Abstract | ||
---|---|---|
High-performance DRAMs are providing increasing memory access bandwidth to processors, which is leading to high power consumption and operating temperature in DRAM chips. In this paper, we propose a customized low-power technique for high-performance DRAM systems to improve DRAM page hit rate by buffering write operations that may incur page misses. This approach reduces DRAM system power consumption and temperature without any performance penalty. We combine the throughput-aware page-hit-aware write buffer (TAP) with low-power-state-based techniques for further power and temperature reduction, namely, TAP-low. Our experiments show that a system with TAP-low could reduce the total DRAM power consumption by up to 68.6% (19.9% on average). The steady-state temperature can be reduced by as much as 7.84??C and 2.55??C on average across eight representative workloads. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/TVLSI.2009.2014842 | IEEE Transactions on Very Large Scale Integration Systems |
Keywords | Field | DocType |
power management,power consumption,adaptive temperature management,integrated circuit modelling,dram access,dram temperature management technique,high performance dram system,dram temperature,dram performance,temperature,dram chip,low-power-state-based techniques,low-power electronics,dram power reduction,throughput-aware page-hit-aware write buffer,dram chips,high-performance drams,write operations,dram system power consumption,dram,adaptive dram temperature,steady-state temperature,buffer circuits,dram page hit rate,power,dram system,adaptive power management,memory management,low power electronics,chip,energy management,steady state | Dynamic random-access memory,Dram,Power management,Computer science,Electronic engineering,Real-time computing,Write buffer,Non-volatile memory,Energy consumption,CAS latency,Low-power electronics,Embedded system | Conference |
Volume | Issue | ISSN |
18 | 4 | 1063-8210 |
Citations | PageRank | References |
6 | 0.48 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Song Liu | 1 | 216 | 8.86 |
Seda Öǧrenci Memik | 2 | 488 | 42.57 |
Yu Zhang | 3 | 220 | 8.72 |
Gokhan Memik | 4 | 1694 | 111.88 |