Slashdot Mirror
Athlon 64 Debuts
SpinnerBait writes "AMD launches their Athlon 64 and Athlon 64 FX chips today and there is
a full analysis with benchmarks up at HotHardware. Interestingly
enough, Intel pulled a fast one (literally) and released a new breed of Pentium
4 chips with 2MB of on board L3 cache, just in time to boost their performance
in the benchmarks for this launch. Regardless, the performance levels for
AMD's new flagship look very strong." Tom's has a story, or Tech Report, or see info straight from AMD.
So Intel cheated by, uh, making better hardware?
Once Windows for 64bit AMD comes out (soon), I'm sure you'll start seeing quite a few more apps. We're in the transition phase now, where we'll buy 64-bit chips that can still work well in a 32-bit world. It's not an upgrade for Joe Homeuser quite yet, but give it a year.
No, a troll would be saying that you're going to buy some eggs to fry on this processor, or even better some grits to pour on Natalie Portman.
And the end user won't realize a big difference, and the bang-for-buck ratio won't be there either. But serious database apps, cad, and any other high-end market will most definitely benefit.
Finally, a 64-bit desktop processor!
Oh wait it's been done!
But seriously, there are a number of reasons why this is a great chip.
Namely, if Intel actually thinks putting a cache that's too big on a chip is actually going to help, good luck.
A Toast to AMD for once again making the superior product.
Remember when the P4 came out and it was slower than the P3 at the same clock speed? Like P4 was then, the Athlon64 is designed with the future in mind, not blowing away everybody on day one and having no room to scale from then on.
The global economy is a great thing until you feel it locally.
Just because checking mail is all you use YOUR computer for, doesn't mean that's all everyone else uses their computers for. There are already plenty of apps around that will suck up this much processing power and still beg for more, and they're not as obscure as you'd think. I have a friend who does a lot of 3D animation, and rendering will ALWAYS leave you wanting more CPU power and RAM. Enough will never be enough for stuff like that. And when you want to rip your CD collection to mp3 (or ogg, or whatever), you're gonna want the fastest thing around, if you've got a decent collection. DIVX-encoding is pretty nasty on the CPU, too. These are all fairly common tasks now.
Patrick Doyle
I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
...of both the new AMD-64 and the Pentium 4 Extreme is that the prices of the older chips should start dropping like a stone.
Learning HOW to think is more important than learning WHAT to think.
I couldn't care less about their silly-ass naming schemes - I'm much more irritated with their ridiculous lack of planning on socket formats & memory controllers. Single channel on that kind of processor (the non-FX) - what were they smoking? Maybe if they want to call that the new Duron, but otherwise, that's just idiotic. They should also have increased (doubled!) the L1.
:)
It's not like any of this _really_ concerns me, mind, as I'm now saving up for a G5. It's time to 'Switch'!
I'd say with CPU prices like that AMD & Intel are now charging, the whole 'PCs are cheaper than Macs' theory is gonna get a lot less credence.
I'm _really_ interested in seeing some real & comprehensive benchmarks between all the processors, now that they're all out. G5 vs P4 vs P4EE vs Xeon vs Athlon 64/FX.
AMD created the 3DNow! extensions to the 80x86 instruction set architecture (ISA), also known as IA-32. They were a significant improvement over the original set of MMX extensions. However, later, Intel created the SSE (and SSE2) extensions. Guess what? AMD was forced to incorporate them into its future chips in addition to the 3DNow! extensions. Ignoring the SSE extensions would have cost AMD dearly in terms of marketshare. The fact of the matter is that Intel sets the global standard for the IA-32 ISA.
Now, AMD has created its own x86-64 extensions to the IA-32. You can be sure that Intel has created a different set of 64-bit extensions (which we shall call "INTEL-64") to the IA-32. After all, why would Intel support AMD in any way? Once Intel activates the INTEL-64 extensions in the upcoming Prescott, AMD will be forced to go back to the drawing board to incorporate the INTEL-64 into all future chips. The current Athlon64 will be like the K-5 -- interesting but without a future.
AMD will probably take an additional 2 years to produce an INTEL-64-compatiable chip. By that time, Intel would have locked 90% of the 64-bit desktop market with Prescott.
