Topology Awareness in the Tofu Interconnect Series
|
|
- Rosamond Ferguson
- 6 years ago
- Views:
Transcription
1 Topology Awareness in the Tofu Interconnect Series Yuichiro Ajima Senior Architect Next Generation Technical Computing Unit Fujitsu Limited June 23rd, 2016, ExaComm2016 Workshop 0
2 Introduction Networks are getting larger Systems have tens of thousands of nodes Highly scalable network topologies e.g. multi-dimensional torus, dragonfly Channel bisection < 1/2 node count Bisection bandwidth < injection bandwidth Issue: communication algorithms Existing general algorithms will be inefficient (video) MPI_Bcast on the K computer Topology-aware optimization is required This talk presents the topologyawareness design of the Tofu interconnect series, and visualizes the achievements June 23rd, 2016, ExaComm2016 Workshop 1
3 Tofu Interconnect Series Highly scalable 6D mesh/torus network Tofu interconnect Developed for the K computer Tofu interconnect 2 SoC integration and optical transceiver Another version is being developed for the Post-K machine Tofu interconnect Tofu interconnect June 23rd, 2016, ExaComm2016 Workshop 2
4 Index Topology-aware task allocation Topology-aware optimization Tuned collective communication library Low-level features of the network interface Topology-aware algorithms (for long messages) June 23rd, 2016, ExaComm2016 Workshop 3
5 6D Mesh/Torus Network Dimension labels: XYZABC Lengths of A-, B-, and C-axes are fixed; 2, 3 and 2 Z B A C X Y Conceptual Model June 23rd, 2016, ExaComm2016 Workshop 4
6 Task Allocation and Rank Mapping A rectangular region in the physical 6D network for each task Contiguous in the XYZ-axes and not divided in the ABC-axes Virtual torus rank mapping Users defined the logical shape of the task as a virtual 1D/2D/3D torus The length for each dimension is defined in the batch script Example: using the full system of the K computer ( ) Virtual 1D torus Virtual 2D torus Virtual 3D torus #PJM -L "node=82944 #PJM -L "node=576x144 #PJM -L "node=54x48x32 A rank number reflects the logical coordinates of process Embedding a virtual torus into a physical rectangular region A nearest neighbor node in the virtual torus space is guaranteed to be a nearest neighbor node in the physical 6D network The task scheduler may add padding nodes and rotate the shape to increase the chance for allocation June 23rd, 2016, ExaComm2016 Workshop 5
7 Index Topology-aware task allocation Topology-aware optimization Tuned collective communication library Low-level features of the network interface Topology-aware algorithms (for long messages) June 23rd, 2016, ExaComm2016 Workshop 6
8 Manual Tuning with Profiling Dynamic profiling Enable profiling during the application s communication activity The profiler periodically samples performance analysis (PA) counters The profiling log is saved to storage after profiling PA counters of the Tofu interconnect Each counter is a hardware 64-bit register A set of PA counters is provided for each port of the router Bytes transferred, busy cycles, idle cycles, packet buffer depleted cycles, etc. Visualization Users find bottlenecks Manual performance tuning MPI and task allocation options Communication algorithms Screen shot of the Fujitsu Profiler June 23rd, 2016, ExaComm2016 Workshop 7
9 Automatic Tuning without Profiling Custom rank mapping order A default rank mapping order often affects the communication performance in a multi-dimensional torus One of the optimization candidates right after executing a vanilla code RMATT (Rank Mapping Automatic Tuning Tool) Requires no profiling log but execution statistics Calculates rank mapping order using the simulated annealing algorithm Users input the shape of torus and a list of communication pattern Each line of the list includes source and destination pair of processes and total amount of transferred data during a task MPI Application Configuration MPI option 32x32x16 RMATT (machine file) Input 0 (0,0,0) Output 1 (0,0,1) Comm. Pattern 2 (0,1,0) Rank Mapping Optimization 0 1 1kB 0 4 2kB 1 0 1kB MPI rank mapping file Execution environment June 23rd, 2016, ExaComm2016 Workshop 8
