GPU Debugging Made Easy. David Lecomber CTO, Allinea Software

Size: px
Start display at page:

Download "GPU Debugging Made Easy. David Lecomber CTO, Allinea Software"

Transcription

1 GPU Debugging Made Easy David Lecomber CTO, Allinea Software

2 Allinea Software HPC development tools company Leading in HPC software tools market Wide customer base Blue-chip engineering, government and academic research Allinea DDT The leading debugger in parallel computing World's only scalable debugger Record holder for debugging software on largest machines Production use at extreme scale and desktop First at Petascale and first for GPUs! Allinea OPT Profiling tool for parallel applications

3 Some Clients and Partners Aviation and Defence Climate and Weather Energy Electronic Design Automation Academic Over 200 universities

4 Extreme machine sizes HPC core counts Growth in HPC core counts Core count Core count Average Cores Largest Smallest Average Cores Smallest Scientific progress requires more CPU hours Machine sizes are exploding Skewed by largest machines but Year common trend Software changing to exploit the machines

5 HPC's current challenge New rival to traditional processors AMD and NVIDIA GPUs OpenCL and CUDA New problems for HPC developers Data transfer multiple memory levels Grid/block layout and thread scheduling Synchronization New languages, compilers, standards Lower level NVIDIA CUDA C/C++; CUDA Driver API OpenCL Higher level CAPS HMPP PGI CUDA Fortran PGI Accelerators Cray OpenMP Accelerators

6 Today's parallel hybrid world Hardware determines the software Exploit single address space within nodes Shared memory via OpenMP, pthreads, Or to exploit GPUs CUDA, OpenCL Mixture of paradigms message passing, shared memory and GPU MPI + OpenMP Still not typical benefits not worth the shift for many MPI applications MPI + GPU Many HPC systems have GPU as the grunt of the machine Cannot leave majority of flops in a system idle! Extreme scale Many software projects are in progress because of GPUs More complex and heterogeneous than before More languages...

7 How do we fix software? With Thousands of threads Millions of variables Terabytes of data How do you figure out what's going on with your code? Old tricks long dead: multiple terminals, print statements, Different from (eg.) Google Everything is inter-related not independent We need to see all threads and processors together Does it look like your problem? Does it look like your next problem?

8 Allinea DDT Graphical debugger designed for: Multithreaded code Single address space Multiprocess or parallel code Interdependent or independent processes Multi-node software Hybrid code GPU + CPU code Any mix of the above Strong feature set Memory debugging Data analysis Managing concurrency Emphasizing differences Collective control Make as simple as possible, no more

9 Simplifying control flow Typical crash scenario: Threads/processes can be anywhere Cannot examine individually but locating threads is essential A good overview is important Leap to source for crashes Allinea DDT merges stacks from processes and threads into a tree Information scalably without overload Common faults patterns evident instantly Divergence, deadlock

10 Controlling progress Bulk control is essential for parallel debugging Group together processes Step, breakpoint, play, based on group Change interleaving order by stepping/playing selectively Integrated throughout Allinea DDT Stack and data views for group creation Morphs to scale!

11 Simplifying data divergence Developers need to see data Too many variables to trawl manually Allinea DDT compares data automatically Smart Highlighting Subtlely highlights if different on other process or if changed Now with sparklines! More detailed analysis Full cross process comparison Historical values of variables via tracepoints

12 Searching haystacks Arrays are the building blocks of HPC Largest jobs accumulate vast terabytes of data ~2GB per core is typical max available and frequently used Allinea DDT displays and searches across whole job in parallel Sometimes need to search for NaN/Inf etc. Export at runtime Working on real visualization integration

13 Debugging for Petascale Allinea DDT scales DDT 3.0 Performance Figures A tree network communicates with daemons Logarithmic performance Jaguar Cray XT5 Partnership with largest users US DoE Oak Ridge National Laboratories Also projects with Argonne National Lab, CEA (France), and others Time (Seconds) 0.08 High performance debugging 0.06 Over 220,000 cores debugged simultaneously 0.04 Step all and display stacks in ~1/10 second , , , ,000 Usability: Scalable interface and features Memory debugging Array filtering MPI Processes All Step All Breakpoint Data comparison, etc.

14 but what about the GPUs?

15 Heterogeneity example - GPU Command line tool difficult to see through Fundamentals of control and inspection in place... But... intractable thread lists make usage impossible Now consider multiple such tools for MPI! Support for the other compilers?

