AMD's Socket 939, Athlon 64 FX-54 amd 64 3800+

BudKnight writes "It looks like AMD is launching four new desktop processors, a new core, and a new socket infrastructure today. HotHardware has tested AMD's two new flagship processors, the Athlon 64 FX-53 and the Athlon 64 3800+. The new FX-53 no longer needs registered memory to function and the 3800+ has only 512K of cache, but it gets an upgraded 128-bit memory controller. The usual suspects also have reviews posted as well - TechReport, Hard|OCP, Beyond3D - more are sure to follow."

Comments

No 64bit scores

[brejc8]

One silly thing about review sites comparing AMD64 to anything else is that they are still running them in 32bit mode. I found running in 64 bit mode gives you about 20% improvement in general code.
When running guile working on very long integer operations we got a _6_ times improvement. Our simulations dropped from taking an 66 minutes to just over 11 minutes.

Re:No 64bit scores

[MrRuslan]

Due to lack of commericial 64 bit code they run 32 bit code cause thats what evryone runs in the real world and it still kicks ass. AMD is not joking around anymore and comming out with good stuff like this.This is the first time I seen something "backwards compatible" thise good.

Re:No 64bit scores

[Piranhaa]

That is true, however the average consumer WILL NOT be running 64-bit until Windows does get its 64-bit edition running perfectly and shipping with it. Although I do think they should have at least benchmarked it with some type of *nix for 64-bit...

Re:No 64bit scores

[rice_web]

Hopefully you understand that not many programs are optimized, as of yet, for 64-bit processors. When the more software makes the transition, you can bet that AMD will inch further ahead of Intel in the CPU-speed game (barring an Intel processor with 64-bit extensions anytime soon).

Re:No 64bit scores

[WegianWarrior]

Since just about anything else avilable today (at least to general consumers) are running at 32 bit (disregarding the fact that it's still possible to get hold of 16 bit and 8 bit chips off course) it make damn good sence to compare the new AMD64 to other chips while running it in 32 bit mode. Otherwise, you would be comparing apples and oranges... since no other CPU runs in 64 bit mode.

Could be interesting to benchmark a AMD64 in 32 bit mode against a AMD64 in 64 bit mode thought... that would say a lot about how much there is to gain in going to 64 bit mode in the first place...

Re:No 64bit scores

[Anonymous Coward]

The average consumer don't even know how many bits its CPU has.

Re:No 64bit scores

[Short Circuit]

No kidding. I went to the TechReport review because it was the first one that's not running slow, and my jaw dropped. AMD's really taking the lead with their recent offerings.

Re:No 64bit scores

[brejc8]

Incase people are intrested here are the scores of scibench2 for a load of machines in our office.

Athlon64 3200 64: 523.70
Athlon XP2700: 467.15
Athlon64 3200 32: 449.07
Athlon XP2600: 448.42
Pentium4 3.0GHz: 387.57
Athlon 1400: 305.26
AMD Athlon 950: 209.51
Sparc 500MHz: 52.21
Sparc 440MHz: 51.89

Re:No 64bit scores

[Anonymous Coward]

If you used ocaml instead of Guile, you could make your simulations finish in 1 minute...

(for people who don't know just how slow Guile is: take a look at e.g. the shootout

Re:No 64bit scores

[lachlan76]

Otherwise, you would be comparing apples and oranges... since no other CPU runs in 64 bit mode.

I take it you mean no other CPU runs in x86-64 mode.
Just remember, Itanium 2s do exist, but they are hardly something to benchmark a lot...I would assume with a starting price of about 3 grand a chip, which is meant to be used in up to an 8-way configuration, probably about 3 people have them.
And they can't run 32 bit code natively, it must be done in emulation.
However, when the Itanium 2 is used in it's native 64-bit mode, without any 32-bit emulation, it would be worth the money.

Re:No 64bit scores

[MrWim]

Personally if I had a 64bit processor I would run as much stuff as possible in 64bit mode. You might argue that I am not a general consumer as I run linux, etc but I don't think general consumers generally read hardware benchmarking websites either, but I do and I would. 32bit comparisons are neccessary of course and I find them interesting also (i.e for when I boot into w2k for games), but to not have one 64bit test does seem a bit silly.

I don't think it is comparing apples to oranges, and if it is this doesn't make it unfair just like it's not unfair to run SSE compiled apps on your SSE enabled chip

Re:No 64bit scores

[Short Circuit]

SGI's Origin supercomputer's are essentially clusters of Itanium 2 boxes in a NUMA architecture...And they're still supporting them.

Re:No 64bit scores

[lachlan76]

I wouldn't bet on an Intel x86-64 processor in the near future. The Yamhill extensions have probably been scrapped along with the Tejas and the rest of the P4 R&D.
Moving the extensions back to the P6 architecture will probably extend the time before any Pentium-64 processors are made by a few years at least.

Re:No 64bit scores

[swillden]

Otherwise, you would be comparing apples and oranges... since no other CPU runs in 64 bit mode.

By that logic, when a processor comes out with a new multimedia extension, or an increased L1 cache size, or a deeper pipeline, or a more efficient instruction scheduler, we should do comparisons with the new feature turned off, because no other CPU has it.

The real reason these chips were tested in 32 bit mode is because the testers ran WinXP on them for the tests. This is reasonable in that it's what most potential purchasers of the processors would be running, not because it's a more valid comparison against other 32-bit chips. If the most common software were available in 64-bit versions, it would be unreasonable not to use that and let the AMD64 chips show their full capability. (Assuming the software would run faster in 64-bit mode, which isn't necessarily true).

Users of more flexible software would find it interesting to see how their favorite tools run in 64 bit mode, of course, but that's a smaller audience, so those tests will come later.

Re:No 64bit scores

[MrRuslan]

I agree with you. I think they need to take sometime and benchmark suse 32 bit and 64 bit or any other distro for that matter and compare on the same computer to see the advantage of 64 bit code.

Re:No 64bit scores

[MrRuslan]

People who read hardware reviews are not average consumers who get a dell.

Re:No 64bit scores

[Rich0]

Assuming the software would run faster in 64-bit mode, which isn't necessarily true.

Most likely it will - though not necessarily through the use of 64-bit math. The AMD64 adds several additional registers, and that alone can make for a huge performance boost when a complier knows how to use them...

Re:No 64bit scores

[Anonymous Coward]

So I guess it mainly measures the speed of 64x64->128 multiplication?
If so, it's not surprising. Emulating that takes three 32x32->64 multiplies plus several adds/subtracts.

Re:No 64bit scores

[Jarnis]

What?

Have you been hibernating past few months?

Prescotts with Intel's version of x86-64 are coming out by early autumn. MS delaying the OS is partly because they don't want to piss Intel off. They also want to ensure the thing works perfectly on both versions, and while they are largerly compatible, there are couple of small differences.

Re:No 64bit scores

[hackstraw]

the average consumer WILL NOT be running 64-bit until Windows does get its 64-bit edition running perfectly

Being that microsfoft's current history with 16 and 32, and 64bit versions of their OSes, I would put "perfectly" as an unreasonable expectation.

I'll buy the "shipping with it" part. That is 100% correct.

Although I do think they should have at least benchmarked it with some type of *nix for 64-bit...

Yes they should, there is a big market for these things, and the 64bit arena has been dominated by big iron up to this point.

Re:No 64bit scores

[BlowChunx]

...probably about 3 people have them.

We have an 8 way SGI Altix 350 down the hall. I didn't know I would be in such refined company.

And they can't run 32 bit code natively, it must be done in emulation.

Intel's original purpose was to put these chips in servers and high end workstations, places where 32-bit compatibility was not its main purpose.

For CFD on the codes that I run (full Navier-Stokes equations with LES), an Itanium2 at 1.5 Ghz is twice as fast as a 3.0Ghz P4. (According to SGI these are $10k/chip, the lowly 1.4 Ghz are $3k/chip)

Re:No 64bit scores

[Anonymous Coward]

This is the first time I seen something "backwards compatible" thise good.

Hmm, 386 pulled off the same bit doubling trick while maintaining full backward compatibility and kicking 286's ass.

Re:No 64bit scores

[MrRuslan]

The 386 did not run at a slower slock speed and kick the 286's ass.the p4 is is 1 GHZ faster in the clock department and still can't beat the AMD64 that's what make's this more impresive.

Re:No 64bit scores

[meringuoid]

Athlon XP2700: 467.15
Athlon64 3200 32: 449.07

Interesting. So the XP actually outperforms a higher-rated 64 processor, when the 64 is running in 32-bit mode? Seems rather odd... What are the actual clock-rates of these things?

Re:No 64bit scores

[hackstraw]

Be aware that this is a benchmark for jvm's, and has little to do with machine performance. According to the benchmarks results page. A PIV 3.0 GHz computer can score anywhere between 228 and 557. This benchark also seems biased towards 32bit machines. One thing that is essential for any test is for it to at least be internally reliable.

Re:No 64bit scores

[JFitzsimmons]

The average consumer don't even know how many bits its CPU has.

And even if they did, they probably wouldn't really understand the significance. ("64 is double 32 so it is twice as fast right??")

Re:No 64bit scores

[magarity]

And the reason they don't understand the significance is overreliance on the sales staff at the local electronics supermart. Back in the days, I once heard a salesperson tell a shopper that the difference between a 386DX and a 386SX was that the DX models came in higher clock speeds.

Re:No 64bit scores

[Astatine]

Rumour has it, however, that Intel's implementation of x86-64 isn't as good as AMD's. Expect the gap between Athlon64/Opteron and Pentium/Xeon to widen in 64-bit mode...

Re:No 64bit scores

[Not_Wiggins]

Soon this should be remedied (sorta) with FarCry for AMD64

Won't be much variety, but could be a good starting point for benchmarking.

Re:No 64bit scores

[JPriest]

Your average consumer does not go online and spec out a dell. They get an HP or compaq from CompUSA or have someone "in the know" help them spec out the system online.

Re:No 64bit scores

[Jeremy Erwin]

You can download the C sources to scimark2. My mac gets a paltry 93.7 with java, but a more respectable 206 with gcc, and 229 with minor optimizations (-03).

So, how much does that Athlon64 score running the C implementation?

Re:No 64bit scores

[Anonymous Coward]

Athlon XP2600: 448.42
Pentium4 3.0GHz: 387.57

Intel got owned!!!1 (Again...)

Re:No 64bit scores

[quasimodal]

One silly thing about review sites comparing AMD64 to anything else is that they are still running them in 32bit mode.

Well, since most of the Windoze crowd never need a decent processor, 32 bit is all they need.

I've also found that in Lunux 64 bit mode makes a large number of programs run much faster and makes the database I'm using (postgresql) usable for much larger datasets. Of course the applications I use are easily recompiled in 64 bit mode, so I don't have to wait for the software to become available.

Re:No 64bit scores

[brejc8]

It is running the C versions

Re:No 64bit scores

[Psymunn]

Or why they don't bench mark them against my Nintendo 64. Or my Jaguar 64 (it's 4 times better then super nintendo, kids)...
Sadly, I think the AMD, with an emulator running Mario 64, would (forgive the L33t speak) r0x0r my N-64 any day of the week...

Re:No 64bit scores

[Hoser McMoose]

I fail to see how this is all that impressive. It's not like AMD *could* clock the Athlon64 up to 3.4GHz on a 130nm manufacturing process like Intel has done with their P4 chips. Nothing at all against AMD's process engineers, they are absolutely top-notch, but it's just that the two chips are designed differently.

Intel chose to get their performance by clocking their chips very highly, the classic "speed demon" design. AMD chose to get their performance by getting their chips to do more per clock cycle, more of a "brainiac" design. These two design philosophies are not exactly mutually exclusive, but there are trade-offs required for each. In the end, the only thing that really matters is which company made the best trade-offs between "speed demon" and "brainiac".

Right now it looks like that company is AMD, though keep in mind that the P4 was released nearly 4 years ago while the Athlon64 core is only 1 year old. Intel must be well on their way to bringing out their next generation core (typically released about 5 or 6 years after the last one first showed up) while AMD still has a ways to go with their core.

Re:No 64bit scores

[Hoser McMoose]

Just remember, Itanium 2s do exist, but they are hardly something to benchmark a lot.

Itaniums actually are benchmarked quite a bit, probably more than their sales figures would justify. They are, of course, also not the only 64-bit chips out there. IBM's got their PowerPC 64-bit chips, SUN and Fujisu have their SPARC chips, HP's got PA-RISC, Alpha and even some old servers running 64-bit MIPS chips (their Non-Stop line)... just to name a few.

I would assume with a starting price of about 3 grand a chip

Not that far off the starting price if you count the high-end ones. Intel does sell a couple "workstation" Itanium2 chips for ~$750 or $1000, but they will only work in 1 and 2P setups. For a 4P+ setup the cheapest chips they'll sell you do indeed come in at around the $2500-$3000 mark, and the top-end ones will set you back over $5000... what's more, those are the prices from Intel! HP adds about a 50-60% mark-up to those prices for the chips they sell!

which is meant to be used in up to an 8-way configuration, probably about 3 people have them.

Itanium sales ahve been somewhat weak, last year they sold approximately 20,000 servers. Sales have picked up fairly consistently throughout last year and apparently are continuing to pick up this year, but right now it's still looking like the chip is largely just a replacement for HP's old PA-RISC servers and SGI's old MIPS servers.

And they can't run 32 bit code natively, it must be done in emulation.

My understanding is that these chips actually do have a full 32-bit x86 core included in the chip right alongside the 64-bit IA-64 core, however it turns out that it's faster to run things in emulation that to use the integrated core.

However, when the Itanium 2 is used in it's native 64-bit mode, without any 32-bit emulation, it would be worth the money.

Here's the real kicker though, often it's NOT worth the money! In many of the tests done so far comparing 64-bit Itanium to 64-bit Opteron, the Opterons actually come out ahead! It's often a tight race, and certainly the Itanium2 does win it's fair share of benchmarks, but it's definitely not the straight-up win that Intel would like to have us believe. These two chips are actually very competitive in terms of performance.

The big advantage that Itanium2 has is that it's well supported at the high-end by both HP and SGI, so where the Opteron is only available in up to 4-CPU servers you can plop down a few million and pick up a 64 to 256-CPU system with Itanium chips.

Re:No 64bit scores

[Anonymous Coward]

... , so I don't have to wait for the software to become available.

Newer 64 bit software kills your older 64 bit software => you has to wait for the newer software and to erase the unpowerful older software.

Linux has not 64-bit kswapd yet!
Your long-mode processes are limited to 4+2 GiB of VM!

open4free ©

Re:No 64bit scores

[fitten]

That is the thing... The Athlon XP and Athlon 64 are very similar clock-for-clock on x87 codes (and scalar SSE I believe). The Athlon XP 2700+ actually has a higher core frequency than the Athlon 64 3200 (the A-64 3200+ is actually 2.0 GHz, the A-XP 2700+ is 2.167 GHz). The FPUs didn't change that much from the Athlon XP to the Athlon 64. This gives the XP line an actual advantage in many FPU intensive apps that make good use of the cache.

Re:No 64bit scores

[Bedouin X]

The Athlon 64 CORE is simply a K7 with X86-64, Hypertransport, SOI, and an integrated memory controller. They made a few other minor tweaks (like slightly increasing the pipeline) but there is a lot more that is old about the A64 than there is new. Clearly these deseign enhancements have paid off, but to compare the XP/64 to the PIII/PIV is not really apples to apples. The PIV was a radical change in design.

Of course the irony is that Intel looks to be going back to a PIII-like architecture for the future.

Re:No 64bit scores

[mrchaotica]

Except that if Microsoft and Intel are colluding to the extent that the grandparent says, then it's entirely possible that they plan to optimize out the Intel processor's deficiencies

(not that Windows performance == perfromance in general, but still...)

Re:No 64bit scores

[mrchaotica]

Apparantly, the Sparcs are bad at that benchmark (i.e. worse than you'd think they'd be, since the twice as fast Athlon had a score more than twice as high).

Out of curiosity, what are they good at?

Re:No 64bit scores

[brejc8]

The sparcs are good at _NOTHING_. They are really awful. The reason we use them is becuse cadence runs on them and nothing* else. We are currently trying to get cadence to run on linux but the only version supported is RedHat 7.2. Anything above that fails. We are getting desperate to run it on something else.