10 Evaluations of Improvement by RMATT NAS Parallel Benchmark (CG) Case 1: NPROCS=1024, CLASS=B, 2D Torus 32x32 Default(x-y order) Rank map optimized by RMATT Default RMATT Execution time 1.33 sec 1.24 sec 7% improved (includes calculation time) Case 2: NPROCS=8192, CLASS=D, 2D Torus 128x64 Default RMATT Execution time sec 9.98 sec 9% improved (includes calculation time) June 23rd, 2016, ExaComm2016 Workshop 9
11 Index Topology-aware task allocation Topology-aware performance optimization Tuned collective communication library Low-level features of the network interface Topology-aware algorithms (for long messages) June 23rd, 2016, ExaComm2016 Workshop 10
12 Low-Level Network Interface Fujitsu s FJMPI is developed based on Open MPI The tuned collective communication library bypasses the Open MPI stack and uses the low-level network interface directly MPI Interface Layer tuned COLL ob1 PML bypass tofu LLP r2 BML tofu BTL bypass tofu COMMON Tofu Library Tofu Interconnect June 23rd, 2016, ExaComm2016 Workshop 11
13 Simultaneous Communication Four RDMA engines (Tofu network interfaces) per node The peak injection bandwidth of each TNI is 5 GB/s for Tofu1 and 12.5 GB/s for Tofu2. The point-to-point messaging layer of the FJMPI uses four TNIs in a round-robin manner The tuned COLL identifies four TNIs to avoid a collision of the destination TNI CPU RDMA Engine 0 RDMA Engine 1 RDMA Engine 2 RDMA Engine 3 link 0 link 1 link 2 link 3 link 4 link 5 link 6 link 7 link 8 link 9 XYZ ABC June 23rd, 2016, ExaComm2016 Workshop 12
14 Injection Rate Control Latency (us) Contention depletes packet buffers and causes congestion Congestion can be avoided by reducing the injection rate Latencies of simultaneous 8-hop data transfer on a 32-node ring size Optimized packet gap Congestion Low injection rate Packet gap (multiples of MTU) June 23rd, 2016, ExaComm2016 Workshop 13
15 Index Topology-aware task allocation Topology-aware performance optimization Tuned collective communication library Low-level features of the network interface Topology-aware algorithms (for long messages) June 23rd, 2016, ExaComm2016 Workshop 14
16 Overview Assumed environment The shape of the communicator is a mesh or a torus One process per node participates in inter-process communication When there are multiple processes in a node, collective communication is fanned out through shared memory Optimization policies (for long messages only) Use multiple network interfaces Communicate with nearest neighbor nodes Control the injection rate for communication with far nodes Algorithms implemented in the FJMPI Triple trinary tree for broadcast and reduce Three-phase quad rings for gather Uniformly overlaid symmetrical pattern for all-to-all June 23rd, 2016, ExaComm2016 Workshop 15
17 Triple Trinary Tree Broadcasts data by dividing into three parts and simultaneously propagating each part via a different path Each path is a spanning trinary tree, and the three trees share no directed edges By reversing the direction of all edges, data can be reduced June 23rd, 2016, ExaComm2016 Workshop 16
18 MPI_Allreduce Two phases First phase reduce data using triple trinary trees Second phase broadcast the reduced data using the reversed trees (video) MPI_Allreduce on the K computer June 23rd, 2016, ExaComm2016 Workshop 17
19 Three-Phase Quad Rings The ring all-gather algorithm transfers data cyclically A C D A B D A B C B C D Divides data into four parts, and simultaneously transfers each part along a different direction Phase 1 Phase 2 Phase 3 June 23rd, 2016, ExaComm2016 Workshop 18
20 MPI_Allgather The three-phase quad ring algorithm (video) MPI_Allgather on the K computer June 23rd, 2016, ExaComm2016 Workshop 19
21 Uniformly Overlaid Symmetrical Pattern (1) A multi-phase all-to-all communication algorithm In each phase, each process transfers data to multiple processes that have symmetrical relative coordinates Each phase is divided into sub-phases June 23rd, 2016, ExaComm2016 Workshop 20
22 Uniformly Overlaid Symmetrical Pattern (2) For each phase, communication patterns of all processes are uniform For each sub-phase, the number of colliding transfers is the same as the hop count of a transfer Injection rate control for each sub-phase avoids congestion and increases effective throughput June 23rd, 2016, ExaComm2016 Workshop 21
23 MPI_Alltoall Uniformly overlaid symmetrical pattern algorithm (video) MPI_Alltoall on the K computer Left: the uniformly overlaid symmetrical pattern algorithm Right: default algorithm of the Open MPI June 23rd, 2016, ExaComm2016 Workshop 22
