  Then I come up with a chip that uses only 20W and uses a high-speed serial 16-bit memory interface. Now, let's go with the "cost is no issue" argument... we want to cram it into our $50 socket, instead of making a $5 socket that's adequate. But wait! Our socket was designed with a 500Mhz FSB in mind, now we need to run it at 3GHz for that memory bus... and our pins' electrical connection wasn't rated for that speed!
  
  Do you propose to design a socket for every possible chip in the next five (say) years now? Do you claim to know what technology we'll be using in five years?
  
  --
  
  I've had this sig for three days.
10. Re:Socket hell by Clay+Pigeon+-TPF-VS- · 2004-01-13 08:54 · Score: 1
  
  I thought that the early ppros used socket 8's I could be wrong.
  
  --
  Viral software licensing is not freedom, it is in fact GNU/Socialism.
11. Re:Socket hell by Cyno · 2004-01-13 09:44 · Score: 1
  
  No, actually you're right. Technology changes so fast we should do away with these expensive sockets alltogether. Just burn the chips directly onto the prototype motherboards and support 'em like a crazy mofo! Whatever floats your boat. Its your time, life and money.
12. Re:Socket hell by addaon · 2004-01-13 10:23 · Score: 1
  
  I'd tend to agree with that (can't tell if you're being sarcastic or not)... but then again, I use laptops and mini-itx boards for 90% of what I do. Processor life cycles are only about a factor of two shorter than supporting technology life cycles; don't charge me half the cost of another processor just so I can spend more money on another processor which will be limited by the motherboard.
  
  --
  
  I've had this sig for three days.
Does it really matter? by UsedToCould · 2004-01-13 03:06 · Score: 1

Faster processors are all very well and good, but what is the point of going to the 64 bit processor if there aren't any OS's or applications that can take advantage of it? We get really cool, expensive equivilents to what we already have. Maybe AMD and Intel should start a push in the app department at Microsuck, otherwise I'm content to hold onto my Athlon 2Ghz. It seems to be get the job done...
1. Re:Does it really matter? by DanglingPointer2004 · 2004-01-13 03:21 · Score: 2, Insightful
  
  The point is that most people keep a CPU for more than a few months, generally for several years. A 64-bit OS is coming. So, why would AMD spend time developing another 32-bit architecture, then have to switch to 64-bit when the software is made? It makes more sense to get there first, so that when the software comes, you've got a proven, trusted technology.
  Also, the Athalon64 and AthalonFX chips blow the old XP chips out of the water, so it's not equivalent at all.
2. Re:Does it really matter? by Atzanteol · 2004-01-13 04:20 · Score: 1
  
  Wow what an insightful question! I don't think I've seen this type of question on *any* other AMD64 related article! Makes me wonder why nobody's ever thought to ask it before...
  
  I believe, IHBT.
  
  --
  "Ignorance more frequently begets confidence than does knowledge"
  
  - Charles Darwin
AMD shot self in foot by gr8_phk · 2004-01-13 03:14 · Score: 3, Insightful

With all the talk of unexpected 90nm delays and scaling problems over at Intel, one hopes AMDs problems are just typical delays with a new process. At any rate, we hope AMD will push ahead of Intel with the K8 architecture. IFF this happens, how on earth are they going to market them using their "false" speed ratings. Their rating system is flawed in that it uses Intel chips as the gold standard to measure performance against. You can't market a 4000+ if Intel has no 4GHz processor. If you do, you risk having the rating not match when Intel catches up, which makes the numbers completely meaningless. Today, they at least help to compare apples and oranges.
1. Re:AMD shot self in foot by DanglingPointer2004 · 2004-01-13 03:25 · Score: 1
  
  The 4000+ rating would mean that it is faster than the 3700+. That's not really meaningless at all. It's sticking to a convention they've been using for years.
2. Re:AMD shot self in foot by Realistic_Dragon · 2004-01-13 03:29 · Score: 2, Insightful
  
  All AMDs ratings are measured against a Duron 1ghz (so a 2000+ is exactly twice as fast).
  
  This means the scale is LINEAR unlike measuring against Pentium speed which is inverse-square (or similar, only done rough calcs) related to performance. You have more certainty with the AMD rating system.
  
  --
  Beep beep.
3. Re:AMD shot self in foot by ultrabot · 2004-01-13 03:35 · Score: 1
  
  You can't market a 4000+ if Intel has no 4GHz processor.
  
  Umm... yes you can. Most Joe Sixpacks can extrapolate the performance.
  
  --
  Save your wrists today - switch to Dvorak
4. Re:AMD shot self in foot by Anonymous Coward · 2004-01-13 04:20 · Score: 0
  
  Wow, I didn't think you could pack so much Intel fanboyism into such a short post.
  
  Reality check. AMD already DID "push ahead" of Intel.
  
  As far at AMD's "true" speed ratings go I wouldn't worry yourself too much. If you bothered to read AMD's rating system you'd see its not based directly on Intel's chips. So even if they came out with a 7000+ that number would STILL represent what happened if you took the typical AMD 3000+ and scaled it up. Figure out what the 3000+ does then benchmark a 7000+ and then you get a "meaningful" number or difference. So No your wrong, the number won't be meaningless.
  
