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
bespoke - Tuesday, June 27, 2006 - link
Once again, the southbridge chip and fan are right underneath the top video card clot. A large cooling solution on the video card will completely cover the sb chip - possibily preventing the video card from seating correctly and certainly not helping with airflow.Please move the SB chip or get rid of the fan! Arrrgh!
Gary Key - Wednesday, June 28, 2006 - link
Due to the required two chip solution for dual x16 GPU operation, there is not another area on the board to place the chipset and still retain the required trace layouts. Due to the heat generated by the MCP, it requires active cooling or a large passive heatsink (as MSI did on their 570 board). These issues will be solved late this year when NVIDIA goes to a single chip solution for their dual x16 boards. In the meantime, we are not happy either. ;-)
Anemone - Thursday, June 29, 2006 - link
Probably should use DDR2 800 on the Asus and 667 on the 590 as the highest supported on each and recompare. I know that feels unfair but I'm saying that from a "highest supported" basis. Enthusiasts are likely to go beyond that, but you'll be giving the full oc tests a go in the next round.Initially however think 533 on both skewed things.
Per Hansson - Tuesday, June 27, 2006 - link
"The reference board features an excellent voltage regulator power design along with Rubycon and Sanyo capacitors that yielded superb stability and overclocking results even with our early BIOS and board design."Actually those capacitors with a T vent are Panasonic FL, in the 12v input for the VRM and also for the 5v or 12v input for the memory regulators...
Still very excellent capacitors; if it only where a requirement to also use them on the revised boards by the mainboard manufacturers... Wishful thinking I guess but with continued reporting of what components are used like this by you Anandtech eventually they will listen... (I hope atleast) Again thanks and great work! Hoping you will help to ease the confusion on what chipset to go with that Conroe...
Griswold - Tuesday, June 27, 2006 - link
For some reason, pictures of the mobo wont show in Opera (v9) for me. The benchmark charts are there though. What gives? Anyone else experience this?Never had any kind of problem with Opera and AT before. :/
Per Hansson - Tuesday, June 27, 2006 - link
Works fine in Opera 9 here, I think your issue might be that your browser is not set to enable refferer logging (under advanced>network)Griswold - Tuesday, June 27, 2006 - link
That was it. Not sure why that one was off, however, it works now. Thanks a bunch!Gary Key - Tuesday, June 27, 2006 - link
I will load up Opera 9 and test it shortly.Myrandex - Tuesday, June 27, 2006 - link
That eSata port looks a lot like the ieee1394B port, any relation? I heard there was apush once for eSata to use Firewire cables, but I thought only one manufacturer was trying for that (maybe Highpoint?).eskimoe - Tuesday, June 27, 2006 - link
First off, thanks for one of the very few test on the new nforce5 intel edition!For a long time now I have built my pcs with amd cpus, next month will be the first time since the first p3s that Ill build another intel pc!
So at the moment, I am not really sure which chipset to use,
of course it seems natural to use an intel chipset for an intel cpu..
but the nforce chipsets have been very nice (at least for amd), and theres more competition than in the intel area...
The only thing that intel has and nvidia doesnt, is the intel matrix storage
(btw, a single nvidia card shouldnt have any probs running on an intel board/have disadvantages over a single ati card, should it?),
which sounds very nice in my opinion.. therefore, I'd love to see
some comparison in the RAID compartement between nforce5 and intel 975/965,
especially since I cant find any information how RAID5 performs on
nforce5 and intel chipsets.. until now, all onboard variants were
very slow/used alot of cpu (at least when writing)
So, I'd love to see some tests comparing raid0 performance/cpu utilization
between the chipsets, as well as raid5 tests...
and perhaps someone knows of some tests on matrix raid 5?
The possibility to have 3x200gb drives, using for example 500gb as raid0,
and 100gb as raid5 seems very promising, as long as the raid5 calculations
are somewhat supported by chipset hardware, not only the cpu!
Thanks alot