*Nothing reasonable anyway

Re:No 64bit scores

[barneyfoo]

install the libs required in 7.2 in a chrooted environment and run cadence there? Try it out

Re:No 64bit scores

[brejc8]

Thats not the only problem. Cadence needs all manner of old software like csh... CSH!! I mean WHY?!? Why cant they just write sh ? And why can't they correct the bugs arising from new versions of csh?
It is much more painful to even think about it. We are working on it but it may take a few weeks. I made a new machine and installed 7.2 on iit today so we can get it orking and migrate each part one by one. It sortof feels like installing Windows 95 in 2004.

Re:No 64bit scores

[l33t gambler]

Athlon64 64-bit testing under Linux

Re:No 64bit scores

[swillden]

Most likely it will - though not necessarily through the use of 64-bit math. The AMD64 adds several additional registers, and that alone can make for a huge performance boost when a complier knows how to use them...

That's a positive factor, certainly, but there are other factors as well. In particular, I understand that 64-bit code has larger parameter fields, increasing the size of the code. If the code size happens to increase enough that, for example, a loop that used to fit in the instruction cache now overflows, then any other 64-bit performance gains will be destroyed by repeated stalls while data is fetched from further up the cache hierarchy.

Re:No 64bit scores

[Frnknstn]

This would be grave mistake for Microsoft. If they did, Linux could gain even more of a performance advantage on AMD hardware, which would further damage their sales. I suspect Microsoft will once again take the selfish option and give the best performance possible.

Too long.

[Piranhaa]

It's a really good idea AMD is finally making the transition to dual-channel non buffered memory. They really should have done this a LOT sooner, before consumers started getting adjusted to the other socket, so they wouldn't have to replace their board when upgrading to the newer chip.

Re:Too long.

[swordboy]

so they wouldn't have to replace their board when upgrading to the newer chip.

Who still does this?

I've never upgraded without swapping both the processor and mobo. This isn't a troll but rather just curiosity - I'd like to know if there is any significant percentage of non-gamers that upgrade *only* the processor. I'dathunk that the "processor bottleneck" was just a myth.

I actually underclocked my Athlon 1800+ because it ran much cooler/lower power without any noticeable decrease in average usage habbits. Now, moving from a 5400rpm hard drive to a 7200rpm unit was a huge upgrade. I can't wait for cheap, desktop-oriented 10k and 15krpm units.

Re:Too long.

[sumdumass]

The AMD64 platform design was released several years late and amd had to honor obligation with manufacturers that had already invested time and effort in the r&d based on the specs it issued before the delays. Once most of these "proto-type" boards (or whatever you will call them) were reasonably sold out, they could go ahead with thier advancments they discovered along the line.

It sounds like the consumer got the raw end, but in reality it allowed the motherboard and chipset manufacturers to have a sence of confidence and time to develope working designs for the newer socket. It is a win-win type situation except for those that bought with the intention of upgrading. But then again most people in that situation (like me) would have been reading about the new socket when researching whether or not to get one and made a decision to live with it. Others would be just getting it for a system that would last a while bfore buying another.

Re:Too long.

[aelbric]

You underclocked your Athlon 1800+?!

Turn in your National Geek Association membership card at the door as you leave, sir! ;-)

Re:Too long.

[Short Circuit]

Who still does this?

I would. I'm running a Duron 750MHz, and I'd like to upgrade it to an Athlon 1.4GHz. (The only problem is finding the darn part.)

I can't wait for cheap, desktop-oriented 10k and 15krpm units.

Don't hold your breath. 10k drives generate a lot of heat.

Re:Too long.

[pebs]

You underclocked your Athlon 1800+?!
Turn in your National Geek Association membership card at the door as you leave, sir! ;-)

Blah.. Underclocking is completely acceptable for geeks. Most overclockers on the other hand, are the rice boy equivalent for the computer world. Overclocking is hardly even considered geeky. Most geeks, especially professionals, will look down upon overclocking.

Re:Too long.

[joib]

Who still does this?


As you hinted below, gamers. And immature people who feel that their worth as human beings is measured by their computers. In short, the fanboys who are the target market for all these quadrillion hardware review sites.

Re:Too long.

[hattig]

If you are running on a KT133 motherboard, whilst the Palominos weren't compatible (presumably why you are looking for a Thunderbird core Athlon), apparently the TBreds are. You should be able to run a fast TBred on your hardware without a problem. Best to investigate this online though for your particular motherboard.

If I'd known this myself I wouldn't have spent the massive amounts of money (22) on a new cheap motherboard.

Re:Too long.

[sumdumass]

what about the people building thier own computer and selected a smaller processor because it wass afordable and then plan on buying a better one when availible. I did this witha system i built for less then $300 The processor i wanted at the time cost almost that much. so i took an extra year or so to get one. With the socket A, i was able to get even a newer/faster processor then i originally wanted to.

Re:Too long.

[Jeff DeMaagd]

Dual channel wasn't that great a benefit for Athlon 64 anyway, although I suspect latency is a smidge shorter for unbuffered.

IMO, the FX series isn't exactly a toy, either, and buffered allows more memory and bigger sticks per channel. This might mean that pro gear that got by with FX might have to switch to Opteron for the next upgrade.

Re:Too long.

[stratjakt]

I built a PC last year with a 1.8ghz celeron, and recently replaced it with a 3.06 I got on the cheap. The performance increase is more than noticable, even though I'd need to reinstall XP to enable HT.

I didn't want to have to tear apart my box, reinstall my OS and all its files, etc, etc.. I just popped out the old CPU and heatsink, and popped in the new one.

It was always my plan to do so, the money I saved going with the 1.8 celery short-term went to a DVD burner and a gig of quality RAM.

Socket 478 stuff is going cheap now and DDR has come way down, I have some other machines I plan to upgrade, even though the performance in many cases wont be that significant, it's cheap enough to be worth it to "max out" the machines.

Re:Too long.

[Halthar]

I have for quite a while upgraded the mobo when getting a faster processor, in the past I would stick with the same mobo. There are two primary reasons I have been swapping both at once.

The first is that I have had two boards die as a result of bad caps within the past year. When I went to get new boards, processor prices had dropped so I figured why not, and replaced the processors as well.

The second reason being that now my two main machines, when things get upgraded, pass on their hardware to older machines that can use it. When a processor/motherboard gets upgraded, another machine gets upgraded with my old used hardware.

If I hadn't had boards passing away from bad caps, and I hadn't had a massive number of machines that could use processor/motherboard upgrades, I wouldn't be replacing the boards. Most of the boards I have now are fairly up to date in terms of features, so I really have no use for upgrading boards anymore until I get the cash for a dual Opteron, which is my next planned upgrade.

So until then, all computers in my apartment (sorry, no, I don't live in mom's basement, either my own or someone elses.) get processor upgrades, maybe memory upgrades, but no more board upgrades. Unless, of course, more caps go bad.

Re:Too long.

[ArsonSmith]

I currently run hacked Athlon XP 2000s to run in a dual Tyan motherboard. The hack worked flawlessly and saved me sevral hundred $$$$.

I'm not upgrading until I can get a dual core, dual proc system. I can't wait for 4 penguins on the boot screen for my Debian desktop.

Re:Too long.

[JFitzsimmons]

However, unlike ricing a car, overclocking actually does make your computer faster... assuming you can stand the heat, and the increase in power usage, and quite possibly the instability (if it isn't done properly).

Re:Too long.

[swillden]

I didn't want to have to tear apart my box, reinstall my OS and all its files, etc, etc..

Why would replacing the mobo force you to reinstall the OS?

Re:Too long.

[PhrostyMcByte]

I'dathunk that the "processor bottleneck" was just a myth.

It doesn't really matter for non-gamers. My dad runs an XP2000+ and is able to browse the web/play mp3s without a problem. But for gamers it really matters: current games are almost completely CPU limited. Until some games come out that seriously stress the video hardware with shaders, all the new video cards can do for you is increase resolution and AA/AF. With a recent system you should get around the same FPS in UT2004 and FarCry until you hit high resolutions and AA/AF settings that stress fillrate. Physics, AI, and just generally pushing lots of geometry through AGP is a big frame limiter.

