FlexPath Network Processor
|
|
|
- Claud Pitts
- 10 years ago
- Views:
Transcription
1 FlexPath Network Processor Rainer Ohlendorf Thomas Wild Andreas Herkersdorf Prof. Dr. Andreas Herkersdorf Arcisstraße München
2 Agenda FlexPath Introduction Work Packages (2nd Phase) Multi-Processor Extensions Load Balancing Techniques in FlexPath Dedicated Assignment Packet Spraying FlexPath Implementation / Demonstrator Project Highlights and Outlook FlexPath NP - 2
3 Basic Ideas of FlexPath NP Flexible packet processing paths on-chip Hardware decision on packet path depending on networking application / protocol Per-packet analysis in real-time Run-time reconfigurable rule base Supports varying traffic patterns over time Hardware-offload relieves programmable resources Ingress Hardware Processing Pipeline Egress Hardware Processing Pipeline AutoRoute-Path CPU Path FlexPath NP - 3
4 Work Packages of Second Phase MPSoC Enhancements How to notify Processing Elements (CPU, HW Acc.)? Multi-Processor Interrupt- Controller / Packet Distributor Software / Drivers Load Balancing Techniques How to get the optimal ressource utilization? Evaluation of different balancing concepts Mapping on FlexPath NP FPGA Demonstrator Fully working Network Processor on FPGA Demonstrator Plattform Demonstration tomorrow! FlexPath NP - 4
5 Multi-Processor Extensions Fully Multi-Processor ready Interrupt Controller Based on Xilinx Single Processor IntC Extended by several configuration registers (e.g. to configure queue- CPU assignment) Atomic register read out (instead of read/modify/write-back) Packet Distributor Priority based Supports Dedicated Assignment and Spraying CPU 3 CPU 2 CPU 1 Packet Distributor CPU 0 IDLE BUSY Path Dispatcher FlexPath NP - 5
6 Load Balancing Techniques Load Balancing is actually not a new problem: Cluster load balancing in HPC but also for NPUs So what's in the NP literature? Simple Hashing & Packet Spraying for "aggressive flows" (Dittmann, 2002) Adaptive HRW Hashing (Kencl, 2003) Adaptive Burst Shifting (Shi, 2005) HABS (Kencl/Shi, 2006) All known techniques applied uniformly to all packets homogeneous balancing no QoS consideration Important side effect: Flow reassignments may lead to packet reordering Packet reordering significantly reduces the efficiency of TCP (>90% of all network packets) FlexPath NP - 6
7 Load Balancing - Networking Applications IP Router: 90% of traffic uses TCP 50% of TCP packets are ACKs <10% of packets are DSCP marked Plain routing is "stateless": each packet is independent from other packets QoS behavior (DSCP) preferential treatment hot candidate for AutoRoute Security / Crypto Gateways: Either requires high processing per packet ( N x 1000 instr / pkt), or invocation of dedicated HW accelerators / coprocessors IPSec is a stateful protocol connection parameters (keys, etc.) sequence numbers processing on same instance optimal may require HW/SW partitioning and use of crypto cores IPsec Tunnel VPN GW GW Corporate Corporate NW NW 2 2 Corporate Corporate NW NW 1 1 VPN GW GW Internet Internet FlexPath NP - 7
8 Load Balancing - Stateless Networking Applications no shared connection state is maintained any processor can work on any packet dedicated assignment flow processor may be inefficient "bursty" traffic patterns lead to temporal overloads high balancing overhead needed to compensate overloads packet spraying is a "self-organizing" solution: assignment of packets to a single queue (difference to Dittmann) every idle CPU fetches packets from this queue QoS may be implemented by providing additional "high priority" queues Dittmann (2002): FlexPath (2009): Path Ctrl. Path Disp. Scheduler Packet Reordering Problem addressed in FlexPath by Path Control! FlexPath NP - 8
9 Load Balancing - Stateful Networking Applications Hashing-based assignment of flows to processors well suited for stateful processing without run-time adaptation: problem of biased hash bundle sizes (Dittmann) run-time adaptation (HRW, Kencl) relatively complex to implement HLU: simple, adaptive flow assignment hashing-based, high flow mapping persistence, low implementation complexity ρ=65% ρ=35% ρ=40% ρ=60% ρ=45% ρ=55% CPU1 CPU2 CPU1 CPU2 CPU1 CPU2 Fl. 1 Fl. 2 Fl. 4 Fl. 2 Fl. 4 Fl. 3 Fl. 4 Fl. 3 Fl. 5 Fl. 3 Fl. 5 Fl. 7 Fl. 5 Fl. 7 Fl. 6 Fl. 7 Fl. 6 Fl. 1 Fl. 6 Fl. 1 Fl. 2 FlexPath NP - 9
10 Load Balancing - System Simulation % % FlexPath: assignment for stateful traffic slightly better than Kencl's adaptive scheme Loss Rate (%) % % % % % HABS HLU spray AHH % FlexPath: assignment for stateless traffic achieves lossless operation with fewest CPUs! Number of PEs in Processor Cluster FlexPath NP - 10 all dedicated assignment schemes reach a minimum packet loss floor!