The worst news is for Sun. With Prescott, Intel has a 64 bit chip that will be significantly faster than the UltraSPARC III/IV. Right now, the Pentium 4 crushes the UltraSPARC III in performance. Please review the performance characteristics of the Pentium 4 at the SPEC web site. Since Prescott (successor to the Pentium 4) will be faster than its predecessor, Prescott will clean UltraSPARC's clock. Moreover, the number of applications that will run on Prescott -- the heir to the software empire of the x86 -- far exceeds the number of applications that run on UltraSPARC III/IV. On the key TPC-C benchmark, Prescott will clearly deliver outstanding performance, compared to the UltraSPARC III/IV.
In short, when Intel activates the INTEL-64 extensions in Prescott, Intel will force (1) AMD back to its usual state of borderline bankruptcy and (2) Sun into being a software company.
Did you see the performace gain by the cache you say is too big (Normal 512K P4 versus Extreme 2MB P4)?
The cache is the main reason the G5 Dual 2.0 isn't that much better than a G4 Dual 1.42. If the G5 had 2MB Cache as the G4's do it would perform even better (L2 would be significantly better than L3 as well, but costs increase significantly).
Next time you're trying to run some 3D modeling or any other intensive CPU based software, just realize the cache is significant.
I think we can all see the wisdom of releasing the new processor before the new OS.
-Looking for a job as a materials chemist or multivariat
I'm looking at a 1TB disk array. Since that's more than 2B blocks, I can't store the disk block address in a signed 32-bit number any more.
Barring that, what do I have that cries out for 64 bit arithmetic? Not much.
Also, try compiling the same app in 32-bit and 64-bit modes. The 64-bit app is a lot bigger and slower, since all the pointers doubled in size, so less code fits in cache, and I'm using more memory bandwidth.
The 16 to 32-bit conversion was forced, because it didn't take much of a problem to overflow a 16-bit number. The need for 64-bit hardware is a little less obvious.
Add in power and cost and I'm guessing that 32-bit hardware will continue to be sold for quite a while.
Though I am a die hard AMD supporter, i have to admit Intel has really pulled one up on AMD this time. The 64bit 3200+ is just about 15-20% faster than the stock and barrel Intel 32bit 3.2 GHz. Bad news for AMD this is, considering the retail price of these babies is 450 & 800$ (Normal and FX).
Yeah. I can't believe that you can get a brand new CPU that's 15-20% faster than the previous champion for only 25% less! Oh, and that's in 32-bit mode. If 64-bit computing takes hold then Intel is SOL at the moment - despite the rumors flying around about Prescott and 64-bit instructions.
Yeah, the Athlon64 3200+ is $465 (note, look at the retail price w/ heatsink to be fair), but the P4 3.2GHz is $619.
The Athlon64 FX-51 is certainly overpriced, given how miniscule the performance differences are, but that's hardly a surprise.
What Intel did pull wasn't a price/performance coup (because it isn't, by any means) but a paper launch debacle. Every single review I've seen thus far includes benchmarks for the P4 3.2EE -- which isn't available until November, and at prices similar to the Ath64-FX (based on preliminary 1000 CPU lot prices). The P4EE is competitive with the Ath64, but it's a smokescreen. You can buy an Athlon64 right now, but the P4EE is non-existant.
And BTW windows released XP 64bit Beta1 today.
Unfortunately it appears that there's a severe lack in available drivers. All the sites are having to use nVidia 5900FX's and even then can't bench any DX9 apps in Win64 due to no 64-bit DX9 being available.
well, it's still better than intels EXTREME EDITION.
i
-
world was created 5 seconds before this post as it is.
when will we see some serious APPS...
Add -m64 to you march flags then emerge -e world
There is nothing wrong with being gay. It's getting caught where the trouble lies.
> 3D animation, sure - but are there 64 bit apps for it? or still 32bit apps? understandibly, i wouldn't give a rats ass if my mail was checking at 32bit, but, why would i spend the money if my 'money' app was still 32 bit aswell?