24 Summary Topology awareness design of the Tofu series Task allocation Virtual torus rank mapping Performance optimization Tofu PA counters for manual tuning with the Fujitsu Profiler Rank Mapping Automatic Tuning Tool (RMATT) Tuned collective communication library in the FJMPI Utilizes low-level network features Simultaneous communication Injection rate control Topology-aware algorithms for long messages Triple trinary tree algorithm for broadcast and reduce Three-phase quad rings algorithm for gather Uniformly overlaid symmetric pattern algorithm for all-to-all June 23rd, 2016, ExaComm2016 Workshop 23
25 24
Programming for Fujitsu Supercomputers
Programming for Fujitsu Supercomputers Koh Hotta The Next Generation Technical Computing Fujitsu Limited To Programmers who are busy on their own research, Fujitsu provides environments for Parallel Programming
More informationPRIMEHPC FX10: Advanced Software
PRIMEHPC FX10: Advanced Software Koh Hotta Fujitsu Limited System Software supports --- Stable/Robust & Low Overhead Execution of Large Scale Programs Operating System File System Program Development for
More informationThe Tofu Interconnect D
The Tofu Interconnect D 11 September 2018 Yuichiro Ajima, Takahiro Kawashima, Takayuki Okamoto, Naoyuki Shida, Kouichi Hirai, Toshiyuki Shimizu, Shinya Hiramoto, Yoshiro Ikeda, Takahide Yoshikawa, Kenji
More informationCurrent and Future Challenges of the Tofu Interconnect for Emerging Applications
Current and Future Challenges of the Tofu Interconnect for Emerging Applications Yuichiro Ajima Senior Architect Next Generation Technical Computing Unit Fujitsu Limited June 22, 2017, ExaComm 2017 Workshop
More informationThe Tofu Interconnect 2
The Tofu Interconnect 2 Yuichiro Ajima, Tomohiro Inoue, Shinya Hiramoto, Shun Ando, Masahiro Maeda, Takahide Yoshikawa, Koji Hosoe, and Toshiyuki Shimizu Fujitsu Limited Introduction Tofu interconnect
More informationTechnical Computing Suite supporting the hybrid system
Technical Computing Suite supporting the hybrid system Supercomputer PRIMEHPC FX10 PRIMERGY x86 cluster Hybrid System Configuration Supercomputer PRIMEHPC FX10 PRIMERGY x86 cluster 6D mesh/torus Interconnect
More informationTofu Interconnect 2: System-on-Chip Integration of High-Performance Interconnect
Tofu Interconnect 2: System-on-Chip Integration of High-Performance Interconnect Yuichiro Ajima, Tomohiro Inoue, Shinya Hiramoto, Shunji Uno, Shinji Sumimoto, Kenichi Miura, Naoyuki Shida, Takahiro Kawashima,
More informationTofu Interconnect 2: System-on-Chip Integration of High-Performance Interconnect
Tofu Interconnect 2: System-on-Chip Integration of High-Performance Interconnect Yuichiro Ajima, Tomohiro Inoue, Shinya Hiramoto, Shunji Uno, Shinji Sumimoto, Kenichi Miura, Naoyuki Shida, Takahiro Kawashima,
More informationInterconnection Networks: Topology. Prof. Natalie Enright Jerger
Interconnection Networks: Topology Prof. Natalie Enright Jerger Topology Overview Definition: determines arrangement of channels and nodes in network Analogous to road map Often first step in network design
More informationAdvanced Software for the Supercomputer PRIMEHPC FX10. Copyright 2011 FUJITSU LIMITED
Advanced Software for the Supercomputer PRIMEHPC FX10 System Configuration of PRIMEHPC FX10 nodes Login Compilation Job submission 6D mesh/torus Interconnect Local file system (Temporary area occupied
More informationICC: An Interconnect Controller for the Tofu Interconnect Architecture
: An Interconnect Controller for the Tofu Interconnect Architecture August 24, 2010 Takashi Toyoshima Next Generation Technical Computing Unit Fujitsu Limited Background Requirements for Supercomputing
More informationWhite paper Advanced Technologies of the Supercomputer PRIMEHPC FX10
White paper Advanced Technologies of the Supercomputer PRIMEHPC FX10 Next Generation Technical Computing Unit Fujitsu Limited Contents Overview of the PRIMEHPC FX10 Supercomputer 2 SPARC64 TM IXfx: Fujitsu-Developed
More informationCray XC Scalability and the Aries Network Tony Ford
Cray XC Scalability and the Aries Network Tony Ford June 29, 2017 Exascale Scalability Which scalability metrics are important for Exascale? Performance (obviously!) What are the contributing factors?