11 Average Packet Latency (µs) Technische Universität München Load Balancing - System Simulation 10,000 1, FlexPath: spraying with 2 priorities QoS guarantee HABS QoS Latency HABS IPSec Latency HABS BE Latency S&H QoS Latency S&H IPSec Latency S&H BE Latency Separating IPsec and Forwarding in FlexPath better Forwarding latency Number of PEs in Processor Cluster FlexPath NP - 11
12 FlexPath Demonstrator - Floorplan Xilinx ML410 (Virtex-4 FX60) Slices: 18,549 (73%) BRAMs: 119 (51%) PPCs: 2 (100%) EMACs: 2 (100%) Critical Path: ns => f max = MHz FlexPath NP - 12
13 FPGA Prototype - Measurement Results (1) 100% % 40 CPU Load (%) 90% 80% 70% 60% 50% 40% 30% Data Plane CPU 1 [%] IPSec [kpps] Fwd [kpps] Packet Rate (kpps) CPU Load (%) 90% 80% 70% 60% 50% 40% 30% Data Plane CPU 1 [%] IPSec [kpps] Fwd [kpps] Packet Rate (kpps) 20% Path Dispatcher 8 20% Path Dispatcher 8 10% 4 10% 4 0% ,000 1,500 2,000 2,500 3,000 3,500 4,000 IPSec Traffic Share (kbit/s) 0% ,000 1,500 2,000 2,500 3,000 3,500 4,000 IPSec Traffic Share (kbit/s) 70% CPU load with IP forwarding on single CPU core (latency: ~20 µs) small IPSec data rate dramatically increases CPU load (latency: >1 ms) IP forwarding performance declines before CPU gets saturated classification in Path Dispatcher reduces CPU load to 37% (latency: ~10 µs) IPSec packets are lost when more than 2.7 Mbps are injected FlexPath NP - 13
14 FPGA Prototype - Measurement Results (2) 100% 90% Data Plane Data Plane % 90% CPU Load (%) 80% 70% 60% 50% 40% 30% Path Dispatcher CPU 1 [%] CPU 2 [%] IPSec [kpps] Fw d [kpps] Packet Rate (kpps) CPU Load (%) 80% 70% 60% 50% 40% 30% Data Plane Path Dispatcher CPU 1 [%] IPSec [kpps] Fw d [kpps] Packet Rate (kpps) 20% 8 20% 8 10% 4 10% 4 0% ,000 1,500 2,000 2,500 3,000 3,500 4,000 IPSec Traffic Share (kbit/s) 0% ,000 1,500 2,000 2,500 3,000 3,500 4,000 IPSec Traffic Share (kbps) forwarding traffic is either processed exclusively by second CPU or traffic is sprayed among both CPUs no more forwarding traffic is lost instead of using second CPU, forwarding traffic may also be AutoRouted... throughput chart identical to 2 CPU case AutoRoute latency ~0.5 µs vs. 10 µs FlexPath NP - 14
15 Demonstrator - NPU HW Enablement Overheads Parsing / Context builder: 2660 slices 5 BRAMs Classification / Balancing: 1446 slices, 14 BRAMs Manipulation: 1615 slices 3 BRAMs MicroBlaze CPU: 1533 slices, 4 BRAMs MicroBlaze CPU MicroBlaze CPU MicroBlaze CPU Forwarding performance: up to 3.2 Gbps ( MHz), independent of packet size Forwarding performance: ~95 kpps, 366 Mbps* *assuming average packet size of 481 Byte (IMIX) FlexPath NP - 15
16 Project Highlights New Architectural Approach for Network Processors Hardware offload possibilites Run-time reconfigurable processing path assignment System adapts itself to various application requirements Application-aware Load Balancing Strategy Concept Evaluation by System-level simulations (SystemC) Prototype Implementation on FPGA and (Proof of concept) Publications Last Phase 1 Publications: International Workshop Paper 8 International Conference Papers "A Packet Classification Technique for On-Chip Processing Path Decision", WASP 2007, Salzburg 2 Journal Papers "A HW Packet Resequencer Unit for Network Processors", ARCS 2008, Dresden "A Processing Path Dispatcher in Network Processor MPSoCs", IEEE Transactions on VLSI, 10/2008 "FlexPath NP - A Network Processor Architecture with Flexible Processing Paths", SoC 2008, Tampere "An Efficient HW Architecture for Packet Re-sequencing in NP MPSoCs", DSD 2009, Patras "An Application-aware Load Balancing Strategy for NPs", HiPEAC 2010, Pisa FlexPath NP - 16
17 Outlook FlexPath NP - 17
18 Outlook Lawrence G. Roberts: "A Radical New Router" might be a FlexPath Router! Path Dispatcher determines processing path GP-Processing for unknown packets AutoRoute for known packet streams FlexPath NP - 18
19 Thank you! FlexPath NP - 19
Cisco Integrated Services Routers Performance Overview
Integrated Services Routers Performance Overview What You Will Learn The Integrated Services Routers Generation 2 (ISR G2) provide a robust platform for delivering WAN services, unified communications,
Software Datapath Acceleration for Stateless Packet Processing
June 22, 2010 Software Datapath Acceleration for Stateless Packet Processing FTF-NET-F0817 Ravi Malhotra Software Architect Reg. U.S. Pat. & Tm. Off. BeeKit, BeeStack, CoreNet, the Energy Efficient Solutions
