High Performance Embedded Computing © 2007 Elsevier Lecture 16: Interconnection Networks Embedded Computing Systems Mikko Lipasti, adapted from M. Schulte.

Slides:



Advertisements
Similar presentations
Data Communications and Networking
Advertisements

Interconnection Networks: Flow Control and Microarchitecture.
1 IK1500 Communication Systems IK1330 Lecture 3: Networking Anders Västberg
Dynamic Topology Optimization for Supercomputer Interconnection Networks Layer-1 (L1) switch –Dumb switch, Electronic “patch panel” –Establishes hard links.
Presentation of Designing Efficient Irregular Networks for Heterogeneous Systems-on-Chip by Christian Neeb and Norbert Wehn and Workload Driven Synthesis.
Jaringan Komputer Lanjut Packet Switching Network.
Module R R RRR R RRRRR RR R R R R Efficient Link Capacity and QoS Design for Wormhole Network-on-Chip Zvika Guz, Isask ’ har Walter, Evgeny Bolotin, Israel.
1 Lecture 12: Interconnection Networks Topics: dimension/arity, routing, deadlock, flow control.
Network based System on Chip Final Presentation Part B Performed by: Medvedev Alexey Supervisor: Walter Isaschar (Zigmond) Winter-Spring 2006.
Network based System on Chip Part A Performed by: Medvedev Alexey Supervisor: Walter Isaschar (Zigmond) Winter-Spring 2006.
EE 122: Router Design Kevin Lai September 25, 2002.
Network-on-Chip Examples System-on-Chip Group, CSE-IMM, DTU.
1 Lecture 24: Interconnection Networks Topics: communication latency, centralized and decentralized switches (Sections 8.1 – 8.5)
Issues in System-Level Direct Networks Jason D. Bakos.
1 Lecture 24: Interconnection Networks Topics: topologies, routing, deadlocks, flow control.
8.1 Chapter 8 Switching Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display.
Network-on-Chip: Communication Synthesis Department of Computer Science Texas A&M University.
Storage area network and System area network (SAN)
1 25\10\2010 Unit-V Connecting LANs Unit – 5 Connecting DevicesConnecting Devices Backbone NetworksBackbone Networks Virtual LANsVirtual LANs.
Low-Latency Virtual-Channel Routers for On-Chip Networks Robert Mullins, Andrew West, Simon Moore Presented by Sailesh Kumar.
High Performance Embedded Computing © 2007 Elsevier Chapter 5, part 1: Multiprocessor Architectures High Performance Embedded Computing Wayne Wolf.
Performance and Power Efficient On-Chip Communication Using Adaptive Virtual Point-to-Point Connections M. Modarressi, H. Sarbazi-Azad, and A. Tavakkol.
Connecting LANs, Backbone Networks, and Virtual LANs
Switching, routing, and flow control in interconnection networks.
Computer Networks Switching Professor Hui Zhang
Interconnection Networks. Applications of Interconnection Nets Interconnection networks are used everywhere! ◦ Supercomputers – connecting the processors.
1 The Turn Model for Adaptive Routing. 2 Summary Introduction to Direct Networks. Deadlocks in Wormhole Routing. System Model. Partially Adaptive Routing.
Blue Gene / C Cellular architecture 64-bit Cyclops64 chip: –500 Mhz –80 processors ( each has 2 thread units and a FP unit) Software –Cyclops64 exposes.
Interconnect Networks
José Vicente Escamilla José Flich Pedro Javier García 1.
Networks-on-Chips (NoCs) Basics
ATM SWITCHING. SWITCHING A Switch is a network element that transfer packet from Input port to output port. A Switch is a network element that transfer.
1 Lecture 7: Interconnection Network Part I: Basic Definitions Part II: Message Passing Multicomputers.
High-Level Interconnect Architectures for FPGAs An investigation into network-based interconnect systems for existing and future FPGA architectures Nick.
Dynamic Interconnect Lecture 5. COEN Multistage Network--Omega Network Motivation: simulate crossbar network but with fewer links Components: –N.
CPS 356: Introduction to Computer Networks Lecture 7: Switching technologies Ch 2.8.2, 3.1, 3.4 Xiaowei Yang
High-Level Interconnect Architectures for FPGAs Nick Barrow-Williams.
Data and Computer Communications Chapter 10 – Circuit Switching and Packet Switching (Wide Area Networks)
1 Message passing architectures and routing CEG 4131 Computer Architecture III Miodrag Bolic Material for these slides is taken from the book: W. Dally,
Anshul Kumar, CSE IITD CSL718 : Multiprocessors Interconnection Mechanisms Performance Models 20 th April, 2006.
CS 8501 Networks-on-Chip (NoCs) Lukasz Szafaryn 15 FEB 10.
15.1 Chapter 15 Connecting LANs, Backbone Networks, and Virtual LANs Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or.
Routers. These high-end, carrier-grade 7600 models process up to 30 million packets per second (pps).
Packet Forwarding. A router has several input/output lines. From an input line, it receives a packet. It will check the header of the packet to determine.
Anshul Kumar, CSE IITD ECE729 : Advanced Computer Architecture Lecture 27, 28: Interconnection Mechanisms In Multiprocessors 29 th, 31 st March, 2010.
McGraw-Hill©The McGraw-Hill Companies, Inc., 2004 Connecting Devices CORPORATE INSTITUTE OF SCIENCE & TECHNOLOGY, BHOPAL Department of Electronics and.
Run-time Adaptive on-chip Communication Scheme 林孟諭 Dept. of Electrical Engineering National Cheng Kung University Tainan, Taiwan, R.O.C.
Networks-on-Chip (NoC) Suleyman TOSUN Computer Engineering Deptartment Hacettepe University, Turkey.
Interconnect Networks Basics. Generic parallel/distributed system architecture On-chip interconnects (manycore processor) Off-chip interconnects (clusters.
Team LDPC, SoC Lab. Graduate Institute of CSIE, NTU Implementing LDPC Decoding on Network-On-Chip T. Theocharides, G. Link, N. Vijaykrishnan, M. J. Irwin.
McGraw-Hill©The McGraw-Hill Companies, Inc., 2000 CH. 8: SWITCHING & DATAGRAM NETWORKS 7.1.
1 Lecture 15: NoC Innovations Today: power and performance innovations for NoCs.
Virtual-Channel Flow Control William J. Dally
1 Lecture 24: Interconnection Networks Topics: communication latency, centralized and decentralized switches, routing, deadlocks (Appendix F)
Design Space Exploration for NoC Topologies ECE757 6 th May 2009 By Amit Kumar, Kanchan Damle, Muhammad Shoaib Bin Altaf, Janaki K.M Jillella Course Instructor:
Data Communication Networks Lec 13 and 14. Network Core- Packet Switching.
Power-aware NOC Reuse on the Testing of Core-based Systems* CSCE 932 Class Presentation by Xinwang Zhang April 26, 2007 * Erika Cota, et al., International.
Runtime Reconfigurable Network-on- chips for FPGA-based systems Mugdha Puranik Department of Electrical and Computer Engineering
SWITCHING. Switching is process to forward packets coming in from one port to a port leading towards the destination. When data comes on a port it is.
Chapter 8 Switching Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display.
Lecture 23: Interconnection Networks
Packet Forwarding.
Addressing: Router Design
Azeddien M. Sllame, Amani Hasan Abdelkader
Switching, routing, and flow control in interconnection networks
Data Communication Networks
Advanced Computer and Parallel Processing
EE 122: Lecture 7 Ion Stoica September 18, 2001.
Advanced Computer and Parallel Processing
Multiprocessors and Multi-computers
Presentation transcript:

High Performance Embedded Computing © 2007 Elsevier Lecture 16: Interconnection Networks Embedded Computing Systems Mikko Lipasti, adapted from M. Schulte Based on slides and textbook from Wayne Wolf

© 2006 Elsevier Topics Interconnection Terms and Metrics Interconnection Models Routing and Flow Control Network-on-Chips

© 2006 Elsevier Interconnection networks Client: sender or receiver on a network. Port: connection to a network on a client Link: connection between two clients (full/half duplex) Topology: organization of network links. Network metrics:  Throughput.  Latency.  Energy consumption.  Area (silicon or metal). Quality-of-service (QoS) is important for multimedia applications.

© 2006 Elsevier Interconnection network models Source termination. Throughput T, latency D. Link transmission energy E b. Physical length L. Total link area A. Traffic models often use Poisson distribution  P(X = x) =  x e -   /(x)!x =0, 1, 2, …  E(x) = , Var(x) = . Streaming data is produced periodically with rate  and burstiness 

© 2006 Elsevier Network topologies Major choices for network topologies include.  Bus: common connection between a set of senders and receivers  Crossbar: fully connected network from every input port to every output port.  Buffered crossbar: add queues to a crossbar to enable multiple sources to share crossbar input  Mesh: network in which every node is connected to all of its neighbors.  Application-specific: topology is matched to the characteristics of the application.

