Memory Benchmarks
Everest Ultimate is the most useful tool for any and all benchmarkers or overclockers. With the ability to pick up most voltage, temperature, and fan sensors on almost every motherboard available, Everest provides the ability to customize the outputs in a number of forms on your desktop. In addition to this, the memory benchmarking utility provides a useful tool of measuring the changes to your memory sub-system.
For both the stock and overclocked configurations, the memory sub-system was running in unganged mode, which means that the two 64-bit memory controllers in the Phenom II were operating independently of each other and thus two memory requests could be processed simultaneously, which provides faster performance in multi-threaded apps. The CPU/NB frequency was running at the default 2000Mhz for the stock configuration, and 2200Mhz for the overclocked setup. With a 47% memory clock difference (DDR2-800 vs DDR2-1179) between the stock and overclocked configurations, we are seeing a 10% to 30% performance improvement in bandwidth numbers. This is respectable, and that additional bandwidth make its presence felt in bandwidth starved apps like WinRAR. Surprisingly, our overclocked memory bandwidth numbers are actually higher than those we achieved with the ASUS M4A78T-E running at DDR3-1600. Quite a good showing for the dirt cheap Gigabyte MA770-UD3.
Due to the aforementioned similarity in the memory sub-system settings, the memory latency is effectively identical across the board. However, there was an unusual sweet spot at 3.2Ghz (16 x 200). There is no rhyme or reason for this anomaly, and it is only 1% lower than the other results, but we were able to repeat the results on numerous occasions.
Although last updated almost 3 years ago, and despite its rudimentary interface, ScienceMark v2.0 remains a favorite for accurately calculating bandwidth on even the newest chipsets.
Effectively mirroring the Everest results, ScienceMark demonstrates a 30% improvement in overall bandwidth between the stock and overclocked configurations. The OC'ed results solidly surpass the best numbers we achieved on the DDR3-equipped ASUS 790GX board. Clearly, the lower-end AMD 770 chipset and DDR2 memory are no slouch when it comes to fully utilizing the Phenom II's integrated memory controller.
Memory Benchmarks
Lavalys Everest Ultimate v5.00
Everest Ultimate is the most useful tool for any and all benchmarkers or overclockers. With the ability to pick up most voltage, temperature, and fan sensors on almost every motherboard available, Everest provides the ability to customize the outputs in a number of forms on your desktop. In addition to this, the memory benchmarking utility provides a useful tool of measuring the changes to your memory sub-system.
For both the stock and overclocked configurations, the memory sub-system was running in unganged mode, which means that the two 64-bit memory controllers in the Phenom II were operating independently of each other and thus two memory requests could be processed simultaneously, which provides faster performance in multi-threaded apps. The CPU/NB frequency was running at the default 2000Mhz for the stock configuration, and 2200Mhz for the overclocked setup. With a 47% memory clock difference (DDR2-800 vs DDR2-1179) between the stock and overclocked configurations, we are seeing a 10% to 30% performance improvement in bandwidth numbers. This is respectable, and that additional bandwidth make its presence felt in bandwidth starved apps like WinRAR. Surprisingly, our overclocked memory bandwidth numbers are actually higher than those we achieved with the ASUS M4A78T-E running at DDR3-1600. Quite a good showing for the dirt cheap Gigabyte MA770-UD3.
Due to the aforementioned similarity in the memory sub-system settings, the memory latency is effectively identical across the board. However, there was an unusual sweet spot at 3.2Ghz (16 x 200). There is no rhyme or reason for this anomaly, and it is only 1% lower than the other results, but we were able to repeat the results on numerous occasions.
ScienceMark v2.0
Although last updated almost 3 years ago, and despite its rudimentary interface, ScienceMark v2.0 remains a favorite for accurately calculating bandwidth on even the newest chipsets.
Effectively mirroring the Everest results, ScienceMark demonstrates a 30% improvement in overall bandwidth between the stock and overclocked configurations. The OC'ed results solidly surpass the best numbers we achieved on the DDR3-equipped ASUS 790GX board. Clearly, the lower-end AMD 770 chipset and DDR2 memory are no slouch when it comes to fully utilizing the Phenom II's integrated memory controller.
Last edited by a moderator: