Pagani, SantiagoChen, Jian-Jia
Springer International Publishing (Cham, Switzerland , 2018) (eng) English9783319774794Unknown1st ed. MULTIPROCESSORS; UnknownThis book focuses on two of the most relevant problems related to power management on multicore and manycore systems. Specifically, one part of the book focuses on maximizing/optimizing computational performance under power or thermal constraints, while another part focuses on minimizing energy consumption under performance (or real-time) constraints. Provides a comprehensive introduction to energy, power, and temperature management, highlighting the different optimization goals, particularly computational performance, power and energy consumption, and temperature; Highlights the differences and similarities between the two key challenges of performance optimization under power or thermal constraints and energy minimization under performance constraints; Discusses in detail several means that can be used to optimize performance or energy while satisfying the desired constraints, including core heterogeneity, task-to-core assignment/mapping, dynamic power management (DPM), and dynamic voltage and frequency scaling (DVFS).
Physical dimension
1 online resource (l, 250 p.)Unknownill. (in color.)
Summary / review / table of contents
Introduction --
Background and Related Work --
System Model --
Experimental Framework --
Thermal Safe Power (TSP) --
Transient and Peak Temperature Computation based on Matrix Exponentials (MatEx) --
Selective Boosting for Multicore Systems (seBoost) --
Energy and Peak Power Efficiency Analysis for Simple Approximation Schemes --
Energy-Efficient Task-to-core Assignment for Homogeneous Clustered Manycores --
Energy-Efficient Task-to-core Assignment for Heterogeneous Clustered Manycores --
Conclusions.