  AMD could call the 7000+ the apache and the 4000+ the thunderbird. You'd still be able to see how they perform in relation to current market processors thus giving meaning to a name which doesn't have anything to do with Intel.
  
  You just have to love fanboy posts. You whole premise is that Intel is ahead of AMD right now and that even if they do produce chips that are faster it will be meaningless anyway. Great. So in your mind is there ANY way AMD can win?
5. Re:AMD shot self in foot by TrancePhreak · 2004-01-13 04:37 · Score: 1
  
  Then why was the 3200 slower than the 2800 under many tests? The rating system is flawed. I say it's not a rating system at all, but a version number.
  
  --
  
  -]Phreak Out[-
6. Re:AMD shot self in foot by Anonymous Coward · 2004-01-13 05:03 · Score: 0
  
  "Intel fanboyism"? You are just a bit defensive, arent you. Did you read his post? He plainly stated that he hopes AMD can be successful. AMD hasn't pushed ahead of Intel- their market share has stayed at like 17% for 2 years now.
7. Re:AMD shot self in foot by MrNemesis · 2004-01-13 05:31 · Score: 1
  
  AMD has adopted a different performance schema for it's new (K8) chips. I'm not entirely sure how it works, but (on Opteron at least):
  
  The first digit represents how many CPU's the system can have installed
  The second two digits have some relative performance figures.
  
  So an Opteron 140 is slower than a 148.
  An Opteron 240 is the same speed as an Opteron 140, but is SMP capable.
  
  AMD saw that the "we are seen as a comparison to Intel x.x GHz" approach could be misleading, so they changed it.
  
  --
  Moderation Total: -1 Troll, +3 Goat
8. Re:AMD shot self in foot by Bedouin+X · 2004-01-14 02:41 · Score: 1
  
  Why is the P4 2.6C faster than the P4 3.0?
  
  --
  Dissolve... Resolve... Evolve...
9. Re:AMD shot self in foot by TrancePhreak · 2004-01-14 03:34 · Score: 1
  
  The P4 2.6C verses a P4 3.0a is faster because of the 800mHz vs 533mHz FSB.
  
  --
  
  -]Phreak Out[-
AMD's Roadmap revealed by Anonymous Coward · 2004-01-13 03:25 · Score: 0

The Roadmap starts with Intel agreeing to stop the development of settlements on people's PCs, and with Intel succeeding all of the property on the Sunnyvale bank, where AMD is located, as well as the discontinuation of the building of the wall between Santa Clara and Sunnyvale.

For AMD, they are to cease all guerilla-style marketing efforts, and try to gain control of their rabid overclocking consumer base.
1. Re:AMD's Roadmap revealed by Anonymous Coward · 2004-01-13 05:16 · Score: 0
  
  Mod parent up... sick, but funny.
  
  I like it.
Intel is the Global Warming threat by Brian+Stretch · 2004-01-13 03:37 · Score: 4, Informative

Running at full CPU load, an Athlon 64 3200+ uses less power than an Intel P4 3.2GHz. Furthermore, with AMD's Cool and Quiet power management enabled the Athlon 64 CPU slows down to 800MHz and drops to 1.275v when you don't need much CPU performence, ie, while I'm typing this message. ASUS has a nifty little program that displays the current CPU speed and core voltage on my desktop.

AMD CPU power requirements are expected to drop substantially when they switch to 90nm in the second half of this year. OTOH, Intel's prototype 90nm Tejas CPU burns up 150 watts .

AMD chips haven't used more electricity than Intel chips for years. Pay attention.

BTW, Athlon 64 notebooks are out. $1,550 for a widescreen 64-bit notebook! I'm going to stick with my Athlon 64 desktop, at least until I come up with an excuse to buy a portable. Really, I am...
Socket-939 is going to be fast!!! by Anonymous Coward · 2004-01-13 03:40 · Score: 0

I find it interesting that two chips with the same specs and a different socket have different performance ratings.

Socket-754 3400+ 2.4GHz/512KB
Socket-939 3700+ 2.4GHz/512KB

Now, the Socket-939 version does have support for dual-channel RAM, but what does that have to do with making the chip faster?
1. Re:Socket-939 is going to be fast!!! by Chatterton · 2004-01-13 03:59 · Score: 1, Interesting
  
  Don't like to respond to a troll but:
  The cpu speed is not on par with the ram speed. This fact cause that from time to time the cpu has nothing to do because the new datas from the RAM are not already there. A cpu doing nothing has a worst PR than a cpu doing something. Adding the support for the dual-channel double the speed to the ram and thus the cpu have more work to do and less idle time then a better rating.
2. Re:Socket-939 is going to be fast!!! by Anonymous Coward · 2004-01-13 04:38 · Score: 0
  
  Well that makes sense. A CPU that's not always runnng at 100% is actually slower than the same CPU left at idle most of the time. In that case, AMD could market new chips like this:
  
  *** AMD Athlon 64 10000+ ***
  
  (fine print)
  10000+ rating only applicable if seti@home is always running. Actual chip speed is 2.4GHz.
I used to be a AMD fan by kalislashdot · 2004-01-13 03:44 · Score: -1, Flamebait

I was a hard core AMD fan since my AMD 486 120mhz. My current rig is an Athlon 1.4Ghz, which was top of the line when I bought it. The same speed Intel was twice as expensive.

