Investigations into Socket 939 Athlon 64 Overclocking
by Jarred Walton on October 3, 2005 4:35 PM EST- Posted in
- CPUs
Synthetic Gaming Performance
We've already looked at some Futuremark performance numbers, and most people are already familiar with 3DMark. You'll note that we list 3DMark as a Synthetic Gaming benchmark. This is not meant as a slam on the application, but the truth is that games and graphics are so complex these days that the only thing that any benchmark can really tell you is how well that benchmark runs. Doom 3 says nothing about how Quake 4 will actually run on the same system; we'd assume it will be similar, but we won't know until it comes out and we can test it. If a game can't even give you sure knowledge of how other licensees of the engine will run, how can it possibly give you an insight into how a different engine will run? That's 3DMark in a nutshell: some games will correlate very well with the performance results and scaling that we see in 3DMark, and others will be completely different. The only thing that the benchmark shows for sure is how well it runs.
The good news is that we also get CPUMarks that largely remove the graphics card from the picture. The CPUMarks render a couple of the same tests as the 3DMarks portions of the tests, but they compute the transform and lighting operations and some other areas on the CPU rather than the GPU. The CPU tests are also multi-threaded, but the Venice chips don't gain anything from that. (If we were to compare the results with a Pentium 4 HT, the P4 tends to perform very well relative to actual gaming results.) The CPU scores are more in line with the other results that we've already seen, gaining 46% and 42% in 03 and 05, respectively.
Being able to run the entire 3DMarks03/05 tests from start to finish without crashing is once again a good indication of stability. We went a step further and looped the tests for eight hours or more on the top overclocks, without trouble... at least, without incident on everything 2700 MHz and below. The 2800 MHz overclock would crash after 30 to 60 minutes of looping, usually during the CPU portion of the test.
We've already looked at some Futuremark performance numbers, and most people are already familiar with 3DMark. You'll note that we list 3DMark as a Synthetic Gaming benchmark. This is not meant as a slam on the application, but the truth is that games and graphics are so complex these days that the only thing that any benchmark can really tell you is how well that benchmark runs. Doom 3 says nothing about how Quake 4 will actually run on the same system; we'd assume it will be similar, but we won't know until it comes out and we can test it. If a game can't even give you sure knowledge of how other licensees of the engine will run, how can it possibly give you an insight into how a different engine will run? That's 3DMark in a nutshell: some games will correlate very well with the performance results and scaling that we see in 3DMark, and others will be completely different. The only thing that the benchmark shows for sure is how well it runs.
The good news is that we also get CPUMarks that largely remove the graphics card from the picture. The CPUMarks render a couple of the same tests as the 3DMarks portions of the tests, but they compute the transform and lighting operations and some other areas on the CPU rather than the GPU. The CPU tests are also multi-threaded, but the Venice chips don't gain anything from that. (If we were to compare the results with a Pentium 4 HT, the P4 tends to perform very well relative to actual gaming results.) The CPU scores are more in line with the other results that we've already seen, gaining 46% and 42% in 03 and 05, respectively.
Being able to run the entire 3DMarks03/05 tests from start to finish without crashing is once again a good indication of stability. We went a step further and looped the tests for eight hours or more on the top overclocks, without trouble... at least, without incident on everything 2700 MHz and below. The 2800 MHz overclock would crash after 30 to 60 minutes of looping, usually during the CPU portion of the test.
Facebook
Twitter
RSS
101 Comments
View All Comments
Furen - Monday, October 3, 2005 - link
Actually, Winchesters are pretty bad overclockers. They were even worse overclockers than newcastles and clawhammers back when they came out, which is why the FX-55 was clawhammer based rather than Winchester based.ksherman - Monday, October 3, 2005 - link
hmmm... Im running a 3000+ winchester, and ive got it to 2.56GHz... thats quite an over clock if you ask me... you would probably be the first person I have EVER say that the winchesters do not OC well...ksherman - Monday, October 3, 2005 - link
is there any performance hit when using memory dividers? I have heard that there is, as the memory and CPU are running on different frequencies... and is it better to keep you RAM @ DDR400, and use dividers or run the RAM @ DDR480?ShadowVlican - Monday, October 3, 2005 - link
so i'm guessing basically, A64's prefer low latency than high frequencyJarredWalton - Monday, October 3, 2005 - link
Pretty much. If you think about it, 10x240 with DDR333 setting is actually identical to 12x200 with DDR400 setting. The RAM is at DDR400 in either case. The difference between a 960 MHz HT speed and 1000 MHz HT speed is... well, if you measure more than a 1% difference, I'd be surprised. :)Wesley Fink - Monday, October 3, 2005 - link
Memory dividers DO make a difference in performance on the Intel platform, where the memory controller is in the chipset and latency is relatively high. Basically, the architecture derives memory ratios with added overhead which can definitely impact performance, and 1:1 memory ratio is best.However, the memory controller on the Athlon 64 is on the processor and memory frequencies are derived from HT on the A64, without adding overhead. That means, theoretically, memory dividers should have NO impact at all on Athlon 64 memory performance - everything else being equal (which it rarely is).
ksherman - Monday, October 3, 2005 - link
well i decided to go for the RAM dividers... upto 2.56GHz, memory using the 5/6 divider (DRAM/FSB) RAM @ DDR466 @ 2-2-2-7 3.3V! was at 2.13Ghz, since I didnt want to use memory dividers. so a nice jump in speed! now I just got to find do some benchies! BTW- I am using a DFI Ultra-D and it is the greatest board I have ever owned! havent done the SLI mod yet, but I dont need toksherman - Monday, October 3, 2005 - link
hmm... guess if i read the WHOLE article... ;-)good article though! I highly reccomend the 'Value VX' RAM aka OCZ Value RAM, since when you put enough voltage into it (3.2V in my case) it overclocks like a charm! Im getting DDR 480 with tight timings (not EXATLY sure, but something 2-2-3-8 1T)
Garyclaus16 - Monday, October 3, 2005 - link
Well,...the article states that there have been performance hits with higher dividers. Best way to find out with yourself is to do your own benches! No two systems will overclock exactly the same, so the best way to figure something out is to try it on your own..Aquila76 - Monday, October 3, 2005 - link
If your RAM will run stably at DDR480, leave it. I had to drop mine down becase there's some issue with the mobo higher than 250MHz.