The design and use of simplePower: a cycle-accurate energy estimation tool

By W. Ye, Narayanan Vijaykrishnan, Mahmut Taylan Kandemir, M. J. Irwin. Proceedings - Design Automation Conference, 2000

516 citations recorded by the source corpus.

In this paper, we presen t the design and use of a comprehensiv e framework, SimplePower, for ev aluating the effect of high-level algorithmic, architectural, and compilation trade-offs on energy. An execution-driven, cycle-accurate RT lev el energy estimation tool that uses transition sensitive energy models forms the cornerstone of this framework. SimplePower also pro vides the energy consumed in the memory system and on-chip buses using analytical energy models. We presen t the use of SimplePower to evaluate the impact of a new selective gated pipeline register optimization, a high-level data transformation and a pow er-conscious post compilation optimization (register relabeling) on the datapath, memory and on-chip bus energy, respectively. We find that these three optimizations reduce the energy by 18-36% in the datapath, 62% in the memory system and 12% in the instruction cache data bus, respectively.

Subfields: Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/83e60a73b74fe567151eb6d80290477e272da318

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Hardware and Architecture

Citations in the corpus

Orion: a power-performance simulator for interconnection networks (2002, background): “Power models and simulators for processors and memories have been proposed [3, 4, 25], enabling a rich body of research into power-efficient mechanisms [2, 18].”
The design, implementation, and evaluation of a compiler algorithm for CPU energy reduction (2003, methodology): “Many of the previous results were based on simulation, using simulators such as Wattch [7] and SimplePower [52], and evaluated the proposed algorithms using the power model associated with the particular simulator.”
Estimation of energy consumption in machine learning (2019, methodology): “In order to estimate the power/energy consumption of an application, SimplePower simulates the execution of the set of instructions, using the power models associated to each functional unit that have been activated by the set of instructions.”
Temperature and supply Voltage aware performance and power modeling at microarchitecture level (2005, background): “On the other hand, existing power simulators [8]–[10] calculate leakage power by assuming a fixed ratio between dynamic and leakage power.”
PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications (2010, methodology): “Most existing power profiling research is focused on a single computer component such as processor [6], [36], disk [37], memory [36], and networking interface [35].”