ORNL is managed by UT-Battelle for the US Department of Energy Titan Cross Compile Adam Simpson OLCF User Support.

Slides:



Advertisements
Similar presentations
Three types of remote process invocation
Advertisements

Presented by The Evolving Environment at NCCS Vickie Lynch.
Accelerated Linear Algebra Libraries James Wynne III NCCS User Assistance.
Μπ A Scalable & Transparent System for Simulating MPI Programs Kalyan S. Perumalla, Ph.D. Senior R&D Manager Oak Ridge National Laboratory Adjunct Professor.
ARCHER Tips and Tricks A few notes from the CSE team.
Optimizing Applications on Blue Waters
Istituto Tecnico Industriale "A. Monaco"
Eos Compilers Fernanda Foertter HPC User Assistance Specialist.
Profiling your application with Intel VTune at NERSC
Hybrid Redux: CUDA / MPI 1. CUDA / MPI Hybrid – Why? 2  Harness more hardware  16 CUDA GPUs > 1!  You have a legacy MPI code that you’d like to accelerate.
Architecture and Implementation of Lustre at the National Climate Computing Research Center Douglas Fuller National Climate Computing Research Center /
Using the Argo Cluster Paul Sexton CS 566 February 6, 2006.
Setting up of condor scheduler on computing cluster Raman Sehgal NPD-BARC.
Using Kure and Killdevil
Advanced MPI Lab MPI I/O Exercises. 1 Getting Started Get a training account from the instructor Login (using ssh) to ranger.tacc.utexas.edu.
Getting Started on Topsail Charles Davis ITS Research Computing April 8, 2009.
Parallel/Concurrent Programming on the SGI Altix Conley Read January 25, 2007 UC Riverside, Department of Computer Science.
Plans for Exploitation of the ORNL Titan Machine Richard P. Mount ATLAS Distributed Computing Technical Interchange Meeting May 17, 2013.
HPCC Mid-Morning Break Interactive High Performance Computing Dirk Colbry, Ph.D. Research Specialist Institute for Cyber Enabled Discovery.
HPCC Mid-Morning Break Dirk Colbry, Ph.D. Research Specialist Institute for Cyber Enabled Discovery Introduction to the new GPU (GFX) cluster.
ORIGINAL AUTHOR JAMES REINDERS, INTEL PRESENTED BY ADITYA AMBARDEKAR Overview for Intel Xeon Processors and Intel Xeon Phi coprocessors.
MIGRATING TO THE SHARED COMPUTING CLUSTER (SCC) SCV Staff Boston University Scientific Computing and Visualization.
The Cray XE6 Beagle Beagle Team Computation Institute.
Getting started on the Cray XE6 Beagle Beagle Team Computation.
Zeus Users’ Quickstart Training January 27/30, 2012.
WORK ON CLUSTER HYBRILIT E. Aleksandrov 1, D. Belyakov 1, M. Matveev 1, M. Vala 1,2 1 Joint Institute for nuclear research, LIT, Russia 2 Institute for.
LLNL-PRES-XXXXXX This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.
Tools and Utilities for parallel and serial codes in ENEA-GRID environment CRESCO Project: Salvatore Raia SubProject I.2 C.R. ENEA-Portici. 11/12/2007.
Lecture 8. Profiling - for Performance Analysis - Prof. Taeweon Suh Computer Science Education Korea University COM503 Parallel Computer Architecture &
The Cray XC30 “Darter” System Daniel Lucio. The Darter Supercomputer.
17-April-2007 High Performance Computing Basics April 17, 2007 Dr. David J. Haglin.
Lab System Environment
Jaguar Super Computer Topics Covered Introduction Architecture Location & Cost Bench Mark Results Location & Manufacturer Machines in top 500 Operating.
MPI and High Performance Computing: Systems and Programming Barry Britt, Systems Administrator Department of Computer Science Iowa State University.
GPU Architecture and Programming
1 The Portland Group, Inc. Brent Leback HPC User Forum, Broomfield, CO September 2009.
1 Cray Inc. 11/28/2015 Cray Inc Slide 2 Cray Cray Adaptive Supercomputing Vision Cray moves to Linux-base OS Cray Introduces CX1 Cray moves.
Introduction to the XC30 For Users of Cray’s XT5 and XK7 Aaron Vose 1.
Running Parallel Jobs Cray XE6 Workshop February 7, 2011 David Turner NERSC User Services Group.
2011/08/23 國家高速網路與計算中心 Advanced Large-scale Parallel Supercluster.
ARCHER Advanced Research Computing High End Resource
ORNL is managed by UT-Battelle for the US Department of Energy Using Darshan on Titan Verónica G. Vergara Larrea OLCF Users Conference Call August 26,
Porting processes to threads with MPC instead of forking Some slides from Marc Tchiboukdjian (IPDPS’12) : Hierarchical Local Storage Exploiting Flexible.
PAPI on Blue Gene L Using network performance counters to layout tasks for improved performance.
Intermediate Parallel Programming and Cluster Computing Workshop Oklahoma University, August 2010 Running, Using, and Maintaining a Cluster From a software.
How to use HybriLIT Matveev M. A., Zuev M.I. Heterogeneous Computations team HybriLIT Laboratory of Information Technologies (LIT), Joint Institute for.
Getting Started: XSEDE Comet Shahzeb Siddiqui - Software Systems Engineer Office: 222A Computer Building Institute of CyberScience May.
Cliff Addison University of Liverpool NW-GRID Training Event 26 th January 2007 SCore MPI Taking full advantage of GigE.
Debugging Lab Antonio Gómez-Iglesias Texas Advanced Computing Center.
Wouter Verkerke, NIKHEF 1 Using ‘stoomboot’ for NIKHEF-ATLAS batch computing What is ‘stoomboot’ – Hardware –16 machines, each 2x quad-core Pentium = 128.
Introduction to HPC Debugging with Allinea DDT Nick Forrington
Intra-Socket and Inter-Socket Communication in Multi-core Systems Roshan N.P S7 CSB Roll no:29.
11 Brian Van Straalen Portable Performance Discussion August 7, FASTMath SciDAC Institute.
Towards a High Performance Extensible Grid Architecture Klaus Krauter Muthucumaru Maheswaran {krauter,
What is SeisFlows? -Provides a complete, customizable waveform inversion workflow -So far, has been used for 3D production runs with up to 10 9 model parameters.
Advanced Computing Facility Introduction
GRID COMPUTING.
Auburn University
HPC usage and software packages
Current Generation Hypervisor Type 1 Type 2.
SHARED MEMORY PROGRAMMING WITH OpenMP
CRESCO Project: Salvatore Raia
Cray Announces Cray Inc.
Paul Sexton CS 566 February 6, 2006
Program Control Structures
HPCC Mid-Morning Break
● Taiwania 使用懶人包.
Use of VNC and RAL Systems
Frank Mueller North Carolina State University
ENERGY 211 / CME 211 Lecture 29 December 3, 2008.
Presentation transcript:

ORNL is managed by UT-Battelle for the US Department of Energy Titan Cross Compile Adam Simpson OLCF User Support

2 Cross Compiling Titan node structure - connectivity External Login Service Nodes Internet SSH aprun qsub Compute Nodes

3 Cross Compiling Titan node structure - processor External Login –4 x 8 core AMD Magny-Cours Service Nodes –6 core AMD Istanbul Compute Nodes –16 core AMD Interlagos

4 Cross Compiling Cray Compile Wrapper CC, cc, ftn Controlled by xt-asyncpe module Sets compiler based on PrgEnv-* module –Same command for PGI, GNU, Cray, Intel Sets optimizations and target processor/arch. Adds libraries based on loaded Cray modules –Networking/Communication libraries(MPI, GNI, PMI, etc.) –Science Libraries(CUDA, LibSci, NetCDF,...) –ALPS libraries

5 Cross Compiling Compile for login/service nodes Don’t run wrapper compiled code on non compute nodes –Illegal instruction Interlagos has AVX/SSE4 instructions –Missing shared libraries Error while loading shared libraries: libalpslli.so.0

6 Cross Compiling Compile for login/service nodes module load craype-target-local_host –Compile for external login / service node* –Doesn’t add Cray specific libraries –Doesn’t work as advertised module load craype-target-native –Target node common instruction set –Doesn’t add any module related libraries No MPI, LibSci, CUDA, etc. Bypass wrappers –pgcc, pgCC, pgfortran : gcc, g++, gfortran –craycc, crayc++, crayftn : icc, icpc, ifort

7 Cross Compiling Compile for login/service nodes If Cray libraries required on external logins – module switch craype-interlagos craype-mc8 If Cray libraries required on service nodes – module switch craype-interlagos craype-istanbul

8 Cross Compiling CLE 5.2 Changes xt-asyncpe : deprecated –renamed craype craype-target-* : deprecated –craype-interlagos –craype-istanbul –craype-mc8 – craype-network-gemini – craype-network-none