Investigations into Socket 939 Athlon 64 Overclocking
by Jarred Walton on October 3, 2005 4:35 PM EST- Posted in
- CPUs
RAM Latency
We talked about memory latency a bit before, and we estimated the total latency. Using CPU-Z and the included Latency.exe utility, we can get an actual real value for memory latency - or at least, more real than our estimate. There are different ways of measuring memory latency, but we simply took the highest reported value from the table that was generated. For every system, that value was in the bottom-right corner of the table, indicating a data set of 32MB and a stride of 512. While the values may or may not be entirely accurate, they should at least be consistently measured across all the tested configurations. Here are the results, in CPU cycles as well as nanoseconds. Remember that at higher CPU speeds, each cycle is faster, so pay more attention to the nanoseconds graph.
While the value RAM is clearly slower than the expensive RAM, the big question is: how much performance do you actually lose by opting for more economical RAM? This is one of the areas that we are interested in testing for this article, and we'll comment on the results throughout the benchmarks.
RAM Possibilities
One area of the BIOS that's missing (for now) is support for additional RAM ratios. The reality is that the RAM speed is derived from the CPU clock with a divider. Ideally, we'd like to see a BIOS that gives direct access to the CPU divider rather than hiding it behind approximate memory speeds. That would allow for the selection of a larger range of options, but we're not sure if that's something that AMD controls in the CPU or if the BIOS programmers can do this. Here's a list of the standard RAM Settings, CPU multipliers and the resultant memory dividers that were available in the Infinity BIOS.
We have a LanParty UT nF3 250Gb that includes support for many in-between options from DDR200 through DDR500. Some of the interesting inclusions are DDR240, DDR280, DDR300, DDR360, DDR440, and DDR500. (CPU-Z actually failed to report the divider on a couple of those settings, but the resultant RAM speed was still read properly.) While additional memory dividers on the high end won't really help tweakers looking to get the most from the TCCD, BH5, or CH5 RAM, they can be particularly useful when using value RAM. All you need to do is select the appropriate divider to get your RAM under DDR400 - assuming standard value RAM. That way, you wouldn't take as much of a performance hit by running something like 10x250 (2.5 GHz). You could select a 13X divider rather than the standard 15X divider.
Additional ratios can even be useful for tuning performance RAM. For example, OCZ VX would not run stable above DDR500 (10x250), and we had to use 2-3-3-8-1T timings even then. (The 3.2V limit of the motherboard was at least partially to blame.) Running at 10x270, we had to drop to DDR333 (CPU/12), which resulted in the RAM running at DDR450 rather than the DDR540 result that would have been required for the normal CPU/10 ratio. However, if we could have selected a CPU/11 ratio, we could have run the RAM at DDR490 and gained a bit more performance. The additional ratios aren't required, but they would be nice to have.
If the last two paragraphs didn't make sense, then you can guess why we don't get additional access to RAM dividers. Experienced users might know how to make use of the settings, but many people would simply get confused; a "Catch-22".
We talked about memory latency a bit before, and we estimated the total latency. Using CPU-Z and the included Latency.exe utility, we can get an actual real value for memory latency - or at least, more real than our estimate. There are different ways of measuring memory latency, but we simply took the highest reported value from the table that was generated. For every system, that value was in the bottom-right corner of the table, indicating a data set of 32MB and a stride of 512. While the values may or may not be entirely accurate, they should at least be consistently measured across all the tested configurations. Here are the results, in CPU cycles as well as nanoseconds. Remember that at higher CPU speeds, each cycle is faster, so pay more attention to the nanoseconds graph.
While the value RAM is clearly slower than the expensive RAM, the big question is: how much performance do you actually lose by opting for more economical RAM? This is one of the areas that we are interested in testing for this article, and we'll comment on the results throughout the benchmarks.
RAM Possibilities
One area of the BIOS that's missing (for now) is support for additional RAM ratios. The reality is that the RAM speed is derived from the CPU clock with a divider. Ideally, we'd like to see a BIOS that gives direct access to the CPU divider rather than hiding it behind approximate memory speeds. That would allow for the selection of a larger range of options, but we're not sure if that's something that AMD controls in the CPU or if the BIOS programmers can do this. Here's a list of the standard RAM Settings, CPU multipliers and the resultant memory dividers that were available in the Infinity BIOS.
| Standard AMD Memory Ratios | |||
| RAM Setting | CPU Multiplier | RAM Divider | True RAM Speed |
| DDR200 | 9X | CPU/18 | DDR200 |
| DDR266 | 9X | CPU/14 | DDR257 |
| DDR333 | 9X | CPU/11 | DDR327 |
| DDR400 | 9X | CPU/9 | DDR400 |
| DDR200 | 10X | CPU/20 | DDR200 |
| DDR266 | 10X | CPU/15 | DDR267 |
| DDR333 | 10X | CPU/12 | DDR333 |
| DDR400 | 10X | CPU/10 | DDR400 |
| DDR200 | 11X | CPU/22 | DDR200 |
| DDR266 | 11X | CPU/17 | DDR259 |
| DDR333 | 11X | CPU/14 | DDR314 |
| DDR400 | 11X | CPU/11 | DDR400 |
| DDR200 | 12X | CPU/24 | DDR200 |
| DDR266 | 12X | CPU/18 | DDR267 |
| DDR333 | 12X | CPU/15 | DDR320 |
| DDR400 | 12X | CPU/12 | DDR400 |
We have a LanParty UT nF3 250Gb that includes support for many in-between options from DDR200 through DDR500. Some of the interesting inclusions are DDR240, DDR280, DDR300, DDR360, DDR440, and DDR500. (CPU-Z actually failed to report the divider on a couple of those settings, but the resultant RAM speed was still read properly.) While additional memory dividers on the high end won't really help tweakers looking to get the most from the TCCD, BH5, or CH5 RAM, they can be particularly useful when using value RAM. All you need to do is select the appropriate divider to get your RAM under DDR400 - assuming standard value RAM. That way, you wouldn't take as much of a performance hit by running something like 10x250 (2.5 GHz). You could select a 13X divider rather than the standard 15X divider.
