Testing:
The test system listed in the "Configuration" section on page 2 was used for the execution of all benchmarks. It makes for a solid test bed for DDR3, as it allows for DDR3 to be compared with DDR2 on the same platform. The ASUS P5KC motherboard allows for both memory formats to be used (not at the same time), and provides some decent features in the BIOS for optimizing the performance of both. For this review, a
2GB PC2-6400 kit from OCZ Technology and a
2GB PC3-11000 kit from Kingston will be tested head-to-head with the
Crucial Ballistix 2GB PC3-12800 DDR3.
Testing will consist of three benchmarks used to gauge the performance of seven different memory configurations. The benchmarks executed include tests from these three packages:
» Everest Ultimate Edition 2006
» Sisoftware Sandra Lite 2008.1.12.34
» Performance Test v6.1
The seven memory configurations include the OCZ Technology DDR2 kit running at its rated speed, the Kingston PC3-11000 running at roughly its rated speed and its maximum stable overclock, and with the Crucial PC3-12800 running at 1200, 1280, 1500, and 1600MHz. At 1200, 1280, and 1600 the processor was set to 3.2GHz (400MHz FSB x 8), while at 1500MHz it was scaled back to 3.0GHz (375MHz FSB x 8).
These may seem like odd selections for the Crucial memory to be tested at, but there was a reason for each. 1200MHz is the highest that I could achieve 6-7-7-20 timings, 1500MHz is the highest that I could achieve 7-7-7-20 timings, 1600MHz is the rated speed of the kit, and the mark of 1280MHz (7-7-7-20) proved to be a real performance sweet spot.
The seven configurations summarized:
» OCZ Technology System Elite DDR2 at 800MHz, 4-4-4-13, 2.0V
» Kingston PC3-11000 DDR3 at 1376MHz, 7-7-7-20, 1.7V
» Kingston PC3-11000 DDR3 at 1400MHz, 7-7-7-23, 1.8V
» Crucial PC3-12800 DDR3 at 1200MHz, 6-7-7-20, 1.5V
» Crucial PC3-12800 DDR3 at 1280MHz, 7-7-7-20, 1.7V
» Crucial PC3-12800 DDR3 at 1500MHz, 7-7-7-20, 1.8V
» Crucial PC3-12800 DDR3 at 1600MHz, 8-8-8-25, 1.8V
Everest Ultimate Edition 2006:
The memory benchmarks in Everest Ultimate Edition can provide four sets of results: memory read speed (in MB/s), memory write speed (in MB/s), memory copy speed (in MB/s), and memory latency (in ns). Higher values are better for memory read, write, and copy speeds, while lower values are desirable for latency.
This memory makes light work of these tests! Notice how much higher it scores than the Kingston DDR3, even when set to run at the same timings and about 100MHz slower (1376MHz Kingston vs 1280MHz Crucial. I mentioned earlier how 1280MHz proved to be a real performance sweet spot, and this is the first example of that. I couldn't believe the results, so I duplicated these tests a few times... the combination of memory speed, timings, and frontside bus speed all worked together to provide some great results.