I am currently very disapointed in AMD mainly due to their sleazy naming convention like Athlon 2800. To the average idiot that seems like the speed, but it is not. So then there is a argument that the number means the chip is comparable to an Intell chip of that speed. Benmarks show that to be bull.

Nope, I am looking at an Intel for my next Rig. I like Hyperthreading and the new 875 chipset. I am holding out for a Prescott chip. So Sorry AMD you lost a loyal customer here, but I am guessing that was expected by your marketing department since you probally duped 5 idiots to buy your chip over losing me.
1. Re:I used to be a AMD fan by Chatterton · 2004-01-13 04:12 · Score: 3, Insightful
  
  Well you have compared an apple with an orange. A Athlon 2800 is not on par with a Pentium 2800. On some benchmark the Athlon could loose, but on other Win. If you want to try to compare the 2, compare them on the exact application you use and need power to use them. Not some synthetic benchmark, or ISPEC or FSPEC and then you could make your choice. But please don't troll about the PR rating. AMD NEVER say that the PR rating is something equal to the frequency of an Intel processor. And as a side note. If you compare your applications on the 2 architectures: Please recompile them with the exact architecture of your processor and the hadoc optimizer. This can change a lot of thing. I am not an AMD or Intel FAN. I just choose the best Proc/MB at the best price for the work I need to do. (And I have the facility to try them before buying :))
2. Re:I used to be a AMD fan by Hoser+McMoose · 2004-01-13 07:03 · Score: 2, Insightful
  
  The "2800+" IS the speed. No, it's not the clock speed that the chip runs at, but that really doesn't make it any more or less relevant to the speed.
  
  Intel decided to market their processors using one totally meaningless measure of performance, the clock speed.
  
  AMD decided to market their processors using a different totally meaningless measure of performance, the model numbers.
  
  The problem with the chips is not so much sleezy marketing as with are ridiculous focus on clock speed. That's like buying a car solely based on the displacement of the engine. Sure, a 3.0L engine might produce more power than a 2.5L engine, but that certainly isn't always the case, and it sure doesn't tell you much else about the car. But if the public bought cars based ONLY on the displacement of the engine like they buy PC's based ONLY on the clock speed of the processor, you better believe that companies would bring out "3.0+" engines with 2.5L of displacement.
  
  In any case, AMD's marketing numbers have been extremely successful for the company. They almost instantly increased AMD's profit when they first brought them out years ago. Argue all you like, but the fact is that the computer buying public is, by and large, generally uniformed and buys systems based on two numbers alone, clock speed/model number of the processor and the price.
Re:Dual Processors? (without ECC?) by Anonymous Coward · 2004-01-13 03:53 · Score: 0

Personally, I think it's getting to the point where not using ECC memory is like loading 5 of 6 chambers and then playing russian-roulette with your foot.

If memory bit error rates per Gb haven't really changed, yet we're putting 8x the amount of memory into systems then we used to, it's a safe guestimate that our chance of getting a bit error is 8x as great as before.

ECC memory is typically only 10-25% more expensive then non-ECC memory. (Unlike the situation a few years ago where it was 2x-3x the cost.)
Same reason Intel released the PIV EE by Kjella · 2004-01-13 04:01 · Score: 1

*Why in the world introduce an AthlonFX based on Socket 940, especially at the outrageous price, when you're moving to socket 939 imminently?

Because AMD were making Opterons. And then some bright head said "Why not rebrand the 1x Opteron to AMD FX and sell it as the worlds fastest desktop system, 64 bit desktop, and whatever else? That way we can ship it NOW."

And Intel's Emergency Edition was almost the same thing. Basicly a rebranded Xeon, if I understood it right. Lots of cache, also hideously expensive. But it matched the FX.

I'm sure they were (and are) working on a dual-channel socket 939 board. But in the meanwhile, the FX was a perfectly good PR move. As for upgrades - I don't know about you, but my replacement cycle is getting so slow I don't care.

By the time I replace this computer, I expect the next to be with PCI-X, DDR2, different socket, 64 bit (if AMD), SATA native, preferably a smaller form factor (Shuttle-like mini-PC?) and more which simply doesn't exist yet. There was a time when CPUs were improving so fast, with compatible sockets that there was a point to upgrade, I did so from a Duron 700 to Athlon 1200. But now? By the time I don't like my XP2000+ anymore, I don't think I'll like the rest either.

