Title | ||
---|---|---|
An accurate and flexible early memory system power evaluation approach using a microcomponent method. |
Abstract | ||
---|---|---|
As energy efficiency has become a primary concern, system designers have greater need for a flexible and highly accurate power estimation method for evaluating different architecture options. Since memory is an increasingly dominant power consumer, we reexamine existing memory power models and propose a highly efficient microcomponent-based approach with data-aware refinement for accurate system-level power estimations. The key contribution of our approach is that the proposed microcomponent method allows designers to use flexible architecture compositions. Our approach identifies the common microcomponents used by internal memory commands and accurately pre-calibrates the power consumption pattern of each microcomponent. We decompose target design architectures into these microcomponents to easily derive accurate power estimates. To achieve very high accuracy, we consider the data variation effect by leveraging the fact that memory circuit is mainly doing data passing and hence a simple interpolation technique can further boost accuracy. Our experiments show that the proposed approach produces accurate results of less than 2% error rate in average for system power analysis. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2968456.2968472 | CODES+ISSS |
Keywords | Field | DocType |
flexible early memory system power evaluation approach,microcomponent method,energy efficiency,power estimation method,memory power models,data-aware refinement,system-level power estimations,flexible architecture compositions,internal memory commands,power consumption pattern,memory circuit,data passing,system power analysis | Internal memory,Power analysis,Computer science,Efficient energy use,Word error rate,Interpolation,Real-time computing,Power demand,Memory management,Power consumption | Conference |
ISBN | Citations | PageRank |
978-1-5090-3590-8 | 0 | 0.34 |
References | Authors | |
16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chi-Kang Chen | 1 | 4 | 2.45 |
Hsin-I. Wu | 2 | 2 | 3.92 |
Chi-Ting Hsiao | 3 | 0 | 0.34 |
Tsay, Ren-Song | 4 | 368 | 72.19 |