© 2006 Elsevier Bus network Throughput:  T 1 = P/(1+C). – single word  T b = P*(n/(n + C)) – n word block Advantages:  Well-understood.  Easy to program.  Many standards. Disadvantages:  Contention.  Significant capacitive load.  Do not scale well.

© 2006 Elsevier Crossbar network Fully connected network Advantages:  No contention.  Simple design  Low latency  Broadcast. Disadvantages:  Expensive  Not feasible for large numbers of ports.

© 2006 Elsevier Buffered crossbar network Add queues shared by multiple sources Advantages:  Smaller than crossbar.  Can achieve high utilization. Disadvantages:  Requires scheduling. Clos networks  Connect multiple crossbars together in stages Xbar

© 2006 Elsevier Mesh network Every node connected to all of its neighbors Advantages:  Well-understood.  Regular architecture. Disadvantages:  Poor utilization  Variable latency.

© 2006 Elsevier Application-specific. network Topology is specific for application(s) Advantages:  Higher utilization.  Lower power. Disadvantages:  Must be designed.  Must carefully allocate data.

© 2006 Elsevier Network topology questions What type of network topology would you chose if you were building a 1,000 node system? Why would you use a buffered crossbar network instead of a regular crossbar network? What advantages and disadvantages does a 2D mesh have compared to a 3D mesh? What types of systems would you expect to use application-specific networks?

© 2006 Elsevier Routing and flow control Routing determines paths followed by packets.  Connection-oriented or connectionless.  Wormhole routing divides packets into flits and header flit determines route for remaining flits  Virtual cut-through ensures entire path is available before starting transmission.  Store-and-forward routing stores packets inside network. Flow control allocates links and buffers as packets move through the network.  Virtual channel flow control treats flits in different virtual channels differently.

© 2006 Elsevier Networks-on-chips Impact characteristics of MPSoC:  Energy.  Performance.  Cost. NoCs may not have to interoperate with other networks.  NoCs have to connect to existing IP, which may influence interoperability. QoS is an important design goal.

© 2006 Elsevier Nostrum Mesh network---switch connects to four nearest neighbors and local “resource” Each switch has queue at each input. Selection logic determines order in which packets are sent to output links. [Kum02] © 2002 IEEE Computer Society

© 2006 Elsevier Scalable, Programmable, Integrated Network (SPIN) Scalable network based on fat-tree.  Bandwidth of links is larger toward root of tree. All routing nodes use the same routing function.  Message goes up the tree until a common ancestor reached

© 2006 Elsevier Routing nodes in SPIN Packet consists of 32-bit words  One word header  Variable word packet  One word checksum trailer Network utilizes input queues and partial crossbars Outputs share buffers  Help with contention

© 2006 Elsevier Ye et al. energy model Assume: energy per packet is independent of data or packet address. Histogram captures distribution of path lengths. Energy consumption of a class of packet:  M = maximum number of hops.  h = number of hops.  N(h) = value of h th histogram bucket.  L = number of flits per packet.  E flit = energy per flit.

Ye et al. energy model © 2006 Elsevier Longer packets corresponds to longer block sizes Larger packets Decrease cache misses but increase the miss penalty Decrease number of packets but increase hops per packet Decrease cache and memory energy, but increase network energy

© 2006 Elsevier Goossens et al. NoC methodology Geared towards Application-specific SoCs QoS-intensive apps Network dimensioning – determine size of network and buffers NoC topology – determine connection between elements NoC configuration – set register values that control flow through the network

© 2006 Elsevier QNoC Designed to support QoS. Two-dimensional mesh, wormhole routing.  Fixed x-y routing algorithm. Four different types of service.  Each service level has its own buffers.  Next-buffer-state table records number of slots for each output in each class.  Transmissions based on next stage, service levels, and round-robin ordering. Can be customized for specific application.

QNoC Design Methodology © 2006 Elsevier

Xpipes and NetChip Xpipes is a library of soft IP macros for network switches and links. NetChip generates custom NoC designs using xpipes components.

© 2006 Elsevier Xu et al. H.264 network design Designed NoC for H.264 decoder. Process -> PE mapping was given. Compared RAW mesh to application-specific networks. [Xu06] © 2006 ACM Press

© 2006 Elsevier Application-specific network for H.264 [Xu06] © 2006 ACM Press

© 2006 Elsevier RAW/application-specific network comparison [Xu06] © 2006 ACM Press