More informationTopologies. Maurizio Palesi. Maurizio Palesi 1
Topologies Maurizio Palesi Maurizio Palesi 1 Network Topology Static arrangement of channels and nodes in an interconnection network The roads over which packets travel Topology chosen based on cost and
More informationNetwork-on-chip (NOC) Topologies
Network-on-chip (NOC) Topologies 1 Network Topology Static arrangement of channels and nodes in an interconnection network The roads over which packets travel Topology chosen based on cost and performance
More informationPerformance of Multihop Communications Using Logical Topologies on Optical Torus Networks
Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks X. Yuan, R. Melhem and R. Gupta Department of Computer Science University of Pittsburgh Pittsburgh, PA 156 fxyuan,
More informationFujitsu s Approach to Application Centric Petascale Computing
Fujitsu s Approach to Application Centric Petascale Computing 2 nd Nov. 2010 Motoi Okuda Fujitsu Ltd. Agenda Japanese Next-Generation Supercomputer, K Computer Project Overview Design Targets System Overview
More informationLecture 2 Parallel Programming Platforms
Lecture 2 Parallel Programming Platforms Flynn s Taxonomy In 1966, Michael Flynn classified systems according to numbers of instruction streams and the number of data stream. Data stream Single Multiple
More informationTopologies. Maurizio Palesi. Maurizio Palesi 1
Topologies Maurizio Palesi Maurizio Palesi 1 Network Topology Static arrangement of channels and nodes in an interconnection network The roads over which packets travel Topology chosen based on cost and
More informationWhite paper FUJITSU Supercomputer PRIMEHPC FX100 Evolution to the Next Generation
White paper FUJITSU Supercomputer PRIMEHPC FX100 Evolution to the Next Generation Next Generation Technical Computing Unit Fujitsu Limited Contents FUJITSU Supercomputer PRIMEHPC FX100 System Overview
More informationThe way toward peta-flops
The way toward peta-flops ISC-2011 Dr. Pierre Lagier Chief Technology Officer Fujitsu Systems Europe Where things started from DESIGN CONCEPTS 2 New challenges and requirements! Optimal sustained flops
More information4. Networks. in parallel computers. Advances in Computer Architecture
4. Networks in parallel computers Advances in Computer Architecture System architectures for parallel computers Control organization Single Instruction stream Multiple Data stream (SIMD) All processors
More informationPhastlane: A Rapid Transit Optical Routing Network
Phastlane: A Rapid Transit Optical Routing Network Mark Cianchetti, Joseph Kerekes, and David Albonesi Computer Systems Laboratory Cornell University The Interconnect Bottleneck Future processors: tens
More informationChapter 4. Routers with Tiny Buffers: Experiments. 4.1 Testbed experiments Setup
Chapter 4 Routers with Tiny Buffers: Experiments This chapter describes two sets of experiments with tiny buffers in networks: one in a testbed and the other in a real network over the Internet2 1 backbone.
More informationBlueGene/L. Computer Science, University of Warwick. Source: IBM
BlueGene/L Source: IBM 1 BlueGene/L networking BlueGene system employs various network types. Central is the torus interconnection network: 3D torus with wrap-around. Each node connects to six neighbours
More informationLecture 12: Interconnection Networks. Topics: communication latency, centralized and decentralized switches, routing, deadlocks (Appendix E)
Lecture 12: Interconnection Networks Topics: communication latency, centralized and decentralized switches, routing, deadlocks (Appendix E) 1 Topologies Internet topologies are not very regular they grew
More informationCommunication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems.
Cluster Networks Introduction Communication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems. As usual, the driver is performance
More informationLecture 26: Interconnects. James C. Hoe Department of ECE Carnegie Mellon University
18 447 Lecture 26: Interconnects James C. Hoe Department of ECE Carnegie Mellon University 18 447 S18 L26 S1, James C. Hoe, CMU/ECE/CALCM, 2018 Housekeeping Your goal today get an overview of parallel
More informationNetworking for Data Acquisition Systems. Fabrice Le Goff - 14/02/ ISOTDAQ
Networking for Data Acquisition Systems Fabrice Le Goff - 14/02/2018 - ISOTDAQ Outline Generalities The OSI Model Ethernet and Local Area Networks IP and Routing TCP, UDP and Transport Efficiency Networking
More informationThe Impact of Optics on HPC System Interconnects
The Impact of Optics on HPC System Interconnects Mike Parker and Steve Scott Hot Interconnects 2009 Manhattan, NYC Will cost-effective optics fundamentally change the landscape of networking? Yes. Changes
More informationPerformance Evaluation of TOFU System Area Network Design for High- Performance Computer Systems
Performance Evaluation of TOFU System Area Network Design for High- Performance Computer Systems P. BOROVSKA, O. NAKOV, S. MARKOV, D. IVANOVA, F. FILIPOV Computer System Department Technical University
More informationLecture 20: Distributed Memory Parallelism. William Gropp
Lecture 20: Distributed Parallelism William Gropp www.cs.illinois.edu/~wgropp A Very Short, Very Introductory Introduction We start with a short introduction to parallel computing from scratch in order
More informationMIMD Overview. Intel Paragon XP/S Overview. XP/S Usage. XP/S Nodes and Interconnection. ! Distributed-memory MIMD multicomputer
MIMD Overview Intel Paragon XP/S Overview! MIMDs in the 1980s and 1990s! Distributed-memory multicomputers! Intel Paragon XP/S! Thinking Machines CM-5! IBM SP2! Distributed-memory multicomputers with hardware
More informationA closer look at network structure:
T1: Introduction 1.1 What is computer network? Examples of computer network The Internet Network structure: edge and core 1.2 Why computer networks 1.3 The way networks work 1.4 Performance metrics: Delay,
More informationExploiting InfiniBand and GPUDirect Technology for High Performance Collectives on GPU Clusters
Exploiting InfiniBand and Direct Technology for High Performance Collectives on Clusters Ching-Hsiang Chu chu.368@osu.edu Department of Computer Science and Engineering The Ohio State University OSU Booth
More informationInfiniBand-based HPC Clusters
Boosting Scalability of InfiniBand-based HPC Clusters Asaf Wachtel, Senior Product Manager 2010 Voltaire Inc. InfiniBand-based HPC Clusters Scalability Challenges Cluster TCO Scalability Hardware costs
More information3D WiNoC Architectures
Interconnect Enhances Architecture: Evolution of Wireless NoC from Planar to 3D 3D WiNoC Architectures Hiroki Matsutani Keio University, Japan Sep 18th, 2014 Hiroki Matsutani, "3D WiNoC Architectures",
More informationIntroduction to High-Speed InfiniBand Interconnect
Introduction to High-Speed InfiniBand Interconnect 2 What is InfiniBand? Industry standard defined by the InfiniBand Trade Association Originated in 1999 InfiniBand specification defines an input/output
More informationIntroduction of Fujitsu s next-generation supercomputer
Introduction of Fujitsu s next-generation supercomputer MATSUMOTO Takayuki July 16, 2014 HPC Platform Solutions Fujitsu has a long history of supercomputing over 30 years Technologies and experience of
More informationxsim The Extreme-Scale Simulator
www.bsc.es xsim The Extreme-Scale Simulator Janko Strassburg Severo Ochoa Seminar @ BSC, 28 Feb 2014 Motivation Future exascale systems are predicted to have hundreds of thousands of nodes, thousands of
More informationChapter 16 Networking
Chapter 16 Networking Outline 16.1 Introduction 16.2 Network Topology 16.3 Network Types 16.4 TCP/IP Protocol Stack 16.5 Application Layer 16.5.1 Hypertext Transfer Protocol (HTTP) 16.5.2 File Transfer
More informationComputer Networking. Introduction. Quintin jean-noël Grenoble university
Computer Networking Introduction Quintin jean-noël Jean-noel.quintin@imag.fr Grenoble university Based on the presentation of Duda http://duda.imag.fr 1 Course organization Introduction Network and architecture
More informationAdvanced Computer Networks. Flow Control
Advanced Computer Networks 263 3501 00 Flow Control Patrick Stuedi Spring Semester 2017 1 Oriana Riva, Department of Computer Science ETH Zürich Last week TCP in Datacenters Avoid incast problem - Reduce
More informationExtending the LAN. Context. Info 341 Networking and Distributed Applications. Building up the network. How to hook things together. Media NIC 10/18/10
Extending the LAN Info 341 Networking and Distributed Applications Context Building up the network Media NIC Application How to hook things together Transport Internetwork Network Access Physical Internet
More informationSource-Route Bridging
25 CHAPTER Chapter Goals Describe when to use source-route bridging. Understand the difference between SRB and transparent bridging. Know the mechanism that end stations use to specify a source-route.
More informationCP2K Performance Benchmark and Profiling. April 2011
CP2K Performance Benchmark and Profiling April 2011 Note The following research was performed under the HPC Advisory Council HPC works working group activities Participating vendors: HP, Intel, Mellanox
More informationEmbedded Systems: Hardware Components (part II) Todor Stefanov
Embedded Systems: Hardware Components (part II) Todor Stefanov Leiden Embedded Research Center, Leiden Institute of Advanced Computer Science Leiden University, The Netherlands Outline Generic Embedded
More informationPOLYMORPHIC ON-CHIP NETWORKS
POLYMORPHIC ON-CHIP NETWORKS Martha Mercaldi Kim, John D. Davis*, Mark Oskin, Todd Austin** University of Washington *Microsoft Research, Silicon Valley ** University of Michigan On-Chip Network Selection
More informationScaling to Petaflop. Ola Torudbakken Distinguished Engineer. Sun Microsystems, Inc
Scaling to Petaflop Ola Torudbakken Distinguished Engineer Sun Microsystems, Inc HPC Market growth is strong CAGR increased from 9.2% (2006) to 15.5% (2007) Market in 2007 doubled from 2003 (Source: IDC
More informationLecture: Interconnection Networks
Lecture: Interconnection Networks Topics: Router microarchitecture, topologies Final exam next Tuesday: same rules as the first midterm 1 Packets/Flits A message is broken into multiple packets (each packet
More informationNetSpeed ORION: A New Approach to Design On-chip Interconnects. August 26 th, 2013
NetSpeed ORION: A New Approach to Design On-chip Interconnects August 26 th, 2013 INTERCONNECTS BECOMING INCREASINGLY IMPORTANT Growing number of IP cores Average SoCs today have 100+ IPs Mixing and matching
More informationScheduling Strategies for HPC as a Service (HPCaaS) for Bio-Science Applications
Scheduling Strategies for HPC as a Service (HPCaaS) for Bio-Science Applications Sep 2009 Gilad Shainer, Tong Liu (Mellanox); Jeffrey Layton (Dell); Joshua Mora (AMD) High Performance Interconnects for
More informationCARRIER SENSE MULTIPLE ACCESS (CSMA):
Lecture Handout Computer Networks Lecture No. 8 CARRIER SENSE MULTIPLE ACCESS (CSMA): There is no central control management when computers transmit on Ethernet. For this purpose the Ethernet employs CSMA
More informationChelsio 10G Ethernet Open MPI OFED iwarp with Arista Switch
PERFORMANCE BENCHMARKS Chelsio 10G Ethernet Open MPI OFED iwarp with Arista Switch Chelsio Communications www.chelsio.com sales@chelsio.com +1-408-962-3600 Executive Summary Ethernet provides a reliable
More informationTopology basics. Constraints and measures. Butterfly networks.