Getting the most TCP/IP from your Embedded Processor
Getting the most TCP/IP from your Embedded Processor Overview Introduction to TCP/IP Protocol Suite Embedded TCP/IP Applications TCP Termination Challenges TCP Acceleration Techniques 2 Getting the most
Definition of a White Box. Benefits of White Boxes
Smart Network Processing for White Boxes Sandeep Shah Director, Systems Architecture EZchip Technologies [email protected] Linley Carrier Conference June 10-11, 2014 Santa Clara, CA 1 EZchip Overview
TCP Offload Engines. As network interconnect speeds advance to Gigabit. Introduction to
Introduction to TCP Offload Engines By implementing a TCP Offload Engine (TOE) in high-speed computing environments, administrators can help relieve network bottlenecks and improve application performance.
Architectures and Platforms
Hardware/Software Codesign Arch&Platf. - 1 Architectures and Platforms 1. Architecture Selection: The Basic Trade-Offs 2. General Purpose vs. Application-Specific Processors 3. Processor Specialisation
Multiprocessor System-on-Chip
http://www.artistembedded.org/fp6/ ARTIST Workshop at DATE 06 W4: Design Issues in Distributed, CommunicationCentric Systems Modelling Networked Embedded Systems: From MPSoC to Sensor Networks Jan Madsen
Foundation for High-Performance, Open and Flexible Software and Services in the Carrier Network. Sandeep Shah Director, Systems Architecture EZchip
Foundation for High-Performance, Open and Flexible Software and Services in the Carrier Network Sandeep Shah Director, Systems Architecture EZchip Linley Carrier Conference June 10, 2015 1 EZchip Overview
Networking Virtualization Using FPGAs
Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical and Computer Engineering University of Massachusetts,
Reconfig'09 Cancun, Mexico
Reconfig'09 Cancun, Mexico New OPBHW Interface for Real-Time Partial Reconfiguration of FPGA Julien Delorme, Amor Nafkha, Pierre Leray, Christophe Moy SUPELEC/IETR 10 December 2009 SUPELEC - Campus de
Architecture of distributed network processors: specifics of application in information security systems
Architecture of distributed network processors: specifics of application in information security systems V.Zaborovsky, Politechnical University, Sait-Petersburg, Russia [email protected] 1. Introduction Modern
Intel DPDK Boosts Server Appliance Performance White Paper
Intel DPDK Boosts Server Appliance Performance Intel DPDK Boosts Server Appliance Performance Introduction As network speeds increase to 40G and above, both in the enterprise and data center, the bottlenecks
NFV Network and Compute Intensive H/W Acceleration (using SDN/PI forwarding)
NFV Network and Compute Intensive H/W Acceleration (using SDN/PI forwarding) NFV PoC (Proof of Concept) #21 http://nfvwiki.etsi.org/index.php?title=network_intensive_and_compute_intensive_hardware_ Acceleration
Exploiting Stateful Inspection of Network Security in Reconfigurable Hardware
Exploiting Stateful Inspection of Network Security in Reconfigurable Hardware Shaomeng Li, Jim Tørresen, Oddvar Søråsen Department of Informatics University of Oslo N-0316 Oslo, Norway {shaomenl, jimtoer,
TCP Servers: Offloading TCP Processing in Internet Servers. Design, Implementation, and Performance
TCP Servers: Offloading TCP Processing in Internet Servers. Design, Implementation, and Performance M. Rangarajan, A. Bohra, K. Banerjee, E.V. Carrera, R. Bianchini, L. Iftode, W. Zwaenepoel. Presented
DynaCORE Coprocessor
DynaCORE Coprocessor Dynamically Reconfigurable Coprocessor for Network Processors Carsten Albrecht, Roman Koch, Christoph Osterloh, Thilo Pionteck,, Erik Maehle Universität t zu LübeckL Head: Prof. Dr.-Ing
IP videoconferencing solution with ProCurve switches and Tandberg terminals
An HP ProCurve Networking Application Note IP videoconferencing solution with ProCurve switches and Tandberg terminals Contents 1. Introduction... 3 2. Architecture... 3 3. Videoconferencing traffic and
Optimizing TCP Forwarding
Optimizing TCP Forwarding Vsevolod V. Panteleenko and Vincent W. Freeh TR-2-3 Department of Computer Science and Engineering University of Notre Dame Notre Dame, IN 46556 {vvp, vin}@cse.nd.edu Abstract
Design and Implementation of an On-Chip timing based Permutation Network for Multiprocessor system on Chip
Design and Implementation of an On-Chip timing based Permutation Network for Multiprocessor system on Chip Ms Lavanya Thunuguntla 1, Saritha Sapa 2 1 Associate Professor, Department of ECE, HITAM, Telangana
Quality of Service Analysis of site to site for IPSec VPNs for realtime multimedia traffic.
Quality of Service Analysis of site to site for IPSec VPNs for realtime multimedia traffic. A Network and Data Link Layer infrastructure Design to Improve QoS in Voice and video Traffic Jesús Arturo Pérez,
Congestion Control Review. 15-441 Computer Networking. Resource Management Approaches. Traffic and Resource Management. What is congestion control?
Congestion Control Review What is congestion control? 15-441 Computer Networking What is the principle of TCP? Lecture 22 Queue Management and QoS 2 Traffic and Resource Management Resource Management
Data and Control Plane Interconnect solutions for SDN & NFV Networks Raghu Kondapalli August 2014
Data and Control Plane Interconnect solutions for SDN & NFV Networks Raghu Kondapalli August 2014 Title & Abstract Title: Data & Control Plane Interconnect for SDN & NFV networks Abstract: Software defined
Dynamic Network Resources Allocation in Grids through a Grid Network Resource Broker
INGRID 2007 Instrumenting the GRID Second International Workshop on Distributed Cooperative Laboratories Session 2: Networking for the GRID Dynamic Network Resources Allocation in Grids through a Grid
4 Internet QoS Management
4 Internet QoS Management Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology [email protected] September 2008 Overview Network Management Performance Mgt QoS Mgt Resource Control
Operating System Support for Multiprocessor Systems-on-Chip
Operating System Support for Multiprocessor Systems-on-Chip Dr. Gabriel marchesan almeida Agenda. Introduction. Adaptive System + Shop Architecture. Preliminary Results. Perspectives & Conclusions Dr.
Where IT perceptions are reality. Test Report. OCe14000 Performance. Featuring Emulex OCe14102 Network Adapters Emulex XE100 Offload Engine
Where IT perceptions are reality Test Report OCe14000 Performance Featuring Emulex OCe14102 Network Adapters Emulex XE100 Offload Engine Document # TEST2014001 v9, October 2014 Copyright 2014 IT Brand
MLPPP Deployment Using the PA-MC-T3-EC and PA-MC-2T3-EC
MLPPP Deployment Using the PA-MC-T3-EC and PA-MC-2T3-EC Overview Summary The new enhanced-capability port adapters are targeted to replace the following Cisco port adapters: 1-port T3 Serial Port Adapter
Lustre Networking BY PETER J. BRAAM
Lustre Networking BY PETER J. BRAAM A WHITE PAPER FROM CLUSTER FILE SYSTEMS, INC. APRIL 2007 Audience Architects of HPC clusters Abstract This paper provides architects of HPC clusters with information
Voice over Internet Protocol (VoIP) systems can be built up in numerous forms and these systems include mobile units, conferencing units and
1.1 Background Voice over Internet Protocol (VoIP) is a technology that allows users to make telephone calls using a broadband Internet connection instead of an analog phone line. VoIP holds great promise
Intel Network Builders: Lanner and Intel Building the Best Network Security Platforms
Solution Brief Intel Xeon Processors Lanner Intel Network Builders: Lanner and Intel Building the Best Network Security Platforms Internet usage continues to rapidly expand and evolve, and with it network
Network Simulation Traffic, Paths and Impairment
Network Simulation Traffic, Paths and Impairment Summary Network simulation software and hardware appliances can emulate networks and network hardware. Wide Area Network (WAN) emulation, by simulating
Cut Network Security Cost in Half Using the Intel EP80579 Integrated Processor for entry-to mid-level VPN
Cut Network Security Cost in Half Using the Intel EP80579 Integrated Processor for entry-to mid-level VPN By Paul Stevens, Advantech Network security has become a concern not only for large businesses,
Introduction VOIP in an 802.11 Network VOIP 3
Solutions to Performance Problems in VOIP over 802.11 Wireless LAN Wei Wang, Soung C. Liew Presented By Syed Zaidi 1 Outline Introduction VOIP background Problems faced in 802.11 Low VOIP capacity in 802.11
Requirements of Voice in an IP Internetwork
Requirements of Voice in an IP Internetwork Real-Time Voice in a Best-Effort IP Internetwork This topic lists problems associated with implementation of real-time voice traffic in a best-effort IP internetwork.