Apparently you haven't checked any of the benchmarks out there yet, or you'd know that 64-bit apps aren't even _remotely_ necessary to get great performance out of 32-bit apps on the Athlon64 (or PPC970 aka G5). Despite being '64-bit' chips, they still run 32-bit apps noticeably faster than their previous 32-bit counterparts. Yes, you'll undoubtedly see even more improvement once they're optimized for 64-bit OS & apps, but that's hardly necessary to see great improvements in performance right off the bat. I think that's quite an achievement, actually.
Also note the extreme price premium the FX & EE chips command puts them out of reach of the vast majority of people, and that noone's forcing you to upgrade. It's better to have the option and not need it, than need it and not have it.
The option _I'd_ like to have is enough money to get a G5 system. *sigh*
I've also seen people saying, "Yeah, but wait for Prescott." Uhm, 105W heat dissipation? NO THANKS.
They state on one of the early pages:
Many applications improve performance due to the removal of the 32-bit limitations.
Nice try HotHardware.com. Anybody who is anybody knows that performance does not increase just by increasing register bit size!
I would take your post seriously if you had mentioned what part you believed Microsoft would play in the world of competing 64-bit extensions.
WXP for the Althon 64 is well on its way, as seen in the linked HotHardware review. Will Microsoft and the driver writing departments at hardware firms put up with a stealth announcement of another set of 64-bit extensions?
If you actually want the industry (and 64-bit computing as a whole) to move forward -- then go out and buy a chip...if nobody buys these because no OS/Software manufacturer writes 64-bit code, then there will be big trouble for little AMD. The idea was to build a chip that runs 32 and 64 bit code very quickly. What it sounds like you're saying is that you're waiting for Intel to release a 64-bit chip so that everyone optimizes their code for that. I, for one would rather back the company who was innovative and was first to market with a pretty cool product than the biggest guy on the block (er...industry...whatever).
From the benchmarks I've seen -- it does a pretty damn good job at both 32 and 64 bit code (especially for a first release without a good 64-bit clean codebase). It manages to beat the existing 3.2 Ghz P4 for cheaper.
I hear what you're saying about waiting on at least one level though -- I can't remember ever spending $400 on a CPU, but I'm confident that in 6 months, those things will be selling for quite a bit less than they are now...they'll be a good bargain.
Finally, I have a 1.4Ghz Thunderbird as my primary desktop. At this point, it should be called a 1.4Ghz Shitbird. I intend to replace it -- the only questions are: when, and replace with what? I know that if I decide to get an Athlon64-ish chip, I won't be making that decision based on whether or not there are 64-bit apps/OS'es for it. For what you pay, it works great...I'll make my decision based on price:performance ratio on what's available now...and from what I can see, it already shines against a much more mature platform.
-Turkey
Of course, in a situation where you might want more than 4 GB of RAM (not me, but a good number of people), the 1 TERABYTE of RAM cap on the 64-bit machine sounds pretty enticing. I'm not really sure how allowing more RAM, and upping the on-chip cache, moving the DDR RAM controller to the cpu die, and optimizing the instruction set will cause things to move slower, even if you have a higher storage/instruction requirement.
Space is cheap. Time is not. Space gets cheaper and cheaper. Time is worth more and more every day.
I only wonder why they had to do this today...I look silly drooling on my keyboard at work.
I read several of the reviews, and all stuck with 32 bit code for the comparition between the Intel P4 and the AMD Athalon 64. Linux runs on the Atahlon in 64 bit mode, wouldn't be hard to compile PovRay and Doom on a 64 bit compiler and see if anything changes. Thats just for an easy test.
Many real world (science?) applications benifit from 64 bit processors, find some (presumably running on UltraSparc, PPC, Alpha, or such) and port them over to see how the 64bit abilities of this chip compares to the other existing chips.
I run open source OSes, and open Source applications. I don't care about 32 bit performance because I'm fairly sure that if I did have an Athalon 64 I wouldn't run 32 bit code very often. I can choose between many chips, compatable instruction sets to me means gcc (or other compiler) has an output for them. 32 bit x86 compatiabily is nice for the few times I have to run something 32 bit (normally in Wine) and that doesn't happen very often.
FUD, lack of evidence, and outright lies - they call this journalism? They dismiss the Apple's claims about the G5's performance without a) including it in their later benchmark or b) citing any references.