Additional ratios can even be useful for tuning performance RAM. For example, OCZ VX would not run stable above DDR500 (10x250), and we had to use 2-3-3-8-1T timings even then. (The 3.2V limit of the motherboard was at least partially to blame.) Running at 10x270, we had to drop to DDR333 (CPU/12), which resulted in the RAM running at DDR450 rather than the DDR540 result that would have been required for the normal CPU/10 ratio. However, if we could have selected a CPU/11 ratio, we could have run the RAM at DDR490 and gained a bit more performance. The additional ratios aren't required, but they would be nice to have.
If the last two paragraphs didn't make sense, then you can guess why we don't get additional access to RAM dividers. Experienced users might know how to make use of the settings, but many people would simply get confused; a "Catch-22".
Facebook
Twitter
RSS
101 Comments
View All Comments
photoguy99 - Monday, October 3, 2005 - link
Dual Core was not mentioned -Anyone know how difficult it is to get a stable dual-core to 2.8Ghz with water-cooling?
Easy, difficult, impossible?
JarredWalton - Monday, October 3, 2005 - link
Part two/three will cover other chips. I wanted to get the base overclocking article out, and I will be looking at both Sempron and X2 overclocking in the near future. 2.80 GHz wasn't stable on my Venice, though - not entirely - and it won't even post on my X2 3800+. Your mileage may vary, naturally, but I'm getting about 100MHz less from my X2 vs. Venice. (I'd take the second core over the extra 100MHz any day, however!)MemberSince97 - Monday, October 3, 2005 - link
Thanks for the detailed explanation and charts. Thanks for the hard work.Nunyas - Monday, October 3, 2005 - link
I'm a bit supprised that you guys forgot to mention the overclocking abilities of the venerable Athlon Thunderbirds with the AXHA and AXIA steppings. I had a 1GHz T-Bird with AXHA stepping that allowed me to OC it to 1.533 GHz (53%), and it's documented all over the place with people achieving even better results with the same model CPU. At the time that the 1GHz became a great OC'er it was around $99 and gave you the performance of the then high end Athlons and P4's. Thus, by far a better OC'er than the Celeron 300A.OvErHeAtInG - Monday, October 3, 2005 - link
Meh, my AXIA 1.2 would do 1.4 or 1.33 sorta stable, with really good cooling, tweaked voltage, and so forth. When I sold it to my friend I had to put it back to stock speeds just so it would stay stable in the hands of someone who doesn't monitor her CPU temperature all the time ;) My "B" Northwood, IMO, is a more stable OC'er. Having said that, I guess others were more lucky than me... but yeah no 300A killer IMO.kmmatney - Monday, October 3, 2005 - link
The celeron 300A set the standard for overclocking. It was less the $100 (oem version) and performed better than any stock cpu you could buy, including those costing 3 times more. It really sparked the whole overclocking phenonema. Another good one was the Celeron II 500, which could easily overclock to 800 MHz. I had both of those.I had a cyrix 486DX-66 overclocked to 80 Mhz, and an AMD 586 DX4-133 overclocked to 150 MHz, but the celeron 300A was simply unbelievable at the time.
JarredWalton - Monday, October 3, 2005 - link
I didn't bother to try and include everything, especially where it was only specific steppings of a CPU. (I.e. not all T-birds did a 53% OC, right?) Anyway, I was basically an Intel user up until the Athlon XP era. I went from socket 478 with a Celeron 1.1A (OC'ed to 1.47 GHz) to the XP-M 2500+. The "history lesson" was just an introduction anyway, setting the stage. :)Aquila76 - Monday, October 3, 2005 - link
I've been waiting for a reputable site to post OC testing like this. I feel pretty good with the OC I get out of my rig (3500+ Winch @ 2.7GHz, Mem on divider) - thanks to the forums here - and it's close to what you guys acheived. I may swap to that DFI board instead as I know the A8N-SLI is holding me back.Garyclaus16 - Monday, October 3, 2005 - link
Job well done. I like how the benchmarks showed overclocking for anything 1024x768+ means nothing for games. I was aware the increase was small with high resolution..but an almost null increase in performance kind of makes me want to leave my 3200+ winchester the way it is. Do the venice cores OC better than winchesters?...JarredWalton - Monday, October 3, 2005 - link
Venice and Winchester should be about the same, though you might get an extra 100 MHz out of Venice (?). You can get higher performance at resolutions above 1024x768, but you'll need a much faster graphics card than the X800 Pro (or a 6800GT) for most of that. It depends on the game being tested as well.