Download Energy-aware Scheduling on Multiprocessor Platforms by Dawei Li, Jie Wu PDF

Posted by

By Dawei Li, Jie Wu

Multiprocessor systems play vital roles in glossy computing structures, and seem in numerous purposes, starting from energy-limited hand held units to giant facts facilities. because the functionality necessities bring up, energy-consumption in those structures additionally raises significantly. Dynamic Voltage and Frequency Scaling (DVFS), which permits processors to dynamically alter the availability voltage and the clock frequency to function on different power/energy degrees, is taken into account an effective option to in attaining the aim of energy-saving. This publication surveys current works which have been on energy-aware job scheduling on DVFS multiprocessor platforms.

Energy-aware scheduling difficulties are intrinsically optimization difficulties, the formulations of which drastically rely on the platform and activity types into consideration. hence, Energy-aware Scheduling on Multiprocessor Platforms covers present examine in this subject and classifies current works in response to key criteria, specifically, homogeneity/heterogeneity of multi­processor systems and the duty varieties thought of. less than this classification, different sub-issues also are incorporated, akin to, slack reclamation, fixed/dynamic precedence sched­uling, partition-based/global scheduling, and application-specific strength intake, etc.

Show description

Read Online or Download Energy-aware Scheduling on Multiprocessor Platforms PDF

Similar design & architecture books

A+ Complete Lab Manual

This re-creation of the A+ entire Lab handbook has been completely up-to-date to hide the most recent CompTIA pursuits. it is also been revised for less complicated navigation and a tighter healthy with David Groth's best-selling A+ whole research consultant. Use those assets jointly to realize the data, talents, and self belief you must cross the assessments and start a profitable profession.

Web 2.0 Architectures : What Entrepreneurs and Information Architects Need to Know

Net 2. zero is extra pervasive than ever, with company analysts and technologists suffering to realize the chance it represents. yet what precisely is net 2. 0--a advertising time period or technical truth? This attention-grabbing ebook eventually places substance at the back of the phenomenon by means of making a choice on the middle styles of net 2.

High Performance Data Mining: Scaling Algorithms, Applications and Systems

Excessive functionality information Mining: Scaling Algorithms, functions andSystems brings jointly in a single position very important contributions and updated study ends up in this fast-paced sector. excessive functionality information Mining: Scaling Algorithms, functions andSystems serves as a great reference, offering perception into one of the most demanding study concerns within the box.

Integrated Circuits for Wireless Communications

"High-frequency built-in circuit layout is a booming quarter of progress that's pushed not just by means of the increasing services of underlying circuit applied sciences like CMOS, but additionally by means of the dramatic elevate in instant communications items that depend upon them. built-in CIRCUITS FOR instant COMMUNICATIONS comprises seminal and vintage papers within the box and is the 1st all-in-one source to deal with this more and more very important subject.

Extra info for Energy-aware Scheduling on Multiprocessor Platforms

Example text

It can be seen that, in some cases, assigning the last task according to this iterative scheme may not be optimal. Thus, for the last task, the assignment, which can achieve the minimal overall energy consumption among all possible assignments for the last task, is selected. An illustrative example is provided below, which deals with assigning eight tasks to three processors. 1. A reference execution time matrix is denoted by t8×3 , where ti, j = WCECi /λi, j , which is also provided in the same table.

Based on the optimal LLREF algorithm described above, the authors in [17] propose two static energy-efficient algorithms for homogeneous multiprocessor systems. The first one is called Uniform RT-SVFS, which claims that a periodic task 34 3 Scheduling on Homogeneous DVFS Multiprocessor Platforms 4 0 8 8 0 16 12 6 0 12 20 24 18 24 16 24 Fig. 13 Creating T-L planes according to periodic tasks’ deadlines Fig. 14 The first T-L plane 4 3 2 1 0 1 3 2 4 4 0 4 6 8 12 16 18 20 24 Fig. 15 All of the T-L planes for the periodic task set set with total utilization U total ≤ α m and U max ≤ α will be scheduled to meet all deadlines on m processors with frequency α by LLREF.

The total energy consumption of the m cores for each combination of m1 + m2 = m is calculated, and finally, the best combination is selected. 2. 225. Thus, τ1 is a Heavy Task, τ2 is Medium Task, and τ3 is a Light Task. Assume that the optimal number of processors to execute τ1 concurrently is 3. 4 are the utilizations of τ1 split onto M1 , M2 , M3 , respectively. 28 3 Scheduling on Homogeneous DVFS Multiprocessor Platforms Fig. 7 Assignment of sufficient cores f t1 t f t1 t f t1 t f t2 t f t3 t Fig.

Download PDF sample

Rated 4.44 of 5 – based on 27 votes