Because sane, savvy people in the technology industry should know better.
We have had 64bit AMD systems running here before the Apple G5 announcement, additionally, we have had Itanium with Windows XP 64 edition running here for over a year.
Considering we ACTUALLY have these 'shipping' systems already in our office and labs for quite some time, do we need a reference from the article's author to know that Apple was lying out their ass?
Where in the hell have you been?
Apple was NOT the first 64bit desktop PC, their performance numbers were 'admittedly' pulled from a comparison of slower 32bit Xeon CPUs, and only showed the specific few tests that the G5 actually outperformed even the older Xeon chips.
And the last nail in this Apple shenanigan is that Mac OSX (even the new release for the G5s) is NOT a 64bit OS, and has no plans to be a 64bit OS in the near future.
I don't dislike Apple or their products, but their marketing department needs to be whacked up side the head. Instead of billing the G5 for what it IS and its TRUE good points, they go out on this hyperbole that is false and make a fool of themselves.
I'm sorry you and other people buy into it. If you are so worried about facts and citing references, why haven't you checked the facts that Apple has been purporting? You would have found they are false which is what the rest of the industry already knew.
I'm not sure that you really understand the meaning of the word "Troll." Check here for a good definition of "Troll." The word came from "Trolling for n00bs," where people would purposely get something wrong in order to get all the new people to jump on them. A good troll is really quite amusing, and very difficult to pinpoint... such as this comment's parent's post, I would guess. ;-) Good trolls usually do not include Natalie Portman, Grits, or AYB. Those posts would generally be modded "Offtopic," which is a euphamism for "Useless."
What is interesting is that the grandparent thought they were posting a Troll by posting a valid thought held by many people. If there are no apps, then why would I buy the processor?
In answer to that question, I would propose the analogy: Would you wait until the flood hit to get sandbags? It's always good to have the sandbags on hand, they don't get in the way, nor do they cause you to live life in a different way. The Athlon64 is like that, a latent 64 bit platform that doesn't hurt to have, and even gives incredible performance gains in 32 bit apps.
You need to restart your computer. Hold down the Power button for several seconds or press the Restart button.
You claim to have been using 64 bit x86 CPUs for over a year (Itanium) as well as from AMD (Opteron), but what you fail to realize is that Apple is claiming first 64 bit DESKTOP. The Itanium and Opteron chips are not desktop CPUs, but server and workstation chips. This is just silly semantics, and anyone who believes marketing drivel should have their head examined. But to simply dismiss a whole platform for these stupid marketing claims is ridiculous. The 1.6 and 1.8 GHz G5s have been in the marketplace with a final version of MacOS X 10.2.7 for over a month, making them the first viable 64 bit DESKTOP solution available in my book, since they run a final, stable version of MacOS X which is as tuned as it needs to be for 64 bit operation (mostly 42 bit memory address space support and a few 64 bit math libs), and a good consumer user experience. Someone trying to use Windows XP 64 right now had better be an expert user, to deal with all the problems with missing drivers. If you want to argue that the opteron was a desktop CPU or had desktop solutions (since it can run Win32), that might be a valid argument, but you can't fault Apple's marketing department for trying to cash in on the 64bit buzz, especially since most people who watch those commercials have never heard of an opteron.
As for benchmarks, it's silly to omit the G5s from the comparison for religious reasons, and people want to see how they stack up. The only way to counter Apple's marketing drivel is to do actual real-world benchmarking using cross platform apps and benches. The 'slow' Xeon chips Apple compared the G5 to were the fastest available at the time from Intel. I don't know why they didn't compare themselves to the Opterons, but them's the breaks. What we need now is for all these PC tech sites to get some dual G5s and compare them to what they think is the top of the line on the x86 platform. FUD and hostility will only make people see these sources as biased and unprofessional. Objective comparisons between G5s, Athlon64 FX and P4 EE will drive lots of page hits, since people are starved for this info right now (due in part to Apple's excessive marketing claims). So, either put up or shut up, and be happy that Apple's marketing claims drove so much interest in G5 comparisons w/ x86 offerings.
"I like systems, their application excepted", George Sand (French)