customer-aware task allocation and scheduling for multi-mode mpsocs

10
1 Customer-Aware Task Allocation and Scheduling for Multi-Mode MPSoCs Lin Huang, Rong Ye and Qiang Xu CHhk REliable computing laboratory (CURE) The Chinese University of Hong Kong

Upload: miller

Post on 08-Feb-2016

56 views

Category:

Documents


0 download

DESCRIPTION

Customer-Aware Task Allocation and Scheduling for Multi-Mode MPSoCs. Lin Huang, Rong Ye and Qiang Xu CHhk REliable computing laboratory (CURE) The Chinese University of Hong Kong. T 0. Task Graph. T 1. MPSoC Platform. T 2. P 1. P 2. T 3. T 4. P 1. Periodical Schedule. T 2. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

1

Customer-Aware Task Allocation and Scheduling for Multi-Mode MPSoCs

Lin Huang, Rong Ye and Qiang XuCHhk REliable computing laboratory (CURE)

The Chinese University of Hong Kong

Page 2: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

2

TAS and Execution Modes• Task Allocation and Scheduling

• Multi-Mode MPSoCs (multiple execution modes)• Communication service• Audio/Video player• Digital camera…

P1 P2

MPSoC PlatformT0

T1

T2

T3

T4

TaskGraph

Allocation &Scheduling

T0

P1

P2 T1

T2

T3

T4PeriodicalSchedule

Page 3: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

3

Personalized TAS• Prior Works [Huang etc., DATE’09, DATE’10]

• TAS solutions are generated at design stage• A unified task schedule for each execution mode is

constructed for all the products

• Usage Strategy Deviation• The products, bought by different end users, experience

different life stories.• Personalized TAS solution for each individual product

can be more energy-efficient and/or reliable

Page 4: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

4

Motivational Example• Consider

• A simple MPSoC product with 3 execution modes and 2 processor cores• 10,000 sample products

Page 5: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

5

Problem Formulation• Problem 1 [Design Stage]

• Given– q execution modes and a directed acyclic task graph for each mode;– The joint probability density function;– A platform-based MPSoC embedded system;– Execution time table;– Power consumption table;– The target service life and the corresponding reliability requirement.

• To determine a periodical task schedule for each execution mode, such that the expected energy consumption over all products is minimized under the performance and reliability constraints

• Problem 2 [Online Adjustment]• Given

– Interval length;– Usage strategy of a specific interval;– Task mapping flexibility constraints.

• To achieve the same optimization as Problem 1

Page 6: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

6

Proposed TAS at Design Stage• Simulated annealing-based algorithm to minimize the

expected energy consumption over all the products• Solution representation

• Two kinds of moves• M1: Insert a task in the front of its sink, if no precedunce constraint between them• M2: Change the resource assignment of a task

• Cost function

Task Graph Task Schedule Zone Representation

1

( ) exp( ( ) )( )

jm

sys LL

j

tR ts

Page 7: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

7

Proposed Online Adjustment• Overall flow

• Resort to similar technique as design stage;• The main difference stays in particularly in the cost function.• Since aging effect is a slow process, online adjustment is performed

at regular intervals in range of days or months as a special task.• Analytical model

• A forgetful scheme to infer future usage strategy

• System reliability is given by

11 1(1 ) (1 ) u

u uy y y y

1 11 1

( ; , | , ; ; , ) exp( ( ) )( ) ( )

jm u

sys L I IL u u

j j j

t u t tR t y s y s y ss s

Page 8: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

8

Experimental Results• Without mapping constraints

Initial Solution Online Adjustment

Page 9: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

9

Experimental Results• With mapping constraints

Online Adjustment (25% tasks with constraints)

Online Adjustment(50% tasks with constraints)

Page 10: Customer-Aware Task Allocation and Scheduling for Multi-Mode  MPSoCs

10

Conclusion• Customer-aware TAS on multi-mode MPSoCs• Two phases of proposed approach

• Simulated annealing-based algorithm at design stage• Usage-specific online adjustment

• Experimental results • Based on hypothetical MPSoCs with various task graphs;• Show the capability to significantly increase the lifetime reliability

and energy reduction of MPSoC products.

Welcome to visit our poster!