Self-optimization of Performance-per-Watt for Interleaved Memory Systems
نویسندگان
چکیده
With the increased complexity of platforms coupled with data centers’ servers sprawl, power consumption is reaching unsustainable limits. Memory is an important target for platform-level energy efficiency, where most power management techniques use multiple power state DRAM devices to transition them to low-power states when they are “sufficiently” idle. However, fully-interleaved memory in highperformance servers presents a research challenge to the memory power management problem. Due to data striping across all memory modules, memory accesses are distributed in a manner that considerably reduces the idleness of memory modules to warrant transitions to low-power states. In this paper we introduce a novel technique for dynamic memory interleaving that is adaptive to incoming workload in a manner that reduces memory energy consumption while maintaining the performance at an acceptable level. We use optimization theory to formulate and solve the powerperformance management problem. We use dynamic cache line migration techniques to increase the idleness of memory modules by consolidating the application’s working-set on a minimal set of ranks. Our technique yields energy saving of about 48.8 % (26.7 kJ) compared to traditional techniques measured at 4.5%. It delivers the maximum performance-per-watt during all phases of the application execution with a maximum performance-per-watt improvement of 88.48%.
منابع مشابه
Performance Enhancement of Continuous-Phase Modulation Based OFDM Systems Using Chaotic Interleaving
In this paper, we propose a chaotic interleaving scheme for continuous-phase modulation based orthogonal frequency-division multiplexing (CPM-OFDM) systems. The idea of chaotic maps randomization (CMR) is exploited in this scheme. CMR generates permuted sequences from the sequences to be transmitted with lower correlation among their samples, and hence a better bit error rate (BER) performance ...
متن کاملThe Optimization of Energy Supply Systems by Sequential Streamflow Routing Method and Invasive Weed Optimization Algorithm; Case Study: Karun II Hydroelectric Power Plant
Among the major sources of energy supply systems, hydroelectric power plants are more common. Energy supply during peak hours and less environmental issues are some of the most important advantages of hydroelectric power plants. In this study, designing parameters to supply maximum amount of energy was determined by using the simulation-optimization perspective and combination of IWO-WEAP model...
متن کاملAchieving 10Gbps Line-rate Key-value Stores with FPGAs
Distributed in-memory key-value stores such as memcached have become a critical middleware application within current web infrastructure. However, typical x86based systems yield limited performance scalability and high power consumption as their architecture with its optimization for single thread performance is not wellmatched towards the memory-intensive and parallel nature of this applicatio...
متن کاملDisk I/O Performance-per-Watt Analysis for Cloud Computing
Assessing disk I/O performance and power consumption associated with a given cloud workload is important especially for workloads that are bounded by disk I/O. Disk performance becomes a bottleneck for achieving higher performance and lower power consumption especially when memory size is not enough to process large blocks of data. This will lead to a negative impact on the Quality-of-Service (...
متن کامل