EE48: Advanced Computer Organization Lecture # Interconnection Networks Architecture and Design Stanford University Topology basics. Constraints and measures. Butterfly networks. Lecture #: Monday, 7 April
More informationEN2910A: Advanced Computer Architecture Topic 06: Supercomputers & Data Centers Prof. Sherief Reda School of Engineering Brown University
EN2910A: Advanced Computer Architecture Topic 06: Supercomputers & Data Centers Prof. Sherief Reda School of Engineering Brown University Material from: The Datacenter as a Computer: An Introduction to
More informationINTERCONNECTION NETWORKS LECTURE 4
INTERCONNECTION NETWORKS LECTURE 4 DR. SAMMAN H. AMEEN 1 Topology Specifies way switches are wired Affects routing, reliability, throughput, latency, building ease Routing How does a message get from source
More informationOFAR-CM: Efficient Dragonfly Networks with Simple Congestion Management
Marina Garcia 22 August 2013 OFAR-CM: Efficient Dragonfly Networks with Simple Congestion Management M. Garcia, E. Vallejo, R. Beivide, M. Valero and G. Rodríguez Document number OFAR-CM: Efficient Dragonfly
More informationEnd-to-End Adaptive Packet Aggregation for High-Throughput I/O Bus Network Using Ethernet
Hot Interconnects 2014 End-to-End Adaptive Packet Aggregation for High-Throughput I/O Bus Network Using Ethernet Green Platform Research Laboratories, NEC, Japan J. Suzuki, Y. Hayashi, M. Kan, S. Miyakawa,
More informationOptimization of MPI Applications Rolf Rabenseifner
Optimization of MPI Applications Rolf Rabenseifner University of Stuttgart High-Performance Computing-Center Stuttgart (HLRS) www.hlrs.de Optimization of MPI Applications Slide 1 Optimization and Standardization
More informationHigh-Performance Broadcast for Streaming and Deep Learning
High-Performance Broadcast for Streaming and Deep Learning Ching-Hsiang Chu chu.368@osu.edu Department of Computer Science and Engineering The Ohio State University OSU Booth - SC17 2 Outline Introduction
More informationThe Road to ExaScale. Advances in High-Performance Interconnect Infrastructure. September 2011
The Road to ExaScale Advances in High-Performance Interconnect Infrastructure September 2011 diego@mellanox.com ExaScale Computing Ambitious Challenges Foster Progress Demand Research Institutes, Universities
More informationLecture 2: Topology - I
ECE 8823 A / CS 8803 - ICN Interconnection Networks Spring 2017 http://tusharkrishna.ece.gatech.edu/teaching/icn_s17/ Lecture 2: Topology - I Tushar Krishna Assistant Professor School of Electrical and
More informationDesigning Optimized MPI Broadcast and Allreduce for Many Integrated Core (MIC) InfiniBand Clusters
Designing Optimized MPI Broadcast and Allreduce for Many Integrated Core (MIC) InfiniBand Clusters K. Kandalla, A. Venkatesh, K. Hamidouche, S. Potluri, D. Bureddy and D. K. Panda Presented by Dr. Xiaoyi
More informationLecture 24: Interconnection Networks. Topics: topologies, routing, deadlocks, flow control
Lecture 24: Interconnection Networks Topics: topologies, routing, deadlocks, flow control 1 Topology Examples Grid Torus Hypercube Criteria Bus Ring 2Dtorus 6-cube Fully connected Performance Bisection
More informationAPENet: LQCD clusters a la APE
Overview Hardware/Software Benchmarks Conclusions APENet: LQCD clusters a la APE Concept, Development and Use Roberto Ammendola Istituto Nazionale di Fisica Nucleare, Sezione Roma Tor Vergata Centro Ricerce
More informationCS 6230: High-Performance Computing and Parallelization Introduction to MPI
CS 6230: High-Performance Computing and Parallelization Introduction to MPI Dr. Mike Kirby School of Computing and Scientific Computing and Imaging Institute University of Utah Salt Lake City, UT, USA
More informationInterconnection Network. Jinkyu Jeong Computer Systems Laboratory Sungkyunkwan University
Interconnection Network Jinkyu Jeong (jinkyu@skku.edu) Computer Systems Laboratory Sungkyunkwan University http://csl.skku.edu Topics Taxonomy Metric Topologies Characteristics Cost Performance 2 Interconnection
More informationComputer-to-Computer Networks (cont.)