Kjella

--
Live today, because you never know what tomorrow brings
Dual CPU capability? by obsid1an · 2004-01-13 04:19 · Score: 1

What I really want to see is dual CPU capability for the Socket 939. I guess the opteron is a viable alternative, but the price is just too high. Something like they did with the Athlon MP would be great.
1. Re:Dual CPU capability? by tkg · 2004-01-13 05:44 · Score: 1
  
  Agreed, but I'd bet that pin 940 is necessary for multi-cpu systems. Why else would they remove a single pin on the fx while keeping it on the opteron? Any hardware hackers out there have the low down?
Like a Cartoon Roadmap? by Anonymous Coward · 2004-01-13 04:25 · Score: 0

According to the first chart in the article I'm curently running a non-existant processor?!? It's saying the the XP 2800 processor will be released Q3 04. Somthing fishy going on here.
1. Re:Like a Cartoon Roadmap? by scharkalvin · 2004-01-13 04:42 · Score: 1
  
  Read it again. Your XP 2800+ is a SOCKET A cpu. It won't work in a socket 754 mb. The new chip is a socket 754, same socket as the Athlon64. Get it? This new chip is a 32 bit Athlon-xp that plugs into an Athlon-64 mb! Why? Because AMD probably has plans to kill socket A and ALL desktop Athlons will move to the socket 754.
FX = rebelled Opteron by Anonymous Coward · 2004-01-13 04:26 · Score: 0

Heh.
After 10 hours at work I read that as "FX = rebelled Opteron".
I kind of like it, actually. There's not enough rebellion in CPU marketing these days.
Athlon Thunderbird by Chicks_Hate_Me · 2004-01-13 04:29 · Score: 5, Informative

Correct me if I'm wrong, but I was told the PR xxxx+ was in comparison of what a Athlon Thunderbird clock speed would be.
1. Re:Athlon Thunderbird by Carewolf · 2004-01-13 06:43 · Score: 1
  
  Nope. It's to be compared with Pentium IV or duron 1Ghz.
  
  The thunderbirds was almost as fast as the XP processors. The last thunderbird was something like 1.4Ghz and faster than an XP1500+ (1.33GHz)
2. Re:Athlon Thunderbird by Hoser+McMoose · 2004-01-13 06:52 · Score: 1
  
  That's the official story, and AMD is sticking to it!
  
  Of course, in reality the model numbers are in direct comparison to the P4. AMD might not say that in public, but that has always been the intention.
  
  Is this a good thing or a bad thing? I don't see that it really matters. The replaced one TOTALLY MEANINGLESS number (clock speed) with another totally meaningless number (model number).
  
  Personally I like the Opteron's numbering system best.
3. Re:Athlon Thunderbird by StarCat76 · 2004-01-13 09:56 · Score: 1
  
  Correct me if I'm wrong, but I was told the PR xxxx+ was in comparison of what a Athlon Thunderbird clock speed would be.
  
  That is always AMD's official explanation of their naming scheme, but it seems much more likely to be viewed as a direct comparison with Intel's processor. AMD knows that in order to do well on the desktop, it has to sound as though it is as fast or faster that Intel's offerings. This naming scheme allows AMD to tell possible consumers how it should perform in relation to it's Intel counterpart.
There ARE 64 bit OSes by miodekk · 2004-01-13 04:30 · Score: 2, Informative

Of course there are 64 bit systems ready to install.
If you need better performance it may be another reason to switch to linux :-)
Only Microsoft didn't catch up, but who cares ;-)
Regards
Bullshit. by Ayanami+Rei · 2004-01-13 04:40 · Score: 1

You can get a 4-way 846 Opteron with 16gigs already stuffed IN IT for that price, and a few 143GB SCSI drives.

Unless you meant to be funny. But really, they're not THAT expensive. Look to spend about $600-$1000 on a board that can support 8+ GB ram.

--
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
Yawn. by ProtonMotiveForce · 2004-01-13 04:40 · Score: 1

I think you misspelled "Pentium III", "Pentium 4", "Celeron 4", and most most especially "Centrino/Pentium-M".

Or by successful do you mean with nerds who think IPC is somehow a better way to achieve performance than ramping clockspeed?

In the _real_ world, a successful processor is one that makes the company money.

Like the AMD ... Oh, I forgot, AMD doesn't make money.
confuse much? by imbezol · 2004-01-13 04:48 · Score: 3, Insightful

What a load of crap. I have bought only AMD processors and I swear by their performance. I jump at the chance to race a P4 touting fool through a compile of Mozilla. But this is getting ridiculous.

They've got to the point with all these different lines that it's no longer possible to talk AMD CPU's with anyone but the most avid AMD enthusiast. If you do try to talk the talk it ends up being a group memory excercise to see if together we can remember 50% of the difference in the varying jungle lines of processors.

Opteron is a good thing. Keep it simple. Give the FX a real name too. Don't call it an Opteron FX or 64 FX or whatever the hell it might be. Give it a damned name. How about an AMD Jargon? That would be a good name for a processor. If they all had names, you could associate the capabilities of the lines to the names and people could pick a favorite and learn the product.

As it is there must be extremely few people that can rattle off all the cache sizes, 398043+++ ratings, what core it is, blah blah blah. Not only do the different lines have different specs, but there are different specs within a line. There several instances of the same + rating with different specs in the same line. "I got a 2600+" "Which one?"

Not that I won't do all the research before I buy the next one, but I envy the Intel enthusiast that can just look and say Bigger is Better, and buy what they can afford.

