PROJECT TITLE :

Power Variability in Contemporary DRAMs

ABSTRACT :

Technology scaling has led to vital variability in chip performance and power consumption. During this work, we have a tendency to measured and analyzed the power variability in dynamic random access memories (DRAMs). We have a tendency to tested twenty two double date rate third generation (DDR3) dual inline memory modules (DIMMs), and found that power usage in DRAMs depends on both operation sort (write, scan, and idle) also information, with write operations consuming a lot of than reads, and 1s in the information usually costing more power than 0s. Temperature had very little effect (1–3percent) across the $-hbox50~^circ$C to fifty$~^circ$C vary. Variations were up to twelve.29% and sixteen.40percent for idle power among one model and for various models from the same vendor, respectively. In the scope of all tested one gigabyte (GB) modules, deviations were up to 21.eighty four% in write power. Our ongoing work addresses memory management strategies to leverage such power variations.