Re:Too long.

[CaptnMArk]

You went from p4 celeron to a real P4.

obviously the difference is noticeable because the P4 celeron is, relatively speaking, crap.

Re:Too long.

[Mr Smidge]

Who still does this?

I upgraded my Athlon XP 2000+ to a 2400+ without changing the motherboard (though I did need to update the BIOS - Abit AT7-MAX).

The reason for that though was a bit of a one off: The newer processors (Thoroughbred, Palamino, I don't remember which way round it is) ran significantly cooler than the old ones, so for ~50GBP I got a 2400+ and put it in.. lo and behold, the CPU temperatures now run around 10 degrees C lower. Fantastic.

Re:Too long.

[froody]

I'm actually going to do this for the first time. I'll be upgrading my 650MHz Duron to a 1400MHz Athlon. Still stuck with the slow 100MHz FSB, but I think it'll make my system quite a bit snappier. I would've made a bigger upgrade, but nowadays I'm trying to save money for an early retirement.

Tim

Re:Too long.

[stone2020]

Several years late? Why? Cause they released the spec for AMD64 a few years ago? It was well planned out and released on time. Intel has switched socket sizes so many times its not even funny. If you did your research without being biased you would know that Socket 754 is going to be supported for at least another year. Isn't Intel switching sockets again? Socket T or LGA 775? Are those even gonna be 64-bit? Probably have to buy DDR2 also.

Re:Too long.

[pyrrhonist]

You underclocked your Athlon 1800+?!

That's nothing. I'm building a machine now where I have to underclock a K6-2! Whee!!

Of course, it's not a total geek-loss...

• I have to build all the external case connectors for it, because the motherboard only has IDC connectors.
• I have to build a case to put it in since the board isn't a standard size.
• I have to hope that I calculated the wattage correctly so that I don't have issues with my external power supply brick.
• I have to install Linux on a CompactFlash and hope that there aren't BIOS issues when booting from it.

Why am I doing this again?

Re:Too long.

[Jeff DeMaagd]

even though I'd need to reinstall XP to enable HT.

I highly doubt you need to reinstall XP to enable hyperthreading.

I didn't need to reinstall W2k to do so, there was a way to switch from uniprocessor kernel to multiprocessor kernel in the System Hardware control panel. I sure as heck hope they didn't change that for XP. Google it to be sure, unless you want to reinstall for the sake of reinstalling.

Re:Too long.

[Jeff DeMaagd]

For the thermally and electrically concious, 10k RPM drives may not be wise, but a LOT of heat? My 15k drives do get warm. I guess it's probably good to check storagereview.com to be sure, they are one of the few sites that measure things that don't necessarily affect speed, namely heat and noise.

Re:Too long.

[Jeff DeMaagd]

Athlon64 was about nine months late, but hardly years, they managed to eke some Opterons out before the Athlon version was released.

Intel will be switching sockets, but IIRC, because of the increased FSB speeds, I thought the next bump was to be 1.2GHz so the pins themselves needed to go away I gues because that is into the microwave region. That might have been temporarily scrapped though, now that they've halted the development of post-Prescott P4 chips in favor of developments based on the Pentium M core.

Ceramic vs Organic packaging

[danormsby]

Anyone got a definition on what the "Organic" packaging on the new Socket 939 processors is and how it compares with the previous ceramic packaging?

I guess it isn't wicker based.

Re:Ceramic vs Organic packaging

[Ninja Programmer]

Organic packaging means its made of plastic.

Re:Ceramic vs Organic packaging

[JFitzsimmons]

Am I the only one who thinks there is something wrong with this naming scheme?

Re:Ceramic vs Organic packaging

[Foolhardy]

Organic means that it contains carbon and hydrogen; and is derived from an organism.

Sockets again

[tronicum]

I wonder how often they will introduce new sockets for just a bunch of CPUs.

939 will not support dual CPUs, after all that "Slot A", Socket 7xx/9xx nonsens you cant just buy a board and hope to upgrade the CPU. They change the memory systems, introduce new bus systems (graphic : PCI->AGP->PCI-X/PCI-Express).

Anyway I like my Athlon64 and at least the TDP (Thermal Design Power) of the new CPUs does not rise....

Re:Sockets again

[Anonymous Coward]

939 will be the AMD desktop standard for a long time (like SocketA was). 940 on the desktop was a temporary measure, a bit like SlotA.

You could also compare it with the s478/s423 of the early P4 days...

Re:Sockets again

[Rufus211]

> after all that "Slot A", Socket 7xx/9xx nonsens you cant just buy a board

Erm, what "Slot A nonsens"? Yeah, years ago AMD switched from Slot A to Socket A for very good reasons and has stuck with Socket A up until now. In fact my CPU (Barton 3200+) recently died and I threw in a Duron 1ghz to keep my board running until I got a replacement. Again, PCI->AGP made a hell of a lot of sense and was again years ago, as does the current PCI -> PCI-E. Now the only "nonesens" has been the 754>939 change for single to dual channel, but AMD has publicly stated this will happen the whole time, plus they'll still produce at least one more round for 754 and 940 sockets.

So yeah, things change and your old stuff won't work any more, stop wining. At least it's not as bad as Intel (how many sockets have they had in the past few years anyway?).

Re:Sockets again

[CTho9305]

As I understand it, you can't build a 4-layer motherboard with socket 940 (you have to use 6 layers). By changing the pin layout for socket 939, it is now possible to use 4 layers. This should reduce the cost of motherboards.

Re:Sockets again

[sweede]

Sorry, but from overclockers.com

This place (http://www.amdboard.com/) says that AMD is trying out a 90nm CPU that uses a different socket, socket 900.

The code name of the chip, Toledo, is one that has been on AMD roadmaps for introduction sometime the second half of 2005.

The blurb says that Toledo handles DDR2, and it's hard to see what else might cause the need for a new socket. It also says that dual cores coming after Toledo will also use DDR2.

While I don't think the article is correct in assuming that we'll see these products rather soon, it probably is correct in assuming that a DDR2 compatible platform is not going to be compatible with any Hammers or mobos you'll be able to buy anytime soon.

Effectively that means if you want a DDR2 Hammer system, you'll have to wait until all the pieces of the puzzle are together before you do so. You won't be able to buy a Hammer now, and buy a new mobo and memory later.

And then based on AMDs current handeling of the chips, they'll probably stop making socket 939 processors just like they will be dropping the AMD Socket A and Socket 940/754 chips

Re:Sockets again

[TheLink]

How'd your CPU die anyway? Curious.

Seriously. No puns please.

Re:Sockets again

[Rufus211]

It got unhappy when I went past 2.1V for vcore (and it was a mobile barton with a default vcore of 1.45 =). And yes, I am using watercooling.

Bah!

[hendot]

Sounds like a ripoff to me. You pay $x for a new cpu and they don't even give you the full 940 pins :p

Re:Bah!

[Anonymous Coward]

"Sounds like a ripoff to me. You pay $x for a new cpu and they don't even give you the full 940 pins :p"

You only paid $x for yours? I just paid $x+200. Dammit!

Where to buy them in the UK?

[r1ch]

I've been waiting for these to come out before building my new dev box. Does anyone know where I can buy them in the UK? And a socket 939 mboard too? I'm thinking of the Asus A8V. I've tried Dealtime, Kelkoo and some specific dealers but no luck yet other than US stores.

Re:Where to buy them in the UK?

[Anonymous Coward]

I bought the Asus K8V deluxe for my AMD 64 3200+
Running 1gig unregistered memory and it works fine.

Re:Where to buy them in the UK?

[sundling]

monarchcomputers.com has them, but they list ETA for the Asus A8V as June 17th.

I've bought stuff from that sight before and they have the best customer service bar none.

Paul Sundling
http://www.planatar.com

Re:Where to buy them in the UK?

[sundling]

Silly me, I should have given the direct link:
Asus A8V Deluxe Socket 939 board

Paul Sundling
www.planatar.com

Re:Where to buy them in the UK?

[r1ch]

Thanks, but monarchcomputers.com seems to be a parked domain - do you have another URL please?

backwards compatibility

[Anonymous Coward]

do these new systems still run Windows 98SE / Me?

Re:backwards compatibility

[Anonymous Coward]

Seriously -

Yes.

Are you scared yet?

Re:backwards compatibility

[sumdumass]

Should run windows 98 and me.

Although you might run into the ndis.sys problem asociated with some clock speeds over 2.2 gig in win9x and i'm sure if microsoft is still giving the fix for it. Also win9x and me might not be able to take full advantage of the spped. (but that more of a guess then anything)

Tinfoil anyone?

[Gothmolly]

IANACD (I am not a CPU Designer), but I'd imagine that they're redesigning these things for a reason, NOT just to screw users and force an upgrade cycle. Intel did the same thing with their CPUs, and IBM/everyone did the same when they went from 30 pin to 72 pin SIMMS, then to DIMMS, then to DDR DIMMS. Was this all a vast Taiwanese component manufacturer conspiracy? I somehow doubt it. When it first came out, the PCI bus was limited to 3 slots due to physical 'ring' characteristics on the signal lines. Some propeller-heads at HP figured out a way to get 4 slots, and everyone ooh'd and aaah'd over it. Nowadays we have more slots due to bridge chips, are we going to complain that those pesky motherboard manufacturers keep updating their chipsets?
Are you also angry at the music industry cabal that forced everyone to upgrade from vinyl to 8-track to cassette to CD to DVD ?

Schernau's 2nd law: bolding part of your post actually detracts from your argument

Re:Tinfoil anyone?

[Short Circuit]

IBM/everyone did the same when they went from 30 pin to 72 pin SIMMS, then to DIMMS, then to DDR DIMMS.

The switch from 30-pin to 72-pin SIMMS, and then on to DIMMS, occured as a result of the memory bus width increasing.

When the normal width for a memory bank reached 64 bits, they went from 30-pin to 72-pin. (It was easier to insert one 72-pin SIMM than four 30-pin SIMMs.)

When the normal width for a memory bank reached 128 bits, they switched from SIMMs to DIMMS. (Again, it is easier to insert one DIMM than two 72-pin SIMMs. Imagine what would happen if every RAM upgrade meant you had to insert eight 30-pin SIMMs.)

However, the switch from SDRAM DIMMs to DDR SDRAM DIMMs was strictly for bandwidth, not for making memory insertion cheaper/easier. ("Cheaper" because one DIMM socket takes up much less board space than eight 30-pin SIMM sockets.)

Re:Tinfoil anyone?

[sweede]

you know, your totally right.. the changed from 30 pin memory to 72, then DIMM, DDR. Intel changing from a socket to a slot then back to a socket, etc.

however, each one of those was a MAJOR change in in the architecture and took a while to implement the change.

AMD has release what, 4 incompatable sockets in the past year?
939, 940,754, 740
And soon it will be releasing another socket, socket 900.

Im sure they had other socketed versions that they never made public.

to make things worse is that AMD has stated that they wont be putting PCI Express on socket A (Athlon) or socket 754 systems.

So, all those people that went out and bought a socket 754 motherboard are screwed when PCI express starts to be rolled out.

in contrast, the Socket 7 arch for Intel lasted from the introduction to PCI to the introduction of AGP. I have a socket 7 motherboard with 2 ISA, 4 PCI and an AGP slot that i can run anything from a p133, P233, and the AMD K7 processor line.

Also, going from vinyl to CD/DVD took decades and is simply un-comparable to the stupidity of AMD changing their sockets 3-4 times in a year.

Re:Tinfoil anyone?

[Bedouin X]

740 was not released in the last year, it has been around forever as the Athlon XP socket.

940 is for the high end. You can't put a Xeon in a P4 board. It's not going anywhere.

754 was a stepping stone to 939 which is better and cheaper. Intel did the exact same thing when the P4 came out and they went from Williamette to Northwood (socket 423 to 478). It may be inconvenient to people who didn't do their research - socket 939 was known to be coming from day one - but it's not unreasonable or unprecedented. Also, Socket 754 will be supported for at least another year so it's not like they are totally abandoning it today. The 3700+ which is very comprable to the 3800+ is on 754.

Re:Tinfoil anyone?

[Physics Nobody]

"AMD has release what, 4 incompatable sockets in the past year? 939, 940,754, 740"

What the heck is socket 740? There's no such thing, at least not for AMD. Do you mean socket A? That's been around for years.

"And soon it will be releasing another socket, socket 900."

I don't know where you heard that, but it's simply not true.

"Im sure they had other socketed versions that they never made public."

I'm not even sure what you mean by that. How on earth can you have a socket format that isn't made public? A socket format is by definition a public standard. Do you mean something they use for internal testing or development? Why do you even care? How does it effect you in any way.

"to make things worse is that AMD has stated that they wont be putting PCI Express on socket A (Athlon) or socket 754 systems.

"So, all those people that went out and bought a socket 754 motherboard are screwed when PCI express starts to be rolled out."

OK, this just made me really confused. How on earth do you plan on getting PCI Express without upgrading your motherboard?! Are you going to solder it on or something? The only situation I can imagine in which this is possibly relevant is if you want to upgrade your motherboard without upgrading your processor, but honestly how often does that happen? Upgrading to PCI Express is going to be a major investment anyway, as you're going to have to buy new cards, so you might as well get a new processor while you're at it.

"in contrast, the Socket 7 arch for Intel lasted from the introduction to PCI to the introduction of AGP. I have a socket 7 motherboard with 2 ISA, 4 PCI and an AGP slot that i can run anything from a p133, P233, and the AMD K7 processor line."

Socket 7 lasted so long primarily because of AMD and their Super 7 initiative. They did this because back then they did not have the clout among motherboard manufacturers to introduce an entirely new standard. This wasn't all fine an dandy, though. AMD really was put at a disadvantage in the marketplace because of the old bus standard they were stuck to. Intel had no interest in keeping socket 7 going that long and abandoned it early on.

Oh, and there is no way a socket 7 motherboard can support a K7. A K6, certainly, but not a K7.

"Also, going from vinyl to CD/DVD took decades and is simply un-comparable to the stupidity of AMD changing their sockets 3-4 times in a year."

It's also an uncomparable market. Music is a commodity item which most people own lots of and want standard players to be able to play. Processors are an expensive item that most people don't have more than one of and would never, ever, purchase without the motherboard anyway. The comparison is pointless.

Re:Tinfoil anyone?

[Anonymous Coward]

IANACD (I am not a CPU Designer)..

I know everyone does this anyways, but why go out of your way to type out an acronym if you're going to have to just explain what it means anyways? How about just saying "I am not a CPU Designer"?

Oh thats right, you are a karma whore.

Re:Tinfoil anyone?

[Anonymous Coward]

How does it effect you in any way.

"affect".

Re:Tinfoil anyone?

[Anonymous Coward]

why go out of your way to type out an acronym if you're going to have to just explain what it means anyways?

IDK (I Don't Know), BITTIMBTHPWHNYSTA (But I Think That It May Be To Help People Who Have Not Yet Seen The Acronym).

Anandtech review

[Karamchand]

Review on Anandtech! (I like them for their print view:)

A new core?

[Anonymous Coward]

AMD released a new core? First I've heard of it.. and this is slashdot, so now I'm worried!

Anyone have a die photo? (I guess this is like asking for the obligatory screenshot...)

More review links

[JaF893]

Here are some more review links for those who are interested:
Tom's Hardware
Bit-Tech
Driver Heaven
AMD Zone
Hard Tecs 4U
PC Perspective
Ace's Hardware
Sudhian

Low-power chips

[_|()|\|]

I'd like to build a system with a 35 W mobile Athlon 64 (e.g., AMD2800BQX4AX). It would be just the ticket for a Shuttle, or even a quiet mid tower. The only problem is, it lacks the integrated heat spreader, so I don't know what heat sink to use.

Aceshardware Review

[hattig]

AcesHardware found that disabling the 2T memory timing in the BIOS improved S939 performence by over 10%. The only limitation with this is one DIMM per memory channel.

A lot of reviews you read today will not be using this, and the results will therefore be significantly lower than what is possible.