I can't imagine my the other members of my family buying an AMD. They'd have to take a 3 week course, 2 hours a day, before they'd know which of the AMD's to buy. "This one costs more, but is it better?" "I have no idea." "This one has a bigger rating." "Yeah, but I heard this one is more advanced."

Is AMD hoping nobody will know what they're buying? Is that the ultimate goal? Why not just put a random number on each chip and put a MSRP on it and call it good.
1. Re:confuse much? by Loki_1929 · 2004-01-13 05:20 · Score: 4, Insightful
  
  "There several instances of the same + rating with different specs in the same line. "I got a 2600+" "Which one?""
  
  The idea is that you don't have to know what the exact specs are. What AMD is trying to do is show that CPU performance is relative. Within a few percentage points, every 2600+ CPU will perform equally, regardless of its core, amount of cache, socket, memory lines, clock frequency, etc. That's the whole point - you don't have to know. If you're "in the know", you can look at individual 2600+ CPUs to see which one has more of what will help you in the specific applications you use. If you're a general user, then 2600+ is the only thing you need to know. How many people buy a 3.06GHz P4 instead of a 3.00GHz P4 because they think the former is faster? The clock frequency alone belies the fact that the higher FSB on the latter CPU will actually make it perform far better on nearly every application. AMD is trying to hand you the whole package in a single number to simply the buying process for everyday people.
  
  The fact is, neither AMD nor Intel are telling the whole performance truth, nor could they do so. The only way to do that is to educate consumers about CPU mechanics, latency, IPC, L1/L2 cache, cache hits and misses, branch prediction, pipeline stages, and so on. The average consumer (hell, the average geek) can't understand half of these things. Thus, Intel has chosen to show the clock frequency of its CPUs, and AMD has chosen to use performance ratings that give consumers a performance index relative to the Athlon's Thunderbird core. Neither system is perfect, but neither system is more imperfect than the other, in my opinion.
  
  "Is AMD hoping nobody will know what they're buying?"
  
  AMD is hoping that those who need to know, will know, and that the rest who buy the "bigger number" will at least have an idea of what to get.
  
  --
  -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
Are the mods retarded or something? by Ayanami+Rei · 2004-01-13 05:14 · Score: 1

The reason why they keep introducing new sockets is precisely because the processors are changing design so rapidly (power requirements, location of the memory controller, address/data line widths, # of hypertransport hookups).

The AthlonXP is radically different from AMD64 (using hypertransport) which is configured differently than the Opterons.

If the nextgen XPs get a builtin memory controller, OF COURSE THE SOCKETS GOING TO CHANGE.

The only design decision I'm wondering why they couldn't just use the 939 connector for the nextgen Athlons and just ground the unused pins.

Probably the answer is that the extra unit cost made the difference: they wouldn't be able to sell the XPs at a decent price point because the 939 sockets are not cheap.

--
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
1. Re:Are the mods retarded or something? by -tji · 2004-01-13 07:29 · Score: 1
  
  Your point is valid, for the jump from Socket A to something better..
  
  It does not explain the Socket 754, Socket 939, Socket 940 confusion. They are all for the same generation of processors. AMD is abandoning two socket/processor models only months after introducing them.
  
  Not only is this bad for users, it's bad for AMD.. Most people are holding off on purchasing Athlon 64's because of this.
Intel's roadmap revealed by livingdots · 2004-01-13 05:15 · Score: 0

Well, I recently got MY hands on Intel's internal roadmap. Apparently, Intel are going to continue with socket 478, and will release the .5-nanometer "Andre 3000"-processor sometime in the fourth quarter of 2008 (codename: MelindaSaysBillGotMicrosoftDick). It'll be running at 1 Terahertz and having a L2-cache around 1 GB. AND, it'll be compatible with the i865 chipset. So, if you're smart you'll forget about AMD and by a cheap i865 mobo now, and you'll STILL be able to run Longhorn on it in 2006. Amazing! BTW, the Andre 3000 will scale perfectly, and have a fabulous green UV light reactive casing. Also, this chick was recently fired by AMD.
So there's pretty much no reason to go AMD.
That's the worst excuse ever. by Ayanami+Rei · 2004-01-13 05:18 · Score: 1

You'd be a fool not to spend a paltry $90 on a 2500 and then a trivial overclock to 3200 (2.4GHz, IIRC).
RIGHT NOW.

You're lucky if you can get an PIV 2.4GHz for $90. And it won't be using the 400MHz FSB. (266, probably).

--
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
1. Re:That's the worst excuse ever. by VoraciousGorak · 2004-01-13 14:22 · Score: 1
  
  You'd be a fool not to spend a paltry $90 on a 2500 and then a trivial overclock to 3200 (2.4GHz, IIRC). RIGHT NOW.
  
