Benchmarks I
The ABIT nForce2 is being run at the standard 2GHz/133 FSB of the XP2400 in both dual-DDR (synchronouos DDR266) mode and asynchronous single-DDR333 modes. Further, to see just how much effect a faster FSB has, it's also being run at 2GHz/166FSB with dual-channel DDR running synchronously at DDR333. The comparative EPoX KT400 is being run at both 133FSB and 166FSB too, albeit with no dual-DDR support.
Pifast, our first practical test, simply calculates the constant Pi to the desired number of decimal places. I've chosen 10 million using the fastest method possible. Memory bandwidth has historically played a major part in this benchmark.
Here we see that running a single module of RAM asynchronously at DDR333 when the CPU's FSB is at 133 is counterproductive. The latency involved in crossing FSB and memory clocks is evident. It's actually slower than VIA's effort. However, running the stock CPU with dual-channel DDR266 brings us under the 80s barrier. The nForce2 really shows its strength when we raise the unlocked processor to 166FSB (12x multiplier). Running with synchronous DDR333, it takes almost 5 seconds out of the VIA KT400 being run at the same settings.
Next we'll turn our attention to MP3 encoding. We're benchmarking by encoding a 600MB+ custom WAV file (U2's Pop album, incidentally) into 192kb/s MP3 using the LAME 3.92 encoder and Razor-Lame 1.15 front-end.
No real differences here apart from the fact that the comparison P4 2.53GHz CPU is taken to the cleaners by the XP2400. When running with a 133FSB the XP2400 natively resorts to running at 2013MHz. When running at 166FSB, the clock generator lowers the speed to 1996MHz. That helps to explain the slight lead at 133FSB. We're largely CPU-bound here.
