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
randytsuch - Monday, August 14, 2006 - link
HiI am thinking about upgrading my old P4 to a low end conroe, and after reading the article, was also thinking about the 775i65G.
Application will be mostly video rendering, and as a music server for my squeezebox, no gaming.
I am wondering how well the 775i65G overclocks, compared to something like a Gigabyte 865-DS3. I was thinking about the Gigabyte, but the Asrock would save a fair amount of money, will let me keep my AGP card and RAM, as well as being cheaper than the DS4.
Thanks,
Randy
kmmatney - Monday, August 14, 2006 - link
From what I understand, the low multiplier of the Conroe hurts its overclocking chances with this motherboard. People have gotten very good overclocks with Prescotts and Celeron D's with the ADrock board, but only becuase those processors have much higher multipliers. I don't think the lack of voltage adjustment hurts it as much as the fact that you just can't take the FSB very high.Paladin165 - Monday, August 14, 2006 - link
I just want to add that I bought an ASRock 775 Dual-VSTA with a celeron D 326 to hold me over until I get a conroe, and I'm running some old DDR266 with no problems. I'm using an old Geforce 4 ti 4400 AGP in it and it works with most games (not Oblivion though unfortunately). So if you still have some DDR 266 laying around you'd like to use go ahead and buy this board. It has a ton of memory settings including some kind of memory compatability mode so it should work with just about anything.However, even with the Celeron D 326 overclocked to 3.3GHZ, super pi 1M takes 59sec...roughly equal to my sempron 1.6ghz at stock speed. It is definitely a slow POS. Temps are still very low, going to try to get it up higher, 3.8 or 4.0ghz, but I'm not sure I can while keeping the memory at such low speed.
Another thing nice about this board which I haven't seen mentioned in the reviews is that it can run AGP and PCI-E at the same time, so you can have 4 moniters without needing a slow PCI graphics card.
Also, it seems that the AGP is only 4X. The settings in the bios only go up to 4X and Everest or something told me it was running my card at 4X, I doubt it makes any difference though.
cdalgard - Monday, August 14, 2006 - link
I am wondering how a 6800 Ultra would compare to the 7600GS on these platforms. How might the benchmarks look? Is the 6800 Ultra faster than the 7600GS to begin with?ChronoReverse - Monday, August 14, 2006 - link
The 7600GT would be a good match against the 6800U but the 7600GS is definitely behind the 6800U.xsilver - Monday, August 14, 2006 - link
but if i'm not mistaken, the 7600gs and gt only differ in clock speeds, so trying your luck with overclocking the gs may achieve stock gt resultsSixFour - Monday, August 14, 2006 - link
Cooling would stop first before the actual video card did.ChronoReverse - Monday, August 14, 2006 - link
Not to mention the much slower memory. Typically you get GDDR3 with GT while you get GDDR2 (clocked lower as well) with the GS.cdalgard - Monday, August 14, 2006 - link
How does the memory compare on the 6800 Ultra? There does not seem to be any good benchmarks comparing the 3 cards (6800U, 7600GS, 7600GT). Does anyone have a link to a table for specifications (core clock, memory clock, pipelines)? Thanks.Gary Key - Monday, August 14, 2006 - link
The memory on the 6800 Ultra runs at 1.10GHz compared to 400MHz on the 7600GS. We will have scores up for the PCI-E versus AGP on the 6800 Ultra and 7600GS cards shortly.