  The Athlon XP 3200+ runs at 2.2GHz core speed with a 400MHz FSB. The newest 2500+ (and all Bartons, for that matter) are multiplier-locked, with no known way of unlocking them, but the 2500+ uses the same multiplier as the 3200+... just at a different bus speed. So long as the motherboard can do it (and the memory too, but you can use a 6/5 divider if need be) you can just jack up the FSB to 400MHz and have yourself an instant 3200+. All the 2500+ CPUs I've heard of bar two (so, about 97-99%) will do 2.2GHz on stock or near-stock voltage.
What is the FX's market? by Sloppy · 2004-01-13 05:22 · Score: 2, Insightful

I have admired AMD for the last few years, but I think they've made a mistake. I don't understand why a thinking person would buy an Athlon 64 FX.
The plain Athlon 64, sure. I see why someone would buy that. If you want decent performance but also want to keep things dirt cheap, that's a nice chip. I think a low-power "mobile" version of that processor will also be a winner.
But if you want to spend a little extra money and build a "hotrod" machine, the Athlon 64 FX is a dumb move. Most CPU-bound stuff that people do, is parallelizable. (The only major exception I can think of, is that today's apps for multimedia encoding, tend to not take advantage. But they could (e.g. the portion after every key-frame could be handled by a different thread).)
So just spend a little more (it's really not much) and get multiple Opterons. If you're really hurting for money, get "obsolete" 240 models, and two of them will still run rings around any Athlon64FX or single-P4EE system that money can buy.
The class of problems that can't take advantage of multiple CPUs but still needs lots of speed, is small. Maybe I'm just being dumb, but I just don't see a market for a socket-939 or single-socket-940 board. Why would AMD, and motherboard manufacturers, bother to spend money development something that hardly anyone needs?

--
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
1. Re:What is the FX's market? by TheSunborn · 2004-01-13 05:46 · Score: 1
  
  Games don't use more then one processor.
  
  It's as simply as that.
  And me, I still play starcraft which run perfect on a 233Mhz pentium.
2. Re:What is the FX's market? by Anonymous+Cow+herd · 2004-01-13 06:31 · Score: 1
  
  You sir, are a retard.
  
  --
  Ita erat quando hic adveni.
3. Re:What is the FX's market? by Carewolf · 2004-01-13 06:51 · Score: 1
  
  Most games.. didnt.
  
  The new generic 3D engines all games use, have all been parallized since Quake 3.
  
  Since most games use a licensed 3D engine they are likely to benifit from 2 CPUs, even if the game developer hadnt thought of it.
4. Re:What is the FX's market? by PantsWearer · 2004-01-13 07:43 · Score: 1
  
  Even if you ignore that some games today can use multiple processors, what do you think all those other processes on your machine are running on?
  
  Maybe the game is completely single process, single thread, but there are other processes running on just about every operating system out there. This means that the game can basically use the total performance of a single processor without having to worry about giving up performance to background system tasks.
  
  Additional processors are always a performance boost, as long as you have a good scheduler and the memory bandwidth available. And generally they're a boost even when the scheduler and bandwidth are a bit lacking for most tasks.
  
  --
  Be glad life is unfair, otherwise we'd deserve all this.
5. Re:What is the FX's market? by TheSunborn · 2004-01-13 09:43 · Score: 1
  
  Acording to top the only applications currently runnig on my computer is xmms and top itself.
  
  And I do ofcause quit xmms before I play anything. (And yes that is in linux, but windows don't have any cpu intensive applications running in the background either)
  
  But the question was not would a cpu give ANY boost at all, but would the $ be better spendt better on a single faster cpu, which I think they would.
  
  But to get a real usefull answer to that question we need some kind of dual processor gaming benchmark.
6. Re:What is the FX's market? by TheSunborn · 2004-01-13 09:49 · Score: 1
  
  Any benchmark to prove that? Even claims from game producers would be accepted.
7. Re:What is the FX's market? by TheSunborn · 2004-01-13 09:54 · Score: 1
  
  Acording to this benchmark quake3 still don't. It could ofcause be a problem with the linux port, or something but note that the dual processor computers are a small bit slower then the single processor versions. Both for Athlon and Pentium3
  
  The site got a note saying:
  "We just got word from id Software that the SMP Linux Quake III binaries have not been released, but it's on their to-do list. Thanks id!"
  
  So the only thing this benchmark proves is that there don't exists a lot of wierd tasks which take up cpu time.
8. Re:What is the FX's market? by rrhal · 2004-01-13 09:56 · Score: 1
  
  I saw a comment from the president of a game company a few months back. He said that his company would make full use of 64 bit when it came out. In about 16 months when these systems are more common, windows for AMD64 is out, the 64 bit video drivers are out and patched, and software development cycle pumps out a product you'll see some game titles come out that barely run on a 32 bit machine but fully scream on a 64 bit machine.
  
  The new game titles that are coming out soon (half life2 for instance) will barely run on a 700MHz system. I don't know if that is justification for purchasing a $700 cpu when a $160 one is perfectly adequate. There is a large market for people who are willing to spent $3000 on something that is esentially a game console.
  
  The best news about all of this is that in 2 years we'll be able to buy these for 30% of what they cost today. When your 700 Duron finally releases its magic smoke you'll be able to replace it with an XP 2000+ for about $50.
  
