Dual Core Linux Performance: Two Penguins are Better than One
by Kristopher Kubicki on July 1, 2005 5:55 AM EST- Posted in
- Linux
The Test
Testing our dual core Linux system will be done in the same manner as Anand's tests from several weeks ago. There are various test applications that are not exactly drop in compatible between Linux and Windows, but in many instances there are some extremely practical similarities in which it would make more sense to run a Linux application over the Windows alternative. For example, Apple's Shake will only run on Mac OSX or Linux - leaving Windows out in the cold.
Today's benchmarking will be a little different than Linux benchmarks we have done in the past. While we are still keeping strict usage controls and assuring that our benchmarks are 100% replicable, we are also looking more at the quality of performance rather than just the raw numbers. A fluid experience on a Linux machine that is slightly slower than a sporadic Windows alternative would be a design win for Linux - at least in our opinion. Naturally, since we have some very nice processors from Intel and AMD, we can do a slightly more traditional comparison of each of those processors against each other in the various scenarios. Using the applications list Anand set forward in his original benchmarks, we attempted to compile a list of commercial and FOSS Linux software to use for Linux.
Windows Application |
Linux Application |
Adobe® Photoshop® 7.0.1 |
The Gimp 2.3.1 |
No suggestions yet |
Apple Shake 3.5c |
Macromedia® Dreamweaver MX 6.1 |
Mozilla Composer 1.7.8 |
Microsoft® Windows MediaTM |
MPlayer 1.0pre7 |
Encoder 9 Version 9.00.00.2980 (Video) |
MEncoder 1.0pre7, CCE |
Encoder 9 Version 9.00.00.2980 (Audio) |
lame 3.96.1 |
iTunes |
XMMS 1.2.10 |
NewTek's LightWave® 3D 7.5b |
ScreamerNet 7.5b |
WinZip 8.1 |
Gzip 1.2.4 |
VC++ Compilation |
GCC 3.3.4 |
Pro/E Wildfire |
Pro/E Wildfire |
Outlook 2003 |
Mozilla Thunderbird 1.7.8 |
Microsoft Office/Word/Excel 2003 |
OpenOffice 1.1.4 |
Firefox 1.0.2 |
FireFox 1.0.4 |
Nero Burning ROM 6 |
NeroLINUX |
DVD Shrink |
DVD Backup 0.1.1, dvd::rip |
BitTorrent |
BitTorrent |
Macromedia® Director MX 9.0 |
No suggestions yet |
SteinbergTM WaveLabTM 4.0f |
No suggestions yet |
Norton AntiVirus 2004 |
No Suggestions yet |
Microsoft AntiSpyware Beta |
No Suggestions yet |
Some of the suggestions we have made above are more the subject of personal preference than absolutes. There are some loose alternatives for Shake on Windows, but there are also some loose alternatives for WaveLab and Director on Linux as well. The idea is that we want to construct a few multi-threaded benchmarks that emulate the usage of real Linux power users. Below are the seven benchmarks we have outlined our six benchmarks to use in this analysis and why we picked them. We won't be using all of the software from the list above, but the intention is that we will for future benchmarks.
- Multitasking Scenario 1: DVD Transcoding - We will rip a DVD while using moderate usage from web browsing, music and newsgroups. This is very comparable to Anand's original Windows benchmark found here.
- Multitasking Scenario 2: File Compression - We will compress some text files for backup while running a few base applications at the same time. This is also extremely comparable to Anand's original Windows benchmark found here.
- Multitasking Scenario 3: Web Browsing - Here we attempt to utilize an extremely large load of web browsers while also doing some typical background applications. This is also very similar to Anand's original benchmark.
- Multitasking Scenario 4: DVD Burning - Using the same benchmark as the DVD Ripping, we will now burn a DVD instead. Since the DVD burn is typically limited by the burn speed of the hardware, we will compress a file as our benchmark.
- Gaming Multitasking Scenario 1: Heavy Downloading - We will use several BitTorrent clients at once while benchmarking Doom 3.
- Gaming Multitasking Scenario 2: Compiling and Gaming - We will time the compilation of the Linux Kernel and GCC during a Neverwinter Nights session.
We tried to select benchmarks that were a combination of maximum load benchmarks with benchmarks that we can evaluate on quality. For example, compression and Doom3 are easy to quantify in time or FPS since they will utilize as much of the system as possible. Secondary operations like web browsing and playing music will induce load on the system and we will hopefully see really positive results on dual core configurations if the Linux scheduler is doing its job.
