Related Articles

Benchmark Setup

Our benchmark system (and competitors) consisted of the following:

• Intel Pentium 4 560 and 840 processors (LGA775)
• 2*512 MB Corsair XMS2 PC8000UL @ 5-4-4-9 1000 MHz
• 2*512 MB OCZ PC2 5400 4-4-4-12 modules
• Asus P5WD2 Premium
• Asus P5ND2 SLI
• Western Digital WD1200JD SATA hard drive
• nVidia 6600GT with 63.93 drivers
• BFG 7800GTX with 81.98 drivers

We did bump the memory voltage to 2.3V in an attempt to overclock the memory for some tests.

We used Sandra and RightMark for our memory benchmarks - both give useful results in measuring memory performance.

Benchmarks

We used four different programs to test the influence of the memory bandwidth on different programs.

• WinRAR
• Sandra 2004
• RightMark
• Doom3

Overclocking

In order to get a good idea of the performance differences between stock and tweaked memory and processor settings, we are putting our test rig through quite a few tests!

Unlike previous memory reviews, we could not simply increase the memory speed - the processor we were using had a minimum multiplier of 14, and would not run with 100% stability over a 1160MHz FSB that results in a 4.06GHz processor clock unless we dropped the memory speed to DDR2-967. We did sucessfully do some testing with the memory running at 1080MHz, however experimentation revealed that running the processor with a higher speed FSB had a far greater impact on performance than increasing the memory speed above a certain point, as the FSB proved to be the biggest bottleneck to increasing memory performance.

Please note: in order to make our test results easy to read, we labeled the bars on the chart with the processor and memory settings - for example:

560 800 18x200
PC5400 800 4-4-4-7

Means 560 cpu, 800MHz CPU FSB, 18x200 processor setting,
PC5400 memory, 800MHz memory bus, 4-4-4-7 memory timing.

All memory timings at 2T.