  --
  All generalizations are false, including this one. Mark Twain
obligatory Bill Gates Quote by Anonymous Coward · 2004-01-13 05:28 · Score: 0

"640k ought to be enough for anybody."

Yes I know he never actually said this, but it's funnier if I pretend that he did.
Athlon 64: Boon for Unix/Linux/BSD by n9fzx · 2004-01-13 05:33 · Score: 2, Interesting

There are plenty of applications which benefit from a 64 bit memory model -- particularly text string operations, encryption, error control codes, and the like. Given the importance of search engines, privacy, and noise reduction, AMD's decision to push the 64 bit advantage could really help them, at least in the short run.
And since Microsoft is once again behind the curve, the various freeware Unix platforms could benefit a great deal by trumpeting their inherent advantage over Windows in these key areas.

--
...-.-
Questions still unanswered by Anonymous Coward · 2004-01-13 07:14 · Score: 0

a. Can a socket 939 CPU work in a socket 940 board?
b. Too much talk of unbuffered RAM. I still want ECC/chipkill. Can I use ECC on socket 939 CPUs? What about socket 754? Don't try to convince me I don't need it. My old SGIs have taught me otherwise. Remember the controversy when Sun forgot the ECC on a cache?
c. Do these chips have ECC on their cache?
d. Low power is good. Will the socket 939 chips support "cool n quiet"? I don't think the FX does right now. I'd love an FX but I don't want the fan full speed all the time.
e. Does Linux support "cool n quiet" in its ACPI?
f. How good is X86-64 support in Linux? Can I build a full X86-64 system from source yet?
new rule for exclamation points. by thegnu · 2004-01-13 07:28 · Score: 0

i think all names thought up by companies that include exclamation points should be required to spell out the words "EXCLAMATION POINT" in big capital letters.

Pentium EXCLAMATION POINTEXCLAMATION POINTEXCLAMATION POINT

YahooEXCLAMATION POINT

it's freaking annoying. so are quotes used to emphasize things. this is "very" annoying.

--
Please stop stalking me, bro.
Justification for socket change? by -tji · 2004-01-13 07:38 · Score: 0, Redundant

What the hell was AMD thinking?

Obviously, the Socket 754 was a mistake... they are dropping it only months after introducing a new processor on it. So, those of us with our shiny new Athlon 64's have very limited upgrade potential. But, I can see the logic in moving to a dual channel memory design (but they should have decided this prior to release, not immediately after).

But, the Socket 939 / Socket 940 thing is even more baffling.. With the pin count only differing by one, there can't be too much difference between the two sockets. So, why drop the Socket 940?? What was the justification for this move???
1. Re:Justification for socket change? by Anonymous Coward · 2004-01-13 12:44 · Score: 1, Informative
  
  justified by a simpler motherboard; the 940 uses a six layer motherboard, while the 939 only uses a 4 layer one.
OT pointer by Anonymous Coward · 2004-01-13 07:40 · Score: 0

when you don't need much CPU performence, ie, while I'm typing this message

Use "e.g." there, not "i.e."

i.e. - that is
e.g. - for example
Strange Logic by vandan · 2004-01-13 08:11 · Score: 1

Q: Which processor should I buy?
A: The one that makes the biggest profit for it's manufacturer.

Very strange logic.

And if we're talking about sucessful processors, lets not drag the Celeron 4 and Centrino into it. Those things are both complete dogs. Read some reviews if you don't believe me. But of course by your unquestionable powers of deduction, they have been sucessful product lines as far as intel is concerned, so they must be good for consumers!
1. Re:Strange Logic by ProtonMotiveForce · 2004-01-13 09:19 · Score: 1
  
  You don't get it. A 'successful' processor is one that makes the company who builds it money. This is a simple market reality.
  
  Now, you can argue on and on about which has the best technology, performance, etc...
  
  Oh - you're plainly wrong about the Centrino processor. The processor component performs very very well at low wattage. It's based on a high-IPC core. It is the ultimate laptop processor available right now. I've read plenty of reviews. The P4-M rules. Plain and simple. We'll see how AMD's new ones do.
  
  So you clearly don't know what you're talking about. Maybe you mean the wireless component of Centrino, which has received mixed reviews at best?
2. Re:Strange Logic by nulleffect · 2004-01-13 18:38 · Score: 1
  
  Oh - you're plainly wrong about the Centrino processor. The processor component performs very very well at low wattage. It's based on a high-IPC core. It is the ultimate laptop processor available right now. I've read plenty of reviews. The P4-M rules. Plain and simple. We'll see how AMD's new ones do.
  
  Uhh, the processor for "Centrino Mobile Technology" isn't Pentium 4. It's called Pentium-M and is rumored to be based on Pentium III, not Pentium 4.
Re:Socket 8 is hell by Anonymous Coward · 2004-01-13 08:12 · Score: 0

It had no backward compatiblity. Socket 8 was pretty big a quite rectangular. I don't have one sitting here but I would say that it was about 2" by 3.5". So it took up a good bit of space on a mobo. There were some HP Vectra's and Kayaks that used these in a dual proccessor configuration - which is one of the only places I remember them from. I am sure there must have been other computers that used these things but man they were clunky. The Pentium Pro itself had a good weight about it.
different roadmap. by Groo+Wanderer · 2004-01-13 08:13 · Score: 1

OK, you want roadmaps, read the Inq. The roadmaps come in 2 flavors, Opteron and A64. The one Anand gets might have similar numbers to the A64, but it seems way way off. Some things are just not right there.