OpTiMSoC Build Your Own System-on-Chip!
OpTiMSoC Build Your Own System-on-Chip! FOSDEM 2014 February 2nd 2014 Institute for Integrated Systems Prof. Dr. Andreas Herkersdorf Arcisstraße 21 80333 München Germany http://www.lis.ei.tum.de 2 Photo
A Generic Network Interface Architecture for a Networked Processor Array (NePA)
A Generic Network Interface Architecture for a Networked Processor Array (NePA) Seung Eun Lee, Jun Ho Bahn, Yoon Seok Yang, and Nader Bagherzadeh EECS @ University of California, Irvine Outline Introduction
Performance Evaluation of Linux Bridge
Performance Evaluation of Linux Bridge James T. Yu School of Computer Science, Telecommunications, and Information System (CTI) DePaul University ABSTRACT This paper studies a unique network feature, Ethernet
Parallel Firewalls on General-Purpose Graphics Processing Units
Parallel Firewalls on General-Purpose Graphics Processing Units Manoj Singh Gaur and Vijay Laxmi Kamal Chandra Reddy, Ankit Tharwani, Ch.Vamshi Krishna, Lakshminarayanan.V Department of Computer Engineering
Master Course Computer Networks IN2097
Chair for Network Architectures and Services Prof. Carle Department for Computer Science TU München Master Course Computer Networks IN2097 Prof. Dr.-Ing. Georg Carle Christian Grothoff, Ph.D. Chair for
MMPTCP: A Novel Transport Protocol for Data Centre Networks
MMPTCP: A Novel Transport Protocol for Data Centre Networks Morteza Kheirkhah FoSS, Department of Informatics, University of Sussex Modern Data Centre Networks FatTree It provides full bisection bandwidth
Performance of Software Switching
Performance of Software Switching Based on papers in IEEE HPSR 2011 and IFIP/ACM Performance 2011 Nuutti Varis, Jukka Manner Department of Communications and Networking (COMNET) Agenda Motivation Performance
Improving the Performance of TCP Using Window Adjustment Procedure and Bandwidth Estimation
Improving the Performance of TCP Using Window Adjustment Procedure and Bandwidth Estimation R.Navaneethakrishnan Assistant Professor (SG) Bharathiyar College of Engineering and Technology, Karaikal, India.
Programmable Networking with Open vswitch
Programmable Networking with Open vswitch Jesse Gross LinuxCon September, 2013 2009 VMware Inc. All rights reserved Background: The Evolution of Data Centers Virtualization has created data center workloads
LogiCORE IP AXI Performance Monitor v2.00.a
LogiCORE IP AXI Performance Monitor v2.00.a Product Guide Table of Contents IP Facts Chapter 1: Overview Target Technology................................................................. 9 Applications......................................................................
