ASYNC 2000 Eilat April 2 - 6 1 Priority Arbiters Alex Bystrov David Kinniment Alex Yakovlev University of Newcastle upon Tyne, UK.

Slides:



Advertisements
Similar presentations
Network II.5 simulator ..
Advertisements

Categories of I/O Devices
Reading1: An Introduction to Asynchronous Circuit Design Al Davis Steve Nowick University of Utah Columbia University.
1/1/ / faculty of Electrical Engineering eindhoven university of technology Processor support devices Part 1:Interrupts and shared memory dr.ir. A.C. Verschueren.
Delay/Phase Regeneration Circuits Crescenzo D’Alessandro, Andrey Mokhov, Alex Bystrov, Alex Yakovlev Microelectronics Systems Design Group School of EECE.
Slide 1/20IWLS 2003, May 30Early Output Logic with Anti-Tokens Charlie Brej, Jim Garside APT Group Manchester University.
9/20/6Lecture 3 - Instruction Set - Al1 The Hardware Interface.
Asynchronous comparator design
Synchronous Digital Design Methodology and Guidelines
RTL Hardware Design by P. Chu Chapter 161 Clock and Synchronization.
1 Clockless Logic Montek Singh Thu, Jan 13, 2004.
Advanced Topics in Algorithms and Data Structures 1 Lecture 4 : Accelerated Cascading and Parallel List Ranking We will first discuss a technique called.
VMEbus Outline –Introduction –Electrical Characteristics –Mechanics –Functions –Data Transfer –Arbitration –Priority Interrupt Bus –Utilities Goal –Understand.
Embedded Systems Hardware:
Modeling The quadratic integrate and fire follows from a reduced form (1) where F(V) is a voltage dependant function which aims to capture the voltage.
ACSD Conference, Augsburg, Summer Flat Arbiters Andrey Mokhov 1, Victor Khomenko 2, Alex Yakovlev 1 1 School of Electrical, Electronic and Computer.
FF-1 9/30/2003 UTD Practical Priority Contention Resolution for Slotted Optical Burst Switching Networks Farid Farahmand The University of Texas at Dallas.
Demystifying Data-Driven and Pausible Clocking Schemes Robert Mullins Computer Architecture Group Computer Laboratory, University of Cambridge ASYNC 2007,
Give qualifications of instructors: DAP
University College Cork IRELAND Hardware Concepts An understanding of computer hardware is a vital prerequisite for the study of operating systems.
Embedded Systems Hardware: Storage Elements; Finite State Machines; Sequential Logic.
Behavioural synthesis of asynchronous controllers: a case study with a self-timed communication channel Alex Yakovlev, Frank Burns, Alex Bystrov, Albert.
Environment Modeling in Quasi- Static Scheduling EE249 Project Donald Chai Mentors: Alex Kondratyev, Yoshi Watanabe.
Performance and Power Efficient On-Chip Communication Using Adaptive Virtual Point-to-Point Connections M. Modarressi, H. Sarbazi-Azad, and A. Tavakkol.
EE466: VLSI Design Power Dissipation. Outline Motivation to estimate power dissipation Sources of power dissipation Dynamic power dissipation Static power.
Digital System Bus A bus in a digital system is a collection of (usually unbroken) signal lines that carry module-to-module communications. The signals.
1 Computer System Overview Chapter 1. 2 n An Operating System makes the computing power available to users by controlling the hardware n Let us review.
Elastic-Buffer Flow-Control for On-Chip Networks
UK Asynchronous Forum, September Synthesis of multiple rail phase encoding circuits Andrey Mokhov, Crescenzo D’Alessandro, Alex Yakovlev Microelectronics.
High-Level Interconnect Architectures for FPGAs An investigation into network-based interconnect systems for existing and future FPGA architectures Nick.
Network: Location Management Y. Richard Yang 3/21/2011.
Arithmetic Building Blocks
ICCD Conversion Driven Design of Binary to Mixed Radix Circuits Ashur Rafiev, Julian Murphy, Danil Sokolov, Alex Yakovlev School of EECE, Newcastle.
1 5. Application Examples 5.1. Programmable compensation for analog circuits (Optimal tuning) 5.2. Programmable delays in high-speed digital circuits (Clock.
Ratioed Circuits Ratioed circuits use weak pull-up and stronger pull-down networks. The input capacitance is reduced and hence logical effort. Correct.
6 Memory Management and Processor Management Management of Resources Measure of Effectiveness – On most modern computers, the operating system serves.
F. Gharsalli, S. Meftali, F. Rousseau, A.A. Jerraya TIMA laboratory 46 avenue Felix Viallet Grenoble Cedex - France Embedded Memory Wrapper Generation.
Asynchronous circuit design in control driven approach Name: Chi-Chuan Chuang Date:
EEE440 Computer Architecture
ISLIP Switch Scheduler Ali Mohammad Zareh Bidoki April 2002.
Computer System Architecture Dept. of Info. Of Computer. Chap. 13 Multiprocessors 13-1 Chap. 13 Multiprocessors n 13-1 Characteristics of Multiprocessors.
UNIVERSITY OF ROSTOCK Institute of Applied Microelectronics and Computer Science Single-Rail Self-timed Logic Circuits in Synchronous Designs Frank Grassert,
4/19/20021 TCPSplitter: A Reconfigurable Hardware Based TCP Flow Monitor David V. Schuehler.
DLD Lecture 26 Finite State Machine Design Procedure.
Field Programmable Port Extender (FPX) 1 Modular Design Techniques for the FPX.
80386DX functional Block Diagram PIN Description Register set Flags Physical address space Data types.
Dr Mohamed Menacer College of Computer Science and Engineering, Taibah University CE-321: Computer.
1 Practical Design and Performance Evaluation of Completion Detection Circuits Fu-Chiung Cheng Department of Computer Science Columbia University.
AND Gate Inputs Output Input A (Switch) Input B (Switch) Output Y (Lamp) 0 (Open) 0 (OFF) A B Lamp.
Chapter 3 System Buses.  Hardwired systems are inflexible  General purpose hardware can do different tasks, given correct control signals  Instead.
Field Programmable Port Extender (FPX) 1 Modular Design Techniques for the Field Programmable Port Extender John Lockwood and David Taylor Washington University.
1 Recap: Lecture 4 Logic Implementation Styles:  Static CMOS logic  Dynamic logic, or “domino” logic  Transmission gates, or “pass-transistor” logic.
EE141 Arithmetic Circuits 1 Chapter 14 Arithmetic Circuits Rev /12/2003 Rev /05/2003.
Compiling code and Computation into Biochemical Reactions Presenter : Chi-Yun Cheng.
1 Clockless Logic Montek Singh Thu, Mar 2, Review: Logic Gate Families  Static CMOS logic  Dynamic logic, or “domino” logic  Transmission gates,
WAITX: An Arbiter for Non-Persistent Signals
Interconnection Structures
Chapter 6 Input/Output Organization
Network Resources.
The Analysis of Cyclic Circuits with Boolean Satisfiability
Inst.eecs.berkeley.edu/~cs61c CS61C : Machine Structures Lecture #21 State Elements: Circuits that Remember Hello to James Muerle in the.
Hardware Description Languages
Synthesis of multiple rail phase encoding circuits
Synchronous Digital Design Methodology and Guidelines
Chapter 13: I/O Systems.
Synchronous Digital Design Methodology and Guidelines
William Stallings Computer Organization and Architecture
Presentation transcript:

ASYNC 2000 Eilat April Priority Arbiters Alex Bystrov David Kinniment Alex Yakovlev University of Newcastle upon Tyne, UK

ASYNC 2000 Eilat April Outline of presentation l Need for different arbitration disciplines l Types of arbiter l A static priority arbiter l A dynamic priority arbiter l Speed improvements l Results l Conclusions

ASYNC 2000 Eilat April Arbitration l Complex systems may require that some requests overtake others l Here three input channels require access to a single output port l Each request may have a different priority l Priority can be topologically fixed, or determined by a function Dynamic priority arbiter line 0 control line 1 control line 2 control P1 r1 g1 P2 r2 g2 P0 r0 g0 Data switch Output line Data control

ASYNC 2000 Eilat April Types of arbiter l Topologically fixed –priorities determined by structure, e.g. daisy-chain Start requests order of polling ~r 1,r 1 g1g1 d1d1 r2r2 g2g2 d2d2 rnrn gngn dndn l Static or dynamic priority –determined by fixed hardware, or priority data supplied

ASYNC 2000 Eilat April Static or dynamic priority Request lock register Control and Interface requests grants Priority logic priority busses

ASYNC 2000 Eilat April Metastability and priority l Lock the request pattern –incoming requests cause Lock to go high –following MUTEX ensures that request wins or loses l Evaluate priorities with a fixed request pattern MUTEX Lock r s l w ?

ASYNC 2000 Eilat April Static priority arbiter

ASYNC 2000 Eilat April Quasi speed independent Assumptions l s+ must occur before Lock+ –The physics of the MUTEX are such that if r+ is before Lock+, s+ must be asserted l The three inputs to the Lock bistable are implemented as a single complex gate set. –A faster non speed independent implementation in which the gate is separate is possible

ASYNC 2000 Eilat April More than one request l Priority needed if requests are competing l Shared resource free –resolution required only if second request arrives before the lock signal due to first request l Shared resource busy –Further requests may accumulate, and one may be higher priority

ASYNC 2000 Eilat April Two more requests

ASYNC 2000 Eilat April Dual-rail priority module C C C C r1r1 r3 r3 r2 r2 r1 r1 r2r2 r3r3 f1f1 f2f2 f3f3 g1g1 g2g2 g3g3 Completion Detector Priority Logic l Dual rail request inputs l One-hot grant output

ASYNC 2000 Eilat April Dynamic priority sq r* C Lock Register Priority Module MUTEX C s*q r R 0-7 Lock r 0-7 s 0-7 Reset completion detector res_done done P 0 P 1 P 7 G 0-7 Valid Invalid Priority data

ASYNC 2000 Eilat April Accelerated grant l Valid and Invalid signals are generated from the Lock register l Tree computation of grant l Only one channel needs to be valid for the node to be valid l Not all nodes need data evaluation l Data comparison uses dual rail or one hot techniques Root MCC Maximum Calculation Cells Slow computation G4 Done

ASYNC 2000 Eilat April sq r* G1 G2 G3 R1 R2 R3 Lock Lock Register Priority Module MUTEX s1 MUTEX s2 MUTEX s3 C C C Concurrent PM reset l Not speed independent. –Assume that Lock reset is faster than the resource. l Reset of the PM can take place concurrently with grant.

ASYNC 2000 Eilat April Results 0.6  AMS Process DPA l R 0 only to G nS l R 1.. R 7 arrive while processing R 0, then R 0 reset –13.45nS l Priority module –2.74nS (no priority data required) –7.63nS (all priority inputs compared)

ASYNC 2000 Eilat April Conclusions l Arbitrary priority discipline l Resource allocation a function of parameters supplied by active requests (or fixed statically) l Quasi speed independent request locking and priority evaluation l Accelerated grant where possible l Speed improvements possible with relative timing assumptions