Dual Core Linux Performance: Two Penguins are Better than One
by Kristopher Kubicki on July 1, 2005 5:55 AM EST- Posted in
- Linux
Multitasking Scenario 4: DVD Burning
Thanks to NeroLINUX, we can now run the first benchmark we did in reverse. We will be paying particular attention to the buffer for NeroLINUX. If the burn continually empties the buffer, then the system is playing catch-up to the burner. We will count the number of times the buffer dies and graph this separately. We used a NEC 3520A burner and a 4.5GB ISO image for the burn.
- Open FireFox 1.0.4 and load all 5 web pages.
- Open XMMS and start playing a Nine Inch Nails CD ripped to Ogg
- Open Thunderbird for news
- Login to our news server and start downloading headers for our subscribed news groups
- Begin an ISO burn with NeroLINUX and start timing
There seems to be a very linear correlation between the number of buffer dumps and the speed at which the discs burned. We really only saw the buffer even come in danger of decreasing at the beginning of the burn and when Thunderbird took a little too long to process something coming in from the news server.
Even though the processors we used in this analysis are more than capable, the additional tasks of FireFox and Thunderbird proved just a tad too much for the chips to handle at all once. This benchmark is a great illustration of where dual core (or dual socket) goes so wonderfully well on the desktop. The additional overhead to run XMMS, FireFox and the other applications is not very substantial, but when FireFox decides to chew up resources while the only CPU is managing the write buffer on a DVD burn, the results can be quite dramatic.
Facebook
Twitter
RSS
69 Comments
View All Comments
JGunther - Friday, July 1, 2005 - link
They're going for $660 on ZipZoomFly, which is sold out again, but they were in stock yesterday.All I'm saying is, look around. Other review sites have come to the same conclusions: the AMD dual cores are better than their Intel couterpoints. Better deals? No. But this is not a "budget Linux dual core system" article, so let's leave the "best bang for your buck" talk for another time. I'd only ask that it be a performance-oriented review, like it claims to be, instead of him choosing to compare CPUs at only the price-point where Intel comes out on top. Cutting one CPU out because it's just $60 too much seems a bit arbitrary and biased to me.
I tend not to get worked up about the whole AMD vs. Intel stuff-- my laptop at home is runnning a Pentium 4 in it. But when I clicked on this article, and saw who wrote it, I knew EXACTLY which CPU was going to be at the top of the charts. That should never happen. That's all.
Tegeril - Friday, July 1, 2005 - link
I think the compiling graphic is simply in error. Why would the 660 have a-j3 score better than the D 820. That doesn't make much sense. I'd bet the X2 is supposed to occupy that space and the 660 and 640 got shifted down by accident.mikellpp - Friday, July 1, 2005 - link
Now why do you suppose there are no -j3 compile times for any of the Athlons in the last compile test? The author sooo wants intel to look good, he just can't bear to see AMD's better times. Are we supposed to be stupid readers?Tegeril - Friday, July 1, 2005 - link
Ugh "None of his [dual core] CPUs tested..." is what I meant.Calin - Friday, July 1, 2005 - link
Why the Athlon64 X2 has no -j3 compilation benchmarks?Also, in short, one can compare the Intel D840 and the AMD X2 as they cost about the same. And not everyone will keep their mainboards, as not everyone upgrades every six months. I think most buyers will buy both a new mainboard and a new processor. I would have thought of buying myself an Athlon64, but I would like an Socket939, and I think their price (compared to the 754) are highway robbery.
I'll wait with the upgrade
Tegeril - Friday, July 1, 2005 - link
JGunther.None of his CPUs tested topped $600. Newegg has the 4400+ for $719. That is not in the same price range. He drew no unfavorable conclusions, finding AMD fantastic in gaming and showed its dual core option that competes with the D820 and D840 also performs well in multitasking environments.
Your high performance quote is meaningless when you look on the "the hardware" page and read: "These processors are a bit on the high end"
Stop creating controversy where there is none.
JGunther - Friday, July 1, 2005 - link
#19, If he wanted to do some equal price comparisons, there's also the 840 EE vs. the 4800+. Those should have been tested as well-- the article's talking about "high performance Linux machines", so the most prudent thing to do would be to show which CPU actually gives the best performance and let the reader know the respective prices, so that they can come to their own judgements.If Kris wants to nail home the point that doller for dollar, the Intel CPUs are the better deal by omitting benchmarks of competing, though higher priced, CPUs, let him do it on his own time, on a site that doesn't have the same integrity and non-bias standards as Anandtech should.
There is only one dual core AMD chip being compared to two dual core Intel chips, despite the fact that the 4400+ is only a marginal increase in price. I suspect this is to keep his benchmark graphs more Intel-heavy near the top, but if it's because he simply doesn't have a 4400+ (they're in stock at Newegg and ZipZoomFly), as #20 suggests, then he should have waited to post the article until he had a more balanced roundup of CPUs.
Yeah I know my words are harsh, and I'm sorry. But this isn't the first time Kris has done this. It's irresponsible 'journalism' and reflects poorly on the site, and users *should* speak out against it.
TheJet - Friday, July 1, 2005 - link
One thing to note, I usually run -j3 on my _single_ processor Celeron 466 *NIX workstation and get significantly better performance than a standard make. So really, performance numbers should have been shown for -j3 across the board, not just for the dual core parts.Furen - Friday, July 1, 2005 - link
He has mentioned (repeatedly) that he doesnt have an X2 4400 and that Anand is the one who has the X2 4800, so he had to make do with what he had. I, personally, like the article (though I hate pentium Ds ^^), just wish there was more data on some of the tests, heh.IKeelU - Friday, July 1, 2005 - link
#17, He's comparing simiarily-priced CPUs. Would it be more fair to compare a $1000 AMD CPU to intel's $558?