Chapter 7 outline. 7.5 providing multiple classes of service 7.6 providing QoS guarantees RTP, RTCP, SIP. 7: Multimedia Networking 7-71
Chapter 7 outline 7.1 multimedia networking applications 7.2 streaming stored audio and video 7.3 making the best out of best effort service 7.4 protocols for real-time interactive applications RTP, RTCP,
Layer 2 Network Encryption where safety is not an optical illusion Marko Bobinac SafeNet PreSales Engineer
Layer 2 Network Encryption where safety is not an optical illusion Marko Bobinac SafeNet PreSales Engineer Layer 2 Network Encryption where safety is not an optical illusion Todays Agenda Fibre is safe
Mobility research group
Mobility research group professor Hannu H. Kari Helsinki University (HUT) Department of Computer Science and Engineering Laboratory for Theoretical Computer Science Hannu H. Kari/HUT/CS/TCS Page 1/36 Research
PC-over-IP Protocol Virtual Desktop Network Design Checklist. TER1105004 Issue 2
PC-over-IP Protocol Virtual Desktop Network Design Checklist TER1105004 Issue 2 Teradici Corporation #101-4621 Canada Way, Burnaby, BC V5G 4X8 Canada p +1 604 451 5800 f +1 604 451 5818 www.teradici.com
DS3 Performance Scaling on ISRs
This document provides guidelines on scaling the performance of DS3 interface (NM-1T3/E3) for the Cisco 2811/2821/2851/3825/3845 Integrated Services Routers. The analysis provides following test results;
Network Function Virtualization
Intel Network Builders Reference Architecture Network Function Virtualization Network Function Virtualization Quality of Service in Broadband Remote Access Servers with Linux* and Intel Architecture Audience
Accelerating 4G Network Performance
WHITE PAPER Accelerating 4G Network Performance OFFLOADING VIRTUALIZED EPC TRAFFIC ON AN OVS-ENABLED NETRONOME INTELLIGENT SERVER ADAPTER NETRONOME AGILIO INTELLIGENT SERVER ADAPTERS PROVIDE A 5X INCREASE
A Low Latency Library in FPGA Hardware for High Frequency Trading (HFT)
A Low Latency Library in FPGA Hardware for High Frequency Trading (HFT) John W. Lockwood, Adwait Gupte, Nishit Mehta (Algo-Logic Systems) Michaela Blott, Tom English, Kees Vissers (Xilinx) August 22, 2012,
QoS in PAN-OS. Tech Note PAN-OS 4.1. Revision A 2011, Palo Alto Networks, Inc.
QoS in PAN-OS Tech Note PAN-OS 4.1 Revision A Contents Overview... 3 Why QoS... 3 Learn about Applications in your Network... 3 Terms and Concepts... 3 Classification... 3 Priority Queues... 4 Limiting
Achieving Low-Latency Security
Achieving Low-Latency Security In Today's Competitive, Regulatory and High-Speed Transaction Environment Darren Turnbull, VP Strategic Solutions - Fortinet Agenda 1 2 3 Firewall Architecture Typical Requirements
Seeking Opportunities for Hardware Acceleration in Big Data Analytics
Seeking Opportunities for Hardware Acceleration in Big Data Analytics Paul Chow High-Performance Reconfigurable Computing Group Department of Electrical and Computer Engineering University of Toronto Who
Boosting Data Transfer with TCP Offload Engine Technology
Boosting Data Transfer with TCP Offload Engine Technology on Ninth-Generation Dell PowerEdge Servers TCP/IP Offload Engine () technology makes its debut in the ninth generation of Dell PowerEdge servers,
OPTIMIZE DMA CONFIGURATION IN ENCRYPTION USE CASE. Guillène Ribière, CEO, System Architect
OPTIMIZE DMA CONFIGURATION IN ENCRYPTION USE CASE Guillène Ribière, CEO, System Architect Problem Statement Low Performances on Hardware Accelerated Encryption: Max Measured 10MBps Expectations: 90 MBps
Leveraging Advanced Load Sharing for Scaling Capacity to 100 Gbps and Beyond
Leveraging Advanced Load Sharing for Scaling Capacity to 100 Gbps and Beyond Ananda Rajagopal Product Line Manager Service Provider Solutions Foundry Networks [email protected] Agenda 2 Why Load
基 於 SDN 與 可 程 式 化 硬 體 架 構 之 雲 端 網 路 系 統 交 換 器
基 於 SDN 與 可 程 式 化 硬 體 架 構 之 雲 端 網 路 系 統 交 換 器 楊 竹 星 教 授 國 立 成 功 大 學 電 機 工 程 學 系 Outline Introduction OpenFlow NetFPGA OpenFlow Switch on NetFPGA Development Cases Conclusion 2 Introduction With the proposal
Open Flow Controller and Switch Datasheet
Open Flow Controller and Switch Datasheet California State University Chico Alan Braithwaite Spring 2013 Block Diagram Figure 1. High Level Block Diagram The project will consist of a network development
Software Stacks for Mixed-critical Applications: Consolidating IEEE 802.1 AVB and Time-triggered Ethernet in Next-generation Automotive Electronics
