nForce 590 SLI Intel Edition: NVIDIA prepares an Intel 975X Killer
by Gary Key on June 27, 2006 6:15 AM EST- Posted in
- CPUs
Media Encoding Performance
Our first test is quite easy - we take our original Office Space DVD and use AnyDVD Ripper to copy the full DVD to the hard drive without compression, thus providing an almost exact duplicate of the DVD. We then fired up Nero Recode 2, selected our Office Space copy on the hard drive, and performed a shrink operation to allow the entire movie along with extras to fit on a single 4.5GB DVD disc. We left all options on their defaults except we checked off the advanced analysis option. The scores reported are the time for the full encoding process and are represented in minutes, with lower numbers indicating better performance.
The results are very interesting as we did not expect the NVIDIA system to perform this well and to do so is very surprising considering the early build sample and limited BIOS functionality. In fact, we ran the test several times and verified our settings before accepting the test results. It appeared to us that the storage subsystem on the NVIDIA board made a difference, though as you'll see in a moment this is not the case with one of our audio benchmarks.
Audio Encoding Performance
While the media encoding prowess of the NVIDIA nForce 590 SLI was superb in our limited testing, we wanted to see how it faired on the audio side. Our audio test suite consists of Exact Audio Copy v095.b4, LAME 3.98a3, LAME MT3.97a-MS Compiler, and Nero Digital Audio. Our first task was to figure out what test CD to utilize. We needed one that contained a significant number of tracks and had over 600MB of data in order to properly stress our platforms. After rummaging around the lab once again and coming up empty handed we reverted to our INXS Greatest Hits CD. This one time '80s glory masterpiece contains 16 tracks totaling 606MB of songs that can make the sturdiest of optical drives whimper.
Our first test consists of utilizing Exact Audio Copy as the front end for different versions of LAME. We set up EAC for variable bit rate encoding, burst mode for extraction, use external program for compression, and to start the external compressor upon extraction (EAC will read the next track while LAME is working on the previous track, thus removing a potential bottleneck with the drive).
Our two versions of LAME consist of the recently released 3.98a3 and LAME MT 3.97a, which is a multi-threaded version of the LAME MP3 encoder. LAME MT was originally designed as a demonstration to show the advantages of multi-threading on the Pentium 4 with Hyper-Threading enabled. Instead of running multiple parallel threads, LAME MT generates the encoder's psycho-acoustic analysis function in a separate thread from the rest of the encoder using a simple linear pipeline. The results are presented in minutes/seconds for the encoding process, with lower numbers being better.
As in the media encoding section, the more intensive CPU and storage system tests seem to favor the NVIDIA platform, although very slightly. We ran these tests several times with the same results all being within the same percentage of each other. When utilizing LAMEMT we see upwards of a 35% improvement in encoding times. This once again shows the advantages of program when it is written to take advantage of multiple-core processors.
Our first test is quite easy - we take our original Office Space DVD and use AnyDVD Ripper to copy the full DVD to the hard drive without compression, thus providing an almost exact duplicate of the DVD. We then fired up Nero Recode 2, selected our Office Space copy on the hard drive, and performed a shrink operation to allow the entire movie along with extras to fit on a single 4.5GB DVD disc. We left all options on their defaults except we checked off the advanced analysis option. The scores reported are the time for the full encoding process and are represented in minutes, with lower numbers indicating better performance.
The results are very interesting as we did not expect the NVIDIA system to perform this well and to do so is very surprising considering the early build sample and limited BIOS functionality. In fact, we ran the test several times and verified our settings before accepting the test results. It appeared to us that the storage subsystem on the NVIDIA board made a difference, though as you'll see in a moment this is not the case with one of our audio benchmarks.
Audio Encoding Performance
While the media encoding prowess of the NVIDIA nForce 590 SLI was superb in our limited testing, we wanted to see how it faired on the audio side. Our audio test suite consists of Exact Audio Copy v095.b4, LAME 3.98a3, LAME MT3.97a-MS Compiler, and Nero Digital Audio. Our first task was to figure out what test CD to utilize. We needed one that contained a significant number of tracks and had over 600MB of data in order to properly stress our platforms. After rummaging around the lab once again and coming up empty handed we reverted to our INXS Greatest Hits CD. This one time '80s glory masterpiece contains 16 tracks totaling 606MB of songs that can make the sturdiest of optical drives whimper.
Our first test consists of utilizing Exact Audio Copy as the front end for different versions of LAME. We set up EAC for variable bit rate encoding, burst mode for extraction, use external program for compression, and to start the external compressor upon extraction (EAC will read the next track while LAME is working on the previous track, thus removing a potential bottleneck with the drive).
