Memory Tests
The memory tests are designed to highlight the general performance of the memory subsystem on a given system. In this case, with the AA8 the review focus, its memory performance relative to the Intel D925XCV desktop board is what's most interesting. We use a trio of tests to analyse said performance, Pifast is up first. It's our own custom test to 10M decimal places.Pifast
There's no discernable difference between the two Alderwood-powered boards in the Pifast test. Let's see if the Sciencemark bandwidth and latency analysis shows a similar pattern.
Sciencemark 2.0 - Bandwidth
Sciencemark 2.0 measures peak CPU to memory controller bandwidth, the bandwidth available to the CPU for memory intensive tasks. It doesn't take into account any excess bandwidth available on the memory controller, that may or may not be usable by other peripherals.
The AA8 is around 200MB/sec down on the D925XCV at the same memory latencies, using the same processor. A chipset timing difference is the most likely culprit. Access latency is the next biggest determinant of overall memory subsystem performance.
Sciencemark 2.0 - Access Latency
The AA8 allows the CPU to access main system memory slightly faster than the D925XCV. With the difference in bandwidth favouring the Intel board, it seems they both combine to affect the equal Pifast score, balancing it out.