Slashdot Mirror
AMD vs Intel: A Linux Bout
CrzyP writes "AnandTech puts the latest and greatest AMD and Intel CPUs, including 32-bit and 64-bit versions, to the test in their first ever "Linux Desktop CPU Roundup" to see which performs the best in various Linux applications including database, compiling, rendering, encryption, and more. They suggest the Athlon 64 3500+ over the P4 560 for "balancing price and performance". Very informative!"
Aside from the few times Intel released a great overclocker, I have never seen a lower-priced Intel processor beat a higher-priced AMD processor in any significant set of benchmarks..
AMD4tw!
Yet, benchmarks, until recently, always seemed to compare same clock speeds/ratings despite Intel's offerings always costing more. It's nice they're starting to be more fair to AMD.
--- We need more Ron Paul!
Everyone KNOWS that for the best Linux performance you must use a specially optimized compile with Gentoo! It's a FACT!
I'll bite.
That is, to be blunt, a load of shit. I've looked at the "performance benchmarks" on the Gentoo site and they are among the most misleading I've ever seen. I'm sorry, but "binary load" time does not equal performance, especially when the prelinking process breaks a hell of a lot of programs and requires you to be careful compiling any of your own libraries (but, I suppose a Gentoo zealot would never compile anything without an emerge for it, which ought to wipe their asses for them).
If you think that a big render farm quantifies its perfomance in terms of how fact the executable is initially loaded, then you may be stupid enough to think Gentoo gives you better perfomance than anything else.
There you have it. Now you Gentoo pussies can mad me down and stick your heads back in the sand.
Hyperthreading is REALLY good for allowing low work threads to be much more responsive under heavy system conditions. One of the places I've noticed hyperthreading really shines is allowing MS Windows systems to have a more responsive UI when the system is stressed out by heavy CPU workloads.
This is useful in programming because the editor keeps up nicely without going "away" for a couple seconds if I decide I want to make some changes or revisions to a file while compiling the rest of the project.
they make good products sure..
but the dollar per performance ratio isn't as good as amd's - and that's a fact.
nobody cares about the 'little guy' in cpu buying.. otherwise cyrixes and transmetas would have fared better.
most of the guys using amd's i know would be be using intel if it offered better performance per dollar - the intel only users i know just prefer intel for whatever reasons ranging from 'reliability' to "amd's are space heaters" to "amd suxxx".
world was created 5 seconds before this post as it is.
No but it keeps Windows nice and responsive even when somethings crunching away in the background, which is what it's for, IMO. That is, doing a great big compile job in the background doesn't slow down my slashdot reading.
It's not a second CPU, but a way to share a bit of the power. The problem is, Linux treats it like a CPU, Windows has some special rules for it.
I'll just say I noticed the difference as far as "responsiveness under load" between a P4 2.8 (no HT) running at 3.06, and an actual 3.06 with HT, under Windows. Didn't notice any difference with Linux.
I don't need no instructions to know how to rock!!!!
You bought a 64bit consumer orientated chip to use as a server, tried to install 32 bit Windows emulator as AMD64 native binary and have an ATI graphics card to play UT2004?
1+1=5
Wouldn't you be better with WinXP 64 beta? This isn't a troll, I have a rack full of Opterons running linux and a desktop AMD64 machine but I'm not a gamer, and I've no use for Windows programs. You on the other hand...
Since you didn't read the article, why are you asking the question? The testing looked pretty thorough to me, and the analysis was reasonable.
And for the record, I know a number of AMD freaks. None of them are pro-AMD because of the Windows vs Linux thing. A few of them are anti-Intel, but some of them use Windows.
So at least among those I know who voice an opinion, your thesis rings false.
I would certainly agree with you. Many of us who were anti-Intel and wanted a competitor constantly hoped that AMD would produce something better. The same anti-Microsoft sentiment that Linux users continue to enjoy windows take hits from security, stability, etc. I do know Intel is historically good at releasing all the documentation needed for developers. But AMD seems to have gotten more people excited about 64bit processors. Though, AMD's 64bit chip actually has per page locking on it (something no other x86 chip can boast.) Also, the 64bit windows xp isn't out yet, so performance is obviously better with the linux+AMD choice over windows+AMD.