Facebook
Twitter
RSS
69 Comments
View All Comments
xtknight - Friday, July 1, 2005 - link
Why was FireFox 1.0.2 used on Win32 and 1.0.4 used on Linux? Just wondered.KristopherKubicki - Friday, July 1, 2005 - link
Something is wrong with the graph on the Compilation test (the -j3 for the dual core Athlon was in the Pentium 660 slot). We only ran -j3 on the dual core chips. I redid the graph and it should be rendering correctly now.Kristopher
suryad - Friday, July 1, 2005 - link
#34 great question. I was about to ask that but you beat me to it.smn198 - Friday, July 1, 2005 - link
#22 Give him a break - The removal of the 2nd xbox vs ps article meant that this had to come out a day early.Kocur - Friday, July 1, 2005 - link
Well, Kris, do you have any theory of why single core Athlons seem to perform better with regard to single core P4s than X4200+ with regard to dual P4s?
In my opinion there are two possibilities.
1. HT slows both 640 and 660.
2. X4200+ does not stretch its wings.
In my opinion you should have adressed this problem in the article as we have learnt to expect the opposite.
Kocur.
n yusef - Friday, July 1, 2005 - link
I tink tis article is fair. The Pentium D 820 is good for the price, if you don't already have a S939 mobo and RAM. It's not as ceap as you would think, becuase if the extra ~$100 for more expensive RAM, motherboard, and aftermarket HSF, but it's still cheaper for a whole system. For someone like myself who already has a S939 mobo, and DDR1 RAM, the X2s are a better bargain. The make -j3 tag should have been on all of te CPUs (it even makes non-HT single core CPUs faster), especially the 4200+.When you get a chance, please get a 4400+, or lower your 4800+s (Anand's actually) multi to x11 so we can see how much cache affects a dual-core CPU (each core is sharing the same memory bandwidth that only one had to itself before, so even an A64 might be bandwidth limited).
TheMatt - Friday, July 1, 2005 - link
One comment I always have with these tests is why do you never see pbzip2? On *any* dual, quad, etc. machine I use, I always pester the admin to install pbzip2: http://compression.ca/pbzip2/ .I was hoping I'd see it here to see if it gives the same speed-up with dual-core as it does with my SMP machine. I'd suggest to anyone here to try it out, it's a great program.
fishbits - Friday, July 1, 2005 - link
"If you can't admit that the D820 is a good performer at its price, then I don't know what's going on with you, but nowhere did he slam AMD along the way."The D820 is really good for the price, especially if ram/mobo weren't issues. But saying you "pay through the nose" for the AMD chip and not the D840 at virtually the same price was pretty stunning.
"In our opinion, the Pentium D 820 is really an underdog in this roundup"
What the heck does that mean? The 820 looks like a really good multi-tasking performer for the dollar. How does that make it an "underdog?"
We've gotta give the guys a little slack on various errors, but in "Final Thoughts?" Should the concluding paragraphs where judgement and recommendations are handed out be read two or three times before releasing them? Or maybe by at least a second set of eyes?
JGunther - Friday, July 1, 2005 - link
#29Gaming bechmarks are the ONLY benchmarks in this article where the Pentium D doesn't occupy the top spot. Find me another review site that shows this to be the case.
The D820 is definitely a good performer for its price, I'd never say otherwise. But there's no denying that Kris and his articles are slanted. There are no slams, but little statements like this:
"At $558 you pay through the nose for the additional performance of the Athlon 64 X2 4200+."
Attempt to portray AMD as the culprit, but the fact is, you pay through the nose for that additional performance whether you're looking at the 4200+ or the D840 (the latter of which is is actually the more expensive of the two).
Anand once said that visitors to his site, he found, were about 50/50 Intel or AMD users. Though statistically, it could go either way, there is no doubt in my mind that Kris' primary computer at home runs an Intel chip. It's written all over his articles.
Tegeril - Friday, July 1, 2005 - link
I don't see his analysis showing the Pentium CPUs "on top" at all. He specifically states that the AMD offering beats the pants off of Intel as usual in gaming, that the memory costs on the Intel boards are higher, and that the D820 and D840 don't suck quite as much as people want it to. He simply says that at the price point of $252, the D820 becomes a tempting option.To sacrifice minimal overall performance and save $290 - memory costs is probably a very good suggestion and is warranted by the analysis. It's pretty impartial from here.
If you can't admit that the D820 is a good performer at its price, then I don't know what's going on with you, but nowhere did he slam AMD along the way.