Software : Consolidating IEEE 802.1 AVB and Time-triggered Ethernet in Next-generation Automotive Electronics Soeren Rumpf Till Steinbach Franz Korf Thomas C. Schmidt [email protected] September
Bivio 7000 Series Network Appliance Platforms
W H I T E P A P E R Bivio 7000 Series Network Appliance Platforms Uncompromising performance. Unmatched flexibility. Uncompromising performance. Unmatched flexibility. The Bivio 7000 Series Programmable
Using a Generic Plug and Play Performance Monitor for SoC Verification
Using a Generic Plug and Play Performance Monitor for SoC Verification Dr. Ambar Sarkar Kaushal Modi Janak Patel Bhavin Patel Ajay Tiwari Accellera Systems Initiative 1 Agenda Introduction Challenges Why
Frequently Asked Questions
Frequently Asked Questions 1. Q: What is the Network Data Tunnel? A: Network Data Tunnel (NDT) is a software-based solution that accelerates data transfer in point-to-point or point-to-multipoint network
A Preferred Service Architecture for Payload Data Flows. Ray Gilstrap, Thom Stone, Ken Freeman
A Preferred Service Architecture for Payload Data Flows Ray Gilstrap, Thom Stone, Ken Freeman NASA Research and Engineering Network NASA Advanced Supercomputing Division NASA Ames Research Center Outline
Deploying Silver Peak VXOA with EMC Isilon SyncIQ. February 2012. www.silver-peak.com
Deploying Silver Peak VXOA with EMC Isilon SyncIQ February 2012 www.silver-peak.com Table of Contents Table of Contents Overview... 3 Solution Components... 3 EMC Isilon...3 Isilon SyncIQ... 3 Silver Peak
Kirchhoff Institute for Physics Heidelberg
Kirchhoff Institute for Physics Heidelberg Norbert Abel FPGA: (re-)configuration and embedded Linux 1 Linux Front-end electronics based on ADC and digital signal processing Slow control implemented as
Use Cases for the NPS the Revolutionary C-Programmable 7-Layer Network Processor. Sandeep Shah Director, Systems Architecture EZchip
Use Cases for the NPS the Revolutionary C-Programmable 7-Layer Network Processor Sandeep Shah Director, Systems Architecture EZchip Linley Processor Conference Oct. 6-7, 2015 1 EZchip Overview Fabless
Steve Worrall Systems Engineer. [email protected]
Steve Worrall Systems Engineer [email protected] Agenda 100GbE Load sharing/link aggregation Foundry Direct Routing 2 100 Gigabit Ethernet 3 Current Status PAR approved, 802.3ba task force set up
Outline. Introduction. Multiprocessor Systems on Chip. A MPSoC Example: Nexperia DVP. A New Paradigm: Network on Chip
Outline Modeling, simulation and optimization of Multi-Processor SoCs (MPSoCs) Università of Verona Dipartimento di Informatica MPSoCs: Multi-Processor Systems on Chip A simulation platform for a MPSoC
Configuring an efficient QoS Map
Configuring an efficient QoS Map This document assumes the reader has experience configuring quality of service (QoS) maps and working with traffic prioritization. Before reading this document, it is advisable
WhitePaper: XipLink Real-Time Optimizations
WhitePaper: XipLink Real-Time Optimizations XipLink Real Time Optimizations Header Compression, Packet Coalescing and Packet Prioritization Overview XipLink Real Time ( XRT ) is a new optimization capability
Improving Quality of Service
Improving Quality of Service Using Dell PowerConnect 6024/6024F Switches Quality of service (QoS) mechanisms classify and prioritize network traffic to improve throughput. This article explains the basic
Requirements for Simulation and Modeling Tools. Sally Floyd NSF Workshop August 2005
Requirements for Simulation and Modeling Tools Sally Floyd NSF Workshop August 2005 Outline for talk: Requested topic: the requirements for simulation and modeling tools that allow one to study, design,
Design Patterns for Packet Processing Applications on Multi-core Intel Architecture Processors
White Paper Cristian F. Dumitrescu Software Engineer Intel Corporation Design Patterns for Packet Processing Applications on Multi-core Intel Architecture Processors December 2008 321058 Executive Summary
Effects of Filler Traffic In IP Networks. Adam Feldman April 5, 2001 Master s Project
Effects of Filler Traffic In IP Networks Adam Feldman April 5, 2001 Master s Project Abstract On the Internet, there is a well-documented requirement that much more bandwidth be available than is used
A Transport Protocol for Multimedia Wireless Sensor Networks
A Transport Protocol for Multimedia Wireless Sensor Networks Duarte Meneses, António Grilo, Paulo Rogério Pereira 1 NGI'2011: A Transport Protocol for Multimedia Wireless Sensor Networks Introduction Wireless