Re:Aceshardware Review

[Anonymous Coward]

The reason other reviewers don't mention it is probably because this is a memory setting, not a CPU setting. That's not to say that the BIOS settings aren't important in benchmarking (and performance in general). It's just that other reviewers may not feel compelled to give all their BIOS memory settings when the focus of the review is on the CPU. Anyway, I expect that most reviewers would try to standardize the variables (eg. memory tweaks) across each platform so as to give a truer indication of the relative strengths of each CPU (as much as is possible, that is).

BTW, I know that the setting mentioned gives me about the same 10% improvement on my Duron system.

Re:Aceshardware Review

[SnakeJG]

But reading some of the reviews, they report memory speeds for the 939 FX processors as being slower than those on the 940 FX processors. Given that unbuffered DDR has lower latancies, this clearly shouldn't be the case. These sites must not have adjusted this setting on the new socket 939 boards.

Re:Aceshardware Review

[Hoser McMoose]

Given that the memory controller in the Athlon64 is part of the CPU, doesn't it stand that memory settings and CPU settings are kind of one and the same for these chips?

Good review at XbitLabs

[Anonymous Coward]

The source:
Meeting First Socket 939 Processors: AMD Athlon 64 3800+ and Athlon 64 3500+

http://www.xbitlabs.com/articles/cpu/display/ath lo n64-3800.html

I liked the conclusion. From the article:

"First, Socket 939 becomes a "stable platform" with a lifecycle stretching to 2006. Thus, AMD makes a step towards end-users who want to have low-cost upgrade opportunities.

Second, the new processor socket offers dual-channel memory access to the owners of the Socket 939 platform. I can't say that the two channels give the Athlon 64 a great advantage in speed (the performance gain from enabling the second memory channel is 3-5% in average). Well, no one promised any performance breakthroughs from the transition to Socket 939, but the improvements in the memory controller allow users to flexibly configure the memory subsystem and use four two-sided DIMM modules in their systems, while Socket 754 processors only supported two two-sided memory modules.

Third, AMD achieves a 25% reduction of the manufacturing cost of Socket 939 processors by cutting their L2 cache in two. This move will bring in profits and will also allow manufacturing cheap Athlon 64 models to ensure their popularity in the market." ...

Re:Good review at XbitLabs

[Anonymous Coward]

Correct link: Meeting First Socket 939 Processors: AMD Athlon 64 3800+ and Athlon 64 3500+

Arriving Q2 2004 apparently

[Anonymous Coward]

Not to mention the BTX motherboard layout + the possible "you need this to use this (tm)" features!

Re:Arriving Q2 2004 apparently

[Anarke_Incarnate]

BTX is probably going to be a niche unless intel really swings weight behind it. The reasoning for BTX was for better heat dissipation. The need for this was due to the problems with the Prescott cores et al. were getting way too hot. However, BTX sucked for a few reasons. First and foremost, it was single CPU only and much less tolerant of airflow problems. Intel's move to the Pentium M (P6) as their bread and butter will likely make this less of an issue. This is a good thing. I would like to see a redesign in case architecture, but not to BTX. Taiwan was also not eager to do the switch because it was more expensive and not a good payoff for the trade.

Can't wait till...

[Cigarra]

...this guy start selling them.

Do you Remember him?

Re:Can't wait till...

[Anonymous Coward]

I don't think we'll be seeing the 3800+ from him for awhile -

"Fastest Processor - Intel's Pentium 4 3400MHz 'E' HT Processor

Sorry AMD...your just not powerful enough!"

Re:Can't wait till...

[Derkec]

Ah, but now they have a money back guarentee. So if you get a computer from them and send it back they'll cover it. If you "Read Why" they explain that they've never had a return.

I guess you don't get many returns when you don't actually ship the computers.

List of Links to reviews / news

[d3bruts1d]

We've posted a list of links to reviews and news regarding the AMD64 939-pin processors. It's available here for anyone that wants to look at more information on the new CPUs. Currently 18 reviews, and the list is updated as they come in.

It's about time..

[Mechcommander]

I've been building computers for quite some time now, and am very glad AMD has prospered with their Athlon 64 line. And, as I've seen with nearly any computer part, this is just the next (if not final) phase of maturity that Athlon 64 will go through. The technology is getting more powerfull, as well as less expensive. And, since this socket will most likely be put on chipsets with PCI-Express and DDR2 support, I think this is a very good time to upgrade. And don't fret- some motherboard manufactures are starting to add backwards-compatibility for AGP and DDR, while adding the new features, such as PCI Express (16x and 1x), and DDR2. I know I'm saving what little cash I have for these products. It's time to upgrade.

Any concrete guides how to build a 64-ONLY bit...

[Anonymous Coward]

non-media, non-game, developing-oriented workstation using free software!

Preferably using AMD, so this post won't be modded as off-topic or flame.

Compile performance!

[IceFox]

Something I personally look for and most of the time isn't included in any reviews I was presently surprised to find in anandtech's review a Quake compile test!

http://www.anandtech.com/cpu/showdoc.html?i=2065&p =12

It doesn't specify what compiler or platform was used, but at the bare minimum it gives a little glimpse of what you might be able to achieve. Now all you have to do is apply that to a price/performance graph to determine what and how many you want to buy.

-Benjamin Meyer

Re:Compile performance!

[HarvardAce]

From a previous guide, a brief description of their build process.

As introduced with our Athlon 64 article, we are looking at compile times for the Quake III Arena source code. In running this test, we compiled the source for both Q3A and Q3TA in both debug and release modes using the Batch Build feature of Visual C++ 6.0. The build was run three consecutive times for each processor (in order to try to reduce file read time impact), and we used the third compile time.

Athlon64 heat dissipation

[phorm]

Actually, I've heard that - though increased power may heat the chip a bit more - Athlon 64's are a little nicer on the heat end. Why? Much bigger surface area of the processor die. My XP2500, which has reached temperatures of 95celcius (before I installed a new fan), isn't very big on the die. The last AMD64 I saw, quite a big processor. Therefore there's a lot more surface area for heat dissipation to the heatsink/fan.

128 bit memory controller

[Sediyama]

Who will use one 128 bit memory controller nowadays?
A 64-bit architecture could address up to 18 million terabytes.

Re:128 bit memory controller

[-tji]

That's 128 data lines, not address lines. It still addresses memory as 64 bit, which is plenty of address space for the foreseeable future.

The 128 data lines let it transfer twice as much data per clock cycle.. They doubled the memory bandwidth available. (Although, in actual practice, the memory throughput is only modestly improved by this change.)

Question: High temp issues?

[geohump]

I heard that Intel CPU's used to automagically reduce their clock rate when their temperature got too high.

This feature caused some businesses I know to forgo choosing any AMD cpu, since it couldn't protect itself in the event of an unattended fan failure.

First question - does the clocking down feature really exist on Intel CPU's? and second question, Does AMD have this feature yet?

Re:Question: High temp issues?

[geohump]

I'm using the AMD CPU on my personal system right now. If I were trying to generate FUD I would have just blasted away instead of asking for information.

According to my limited stab, googling for info, it looks like AMD still doesn't have the down-clock protection on its CPU's. Thats too bad.

I was hopinfg that someone would point me at info saying otherwise.

I would really like to be able to use them in my client installations but I can't really recommend them for anyplace that doesn't have 7x24 staff within hearing distance of any audible thermal alarms.

I did learn that there are some MB's which will try to save the AMD CPU from cooking itself and that is encouraging. Still - I won't be recommending AMD for Aunt Tillie or my small customers until the AMD CPU's or virtually every AMD capable MB out there has some way of protecting the AMD CPU's from self destruction.

That way I will get fewer "middle of the night" emergency calls.

Interesting that you posted anonymously.

Re:Question: High temp issues?

[Anonymous Coward]

I'm not sure about Intel but the AMD 64's have whats called 'cool n' quiet', basically the cpu will underclock down to around 800 Mhz and will even shutoff the cpu fan if its cool enough. On the flipside some motherboard manufacturers like MSI are including a dynamic overclock setting where you can set a percentage to overclock when the cpu needs it, up to around 13-15% over normal speed. Something to check into as well is Motherboard Monitor, its a neat little freebie software that can be setup to email you when a fan dies or a temp exceeds a predefined amount, you can also initiate auto shutdowns with it.

And as always, you get what you pay for in regards to case/cpu fans and heatsinks.

Re:Question: High temp issues?