Computer-to-Computer Networks (cont.) 1 Connecting Mainframes - Option 1: Full Mesh / Direct Link Infrastructure Downsides: 1) cost - O(n 2 ) links and NICs 2) implementation complexity / scalability [
More informationMPI Optimizations via MXM and FCA for Maximum Performance on LS-DYNA
MPI Optimizations via MXM and FCA for Maximum Performance on LS-DYNA Gilad Shainer 1, Tong Liu 1, Pak Lui 1, Todd Wilde 1 1 Mellanox Technologies Abstract From concept to engineering, and from design to
More informationLecture 13: Interconnection Networks. Topics: lots of background, recent innovations for power and performance
Lecture 13: Interconnection Networks Topics: lots of background, recent innovations for power and performance 1 Interconnection Networks Recall: fully connected network, arrays/rings, meshes/tori, trees,
More informationUpdate on Topology Aware Scheduling (aka TAS)
Update on Topology Aware Scheduling (aka TAS) Work done in collaboration with J. Enos, G. Bauer, R. Brunner, S. Islam R. Fiedler Adaptive Computing 2 When things look good Image credit: Dave Semeraro 3
More informationPhysical Organization of Parallel Platforms. Alexandre David
Physical Organization of Parallel Platforms Alexandre David 1.2.05 1 Static vs. Dynamic Networks 13-02-2008 Alexandre David, MVP'08 2 Interconnection networks built using links and switches. How to connect:
More informationInterconnection Network
Interconnection Network Jinkyu Jeong (jinkyu@skku.edu) Computer Systems Laboratory Sungkyunkwan University http://csl.skku.edu SSE3054: Multicore Systems, Spring 2017, Jinkyu Jeong (jinkyu@skku.edu) Topics
More informationCMSC 611: Advanced. Interconnection Networks
CMSC 611: Advanced Computer Architecture Interconnection Networks Interconnection Networks Massively parallel processor networks (MPP) Thousands of nodes Short distance (
More informationSIGNET: NETWORK-ON-CHIP FILTERING FOR COARSE VECTOR DIRECTORIES. Natalie Enright Jerger University of Toronto
SIGNET: NETWORK-ON-CHIP FILTERING FOR COARSE VECTOR DIRECTORIES University of Toronto Interaction of Coherence and Network 2 Cache coherence protocol drives network-on-chip traffic Scalable coherence protocols
More informationAdaptors Communicating. Link Layer: Introduction. Parity Checking. Error Detection. Multiple Access Links and Protocols
Link Layer: Introduction daptors ommunicating hosts and routers are nodes links connect nodes wired links wireless links layer-2 packet is a frame, encapsulates datagram datagram controller sending host
More informationHigh Performance MPI on IBM 12x InfiniBand Architecture
High Performance MPI on IBM 12x InfiniBand Architecture Abhinav Vishnu, Brad Benton 1 and Dhabaleswar K. Panda {vishnu, panda} @ cse.ohio-state.edu {brad.benton}@us.ibm.com 1 1 Presentation Road-Map Introduction
More informationReal-Time Protocol (RTP)
Real-Time Protocol (RTP) Provides standard packet format for real-time application Typically runs over UDP Specifies header fields below Payload Type: 7 bits, providing 128 possible different types of
More informationInterconnect Your Future
Interconnect Your Future Gilad Shainer 2nd Annual MVAPICH User Group (MUG) Meeting, August 2014 Complete High-Performance Scalable Interconnect Infrastructure Comprehensive End-to-End Software Accelerators
More informationFlow Control can be viewed as a problem of
NOC Flow Control 1 Flow Control Flow Control determines how the resources of a network, such as channel bandwidth and buffer capacity are allocated to packets traversing a network Goal is to use resources
More informationPart IV: 3D WiNoC Architectures
Wireless NoC as Interconnection Backbone for Multicore Chips: Promises, Challenges, and Recent Developments Part IV: 3D WiNoC Architectures Hiroki Matsutani Keio University, Japan 1 Outline: 3D WiNoC Architectures
More informationGeneric Topology Mapping Strategies for Large-scale Parallel Architectures
Generic Topology Mapping Strategies for Large-scale Parallel Architectures Torsten Hoefler and Marc Snir Scientific talk at ICS 11, Tucson, AZ, USA, June 1 st 2011, Hierarchical Sparse Networks are Ubiquitous
More informationFuture of Interconnect Fabric A Contrarian View. Shekhar Borkar June 13, 2010 Intel Corp. 1
Future of Interconnect Fabric A ontrarian View Shekhar Borkar June 13, 2010 Intel orp. 1 Outline Evolution of interconnect fabric On die network challenges Some simple contrarian proposals Evaluation and
More informationLecture 9: Bridging. CSE 123: Computer Networks Alex C. Snoeren