White Paper. Accelerating VMware vsphere Replication with Silver Peak
Accelerating VMware vsphere Replication with Silver Peak Accelerating VMware vsphere Replication with Silver Peak Contents Overview...3 The Challenge of Replicating Over Distance...3 VMware vsphere Replication
Sockets vs. RDMA Interface over 10-Gigabit Networks: An In-depth Analysis of the Memory Traffic Bottleneck
Sockets vs. RDMA Interface over 1-Gigabit Networks: An In-depth Analysis of the Memory Traffic Bottleneck Pavan Balaji Hemal V. Shah D. K. Panda Network Based Computing Lab Computer Science and Engineering
Data Center and Cloud Computing Market Landscape and Challenges
Data Center and Cloud Computing Market Landscape and Challenges Manoj Roge, Director Wired & Data Center Solutions Xilinx Inc. #OpenPOWERSummit 1 Outline Data Center Trends Technology Challenges Solution
VMWARE WHITE PAPER 1
1 VMWARE WHITE PAPER Introduction This paper outlines the considerations that affect network throughput. The paper examines the applications deployed on top of a virtual infrastructure and discusses the
40G MACsec Encryption in an FPGA
40G MACsec Encryption in an FPGA Dr Tom Kean, Managing Director, Algotronix Ltd, 130-10 Calton Road, Edinburgh EH8 8JQ United Kingdom Tel: +44 131 556 9242 Email: [email protected] February 2012 1 MACsec
Open vswitch and the Intelligent Edge
Open vswitch and the Intelligent Edge Justin Pettit OpenStack 2014 Atlanta 2014 VMware Inc. All rights reserved. Hypervisor as Edge VM1 VM2 VM3 Open vswitch Hypervisor 2 An Intelligent Edge We view the
QoS (Quality of Service)
QoS (Quality of Service) QoS function helps you to control your network traffic for each application from LAN (Ethernet and/or Wireless) to WAN (Internet). It facilitates you to control the different quality
GATEWAY TRAFFIC COMPRESSION
GATEWAY TRAFFIC COMPRESSION Name: Devaraju. R Guide Name: Dr. C. Puttamadappa Research Centre: S.J.B. Institute of Technology Year of Registration: May 2009 Devaraju R 1 1. ABSTRACT: In recent years with
Investigation and Comparison of MPLS QoS Solution and Differentiated Services QoS Solutions
Investigation and Comparison of MPLS QoS Solution and Differentiated Services QoS Solutions Steve Gennaoui, Jianhua Yin, Samuel Swinton, and * Vasil Hnatyshin Department of Computer Science Rowan University
VegaStream Information Note Considerations for a VoIP installation
VegaStream Information Note Considerations for a VoIP installation To get the best out of a VoIP system, there are a number of items that need to be considered before and during installation. This document
Broadcom Ethernet Network Controller Enhanced Virtualization Functionality
White Paper Broadcom Ethernet Network Controller Enhanced Virtualization Functionality Advancements in VMware virtualization technology coupled with the increasing processing capability of hardware platforms
Putting it on the NIC: A Case Study on application offloading to a Network Interface Card (NIC)
This full text paper was peer reviewed at the direction of IEEE Communications Society subject matter experts for publication in the IEEE CCNC 2006 proceedings. Putting it on the NIC: A Case Study on application
ReCoSoC'11 Montpellier, France. Implementation Scenario for Teaching Partial Reconfiguration of FPGA
ReCoSoC'11 Montpellier, France Implementation Scenario for Teaching Partial Reconfiguration of FPGA Pierre Leray, Amor Nafkha, Christophe Moy SUPELEC/IETR 22 June 2011 SUPELEC - Campus de Rennes - France
Application Delivery Testing at 100Gbps and Beyond
Application Delivery Testing at 100Gbps and Beyond The Need for Speed 10 Gigabit Ethernet (GE) rapidly became the technology of choice for high speed connections to servers and network devices. Advancements
High-performance vswitch of the user, by the user, for the user
A bird in cloud High-performance vswitch of the user, by the user, for the user Yoshihiro Nakajima, Wataru Ishida, Tomonori Fujita, Takahashi Hirokazu, Tomoya Hibi, Hitoshi Matsutahi, Katsuhiro Shimano
Chapter 5 Configuring QoS
Chapter 5 Configuring QoS Configuring the Basic and Advanced QoS Settings The navigation pane at the top of the web browser interface contains a QoS tab that enables you to manage your FS700TS Smart Switch
SILVER PEAK ACCELERATION WITH EMC VSPEX PRIVATE CLOUD WITH RECOVERPOINT FOR VMWARE VSPHERE
VSPEX IMPLEMENTATION GUIDE SILVER PEAK ACCELERATION WITH EMC VSPEX PRIVATE CLOUD WITH RECOVERPOINT FOR VMWARE VSPHERE Silver Peak Abstract This Implementation Guide describes the deployment of Silver Peak
