Intel Core 2 Duo: Memory Performance Part Deux
by Gary Key on August 14, 2006 4:15 AM EST- Posted in
- Motherboards
Application Performance
We decided to test some real world applications that typically stress the CPU, memory, and storage systems to see if the results from our synthetic memory tests carry over to the desktop. Based upon those results, our DDR2-533 memory settings should significantly outperform the DDR2-667 and DDR-333/400 configurations, while the DDR2-800 setting available on 965/975 should come in at the top of the performance charts.
Our tasks include three activities that are common on the desktop. Our first test was to measure the time it takes to shrink the entire Office Space DVD that was extracted with AnyDVD into a single 4.5GB DVD image utilizing Nero Recode 2. Our second test utilizes WinRAR 3.6 and measures the time it takes to compress our test folder that contains 444 files, 10 folders, and has 602MB of data.
Our third test consists of utilizing Exact Audio Copy as the front end for our version 3.98a3 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 optical drive). Our test CD is INXS Greatest Hits and contains 16 tracks totaling 606MB of songs. The results of our tests are presented in minutes/seconds with lower numbers being better.
The results between our DDR355 settings on the Intel chipset and DDR400 on the VIA chipset are extremely close. If the i865 board was able to operate at a true DDR400 setting we are sure the results would have had a greater spread. Both of the DDR400 and DDR355 settings are very competitive with our DDR2 results, with DDR333 trailing behind.
Unlike the synthetic results, the DDR2-667 results on the VIA PT880 Pro chipset outpace those of the DDR2-533 setting. The Biostar P965 board continues to outperform the other solutions although all results are close to each other. We see that our P965 DDR2-800 memory setting places first in all applications with the largest margin of victory being a 13 second advantage in the WinRAR test. Our DDR-355 results are impressive as they are competitive with the DDR2-533/667 configurations. The effects of the other platform components have basically negated the pure performance advantage of our DDR2 settings in the synthetic memory tests. While our DDR2-800 setting still offers the best overall performance, it would be difficult to tell the actual performance difference between it and our DDR-355 memory without benchmarks.
We decided to test some real world applications that typically stress the CPU, memory, and storage systems to see if the results from our synthetic memory tests carry over to the desktop. Based upon those results, our DDR2-533 memory settings should significantly outperform the DDR2-667 and DDR-333/400 configurations, while the DDR2-800 setting available on 965/975 should come in at the top of the performance charts.
Our tasks include three activities that are common on the desktop. Our first test was to measure the time it takes to shrink the entire Office Space DVD that was extracted with AnyDVD into a single 4.5GB DVD image utilizing Nero Recode 2. Our second test utilizes WinRAR 3.6 and measures the time it takes to compress our test folder that contains 444 files, 10 folders, and has 602MB of data.
Our third test consists of utilizing Exact Audio Copy as the front end for our version 3.98a3 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 optical drive). Our test CD is INXS Greatest Hits and contains 16 tracks totaling 606MB of songs. The results of our tests are presented in minutes/seconds with lower numbers being better.
 |
| Click to enlarge |
The results between our DDR355 settings on the Intel chipset and DDR400 on the VIA chipset are extremely close. If the i865 board was able to operate at a true DDR400 setting we are sure the results would have had a greater spread. Both of the DDR400 and DDR355 settings are very competitive with our DDR2 results, with DDR333 trailing behind.
 |
 |
 |
| Click to enlarge |
Unlike the synthetic results, the DDR2-667 results on the VIA PT880 Pro chipset outpace those of the DDR2-533 setting. The Biostar P965 board continues to outperform the other solutions although all results are close to each other. We see that our P965 DDR2-800 memory setting places first in all applications with the largest margin of victory being a 13 second advantage in the WinRAR test. Our DDR-355 results are impressive as they are competitive with the DDR2-533/667 configurations. The effects of the other platform components have basically negated the pure performance advantage of our DDR2 settings in the synthetic memory tests. While our DDR2-800 setting still offers the best overall performance, it would be difficult to tell the actual performance difference between it and our DDR-355 memory without benchmarks.
Facebook
Twitter
RSS
34 Comments
View All Comments
Questar - Monday, August 14, 2006 - link
Buy the cheapest memory you can find and spend the money you save somewhere else.deathwalker - Monday, August 14, 2006 - link
This does seem to validate from a cost vs. performance basis this motherboard..however I remain a tad sqeemish about making a platform jump from AMD to Intel using this board. Having said that though, if you are on a tight budget and you have to migrate parts I suppose giving this board a shot isn't a bad idea.Gary Key - Monday, August 14, 2006 - link
We will be reviewing some value/budget AMD AM2 combo motherboards in the future so the idea of incrementally upgrading to the newer platform from early S754/939 still holds true to a certain degree.
blppt - Monday, August 14, 2006 - link
On page 6..."Although AGP is basically dead and the most powerful card available is based on the 7800GS chipset, we can see that it is still a very competitive solution in the mid-range market as is low latency DDR memory with the right chipset."
What about the limited edition Gainward 7876 BLISS, which is supposedly actually based on the 7900GT? Thats considerably more powerful than a regular 7800GS.
http://www.gainward.net/products/product.php?produ...">BLISS
Last I checked, overlockers uk still had them in stock. Although at ~$445 american, you'd wonder if its worth it, or just upgrade to an X2 and PCI-E mobo instead.
Gary Key - Monday, August 14, 2006 - link
I have an inquiry into Gainward about the actual core used on this card. They still advertise it as a 7800GS based unit. Yes, it is very expensive when you can upgrade your CPU, motherboard, and memory for about the same price.blppt - Monday, August 14, 2006 - link
Yeah, they advertise it like that, but its a 24 pipe card clocked at 450/1250, which seems to be somewhere between a 7800GT and a 7900GT.poohbear - Monday, August 14, 2006 - link
"Who knew that AGP 8x and DDR would still be this competitive after a myriad of chipset, memory, CPU, and GPU enhancements over the last three years?"i thought it was pretty settled that the move from agp 8x was introduced for 1.) marketing reasons so ppl actually buy new chipsets we dont need and 2.) so nvidia could make some extra cash off their SLI gig. the bandwidth agp 8x provided was never saturated. great article nonetheless showing that value boards are still a nice option (i own the Asrock Dualsata2, great mobo btw after they fixed the 274htt cap).
on a sidenote i love the part "deux" in the title, we're so international @ anandtech aint we.;) or maybe u're just canadian, hafta include some french in everything.:p
bob661 - Monday, August 14, 2006 - link
I guess ATI doesn't count, huh? Also, would AGP provide the bandwidth necessary for SLI and Xfire setups? People keep making these sweeping "we don't need PCIe" statements without knowing or stating all of the factors involved.Kiijibari - Tuesday, August 15, 2006 - link
Have you red the last AGP 3.0 Specification ? If not look here at p. 115 / 5.2.3:http://members.datafast.net.au/dft0802/specs/agp30...">http://members.datafast.net.au/dft0802/specs/agp30...
In Short: Multiple video cards are possible with AGP 3.0 :)
cheers
Kiijibari
Gary Key - Monday, August 14, 2006 - link
I added my sarcastic comment notation at the end of the statement. ;-) While PCI Express is certainly a welcome technology and will be viable for a long time (in computer terms), it was introduced too early and abruptly in my opinion. Except for SLI/CrossFire type setups, there was no real "engineering" requirement for it on the desktop until recently. Yes, there is a French/Canadian influence in the household. :)