Benchmarks II
|
Next we'll turn our attention to MP3 encoding. We're benchmarking by encoding a 638MB custom WAV file into 192kb/s MP3 using the LAME 3.91 encoder and Razor-Lame 1.15 front-end.
Although the graph seeks to show otherwise, the difference between using differing memory speeds is largely negligible. We've demonstrated in the past that WAV - MP3 encoding is almost entirely an FPU affair, this result simply substantiates that claim. If you want fast encoding, get a beefier processor. Incidentally, I ran this same benchmark at 3000 MHz / 176FSB, and came out with a time of 181-seconds. Pure CPU grunt is the key. Another media-related task that many of us indulge in is DVD - DivX encoding, I certainly have been doing a great deal of late. Once again, I'm changing my benchmark suite to something I feel better reflects true performance. I'm now using a quality-driven approach. 2-pass encoding via VirtualDub. Three Kings is the DVD of choice, resized to 720x304, precise bilinear and black borders cropped. YUV2 spacing is used and the bit rate is set to 1700 kbps. I encode a 15-minute section and calculate the average fps from there. DivX 4.12 is still my CODEC of choice.
The average frames-per-second are much lower than when we use XMPEG, but I feel the better quality warrants it. Note that this is the average for just 1-pass. The 2nd-pass usually takes the same time. Also note the decent increase in performance when going from 133MHz to 178MHz memory. DivX encoding just loves bandwidth. The BD7II-R can provide some of what it needs. Again, I tried this at 3000MHz and came out with an average FPS of 30.9. Onto the gaming benchmarks now. |
