 Program Abstractions  Concepts  ACE Structure.

Slides:



Advertisements
Similar presentations
Network II.5 simulator ..
Advertisements

DISTRIBUTED COMPUTING PARADIGMS
Processes Management.
Remote Procedure Call (RPC)
Chapter 4 Conventional Computer Hardware Architecture
CCU EE&CTR1 Software Architecture Overview Nick Wang & Ting-Chao Hou National Chung Cheng University Control Plane-Platform Development Kit.
Chapter 7 Protocol Software On A Conventional Processor.
Socket Programming.
Chapter 11 Exception Handling and Event Handling.
I/O Hardware n Incredible variety of I/O devices n Common concepts: – Port – connection point to the computer – Bus (daisy chain or shared direct access)
©TheMcGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 1 Introduction to Object-Oriented Programming and Software Development.
Communication in Distributed Systems –Part 2
Shyamal Pandya Implementation of Network Processor Packet Filtering and Parameterization for Higher Performance Network Processors 1 Implementation of.
ECE 526 – Network Processing Systems Design IXP XScale and Microengines Chapter 18 & 19: D. E. Comer.
1 Threads Chapter 4 Reading: 4.1,4.4, Process Characteristics l Unit of resource ownership - process is allocated: n a virtual address space to.
.NET Mobile Application Development Remote Procedure Call.
Chapter 9 Classification And Forwarding. Outline.
COS 420 Day 16. Agenda Assignment 3 Corrected Poor results 1 C and 2 Ds Spring Break?? Assignment 4 Posted Chap Due April 6 Individual Project Presentations.
OIS Model TCP/IP Model.
Connecting LANs, Backbone Networks, and Virtual LANs
CP476 Internet ComputingCh.1 # 1 Lecture 2. A Brief Introduction to the Internet The objective is to understand The history of Internet What the Internet.
Paper Review Building a Robust Software-based Router Using Network Processors.
FALL 2005CSI 4118 – UNIVERSITY OF OTTAWA1 Part 4 Web technologies: HTTP, CGI, PHP,Java applets)
Tanenbaum & Van Steen, Distributed Systems: Principles and Paradigms, 2e, (c) 2007 Prentice-Hall, Inc. All rights reserved DISTRIBUTED SYSTEMS.
Presentation by Betsy Kavali
Chapter 9 Message Passing Copyright © Operating Systems, by Dhananjay Dhamdhere Copyright © Operating Systems, by Dhananjay Dhamdhere2 Introduction.
Software Architecture Classification for Estimating the Costs of COTS Integration Yakimovich, Bieman, Basili; icse 99.
1 Chapter Client-Server Interaction. 2 Functionality  Transport layer and layers below  Basic communication  Reliability  Application layer.
1 Lecture 4: Threads Operating System Fall Contents Overview: Processes & Threads Benefits of Threads Thread State and Operations User Thread.
1 Computer Networks DA Chapter 1-3 Introduction.
The Architecture of Secure Systems Jim Alves-Foss Laboratory for Applied Logic Department of Computer Science University of Idaho By, Nagaashwini Katta.
User Datagram Protocol (UDP) Chapter 11. Know TCP/IP transfers datagrams around Forwarded based on destination’s IP address Forwarded based on destination’s.
COP 4930 Computer Network Projects Summer C 2004 Prof. Roy B. Levow Lecture 3.
Delivery, Forwarding, and Routing of IP Packets
1 Internet Routing. 2 Terminology Forwarding –Refers to datagram transfer –Performed by host or router –Uses routing table Routing –Refers to propagation.
Multiplexing FDM & TDM. Multiplexing When two communicating nodes are connected through a media, it generally happens that bandwidth of media is several.
ACEs ACEs 24/ INF5060: Multimedia data communication using network processors.
Processes Introduction to Operating Systems: Module 3.
IS473 Distributed Systems CHAPTER 5 Distributed Objects & Remote Invocation.
Chapter 5: Distributed objects and remote invocation Introduction Remote procedure call Events and notifications.
1 Client-Server Interaction. 2 Functionality Transport layer and layers below –Basic communication –Reliability Application layer –Abstractions Files.
McGraw-Hill©The McGraw-Hill Companies, Inc., 2004 Connecting Devices CORPORATE INSTITUTE OF SCIENCE & TECHNOLOGY, BHOPAL Department of Electronics and.
The Client-Server Model And the Socket API. Client-Server (1) The datagram service does not require cooperation between the peer applications but such.
EECB 473 Data Network Architecture and Electronics Lecture 1 Conventional Computer Hardware Architecture
Unit III Bandwidth Utilization: Multiplexing and Spectrum Spreading In practical life the bandwidth available of links is limited. The proper utilization.
VHDL Discussion Subprograms IAY 0600 Digital Systems Design Alexander Sudnitson Tallinn University of Technology 1.
Distributed objects and remote invocation Pages
ECE 526 – Network Processing Systems Design Programming Model Chapter 21: D. E. Comer.
Parallel Computing Presented by Justin Reschke
UDP: User Datagram Protocol Chapter 12. Introduction Multiple application programs can execute simultaneously on a given computer and can send and receive.
Silberschatz, Galvin and Gagne ©2011 Operating System Concepts Essentials – 8 th Edition Chapter 2: The Linux System Part 5.
Channels. Models for Communications Synchronous communications – E.g. Telephone call Asynchronous communications – E.g. .
CEN6502, Spring Understanding the ORB: Client Side Structure of ORB (fig 4.1) Client requests may be passed to ORB via either SII or DII SII decide.
Interrupts and Exception Handling. Execution We are quite aware of the Fetch, Execute process of the control unit of the CPU –Fetch and instruction as.
Embedded Real-Time Systems Processing interrupts Lecturer Department University.
COMPUTER NETWORKS CS610 Lecture-22 Hammad Khalid Khan.
Topic 4: Distributed Objects Dr. Ayman Srour Faculty of Applied Engineering and Urban Planning University of Palestine.
Processes and threads.
Chapter 3 Internet Applications and Network Programming
MCA – 405 Elective –I (A) Java Programming & Technology
Chapter 3: Windows7 Part 4.
Network Core and QoS.
Running A First Example: The Web Bumper
Implementing an OpenFlow Switch on the NetFPGA platform
Threads Chapter 4.
Chapter 2: The Linux System Part 5
Computer Networks DA2402.
SPL – PS1 Introduction to C++.
Network Core and QoS.
Presentation transcript:

 Program Abstractions  Concepts  ACE Structure

 ACE  Microblock

 Intel uses the term Active Computing Element (ACE) to denote programming abstraction.  It is characterized by  Used to construct packet processing system  Runs on microengines or host  Handle data processing path  Coordinates and synchronizes with other ACE’s  Can have multiple outputs  Can serve as part of pipe lining

 Terminologies  Library ACE – An ACE that has been built by Intel and made available as a part of Intel SDK.  Conventional ACE – An ACE that is built by Intel customers.  MicroACE – An ACE that is made of two components: Core and Microblock. Source Micro- block Transfom Micro- block Sink Micro- block

 There are four conceptual parts  Initialization - It is invoked once, before any other code is executed to built data structure and initialize variable.  Classification - When packet arrives, the ACE classifies the packet.  Actions - An action is invoked whenever a packet satisfies the corresponding classification.  Message and Event management – It generates or handles message and events that provide communication with another ACE or with the underlying hardware.

 Output Targets  Output can be change after it has been compiled.  A programmer create a set of target names and uses a name to specify each output.  During integration process target names can be bound to specific destination.

 ACE Interconnection instead of building a single monotonic ACE software can be divided into several smaller ACEs. Ingress ACE Process ACE Egress ACE Input ports Output ports

 MicroACE  Codes in the ACE run on the StrongARM or on one of the microengines.  Intel provides a mechanism that allows the two components to pass packets in either direction between them. Example : A system that perform IP forwarding with four conceptual ACEs – ingress, egress, IP forwarding and interface to local IP protocol stack.

Core and Microblocks component Stack ACE Ingress ACE (core) Egress ACE (MB) IP ACE (MB) Ingress ACE (MB) Egress ACE (core) IP ACE (core) Strong ARM Microengine I/po/p

 Microblock Groups. microbloack group is Set of microblocks that run on a single microengine. Stack ACE Ingress ACE (core) Egress ACE (MB) IP ACE (MB) Ingress ACE (MB) Egress ACE (core) IP ACE (core) I/po/p Microengine 1Microengine 2

 Replicated Microblocks parallelism can be increases by replicating a microblock group onto multiple microengines.  Dispatch Loop- a machenism to control packet flow among microblocks. Here dispatch loop refer to a small piece of code that control packet flow

Parameter  A buffer handle for a frame that contail a packet  A set of register to store contain information about frame  A variable in which to store a return code

 Exceptions Exception refer to packet passed from a microblock component to corresponding core component on the StrongARM.  ACEs include a queue management named as communication queue to transfer packets between ACEs.  A non-packet communication can be perform by crosscall, the mechanism is related to RPC.  Crosscall are of 3 types Deferred, oneway and twoway.

Thank you