Memory performance
Memory subsystem performance doesn't always track with real-world applications, but it's a good place to start with integrated graphics chipsets that cannibalize a portion of system memory and therefore bandwidth.

The Athlon X2's integrated memory controller works wonders here, providing heaps more bandwidth and much lower access latencies than Intel's G35 Express.

Memory controllers don't always handle four DIMMs gracefully, so we popped an additional two memory modules into each system for another round of tests.

With a full complement of memory modules installed, the performance picture really doesn't change much. The 780G platform is way out ahead again, and it actually offers better memory performance with four DIMMs installed than with two. By contrast, our G35 boards offers a little less bandwidth and higher access latencies when we fill its DIMM slots.

The following latency graphs are a little indulgent, so I won't be offended if you skip them. They show access latencies across multiple block and step sizes, painting a fuller picture of memory controller performance with each chipset. I've arranged the graphs in order of highest latency to lowest. Yellow represents L1 cache, light orange is L2, and dark orange is main memory.

Our G35 system's Pentium E2180 processor may have a bigger L2 cache than the 780G's Athlon X2 4850e, but as we move to block sizes that spill over into main memory, the AMD platform's significantly lower access latencies come into play in dramatic fashion.