:(){
Hyperthreading lets the other thread use execution units that'd otherwise be empty due to pipeline bubbles. This makes a reasonable difference on many applications on the P4, due to its absurdly long pipeline. A more sensible pipeline length (i.e. an AMD processor) means there'll be less benefit to hyperthreading. I can't think of any good reason why the effects will be different between Windows and Linux.
In soviet russia stale jokes recycle you!
I love AMD for the stealth marketing.
AMD has never ran an ad campaign informing me the processor is inside the computer. AMD has never assaulted my ears with crappy noise from painted blue freaks.
1. Put the money into R&D
2. produce a great product a fair price
3. let the word of mouth advertising do it's thing.
4. Profit
There is no ??? in this business strategy.
Is "stuff won't compile right under AMD64 so I'll let you guys beta test the new CPUs and when it's ready for production use I'll look into it" a good enough reason to stay with Intel for our production servers?
No, because AMD also do a range of 32-bit chips which also offer better price/performance ratios than Intel's equivalents.
Got Xeons? Consider buying AMD64s and running them in 32-bit mode. No compatibility problems, and much much cheaper.
There's no need to justify using Intel by slamming AMD - I'm guessing you use Intel because that makes the PHBs/investors more comfortable, not because you have any evidence that AMD chips are unreliable.
the thing may be that with both Linux and AMD one of the reasons to choose them may be the unwillingness to go with the mainstream. It is that way for me anyway. So there certainly is a correlation.
...remember good 'ol times when IP used to mean Internet Protocol....
Ya because todays consumer is well informed about all issues surrounding the product they intend to purchase. Thats why OS/2 and Apple beat out the less then stellar offerings from Microsoft over the past decade.
Hmmmm....
People buy what ever a company makes the most noise about. There are still people that you really have to slam their head against a wall to convince that an AMD processor isn't inferior to Intel, simply because they never hear of this 'AMD thing.' The only real reason to choose one over the other is the cost. That said, being a fan of either is just silly. Unless you run benchmarks that spit out numbers, which are meaningless in the real world, you will not be able to tell what a system is running. If I threw a AMD processor in a box and slapped an Intel Inside sticker on the front, 99 out of 100 people would tell me I'd get better performance from an AMD chip after they used it, the last person probably wouldn't care. You see an increase in performance in an AMD system because you expect to, not because it actually is so much better, since the differences in real performance are imperceptible.
"I use a Mac because I'm just better than you are."
I can only speak for myself and as a gentoo I dont't give a f**k about 3% performance gain by optimizing my CFLAGS. I (and probably others with me) use gentoo because we like portage and use flags. compiling software is a neccesary which I would like to take as short time as possible. So your parent question stands.
How much time is there to gain from going to 64 bit? Anybody have a clue?
The benchmarks would be a lot more credible and useful if scripts and data could be downloaded and run by readers.
How little in the way of data analysis skills even tech savvy people have.
Mouse over to see the 64 bit results, on a different scale? Yuck.
Do the test 3 times and take the maximum? Yuck, how about the average?
Bar charts? With non-constant widths between factors? yuck.
I think probably 3 charts would have sufficed to show the whole thing. One showing total sum of time taken to run each of 3 suites: desktop, content, and benchmark, one color per suite.
One showing the effect of 32 vs 64 bits on processors capable of doing both.
One anova of DDR1 vs DDR2 (text) and of Hyperthreading vs. Not.
One plot of performance to price ratio for the best config of each processor.
And don't even get me started on the HINT benchmark (which is hard to get anymore I guess).
((lambda (x) (x x)) (lambda (x) (x x))) http://www.endpointcomputing.com a scientific approach to custom computing.
In our first look at 64-bit Linux, we used POV-Ray and noticed that not only was the AMD64 architecture much faster at this application, but that due to 64-bit verses 32-bit precision, it produced a truer image.
What does this mean in their review? Are they claiming that 64-bit POVRay uses 64-bit integers to represent color while 32-bit uses 32-bit or something? This sounds somewhat bogus. *Maybe* POVRay uses 64-bit integers internally for calculations until it outputs the 32-bit ARGB pixels is the only thing I can think of, but I doubt that is the case.
Notice in the benchmarks, for example the first one, both the Fx-53 and the 3800+ beat all the intel processors. Thus two AMD 2.4GHz beat a 3.0, 3.4, and a 3.6GHz intel processors. Thus, the slower processors beat the faster processors.