That can lead to either increasing the clock speed or decreasing the power consumption Multiprocessing can be also used to increase speed or reduce power brPage 2br YORK UNIVERSITY CSE4210 Pipelining ab yn xn2 xn1 xn tion multiplica one and additi ID: 26469 Download Pdf

162K - views

Published byliane-varnes

That can lead to either increasing the clock speed or decreasing the power consumption Multiprocessing can be also used to increase speed or reduce power brPage 2br YORK UNIVERSITY CSE4210 Pipelining ab yn xn2 xn1 xn tion multiplica one and additi

Download Pdf

Download Pdf - The PPT/PDF document "YORK UNIVERSITY CSE Mokhtar Aboelaze CSE..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Page 1

YORK UNIVERSITY CSE4210 Mokhtar Aboelaze CSE4210 Winter 2012 YORK UNIVERSITY CSE4210 Pipelining -- Introduction • Pipelining can be us ed to reduce the the critical path. • That can lead to either increasing the clock speed, or decreasing the power consumption • Multiprocessing can be also used to increase speed or reduce power.

Page 2

YORK UNIVERSITY CSE4210 Pipelining ab y(n) x(n-2) x(n-1) x(n) tion multiplica one and additions two is here path critical The mul add mul add YORK UNIVERSITY CSE4210 x(n) x(n) y(n) y(n-1) b(n) a(n) b(n-1) a(n) b(2k) a(2k) b(2k+1)

a(2k+1) y(2k) y(2k+1) x(2k+1) x(2k) Parallel processing Pipelining

Page 3

YORK UNIVERSITY CSE4210 Pipelining • Advantages – Could be used to reduce power and/or to increase clock rate (speed) • Disadvantages – Increases number of delay elements (latches or flip-flops) – Increases latency YORK UNIVERSITY CSE4210 Pipelining Cutset : is a set of edges of a graph if removed, the graph becomes partitioned Feed forward cutset : a cutset where the data moves in the forward direction on all the edges in the cutset • We can place latches on a feed-forward cutset without affecting the

functionality of the graph.

Page 4

YORK UNIVERSITY CSE4210 Pipelining ab y(n) x(n-2) x(n-1) x(n) YORK UNIVERSITY CSE4210 Example Critical Path?

Page 5

YORK UNIVERSITY CSE4210 Data Broadcast Structures • Reversing the direction of all the edges in a given SFG, and interchanging the ,input and output preserves the functionality of the system. YORK UNIVERSITY CSE4210 Data Broadcast y(n) -1 -1 x(n) x(n) -1 -1 y(n)

Page 6

YORK UNIVERSITY CSE4210 Fine-Grain Pipelining cb y(n) x(n) Multiplication time = 10 Addition time = 2 Critical path = ? YORK UNIVERSITY CSE4210 Fine

grain Pipelining

Page 7

YORK UNIVERSITY CSE4210 Parallel Processing cx bx ax cx bx ax cx bx ax cx bx ax YORK UNIVERSITY CSE4210 X(3k) or x(3k-2)?

Page 8

YORK UNIVERSITY CSE4210 Complete Parallel System Serial to Parallel Converter MIMO SYSTEM Parallel to Serial Converter x(n) y(n) Clock period Sampling period T/4 Clock period T/4 x(4k+3) x(4k+1) x(4k+2) x(4k) y(4k) y(4k+1) y(4k+2) y(4k+3) YORK UNIVERSITY CSE4210 S/P and P/S Converter T/4 T/4 T/4 x(4k+3) x(4k+2) x(4k+1) x(4k) y(n) T/4 T/4 T/4

Page 9

YORK UNIVERSITY CSE4210 Parallel Processing • Why use parallel

processing? It increases the hardware. • There is a limit for the use of pipelining, you may not be able to pipeline a functional unit beyond a certain limie • Also, I/O usually imposes a bound on the cycle time (communication bound) YORK UNIVERSITY CSE4210 Combining pipelining and parallel processing

Page 10

10 YORK UNIVERSITY CSE4210 Low Power charge pd total Simple approximation for CMOS total is the total capacitance of th e circuit, Vo is the supply voltage. charge is the capacitance to be charged/discharged in a single clock cycle. Pipelining and parallel processi ng could be

used to minimize power or execution time. YORK UNIVERSITY CSE4210 Low Power • What happens in case of M –pipelining? • Critical path is reduced by , so is charge • If we keep the same , then we have more time to charge charge , which means we can reduce the supply voltage charge charge pip seq

Page 11

11 YORK UNIVERSITY CSE4210 Low Power —Example m1 cb y(n) x(n) m1 m1 a1 a1 YORK UNIVERSITY CSE4210 Example

Page 12

12 YORK UNIVERSITY CSE4210 Parallel processing • What happen for parallel System? • Total capacitance increased by • Same performance, increase T by • More time to

charge charge , can decrease arg charge LT ch par seq YORK UNIVERSITY CSE4210 Parallel Processing Example • Consider a 4-tap FIR filter shown in Fig. 3.18(a) and its 2-parallel version in 3.18(b). The parallel filter has exactly 2 copies of the original filter. The dashed line donates the critical path. • Assume Also that T =8, T =1, V =0.45V, =3.3V, C =8C – What is the supply voltage of the 2-paral lel filter? – What is the power consumpti on of the 2-parallel filter as a percentage of t he original filter?

Page 13

13 YORK UNIVERSITY CSE4210 YORK UNIVERSITY CSE4210 Example

Page

14

14 YORK UNIVERSITY CSE4210 Different Architecture

Â© 2020 docslides.com Inc.

All rights reserved.