16 Life's easier with a GUI Allinea DDT supports NVIDIA GPUs Built on NVIDIA's low level efforts Cuda-gdb Driver Compiler Compile debug fix! nvcc -g -G Running on the GPU Real chance of finding real GPU bugs Not as quick as debugging on CPU GPU and CPU within one interface Easy to switch between contexts Parallel stacks, thread selectors etc. Data and threads from each context is clear Step warps, grids, kernels

17 Simple CUDA debugging Almost like debugging a CPU Double click to set breakpoints Automatically stop on kernel launch Stop at a line of CUDA code Hover the mouse for more information Step a warp, block or kernel Follow the logic of individual threads through the kernel Switch threads to see thread data Run through to a crash CUDA Memcheck feature detects read/write errors Data types shown Register, shared, constant, global...

18 Kernel and system overviews Kernel progress view Shows progress through kernels Click to select a thread Device overview shows system properties Handy for optimizing grid sizes Handy for bug fixing and detecting hardware failure!

19 DDT for CAPS HMPP Source-to-source compiler Higher level than CUDA F90 to C/CUDA, C to C/CUDA Allinea and CAPS developing debugging support for HMPP Debuggable inside C kernels (codelets) on the GPU F90 multi-dimensional arrays supported Auto-reporting of CAPS runtime errors to the DDT GUI Also able to debug codelets running on the CPU

20 DDT For Directives - Cray Source to PTX level compiler Higher level than CUDA OpenMP accelerator directives/pragmas Debuggable Run accelerated code on the CPU by setting -O0 Debugging of the GPU itself: work in progress with Allinea/Cray C/F90 examples debuggable Use -g -Gomp compiler flags to debug on the GPU

21 DDT for Portland compilers PGI Accelerator Model Debug on CPU only use - ta=host to set this Runs as a single thread on the CPU Debugging possible but race conditions wouldn't be seen PGI CUDA Fortran Debug on CPU only use - Mcuda=emu flag Runs multithreaded on the CPU if GPU disabled Works well with DDT Easy to see missing syncthreads, for example

22 Common Errors Part I Kernel bounds getting the right grids and blocks Incorrect kernel thread boundaries can lead to incomplete results Solution: Use DDT's multi-dimensional array viewer to look at data and find the missing indexes with 3D display and filtering support

23 Common Errors Part II Kernel bounds getting the right grids and blocks Incorrect kernel thread boundaries can lead to crashing of the kernel Solution: Bugs often trigger CUDA memcheck errors Run with DDT and CUDA memory debugging enabled

24 Summary GPU debugging can be simple with Allinea DDT On-device debugging is similar to normal debugging Many more threads but still manageable Existing MPI ideas work well for GPU threads Also a solution for cluster systems Multiple language choices for GPUs CUDA may not be the right level for your project Debugging support is available for high and low level languages

Development tools to enable Multicore

Development tools to enable Multicore Development tools to enable Multicore From the desktop to the extreme A perspective on multicore looking in from HPC David Lecomber CTO, Allinea Software david@allinea.com Introduction The Multicore Challenge

More information

Debugging HPC Applications. David Lecomber CTO, Allinea Software

Debugging HPC Applications. David Lecomber CTO, Allinea Software Debugging HPC Applications David Lecomber CTO, Allinea Software david@allinea.com Agenda Bugs and Debugging Debugging parallel applications Debugging OpenACC and other hybrid codes Debugging for Petascale

More information

Debugging for the hybrid-multicore age (A HPC Perspective) David Lecomber CTO, Allinea Software

Debugging for the hybrid-multicore age (A HPC Perspective) David Lecomber CTO, Allinea Software Debugging for the hybrid-multicore age (A HPC Perspective) David Lecomber CTO, Allinea Software david@allinea.com Agenda What is HPC? How is scale affecting HPC? Achieving tool scalability Scale in practice

More information

Development Tools for Parallel Computing. David Lecomber CTO, Allinea Software

Development Tools for Parallel Computing. David Lecomber CTO, Allinea Software Development Tools for Parallel Computing David Lecomber CTO, Allinea Software david@allinea.com Agenda Introduction What is HPC Bugs and Debugging Debugging parallel applications Challenges for the future

