10 years of research on Power Management (now

Transcript:10 years of research on Power Management (now:
10 years of research on Power Management (now called green computing) Rami Melhem Daniel Mosse Bruce Childers Introduction Power management in real-time systems Power management in multi-core processors Performance-Resilience-Power Tradeoff Management of memory power Phase Change Memory Power management techniques Two common techniques: Throttling Turn off (or change mode of) unused components (Need to predict usage patterns to avoid time and energy overhead of on/off or mode switching) Frequency and voltage scaling Scale down core’s speed (frequency and voltage) Designing power efficient components is orthogonal to power management Frequency/voltage scaling Gracefully reduce performance Dynamic power Pd = C f 3 + Pind Static power: independent of f. power Static power C f 3 Pind time When frequency is halved: Time is doubled C f 3 is divided by 8 Energy caused by C f 3 is divided by 4 Energy caused by Pind is doubled Idle time Minimize total energy consumption - static energy decreases with speed - dynamic energy increases with speed Minimize the energy-delay product Takes performance into consideration Minimize the maximum temperature Maximize performance given a power budget Minimize energy given a deadline Minimize energy given reliability constraints Different goals of power management Pind / f DVS in real-time systems CPU speed time deadline Smax Smin Worst case execution Utilize slack to slow down future tasks (Proportional, Greedy, aggressive,…) Implementation of Power Management Points Can be implemented as periodic OS interrupst Difficulty: OS does not know how much execution is remaining Compiler can insert code to provide hints to the OS Example of compiler/OS collaboration PMH Compiler records WCET based on the longest remaining path At a power management hint min average max At a power management point OS uses knowledge about current load to set up the speed PMH PMH Compiler/OS collaboration DVS for multiple cores Manage energy by determining: The speed for the serial section The number of cores used in the parallel section The speed in the parallel section One core To derive a simple analytical model, assume Amdahl’s law: - p % of computation can be perfectly parallelized. p s Streaming applications are prevalent Audio, video, real-time tasks, cognitive applications Constrains: Inter-arrival time (T) End-to-end delay (D) Power aware mapping to CMPs Determine speeds Account for communication Exclude faulty cores T D Mapping streaming applications to CMPs Mapping a linear task graph onto a linear pipeline If the # of stages = #