Utilizing Multi-threading, Parallel Processing, and Memory Management Techniques to Improve Transportation Model Performance Jim Lam Andres Rabinowicz.

Slides:



Advertisements
Similar presentations
THURSTON REGION MULTIMODAL TRAVEL DEMAND FORECASTING MODEL IMPLEMENTATION IN EMME/2 - Presentation at the 15th International EMME/2 Users Group Conference.
Advertisements

Network II.5 simulator ..
Feedback Loops Guy Rousseau Atlanta Regional Commission.
Managing Large Graphs on Multi-Cores With Graph Awareness Vijayan, Ming, Xuetian, Frank, Lidong, Maya Microsoft Research.
COURSE: COMPUTER PLATFORMS
Adventures in Transit PathFinding Jim Lam Jian Zhang Howard Slavin Srini Sundaram Andres Rabinowicz Caliper Corporation GIS in Public Transportation September,
Multi-core systems System Architecture COMP25212 Daniel Goodman Advanced Processor Technologies Group.
11 th TRB Transportation Planning Applications Conference, Daytona Beach, FL Achieving Planning Model Convergence Howard Slavin Jonathan Brandon Andres.
New Findings from the Application of Accelerated UE Traffic Assignments Howard Slavin Jonathan Brandon Andres Rabinowicz Paul Ricotta Srini Sundaram Caliper.
10 REASONS Why it makes a good option for your DB IN-MEMORY DATABASES Presenter #10: Robert Vitolo.
What is the Model??? A Primer on Transportation Demand Forecasting Models Shawn Turner Theo Petritsch Keith Lovan Lisa Aultman-Hall.
13 th TRB Transportation Planning Applications Conference, Reno, NV Computational Challenges and Advances in Transportation Computing Andres Rabinowicz.
PARALLEL PROCESSING COMPARATIVE STUDY 1. CONTEXT How to finish a work in short time???? Solution To use quicker worker. Inconvenient: The speed of worker.
Junction Modelling in a Strategic Transport Model Wee Liang Lim Henry Le Land Transport Authority, Singapore.
Opportunities & Challenges Using Passively Collected Data In Travel Demand Modeling 15 th TRB Transportation Planning Applications Conference Atlantic.
Planning Applications: A City- wide Microsimulation Model for Virginia Beach Craig Jordan, Old Dominion University Mecit Cetin, Old Dominion University.
Multi-core processors. History In the early 1970’s the first Microprocessor was developed by Intel. It was a 4 bit machine that was named the 4004 The.
Challenge 2: Spatial Aggregation Level Multi-tier Modeling in Ohio Attempts to Balance Run Time and Forecast Granularity Gregory Giaimo, PE The Ohio Department.
Implementing a Blended Model System to Forecast Transportation and Land Use Changes at Bob Hope Airport 15 th TRB National Transportation Planning Applications.
An Empirical Comparison of Microscopic and Mesoscopic Traffic Simulation Paradigms Ramachandran Balakrishna Daniel Morgan Qi Yang Caliper Corporation 14.
FOCUS MODEL OVERVIEW CLASS FIVE Denver Regional Council of Governments July27, 2011.
Source: NHI course on Travel Demand Forecasting (152054A) Session 10 Traffic (Trip) Assignment Trip Generation Trip Distribution Transit Estimation & Mode.
TPB Models Development Status Report Presentation to the Travel Forecasting Subcommittee Ron Milone National Capital Region Transportation Planning Board.
Computer System Architectures Computer System Software
Protocols and the TCP/IP Suite
DVRPC TMIP Peer Review TIM 2 Model Oct. 29 th, 2014.
Increasing Precision in Highway Volume through Adjustment of Stopping Criteria in Traffic Assignment and Number of Feedbacks Behruz Paschai, Kathy Yu,
Development of the Graphical User Interface and Improvement and Streamlining of NYMTC's Best Practice Model Jim Lam, Andres Rabinowicz, Srini Sundaram,
Sigrity, Inc © Efficient Signal and Power Integrity Analysis Using Parallel Techniques Tao Su, Xiaofeng Wang, Zhengang Bai, Venkata Vennam Sigrity,
How to Put “Best Practice” into Traffic Assignment Practice Ken Cervenka Federal Transit Administration TRB National Transportation.
Unit R005: Understanding Computer Systems Introduction System Software Software (i.e., programs) used to control the hardware directly Used to run the.
Chapter 2 Parallel Architecture. Moore’s Law The number of transistors on a chip doubles every years. – Has been valid for over 40 years – Can’t.
Comparing Dynamic Traffic Assignment Approaches for Planning
2007 TRB Transportation Planning Applications Conference – Daytona Beach, Florida Pseudo Dynamic Traffic Assignment A Duration Based Static Assignment.
Frank Casilio Computer Engineering May 15, 1997 Multithreaded Processors.
Dynamic Origin-Destination Trip Table Estimation for Transportation Planning Ramachandran Balakrishna Caliper Corporation 11 th TRB National Transportation.
S. Erdogan 1, K. Patnam 2, X. Zhou 3, F.D. Ducca 4, S. Mahapatra 5, Z. Deng 6, J. Liu 7 1, 4, 6 University of Maryland, National Center for Smart Growth.
EMME Users’ Group Meeting Recent toll patronage forecasting using EMME 27 May 2011.
Hyper Threading Technology. Introduction Hyper-threading is a technology developed by Intel Corporation for it’s Xeon processors with a 533 MHz system.
Presented to Time of Day Subcommittee May 9, 2011 Time of Day Modeling in FSUTMS.
A Dynamic Traffic Simulation Model on Planning Networks Qi Yang Caliper Corporation TRB Planning Application Conference Houston, May 20, 2009.
FLSWM 2040 Traffic Projection Hongbo Chi. Introduction FLSWM provides travel forecasting over the entire state reflecting long range demographic and socioeconomic.
Performance Benchmarks in EMME/2 Matt Carlson INRO Seminar, Arup, London
Methodological Considerations for Integrating Dynamic Traffic Assignment with Activity-Based Models Ramachandran Balakrishna Daniel Morgan Srinivasan Sundaram.
MULTICORE PROCESSOR TECHNOLOGY.  Introduction  history  Why multi-core ?  What do you mean by multicore?  Multi core architecture  Comparison of.
McGraw-Hill©The McGraw-Hill Companies, Inc., 2000 OS 1.
Application of Accelerated User Equilibrium Traffic Assignments Howard Slavin Jonathan Brandon Andres Rabinowicz Srinivasan Sundaram Caliper Corporation.
CSE 434: Computer Networks Project Single vs. Per Connection vs. Pooling Threading Techniques Dominic Hilsbos, Dorothy Johnson, Chris Volpe, Andy Wong,
Silberschatz, Galvin and Gagne ©2009Operating System Concepts – 8 th Edition Chapter 4: Threads.
NEW DEVELOPMENTS IN Vision Suite User Group Meeting PTV Group.
Transportation leadership you can trust. presented to Third International Conference on Innovations in Travel Modeling presented by Thomas Rossi Cambridge.
Threads by Dr. Amin Danial Asham. References Operating System Concepts ABRAHAM SILBERSCHATZ, PETER BAER GALVIN, and GREG GAGNE.
Network-Attached Storage. Network-attached storage devices Attached to a local area network, generally an Ethernet-based network environment.
Peter Vovsha, Robert Donnelly, Surabhi Gupta pb
Modeling Big Data Execution speed limited by: Model complexity
A DFA with Extended Character-Set for Fast Deep Packet Inspection
Multi-core processors
Spatial Analysis With Big Data
Multi-core processors
Jim Henricksen, MnDOT Steve Ruegg, WSP
Operating Systems (CS 340 D)
Travel Demand Forecasting: Mode Choice
Computer Architecture Lecture 4 17th May, 2006
After Evans: Working on an Approximation of a Combined Equilibrium Model Based on Precision Assignment May, 2011 TRB Planning Applications Conference,
UNIT IV RAID.
Jim Lam, Caliper Corporation Guoxiong Huang, SCAG Mark Bradley, BB&C
Multithreaded Programming
Operating Systems (CS 340 D)
Operating System Introduction.
A very basic introduction
Presentation transcript:

Utilizing Multi-threading, Parallel Processing, and Memory Management Techniques to Improve Transportation Model Performance Jim Lam Andres Rabinowicz Caliper Corporation TRB Planning Applications 2015 Conference May 18, 2015 Atlantic City, NJ

Overview  Motivation  Overview of Techniques  Model Descriptions  Performance Tests  Limitations  Implementation  Conclusions

Motivation Many more zones for conventional models More complex models (Dynamic Traffic Assignments, choice model etc.) Good modeling practice requires many feedback, calibration, and scenario runs and good assignment convergence Time and budget constraints Long run times lead to compromises

Hardware Improvements Multi-core chips with hyperthreading 64-bit programming More memory Faster drives

Overview of Techniques Multi-threading –Operation is internally broken down and handled simultaneously by processing cores –Order independent operations Parallel Processing –Operations invoked and managed simultaneously Distributed Computing –Operations are invoked on different computers simultaneously Memory Management –Entire datasets are completely processed in memory Combination of Techniques

Examples Matrix Operations –12,000 x 12,000 x multi cores Exp() operation Data Operations –170,000 records, 512 fields, reads, writes, formulas Highway Skim –12,000 x 12,000 x multi time periods and classes Transit Skim –12,000 x 12,000 x multi time periods and classes Gravity –12,000 x 12,000 x multi time periods and purposes Highway and Transit Assignments –5,000 x 5,000 x multi time periods

Performance Tests – Multi-threading

Parallel Processing - Results

Distributed Computing

Memory Management

Combined Techniques Data Example : Transit Skims for SCAG ABM –130 skims for both Trips and Tours Multi-threading only: 19 hours Multi-threading with Parallel: 9 hours Multi-threading with Parallel with Distributed: 5 hours

Limitations Processing Cores Available Memory Disk Speed Network Speed File Conflicts Different User Hardware

Implementation - Code Traditional Parallel

Implementation - Graphic

Conclusions New techniques have potential for dramatic performance improvements Combining techniques can improve performance even further Hardware limitations still exist Additional improvements are still possible