Before you jump down my throat, I write for the Inq, and I can say I have seen both roadmaps, and the Anand one seems, well, lets just say a tad off. Well, lets not be as polite, flat #&%^# wrong. The anand crew is under NDA to the eyeballs, so if they had a real roadmap, they couldn't publish it.

If they did, they get sued and cut off. If not, it means it is a deliberate leak from AMD, or they made stuff. I believe it is a little of both, and personally expect more from AMD this year. Hell, I would put money on it after the chats I had at CES with them.

-Charlie
All this mess with sockets and chipsets is silly. by Myself · 2004-01-13 09:23 · Score: 1

Since motherboards and CPUs upgrade in lock-step anyway, there's no point in leaving them as separate components. What we need is a simple passive backplane design.

ATX was a huge step backwards in that it integrated the serial, parallel, PS/2, and other ports onto the motherboard, making all these connectors and their associated controllers "disposable" with every motherboard upgrade.

Put the CPU, caches, memory controller, and RAM sockets on a simple card that plugs into the backplane. This will be the only piece you upgrade regularly.

Then put the drive controllers, USB controllers, system health monitoring, and other miscellany on a "super i/o" card, covered with connectors. This piece won't get thrown out when you change processors.

What do we end up with? Getting a new CPU will result in replacing only those components that need replacing, keeping a pound of other components out of the landfill.

Manufacturers could still charge the regular amount for a CPU/carrierboard, because that's what people are used to paying. It would involve less design and debugging, because all the perhipheral crap is on a separate board. It would mean more choice for consumers, because you could get whatever CPU you want, coupled with whatever I/O board you want.

What's wrong with this?
drooling yet? by eWarz · 2004-01-13 09:35 · Score: 1

Anyone besides me drooling at the prospect of a 2.6 ghz athlon64 fx? (course the price will likely make you piss your pants)
forgot url http://www.gamepc.com/labs/print_conten by TheSunborn · 2004-01-13 09:57 · Score: 1

Url to test
http://www.gamepc.com/labs/print_content.asp ?id=as mpl&cookie%5Ftest=1
sure bzip is slower by MNNM · 2004-01-13 16:10 · Score: 1

Since it is optimized for more compression in favor of speed (using Huffman coding instead of Lempel-Ziv-Compression). For compression speed, you might want to have a look at lzop.

--
sig is my sith nature.
1. Re:sure bzip is slower by TheLink · 2004-01-13 16:53 · Score: 1
  
  Thanks. Will check lzop out. I hope it comes with Knoppix tho, coz that's what I've been using to image+compress my HDDs.
  
  I think bzip2 uses the burrows-wheeler transform (BWT) to sort blocks (and usually make them more compressible) then does something similar to what gzip does on the result.
  --
  
  Too many replies beneath your current threshold
2. Re:sure bzip is slower by TheLink · 2004-01-14 01:37 · Score: 1
  
  Cool, lzop is on Knoppix. I'm getting about 30MB/sec at the moment. That's about three times faster. The compression appears to be 10%-15% worse tho.
  --
  
  Too many replies beneath your current threshold
i80E86 by HiggsBison · 2004-01-13 17:42 · Score: 1

I would have guessed that they'd take a page from Boeing (whose newest jet is the 7E7), and call it the i80E86. Since the mundanes don't consider "E" a numeral, Intel can go ahead and trademark it.

--
My other car is a 1984 Nark Avenger.
Time for a Riceboy Uprising! by Vagary · 2004-01-13 18:21 · Score: 1

Aren't Riceboys a valid subset of consumers? Somebody should cater to them...

Seriously, why did companies start locking SMP in the first place? Did Intel really think that some Fortune 500 would decide to use overclocked Celerons instead of Xeons in their next mission critical server?
Re:All this mess with sockets and chipsets is sill by wkearney99 · 2004-01-14 05:37 · Score: 1

Doing the CPU interfacing up through a riser card isn't without it's hassles. Timing's critical. RF noise is a problem. Heat dissipation as well. Not to mention the added costs of socketing and various mounting issues. If anyhing that 'super I/O' card would be the thing on a riser. But then there'd be the hassles of interop.

In the face of how cheap it is to add the support chips and connectors it's not worth the bother.
do I care by diablobynight · 2004-01-15 07:56 · Score: 1

Either way, they created an extrordinary high priced processor, so they would have a processor in that gap. Who cares about that small aspect of what I said, I hate writing here sometimes because it seems people are here just to find a small aspect, a single sentence they can prove wrong, and create a feeling of intelligence for themselves.
The point of my statement was that things they're doing, like memory on the processor and such is in preperation for where computers will eventaully go, which is multi proc system in the home.

--
Anonymous Cowards - Oh God, How I hate you