[jp10558]

Well, from personal experiance with an AMD 1700+, if the CPU fan dies, the computer will freeze up. Generally this will result in a reboot by the user(at least in Windows). You will get about 5 min, and the machine will freeze totally again. Eventually someone will realize that something is fubar, and either call you, or turn it off till a tech gets there.

I replaced the CPU fan and continued on my way. There was no damage to the CPU.

My ASUS motherboards have a tempreture monitoring program for windows that can be used to shutdown the computer if the temp gets too high for either the CPU or entire board, or if a fan dies, or any combo you desire.

Re:Question: High temp issues?

[Hoser McMoose]

This feature caused some businesses I know to forgo choosing any AMD cpu, since it couldn't protect itself in the event of an unattended fan failure.

AMD processor will shut down if their CPU fan fails, just like pretty much all previous processors. Intel P4 chips MIGHT just throttle back, though according to Intel tech-docs they will only throttle down to 30% of their full speed at an absolute minimum, so it's quite possible that the chips will still be consume 20-30W of power. What that means is that the chip will still almost certainly crash under extended use and heavy workloads.

First question - does the clocking down feature really exist on Intel CPU's?

Yes. It's a nice little feature that can buy you an extra few minutes to shut down your PC in the event of a fan failure. On a system without this feature the processor would overheat and crash in fairly short period of time, probably 5 minutes or less, if the fan died. With this clock throttling feature it would probably take 10 to 15 minutes before the system locked up.

Does AMD have this feature yet?

Rumor has it that the Athlon64/Opteron die is capable of the same sort of clock throttling, but the feature has not been sufficiently tested yet and is not enabled. At least some of these new chips are using a second generation of the Athlon64 die and therefore *MIGHT* have clock throttling as a feature, but until it's actually tested, enabled and working, the answer to your question is no.

As a quick note: despite what you might see in some faked videos on some rather questionable hardware websites, a P4 will definitely *NOT* run at all without any heatsink at all! Do NOT try yanking the heatsink off your processor in the middle of running a Quake 3 Timedemo, it WILL crash and there's a good chance that you will damage the processor in the process.

Re:Question: High temp issues?

[Imazalil]

Here is what I remember...

Yeah intel has the feature and it works. I don't know if amd had the exact same feature built in to the chip, but just about all amd motherboards have overheating protection built built it. I think tom's hardware had a video of what happens, and it went something like this...

The 'test' was just to take the heatsink right off, not just shutting the fan off. This is a biggie. The Intel processor throttled down when it started getting hot. The amd chip blew out because the sudden chage in temperature was too much for the motherboard sensor to deal with. Had the fan been just stopped and the heatsink left on the chip, I am quite sure that the motherboard would be able to control the heat, or shut the system down.

I have an Athlon XP box right now, and I can set this up in both the bios and in Windows with the proper program. So it's not really built in on the cpu, but it should still protect the chip if the fan fails. Maybe the Ahlon64/Opterons have the same thing as Intel now as they support the clock adjustment depending on load

Im.

Re:Question: High temp issues?

[Hoser McMoose]

I would really like to be able to use them in my client installations but I can't really recommend them for anyplace that doesn't have 7x24 staff within hearing distance of any audible thermal alarms.

As mentioned in another post, the P4 clock throttling will typically not prevent the system from crashing, particularly with the latest and greatest (and rather power hungry) revision of the P4 except maybe if the system is still idle, and even than it's hit and miss. All it will do is give you a bit more time between when the "Fan is not working" alarm first goes off and when the system locks up.

I believe Sun and IBM (among some others) will sell you systems that really and truly CAN stay up and running after a fan failure. If your customers really need that level of uptime, perhaps they would be better served by one of those systems? (I'm actually being serious here, Intel and AMD systems just aren't designed with extremely high reliability and uptime in mind, such designs cost money).

I did learn that there are some MB's which will try to save the AMD CPU from cooking itself and that is encouraging.

This is now included on-die with the Athlon64 and Opteron chips, no more motherboard intervention required. Either way, all AthlonXP boards had this feature enabled, though it sometimes wasn't enough to save the chip if the heatsink was not installed in the first place (or yanked off a running system).

Still - I won't be recommending AMD for Aunt Tillie or my small customers until the AMD CPU's or virtually every AMD capable MB out there has some way of protecting the AMD CPU's from self destruction.

If all you're worried about is fan failures than you should be plenty safe with any AthlonXP or Athlon64/Opteron board. These boards have always shut down just fine if the fan fails.

Most of the stories about AMD chips frying themselves was pure fear-mongering and stupidity, or at the very least it was lazyness. A few people did fry their chips by failing to install the heatsink properly. I've installed a few AthlonXP heatsinks and they are not difficult at all, but apparently some people just slap the things on upside-down and backwards and killed their chips as a result.

Otherwise most of this started with a particular hardware review website that wanted to get MANY page hits (and they succeeded beyond their wildest imaginations) with a video of an AthlonXP frying itself because they yanked the heatsink off the thing while the system is running, while proceeded to show a faked shot of a P4 surviving the same exercise (read Intel's tech docs sometime and/or try running a chip consume 20-30W of power without a heatsink and you'll see why I say this test was faked). While very sensationlized and widely touted across the web, IMO the video did a great diservice to both AMD (people think their chips will fry themselves under anything resembling normal use) and Intel (people think their chips are invulnerable and will run with no cooling).

Re:Question: High temp issues?

[pyrrhonist]

Otherwise most of this started with a particular hardware review website that wanted to get MANY page hits (and they succeeded beyond their wildest imaginations) with a video of an AthlonXP frying itself because they yanked the heatsink off the thing while the system is running

The original article was shot down in an AMDZone article that was covered by Slashdot.

15 Reviews listed

[jmke]

right here HardOCP Tech Report X-bit Labs T-Break Sudhian Bit-Tech HotHardware Beyond3D PCPerspective Legit Reviews HardTecs4U Driver Heaven Anandtech TomsHW AMDZone

Nice start, but that's about it

[sacremon]

All the reviews have pretty much shown that there is little difference between 940-pin and 939-pin versions of the chip, and even 512KB L2 vs. 1MB L2 doesn't make a big difference. Afterall, in the vast majority of applications, are you going to notice a 5% increase in speed?

This is a nice starting point for AMD to ramp up their line of consumer/low-end workstation chips, given that registered RAM isn't required. Higher end workstation users and servers will still want multi-processor systems with registered RAM, so no real change there.

Re:Nice start, but that's about it

[Anonymous Coward]

You said it! Not only that, but what it also means is that if L2 cache and bandwidth don't matter, MHz must be the bottleneck. Ergo MHz is not a myth.

Re:Nice start, but that's about it

[hkroger]

Afterall, in the vast majority of applications, are you going to notice a 5% increase in speed

Oh, sure if it has FPS counter.

yeah...

[Perianwyr Stormcrow]

Just as I got a new board too.

They got me with this the last time too with Slot A processors. Shit hell damn.

If running Windows....

[Perianwyr Stormcrow]

...it most certainly will.

Not since Windows 98 have I been able to swap out a drive from one machine to another without reinstalling.

Nice username, it works

[Gothmolly]

Also win9x and me might not be able to take full advantage of the spped. (but that more of a guess then anything)
This sentence lacks any cognitive value, but I'll refute your point, since I'm bored at work. To claim that an OS doesn't "take full advantage of the speed" is like saying your car engine doesn't take full advantage of all 32 valves. Either you have MHz, or you don't. Just because you're running WinME doesn't make your CPU any slower. It may have poorer memory management, but that has no impact on CPU utilization.

Since you admittedly don't know, and are guessing, how about you keep quiet, since all you're doing is serving to bloat the Slashdot DB more with your content-less posts? And try capitalizing where appropriate.

Re:Nice username, it works

[sumdumass]

Nice refute but, it is a fact that win98 and me won't be able to use the hyperthreading in the new intell processors. Out side of that, I will admit that what I should of said is, "Win98 and ME might not be optimized to eficiently use the faster proccesor speeds" rather then take full advantage of it.

Intel recomends you turn off the hyperthreading when using older versions of windows.

http://www.intel.com/support/platform/ht/os.htm

Windows XP (and possibly 2000) will use the extra MHz in a more eficient way and apear to be faster in the proccess. You are corect in MHz equals MHz. you also skipped the point were I was saying I was guassing on that too.

