Computer Model Simulation STEPHEN GOWDY FNAL 30th March 2015 Computing Model Simulation 1.

Slides:



Advertisements
Similar presentations
Buffers & Spoolers J L Martin Think about it… All I/O is relatively slow. For most of us, input by typing is painfully slow. From the CPUs point.
Advertisements

Performance Analysis of Daisy- Chained CPUs Based On Modeling Krzysztof Korcyl, Jagiellonian University, Krakow Radoslaw Trebacz Jagiellonian University,
COMPUTER ORGANIZATION CHAPTER SUBSYSTEM INTERCONNECTION.
Higher Computing: Unit 1: Topic 3 – Computer Performance St Andrew’s High School, Computing Department Higher Computing Topic 3 Computer Performance.
Intro to Threading CS221 – 4/20/09. What we’ll cover today Finish the DOTS program Introduction to threads and multi-threading.
Instruction Counter Address [3..0] CLK Instruction ROM 0000: : : : : Inst [6..0] Control Unit.
Performance Metrics Parallel Computing - Theory and Practice (2/e) Section 3.6 Michael J. Quinn mcGraw-Hill, Inc., 1994.
Scuola Superiore Sant’Anna Project Assignments Operating Systems.
Chapter 1 and 2 Computer System and Operating System Overview
Chapter 1 and 2 Computer System and Operating System Overview
K.Harrison CERN, 23rd October 2002 HOW TO COMMISSION A NEW CENTRE FOR LHCb PRODUCTION - Overview of LHCb distributed production system - Configuration.
Types of Operating Systems
Motherboard AKA mainboard, system board, planar board, or logic board. It is printed circuit board found in all modern computers which holds many of the.
Ian M. Fisk Fermilab February 23, Global Schedule External Items ➨ gLite 3.0 is released for pre-production in mid-April ➨ gLite 3.0 is rolled onto.
Analysis of Simulation Results Andy Wang CIS Computer Systems Performance Analysis.
 Introduction to Operating System Introduction to Operating System  Types Of An Operating System Types Of An Operating System  Single User Single User.
Alexandre A. P. Suaide VI DOSAR workshop, São Paulo, 2005 STAR grid activities and São Paulo experience.
Grid Canada CLS eScience Workshop 21 st November, 2005.
Spyware How to eliminate it!. What is Spyware? It is a file that copies itself to your computer without your knowledge. It reports your activities to.
1 Data Management D0 Monte Carlo needs The NIKHEF D0 farm The data we produce The SAM data base The network Conclusions Kors Bos, NIKHEF, Amsterdam Fermilab,
Remote Production and Regional Analysis Centers Iain Bertram 24 May 2002 Draft 1 Lancaster University.
D0 Farms 1 D0 Run II Farms M. Diesburg, B.Alcorn, J.Bakken, T.Dawson, D.Fagan, J.Fromm, K.Genser, L.Giacchetti, D.Holmgren, T.Jones, T.Levshina, L.Lueking,
1 Computer Architecture Research Overview Rajeev Balasubramonian School of Computing, University of Utah
Wenjing Wu Andrej Filipčič David Cameron Eric Lancon Claire Adam Bourdarios & others.
1 Distributed Energy-Efficient Scheduling for Data-Intensive Applications with Deadline Constraints on Data Grids Cong Liu and Xiao Qin Auburn University.
Frontiers in Massive Data Analysis Chapter 3.  Difficult to include data from multiple sources  Each organization develops a unique way of representing.
Building a Real Workflow Thursday morning, 9:00 am Greg Thain University of Wisconsin - Madison.
Chapter 9 Memory Organization By Jack Chung. MEMORY? RAM?
PHENIX and the data grid >400 collaborators Active on 3 continents + Brazil 100’s of TB of data per year Complex data with multiple disparate physics goals.
By: Eric Backman Advisor: Dr. Malinowski.  Introduction  Goals  Project Overview and Changes  Work Completed  Updated Schedule.
Update on replica management
Grid Scheduler: Plan & Schedule Adam Arbree Jang Uk In.
PPDG update l We want to join PPDG l They want PHENIX to join NSF also wants this l Issue is to identify our goals/projects Ingredients: What we need/want.
Stores the OS/data currently in use and software currently in use Memory Unit 21.
1 Programming of FPGA in LiCAS ADC for Continuous Data Readout Week 5 Report Tuesday 29 th July 2008 Jack Hickish.
ECE 353 Lab 2 Pipeline Simulator. Aims Further experience in C programming Handling strings Further experience in the use of assertions Reinforce concepts.
CMS Computing Model Simulation Stephen Gowdy/FNAL 30th April 2015CMS Computing Model Simulation1.
The CMS CERN Analysis Facility (CAF) Peter Kreuzer (RWTH Aachen) - Stephen Gowdy (CERN), Jose Afonso Sanches (UERJ Brazil) on behalf.
Kraków4FutureDaQ Institute of Physics & Nowoczesna Elektronika P.Salabura,A.Misiak,S.Kistryn,R.Tębacz,K.Korcyl & M.Kajetanowicz Discrete event simulations.
AMH001 (acmse03.ppt - 03/7/03) REMOTE++: A Script for Automatic Remote Distribution of Programs on Windows Computers Ashley Hopkins Department of Computer.
4330/6310 FIRST ASSIGNMENT Spring 2015 Jehan-François Pâris
HUBbub 2013: Developing hub tools that submit HPC jobs Rob Campbell Purdue University Thursday, September 5, 2013.
DAQ deadtime memo Kaz, Grass 2012/01/04 1. Current dead time Dead time measured on 2011/09/29  With TDCmax=4, Deadtime =350 us  With TDCmax=8, Deadtime.
Stephen Gowdy FNAL 9th Feb 2015CMS Computing Model Simulation 1.
REGISTER TRANSFER LANGUAGE (RTL) INTRODUCTION TO REGISTER Registers1.
Alien and GSI Marian Ivanov. Outlook GSI experience Alien experience Proposals for further improvement.
A Case for Application-Aware Grid Services Gabriele Garzoglio, Andrew Baranovski, Parag Mhashilkar, Anoop Rajendra*, Ljubomir Perković** Computing Division,
WS4.3-1 ANSYS, Inc. Proprietary © 2009 ANSYS, Inc. All rights reserved. July 2009 Inventory # Chapter 4 Volume Meshing – Workshop 3 Femur BF Cartesian.
ALICE Full Dress Rehearsal ALICE TF Meeting 02/08/07.
Best 20 jobs jobs sites.
Mini-Workshop on multi-core joint project Peter van Gemmeren (ANL) I/O challenges for HEP applications on multi-core processors An ATLAS Perspective.
Compute and Storage For the Farm at Jlab
Kevin Thaddeus Flood University of Wisconsin
Address – 32 bits WRITE Write Cache Write Main Byte Offset Tag Index Valid Tag Data 16K entries 16.
REGISTER TRANSFER LANGUAGE (RTL)
Vanderbilt Tier 2 Project
Philippe Charpentier CERN – LHCb On behalf of the LHCb Computing Group
US CMS Testbed.
TYPES OFF OPERATING SYSTEM
ECE 353 Lab 3 Pipeline Simulator
Computer Architecture
Implementation of IDEA on a Reconfigurable Computer
Physics-based simulation for visual computing applications
EE282h: Review Session #3 Programming Assignment #3:
ATLAS DC2 & Continuous production
Operating System Overview
Run time performance for all benchmarked software.
Computer Science. The CPU The CPU is made up of 3 main parts : Cache ALU Control Unit.
Presentation transcript:

Computer Model Simulation STEPHEN GOWDY FNAL 30th March 2015 Computing Model Simulation 1

Changing Parameters  Update the parameters to get an idea of variation on results  Changing maximum file transfer times however is unreasonable 30th March 2015 Computing Model Simulation 2 Half CPU HitNormal CPU HitDouble CPU Hit Parallel Copy 1.31 (7k) Serial Copy 1.31 (7k)1.32 (7k) Remote Read 1.32 (10k)1.35 (11k)1.40 (12k) Half Max TranNorm. Max TranDble Max Tran Parallel Copy 1.31 (7k) 1.35 (7k) Serial Copy 1.32 (7k) 1.35 (7k) Remote Read 1.35 (11k) Total Wall Clock Gs (#jobs not started)

Updating to be clock based  Previously simulation was driven by job start time  Converted to be purly clock based  Determines first job start and last job start times  Runs from first job start to twice the time to the last job start  Currently moves forward five minutes each cycle  Much slower due to all jobs being in system at start  Still getting to work  Should eliminate jobs not started due to full batch systems  Can also update to have jobs sent to sites with free CPUs 30th March 2015 Computing Model Simulation 3

Immediate Plans  Get working with new time driven events  Debug unexpected results when increasing transfer rate  Complete results phase space varying input parameters 30th March 2015 Computing Model Simulation 4