Investigations into Athlon X2 Overclocking
by Jarred Walton on December 21, 2005 12:00 PM EST- Posted in
- CPUs
Encoding Performance
For our encoding performance tests, we use AutoGK 1.96 with both the DivX and Xvid codecs. (A newer version of AutoGK is now available, but performance and scores didn't change noticeably, and so, we will continue using the older version.) We encode chapter 9 from The Sum of All Fears without audio to 75% quality. This results in a file size about 1/3 as large as the original (not counting the audio size). As a more common encoding task, we also encode a TV commercial from 30 MB down to 5 MB, including audio encoding. This results in three encoding passes: the compression test, a first pass, and the final pass. We take the total number of frames in the video (900) and divide it by the time taken, reporting the resulting frames per second. In all AutoGK benchmarks, higher scores will be better.
The performance difference between the slowest and fastest setup is around 35% for every encoding task, scaling linearly with processor speed. AutoGK runs a lot more of the computations within the CPU and doesn't depend much on user input, and it also benefits from multiple processor cores. Compared to the Venice chip, the second core increases DivX performance by about 50% and Xvid performance by about 30%. Comparing the different RAM types, the largest gap is about 4%; so while there is a difference, it's not huge. As we said, clock speed is king for encoding.
For our encoding performance tests, we use AutoGK 1.96 with both the DivX and Xvid codecs. (A newer version of AutoGK is now available, but performance and scores didn't change noticeably, and so, we will continue using the older version.) We encode chapter 9 from The Sum of All Fears without audio to 75% quality. This results in a file size about 1/3 as large as the original (not counting the audio size). As a more common encoding task, we also encode a TV commercial from 30 MB down to 5 MB, including audio encoding. This results in three encoding passes: the compression test, a first pass, and the final pass. We take the total number of frames in the video (900) and divide it by the time taken, reporting the resulting frames per second. In all AutoGK benchmarks, higher scores will be better.
The performance difference between the slowest and fastest setup is around 35% for every encoding task, scaling linearly with processor speed. AutoGK runs a lot more of the computations within the CPU and doesn't depend much on user input, and it also benefits from multiple processor cores. Compared to the Venice chip, the second core increases DivX performance by about 50% and Xvid performance by about 30%. Comparing the different RAM types, the largest gap is about 4%; so while there is a difference, it's not huge. As we said, clock speed is king for encoding.
Facebook
Twitter
RSS
46 Comments
View All Comments
Puddleglum - Wednesday, December 21, 2005 - link
Neermind.. read this in the closing thoughts:"There is one other point to mention on the memory: overclocking with four 512MB DIMMs was almost a complete failure on the setup that we used. Other motherboards, or perhaps a BIOS update for this motherboard, might improve the results, but for now we would recommend caution with such attempts. If you want to run 2GB of RAM, two 1GB DIMMs would be a much better choice."
Good info.
bobsmith1492 - Wednesday, December 21, 2005 - link
Actually, switching supply efficiencies can change dramatically with load; I wouldn't count on the draw at the wall as a good indicator of system load change. The efficiency may change from, say 70% at half-load to 85% at 3/4 load, which, on a 400 watt supply, would show up as: 285.7 watts draw (lower power) and 352.9 watts draw (high power). Now, the system is drawing 50% more power, while the meter is only showing 23.5% more power draw.Something to keep in mind anyway as I don't know exactly what the difference in efficiency for that particular supply is....
Cerb - Wednesday, December 21, 2005 - link
It would be nice to know. However, if it's like the 470w one, it is 'close enough' at all loads.http://www.silentpcreview.com/article173-page4.htm...">http://www.silentpcreview.com/article173-page4.htm...
bobsmith1492 - Wednesday, December 21, 2005 - link
Yeah, from 2-400W it's pretty close. Nevermind me then. :)WRXSTI - Wednesday, December 21, 2005 - link
I cannot wait to get a 64 X2 chip! Maybe by next year is better...Futurebobis - Thursday, December 1, 2022 - link
Yo, sup past people