Our two versions of LAME consist of the recently released 3.98a3 and LAME MT 3.97a, which is a multi-threaded version of the LAME MP3 encoder. LAME MT was originally designed as a demonstration to show the advantages of multi-threading on the Pentium 4 with Hyper-Threading enabled. Instead of running multiple parallel threads, LAME MT generates the encoder's psycho-acoustic analysis function in a separate thread from the rest of the encoder using a simple linear pipeline. The results are presented in minutes/seconds for the encoding process, with lower numbers being better.
As in the media encoding section, the more intensive CPU and storage system tests seem to favor the NVIDIA platform, although very slightly. We ran these tests several times with the same results all being within the same percentage of each other. When utilizing LAMEMT we see upwards of a 35% improvement in encoding times. This once again shows the advantages of program when it is written to take advantage of multiple-core processors.
Facebook
Twitter
RSS
37 Comments
View All Comments
rallyhard - Friday, June 30, 2006 - link
I, too, would like to see some RAID benchmarks for the motherboards when they're reviewed. Maybe even just reviewing the performance of a particular HD/RAID controller once, when it is tested on the first motherboard that you come across with that controller, would suffice.(I don't know how much HD/RAID performance varies from mobo to mobo with the same controller)
I certainly wouldn't have bought my Gigabyte 7n400 Pro2 socket A board if I had known the performance penalty of running RAID on the ITE 8212 chip as opposed to running a single drive on the nForce2 controller. The IDE raid functionality was the only reason I chose that board over the Abit NF7. The only way I found out that my horrible performance was truly and solely due to that 8212 chip is by doing a search on that chip and reading forums.
Incredibly, some manufacturers are still using that same chip for their IDE.
Anyway, I'm sure IDE performace is now a moot point for most, but yeah, RAID performance testing on future mobo (or controller) testing would, to me, be a useful addition to your excellent reviews.
Keep up the good work!
Crassus - Tuesday, June 27, 2006 - link
Perhaps someone can enlighten me on this: How much of an real-world impact in contemporary games does SLI 8/8 lanes compared to 16/16 lanes have? I remember reading an article about this issue back in the days when PCI-E was introduced, but I haven't really heared anything about it since. So, did anyone do a test on this?DigitalFreak - Tuesday, June 27, 2006 - link
I think X-Bit did a test not so long ago, and concluded there is still no advantage of 16x16 over 8x8.Avalon - Tuesday, June 27, 2006 - link
Sheesh, this is a pre-production board.CrystalBay - Tuesday, June 27, 2006 - link
Sheesh, look at the size NB fan.nullpointerus - Tuesday, June 27, 2006 - link
Just below the big features table on the basic features page, there's a sentence which should read:"Intel didn't officially want their 975X chipset to support 533FSB processors, but [a few] motherboard manufacturers disagreed on this point[, and] the end result is that 975X motherboards are able to run Celeron D chips."
At least I think that's how it's supposed to read.
nullpointerus - Tuesday, June 27, 2006 - link
Further down:"Considering the layout of expansion slots on ATX/BTX motherboards, [this] would be our ideal configuration, and the remaining expansion slots can be filled out with either X1/X2 PCI-E or regular PCI connectors."
...and also:
"There really doesn't see[m to be] much point in including X1 physical slots, particularly on enthusiast level hardware, and ATI at least has already recommended that motherboard manufacturers begin including more X16 physical connectors."
Gary Key - Tuesday, June 27, 2006 - link
Jarred and I got our wires crossed during the edit process this morning, it was easy to do at 5:30am after being up for about 26 hours with this board and another "new" chipset preview that should be finished shortly. ;-> However, no excuse on my part for not noticing the missing/incorrect text. I have corrected our mistakes and sincerely hope the changes are acceptable. Thank you for the comments and taking time to write. :)PedroDaGr8 - Tuesday, June 27, 2006 - link
I noticed on the compression/decompression page, page 7 I think. Both of the graphs are labeled File compresision - WinRAR 3.60b5 602MB Test Folder - Time In Minutes - Lower Is Better. Shouldn't one of them (the bottom one I guess) be labeled File Decompression, or atleast since you mention it first in the article shouldn't it be on top. That led to a quick bout of confusion for me, hey maybe it is just the painpills (I blew out my knee last week, tore my ACL and LCL (Lateral Colateral Ligament) with possible damage to my PCL and MCL as well. Nothing like playing cricket for the first time and injuring yourself.JarredWalton - Tuesday, June 27, 2006 - link
I added a word to the subtitle now. Basically, File Compression is the benchmark category, followed by the benchmark application. The subtitle is for extra information about the particular test. Hopefully that makes sense - I can't say my brain is entirely functional at this hour of the morning. :)