Lecture 9: Bridging CSE 123: Computer Networks Alex C. Snoeren Lecture 9 Overview Finishing up media access Ethernet Contention-free methods (rings) Moving beyond one wire Link technologies have limits
More informationIV. PACKET SWITCH ARCHITECTURES
IV. PACKET SWITCH ARCHITECTURES (a) General Concept - as packet arrives at switch, destination (and possibly source) field in packet header is used as index into routing tables specifying next switch in
More informationCS 421: COMPUTER NETWORKS SPRING FINAL May 24, minutes. Name: Student No: TOT
CS 421: COMPUTER NETWORKS SPRING 2012 FINAL May 24, 2012 150 minutes Name: Student No: Show all your work very clearly. Partial credits will only be given if you carefully state your answer with a reasonable
More informationLecture 3: Topology - II
ECE 8823 A / CS 8803 - ICN Interconnection Networks Spring 2017 http://tusharkrishna.ece.gatech.edu/teaching/icn_s17/ Lecture 3: Topology - II Tushar Krishna Assistant Professor School of Electrical and
More informationUnderstanding the Routing Requirements for FPGA Array Computing Platform. Hayden So EE228a Project Presentation Dec 2 nd, 2003
Understanding the Routing Requirements for FPGA Array Computing Platform Hayden So EE228a Project Presentation Dec 2 nd, 2003 What is FPGA Array Computing? Aka: Reconfigurable Computing Aka: Spatial computing,
More informationIn-Network Computing. Paving the Road to Exascale. 5th Annual MVAPICH User Group (MUG) Meeting, August 2017
In-Network Computing Paving the Road to Exascale 5th Annual MVAPICH User Group (MUG) Meeting, August 2017 Exponential Data Growth The Need for Intelligent and Faster Interconnect CPU-Centric (Onload) Data-Centric
More informationTopology and affinity aware hierarchical and distributed load-balancing in Charm++
Topology and affinity aware hierarchical and distributed load-balancing in Charm++ Emmanuel Jeannot, Guillaume Mercier, François Tessier Inria - IPB - LaBRI - University of Bordeaux - Argonne National
More informationLecture 9: Bridging & Switching"
Lecture 9: Bridging & Switching" CSE 123: Computer Networks Alex C. Snoeren HW 2 due Wednesday! Lecture 9 Overview" Finishing up media access Contention-free methods (rings) Moving beyond one wire Link
More informationArchitecting Low Latency Cloud Networks
Architecting Low Latency Cloud Networks As data centers transition to next generation virtualized & elastic cloud architectures, high performance and resilient cloud networking has become a requirement
More informationScalable Ethernet Clos-Switches. Norbert Eicker John von Neumann-Institute for Computing Ferdinand Geier ParTec Cluster Competence Center GmbH
Scalable Ethernet Clos-Switches Norbert Eicker John von Neumann-Institute for Computing Ferdinand Geier ParTec Cluster Competence Center GmbH Outline Motivation Clos-Switches Ethernet Crossbar Switches
More informationLecture 18: Communication Models and Architectures: Interconnection Networks
Design & Co-design of Embedded Systems Lecture 18: Communication Models and Architectures: Interconnection Networks Sharif University of Technology Computer Engineering g Dept. Winter-Spring 2008 Mehdi
More informationParallel Computing Interconnection Networks
Parallel Computing Interconnection Networks Readings: Hager s book (4.5) Pacheco s book (chapter 2.3.3) http://pages.cs.wisc.edu/~tvrdik/5/html/section5.html#aaaaatre e-based topologies Slides credit:
More informationBasic Communication Operations (Chapter 4)
Basic Communication Operations (Chapter 4) Vivek Sarkar Department of Computer Science Rice University vsarkar@cs.rice.edu COMP 422 Lecture 17 13 March 2008 Review of Midterm Exam Outline MPI Example Program:
More informationIBM HPC Development MPI update
IBM HPC Development MPI update Chulho Kim Scicomp 2007 Enhancements in PE 4.3.0 & 4.3.1 MPI 1-sided improvements (October 2006) Selective collective enhancements (October 2006) AIX IB US enablement (July
More informationMulti-class Applications for Parallel Usage of a Guaranteed Rate and a Scavenger Service
Department of Computer Science 1/18 Multi-class Applications for Parallel Usage of a Guaranteed Rate and a Scavenger Service Markus Fidler fidler@informatik.rwth-aachen.de Volker Sander sander@fz.juelich.de
More informationNetwork Design Considerations for Grid Computing
Network Design Considerations for Grid Computing Engineering Systems How Bandwidth, Latency, and Packet Size Impact Grid Job Performance by Erik Burrows, Engineering Systems Analyst, Principal, Broadcom
More information