Processor Frequency Setting for Energy Minimization of Streaming Multimedia Application by A. Acquaviva, L. Benini, and B. Riccò, in Proc. 9th Internation.

Slides:



Advertisements
Similar presentations
1 “Scheduling with Dynamic Voltage/Speed Adjustment Using Slack Reclamation In Multi-processor Real-Time Systems” Dakai Zhu, Rami Melhem, and Bruce Childers.
Advertisements

Lecture Objectives: 1)List the 5 classical components of a computer and show their relationships graphically. 2)Define instruction set architecture. 3)Define.
VADA Lab.SungKyunKwan Univ. 1 L3: Lower Power Design Overview (2) 성균관대학교 조 준 동 교수
System Design Tricks for Low-Power Video Processing Jonah Probell, Director of Multimedia Solutions, ARC International.
E0262 MIS - Multimedia Playback Systems Prof Pallapa. Venkataram, Electrical Communication Engineering, Indian Institute of Science, Bangalore – ,
CS Spring 2012 CS 414 – Multimedia Systems Design Lecture 14 – Introduction to Multimedia Resource Management Klara Nahrstedt Spring 2012.
Multimedia Systems As Presented by: Craig Tomastik.
Chapter 20: Multimedia Systems Silberschatz, Galvin and Gagne ©2005 Operating System Concepts Chapter 20: Multimedia Systems What is Multimedia.
Silberschatz, Galvin and Gagne ©2009 Operating System Concepts – 8 th Edition Chapter 20: Multimedia Systems.
Design of a Power-Efficient Interleaved CIC Architecture for Software Defined Radio Receivers By J.Luis Tecpanecatl-Xihuitl, Ruth Aguilar-Ponce, Ashok.
Motivation Application driven -- VoD, Information on Demand (WWW), education, telemedicine, videoconference, videophone Storage capacity Large capacity.
Oscilloscope Watch Teardown. Agenda History and General overview Hardware design: – Block diagram and general overview – Choice of the microcontroller.
ENERGY-PROPORTIONAL IMAGE SENSING FOR Robert LiKamWa Bodhi Priyantha Matthai Philipose Victor Bahl Lin Zhong CONTINUOUS MOBILE VISION
Project Proposal Presented by Michael Kazecki. Outline Background –Algorithms Goals Ideas Proposal –Introduction –Motivation –Implementation.
L27:Lower Power Algorithm for Multimedia Systems 성균관대학교 조 준 동
A Case for Custom Silicon in Enabling Low-Cost Information Technology for Developing Regions Z. Foo, David Devecsery, T. Schmid, N. Clark, R. Frank, M.
CS-3013 & CS-502, Summer 2006 Multimedia topics (continued)1 Multimedia Topics (continued) CS-3013 & CS-502 Operating Systems.
Aleksandra Tešanović Low Power/Energy Scheduling for Real-Time Systems Aleksandra Tešanović Real-Time Systems Laboratory Department of Computer and Information.
1 Soft Timers: Efficient Microsecond Software Timer Support For Network Processing Mohit Aron and Peter Druschel Rice University Presented By Jonathan.
SWE 423: Multimedia Systems Chapter 7: Data Compression (1)
Performance and Energy Bounds for Multimedia Applications on Dual-processor Power-aware SoC Platforms Weng-Fai WONG 黄荣辉 Dept. of Computer Science National.
Digital Video 1.
Optimization Of Power Consumption For An ARM7- BASED Multimedia Handheld Device Hoseok Chang; Wonchul Lee; Wonyong Sung Circuits and Systems, ISCAS.
Porta-AMP Portable Audio MP3 Player By : Kevin Mlazgar Dan Leder Edmund Fung John Koob.
Strictly private and confidential
Jamie Unger-Fink John David Eriksen. Outline Intro to LCDs Power Issues Energy Model New Reduction Techniques Results Conclusion.
BLDC MOTOR SPEED CONTROL USING EMBEDDED PROCESSOR
1 EE 587 SoC Design & Test Partha Pande School of EECS Washington State University
CS 423 – Operating Systems Design Lecture 22 – Power Management Klara Nahrstedt and Raoul Rivas Spring 2013 CS Spring 2013.
SE-IR Corporation 11/04 Goleta, CA (805) CamIRa TM SE-IR Corporation 87 Santa Felicia Dr. Goleta, CA (805)
Using Multimedia on the Web