Now lets look at some marketing material.

http://www.amd.com/us-en/Processors/ProductInfor ma tion/0,,30_118_3734_3736,00.html

says that the AMD athlon xp is taylored for the windows XP operating system. It futher goes on to say

Microsoft optimized the DirectX 8.0 interface for Windows XP specifically for the AMD Athlon XP processor

Considering other things it states, the overal message is that the new proccesors perform better on windows xp.

SO YES WINDOWS 9x -ME MIGHT NOT BE ABLE TO TAKE FULL ADVANTAGE OF THE PROCESSORS SPEED IN A WAY THAT XP CAN. Also this is more of a guess because the manufacturers implied it instead of comming right out and saying it.

Re:Nice username, it works

[Gothmolly]

Except that AMD chips don't hyperthread. There is no basis for the statement "Win98 and ME might not be optimized to eficiently use the faster proccesor speeds".

You base your entire argument on AMD's Marketing press release that says "Microsoft optimized the DirectX 8.0 interface for Windows XP specifically for the AMD Athlon XP processor".

This is a highly dubious statement at best, since MS would have no incentive to optimize it for AMD at the expense of Intel. DX8 may include 3DNow instructions, but it also may include SSE2 instructions.

Lastly, you qualify your whole counterpoint with "Also this is more of a guess because the manufacturers implied it instead of comming right out and saying it.", thus ripping the foundation out from underneath your shaky argument.

Have you even graduated high school? I suggest taking a critical thinking or logic class, if you hope to accomplish anything in the real world.

Re:Nice username, it works

[sumdumass]

Lastly, you qualify your whole counterpoint with "Also this is more of a guess because the manufacturers implied it instead of comming right out and saying it.", thus ripping the foundation out from underneath your shaky argument.

And you point is what? I said that is was more or less a guess in the first post. The only difference is i didn't cite a reference that would make a reasonable person belive it. And I based my opinion on other stuff being spread around by other sites too, thats just the only like I gave you because it was from AMD itself and probably the only link I will give you. Google isn't too complexed for a person like you to use.

Maybe you are just a troll and I should just ignore you. My answer stands as it is, AMD claims it designed the athlon XP to work with windows XP and insinuates it would be more efficient when running under windows XP. THE asumption is more or less a guess.

GO back and read my first post then read the press relases from AMD. It says microsoft done stuff to make it work better in windows XP. Also the hyperthreading was just another example of how win98-ME might not be able to take full advantage of the speed of the newer proccesors Including the intels. Call it an added bonuns for your time.

Good day to you and I wish you well

Re:No 64bit scores (and CPU cost ...)

[hobbs]

Out of curiosity, I tied these scores to CPU prices as listed at http://www.pricewatch.com/:

CPU SCORE US$
Athlon64 3200 64: 523.70 $255
Athlon XP2700: 467.15 $ 80
Athlon64 3200 32: 449.07 $255
Athlon XP2600: 448.42 $ 71
Pentium4 3.0GHz: 387.57 $203
Athlon 1400: 305.26 $ 97
AMD Athlon 950: 209.51 $ 69
Sparc 500MHz: 52.21 ???
Sparc 440MHz: 51.89 ???

Are you for real or ignorance is bliss?

[Anonymous Coward]

The p4 has been around for years and it's down clocking a much discussed and widely promoted feature to the point where even non computer people are aware of it and you're that unfamilier with it? Looking at your post history leads me to believe your technical savy enough to know better and thereby that the point of this post is to drudge up old FUD. If you wanted to promote Intel processors, there are legit ways like pointing out where they perform better in some types of applications.

What is that necklace made of?

[MarcQuadra]

Haven't you ever seen 'Labyrinth'? In some alternate fantasy worlds plastic, or 'plaz-tech' as they call it is quite desireable.

Of course, in the same world David Bowie is a king and god, wears tight spandex pants and eyeshadow.

Maybe they don't have their value systems clearly defined as they should.

Compile EVERYTHING

[Psymunn]

Man, a gentoo box on a AMD-64 w/ the right flags ... *drools a bit.* Frozen Bubble is going to be soooo smooth.

price/performance

[bani]

Itanium2 @ 1.5ghz : ~5500
P4 @ 3.0ghz : ~$200

If your Itanium2 is only getting 2x the performance of the P4, its not exactly cost effective is it? You could build a cluster of ~20 P4s and get ~10x the performance of that Itanium2 for the same price.

Re:price/performance

[BlowChunx]

Define cost effective.

If you can write OpenMP/MPI code that runs on the cluster, then yes, the cluster of P4's would probably get you better performance. But the way to code is written, it's horribly non-parallelizable...and of course, rewriting it takes money (or time, and they are equivalent).

If you can't and just need speed from serial code, then the Itanium might be the better choice.

Re:price/performance

[Anonymous Coward]

Ahh, guys, I don't think you understand... Chunx is my dog.

Re:Any concrete guides how to build a 64-ONLY bit.

[Wesley Felter]

Sure, I've done this.

1. Buy whichever AMD64 processor you like.
2. Buy a motherboard that supports that processor.
3. Buy all the other parts (RAM, hard disk, graphics card, etc.).
4. Put it together.
5. Install Fedora Core 2.

Personally I used an Athlon 64 FX-51, an ASUS SK8N, Corsair low-latency RAM, and a Radeon 9800 Pro (if you're not playing games, get a cheaper video card).

The real world is a big place.

[LWATCDR]

Not everyone will be running 32 bit code on these chips. Some maybe a lot of the first people to use them will at least recompile if not port to 64 bit code. Thinks like renderfarms and clusters could be some of the first to use them. Now on the desktop you are most likly right.

Hello! I'm earth have we met?

[NEOtaku17]

Ever tried to run a AMD proc in a PC with the heatsink off? It shuts down immediately. It's not just going to fry and melt into a money wasting puddle.

Re:Any concrete guides how to build a 64-ONLY bit.

[mrchaotica]

Yes. It's called "Get yourself an Athlon 64, and then install Gentoo on it, compiling with --march=x86-64, or whatever the flag is.

(note that I'm not trying to be a fanboy, but few of the other good distros are easily source-based)

Re:Any concrete guides how to build a 64-ONLY bit.

[merky1]

and a Radeon 9800 Pro (if you're not playing games, get a cheaper video card).

Heck, if you do want to play games, get a cheaper card. ATI has yet to release the 64 bit driver for X, so no 3d for us. Makes me wanna find my old Matrox G-400 and fire it up again.

Athlon64 platform will not allow this anymore.

[MojoStan]

what about the people building thier own computer and selected a smaller processor because it wass afordable and then plan on buying a better one when availible.

I hear ya. Since my current processor needs are met by today's "value" processors, I have considered building an Intel Celeron-based system using the Intel 865PE chipset or an AMD Duron-based system using the nVIDIA nForce2 Ultra 400Gb chipset. Then a year or two later, I can buy a much faster Pentium4 or AthlonXP when prices are way lower.

Unfortunately, it looks like the Athlon64 platform will not allow us to install "low end" processors into motherboards made for "high end" processors. I read on Anandtech's review that AMD's value line of processors (including an upcoming 32-bit only version of Athlon64) will all be Socket 754 processors while future Athlon64's will eventually all be Socket 939.

What I'm pretty sure this means is that I will not be able to install AMD's Athlon64-based value processor into a Socket 939 motherboard, then install a real Athlon64 4000+ a year or two later when prices are way lower. Even though AMD's "value" processors will be based on the same Athlon64 core, I'm pretty sure socket converters (e.g. slockets, socket370 to fc-pga converters) will not work because of the different on-chip memory controllers (single-channel vs. dual-channel).

So there goes my plan on building a Socket 939 system using AMD's "value" processor, then upgrading to Athlon64 later. Now I'm considering building an Intel Socket 775 Grantsdale-based system with DDR2, PCI-Express, BTX form factor, and a (I'm not kidding) Prescott-based Celeron 325 processor (2.53GHz, 533MHz bus, 256KB L2 cache). By the time I need more processing power, a 4GHz+ Pentium4 (1066MHz bus, x86-64) will be reasonably priced.