1 Design and Implementation of an Efficient MPEG-4 Interactive Terminal on Embedded Devices Yi-Chin Huang, Tu-Chun Yin, Kou-Shin Yang, Yan-Jun Chang, Meng-Jyi.
HARDWARE Lesson 2. Components of a computer: 1)A Processor (or CPU) The brain of the computer 2)Memory To remember the programs and data that it uses.
© 2011 The McGraw-Hill Companies, Inc. All rights reserved Chapter 6: Video.
Computer Science Department University of Pittsburgh 1 Evaluating a DVS Scheme for Real-Time Embedded Systems Ruibin Xu, Daniel Mossé and Rami Melhem.
8086/8088 Hardware Specifications A Course in Microprocessor Electrical Engineering Dept. University of Indonesia.
XE33OSA Chapter 20: Multimedia Systems. 20.2XE33OSA Silberschatz, Galvin and Gagne ©2005 Chapter 20: Multimedia Systems What is Multimedia Compression.
SPCA554A Mobile Camera Multimedia Processor By Harrison Tsou.
CS Spring 2012 CS 414 – Multimedia Systems Design Lecture 29 – Buffer Management (Part 2) Klara Nahrstedt Spring 2012.
Sogang University Advanced Computing System Chap 1. Computer Architecture Hyuk-Jun Lee, PhD Dept. of Computer Science and Engineering Sogang University.
C OMPUTER O RGANIZATION AND D ESIGN The Hardware/Software Interface 5 th Edition Chapter 1 Computer Abstractions and Technology Sections 1.5 – 1.11.
1 Digitally Controlled Converter with Dynamic Change of Control Law and Power Throughput Carsten Nesgaard Michael A. E. Andersen Nils Nielsen Technical.
Towards the Design of Heterogeneous Real-Time Multicore System m Yumiko Kimezawa February 1, 20131MT2012.
CS Spring 2014 CS 414 – Multimedia Systems Design Lecture 18 – Multimedia Transport (Part 1) Klara Nahrstedt Spring 2014.
Senior Design Project “ MP3 Player ” Brian P. Allen Zeeshan A. Khan Jerry T. Koshy.
Audioprocessor for Automobiles Using the TMS320C50 DSP Ted Subonj Presentation on SPRA302 CSE671 / Dr. S. Ganesan.
Adaptive Sleep Scheduling for Energy-efficient Movement-predicted Wireless Communication David K. Y. Yau Purdue University Department of Computer Science.
CS 351/ IT 351 Modeling and Simulation Technologies HPC Architectures Dr. Jim Holten.
Multimedia Computing and Networking Jan Reduced Energy Decoding of MPEG Streams Malena Mesarina, HP Labs/UCLA CS Dept Yoshio Turner, HP Labs.
VLSI Design & Embedded Systems Conference January 2015 Bengaluru, India Few Good Frequencies for Power-Constrained Test Sindhu Gunasekar and Vishwani D.
Energy-efficient Sleep-mode Operations for Broadband Wireless Access Systems You-Lin Chen and Shiao-Li Tsao Department of Computer Science, National Chiao.
CS4315A. Berrached:CMS:UHD1 Introduction to Operating Systems Chapter 1.
Μ [sic] design constraints wesley :: chris :: dave :: josh.
Multimedia Retrieval Architecture Electrical Communication Engineering, Indian Institute of Science, Bangalore – , India Multimedia Retrieval Architecture.
Saving Bitrate vs. Users: Where is the Break-Even Point in Mobile Video Quality? ACM MM’11 Presenter: Piggy Date:
Embedded Systems February 10, Serial Interface - SPI  Serial Peripheral Interface  Synchronous communications  Clock supplied by the Master.
 Kim  Allen  Kenneth. Chapter 1 Computer Fundamentals.
Introduction to Quality of Service Klara Nahrstedt CS 538.
Determining Optimal Processor Speeds for Periodic Real-Time Tasks with Different Power Characteristics H. Aydın, R. Melhem, D. Mossé, P.M. Alvarez University.
PRESENTED BY: MOHAMAD HAMMAM ALSAFRJALANI UFL ECE Dept. 3/31/2010 UFL ECE Dept 1 CACHE OPTIMIZATION FOR AN EMBEDDED MPEG-4 VIDEO DECODER.
Identify internal hardware devices (e. g
Andrea Acquaviva, Luca Benini, Bruno Riccò
Data Compression.
Chapter 6: Video.
Video Transcoding for Wireless Video
Dynamic Voltage Scaling
Embedded Sound Processing : Implementing the Echo Effect
Presentation transcript:

Processor Frequency Setting for Energy Minimization of Streaming Multimedia Application by A. Acquaviva, L. Benini, and B. Riccò, in Proc. 9th Internation Symposium on Hardware/Software Codesign, Apr

Agenda Introduction Power optimization model derivation Power optimization algorithm Experimental results Conclusion

Introduction With technology enhancement, multimedia capabilities are being added to handheld devices. Examples:  Picture taking  MP3 audio playback  Video playback  Audio recording A new problem arises  power management

Introduction Power management options  Shut down devices when in idle mode Problem: Background tasks have to be stopped as well  Better approaches: clock frequency and voltage regulation Lowers system speed in idle states Reduces LCD display brightness

Introduction Real-time media streaming applications  Retrieve stream data from off-CPU interface (e.g. discs, memory cards)  Process data (e.g. decoding, decompression)  Deliver processed data to output interface (e.g. display, speakers)

Power Optimization Model Derivation System settings:  The CPU must communicate with relatively slower I/O interfaces  Clock frequency can be adjusted by software  Frame-based media (e.g. MP3 audio, MPEG video)

Power Optimization Model Derivation Power consumption: Energy per frame: V – supply voltage, C – switched capacitance, f – CPU clock frequency, T f – frame processing time, N f – number of cycles to process frame, t – cycle time

Power Optimization Model Derivation Due to speed difference between the CPU and external hardware: where N idle is a non-decreasing function of f We now have

Power Optimization Model Derivation To satisfy real-time synchronization constraint: T max – maximum allowed time for a frame (e.g. 1/30s in 30fps movie)

Power Optimization Model Derivation In words, target of power optimization is to reduce the term N idle in under the constraint

Power Optimization Model Derivation This technique is more effective if application requires much memory access However, delay and energy spent for frequency adjustment must also be considered

Proposed Algorithm Define three curves FR B (f), FR A (f), FR W (f), the best- case, average-case and worst-case frame rate at f. Compute curves for all bit rate and sampling rate values and obtain FR o B (f), FR o A (f), FR o W (f) Compute FR req by N sample : samples per frame, fixed at 576 for MP1 and MP1 phase 2

Proposed Algorithm Normalize the curves FR o B (f), FR o A (f), FR o W (f) by FR o A (f max ) from a pre-calculated look-up table Intersect FR req with three curves to obtain f min, f av and f max.

Proposed Algorithm CPU frequency can be set to:  f min if we find constantly frames processed faster than the average rate  f av if we want continuous playback, with some buffering storage for decoding rate jitter  f max to guarantee real-time performance on a frame-by-frame basis  Greater than f max if the processor is not dedicated to the application only

Experimental Results Energy consumption per frame

Experimental Results Energy consumption for 16KHz, 16KBit/s audio

Experimental Results Frequency setting

Example Calculation An audio stream of 16KHz, 16KBit/s Without any optimization, E f = mJ FR req = / 576 = fps FR A (f max ) = fps Normalized FR = 27.8 / = fps f min = 85.7MHz, f max = 106.7MHz Choosing f max, E f = 8.9mJ  19% energy reduction

Conclusion Frequency-energy relationship is derived An energy optimization algorithm is proposed Experiment shows dramatic save in power consumption