More information

Debugging at Scale Lindon Locks

Debugging at Scale Lindon Locks Debugging at Scale Lindon Locks llocks@allinea.com Debugging at Scale At scale debugging - from 100 cores to 250,000 Problems faced by developers on real systems Alternative approaches to debugging and

More information

Understanding Dynamic Parallelism

Understanding Dynamic Parallelism Understanding Dynamic Parallelism Know your code and know yourself Presenter: Mark O Connor, VP Product Management Agenda Introduction and Background Fixing a Dynamic Parallelism Bug Understanding Dynamic

More information

Developing, Debugging, and Optimizing GPU Codes for High Performance Computing with Allinea Forge

Developing, Debugging, and Optimizing GPU Codes for High Performance Computing with Allinea Forge Developing, Debugging, and Optimizing GPU Codes for High Performance Computing with Allinea Forge Ryan Hulguin Applications Engineer ryan.hulguin@arm.com Agenda Introduction Overview of Allinea Products

More information

Debugging CUDA Applications with Allinea DDT. Ian Lumb Sr. Systems Engineer, Allinea Software Inc.

Debugging CUDA Applications with Allinea DDT. Ian Lumb Sr. Systems Engineer, Allinea Software Inc. Debugging CUDA Applications with Allinea DDT Ian Lumb Sr. Systems Engineer, Allinea Software Inc. ilumb@allinea.com GTC 2013, San Jose, March 20, 2013 Embracing GPUs GPUs a rival to traditional processors

More information

Allinea Unified Environment

Allinea Unified Environment Allinea Unified Environment Allinea s unified tools for debugging and profiling HPC Codes Beau Paisley Allinea Software bpaisley@allinea.com 720.583.0380 Today s Challenge Q: What is the impact of current

More information

Welcomes PRACE/LinkSCEEM 2011 Winter School Jacques Philouze Vice President Sales & Marketing

Welcomes PRACE/LinkSCEEM 2011 Winter School Jacques Philouze Vice President Sales & Marketing Welcomes PRACE/LinkSCEEM 2011 Winter School Jacques Philouze jacques@allinea.com Vice President Sales & Marketing Content Company Background Products in more depth Allinea OPT (Optimization and Profiling

More information

Addressing the Increasing Challenges of Debugging on Accelerated HPC Systems. Ed Hinkel Senior Sales Engineer

Addressing the Increasing Challenges of Debugging on Accelerated HPC Systems. Ed Hinkel Senior Sales Engineer Addressing the Increasing Challenges of Debugging on Accelerated HPC Systems Ed Hinkel Senior Sales Engineer Agenda Overview - Rogue Wave & TotalView GPU Debugging with TotalView Nvdia CUDA Intel Phi 2

More information

Tools and Methodology for Ensuring HPC Programs Correctness and Performance. Beau Paisley

Tools and Methodology for Ensuring HPC Programs Correctness and Performance. Beau Paisley Tools and Methodology for Ensuring HPC Programs Correctness and Performance Beau Paisley bpaisley@allinea.com About Allinea Over 15 years of business focused on parallel programming development tools Strong

More information

Productive Performance on the Cray XK System Using OpenACC Compilers and Tools

Productive Performance on the Cray XK System Using OpenACC Compilers and Tools Productive Performance on the Cray XK System Using OpenACC Compilers and Tools Luiz DeRose Sr. Principal Engineer Programming Environments Director Cray Inc. 1 The New Generation of Supercomputers Hybrid

More information

Introduction to debugging. Martin Čuma Center for High Performance Computing University of Utah

Introduction to debugging. Martin Čuma Center for High Performance Computing University of Utah Introduction to debugging Martin Čuma Center for High Performance Computing University of Utah m.cuma@utah.edu Overview Program errors Simple debugging Graphical debugging DDT and Totalview Intel tools

More information

Portable and Productive Performance with OpenACC Compilers and Tools. Luiz DeRose Sr. Principal Engineer Programming Environments Director Cray Inc.

Portable and Productive Performance with OpenACC Compilers and Tools. Luiz DeRose Sr. Principal Engineer Programming Environments Director Cray Inc. Portable and Productive Performance with OpenACC Compilers and Tools Luiz DeRose Sr. Principal Engineer Programming Environments Director Cray Inc. 1 Cray: Leadership in Computational Research Earth Sciences

More information

Parallel Programming and Debugging with CUDA C. Geoff Gerfin Sr. System Software Engineer

Parallel Programming and Debugging with CUDA C. Geoff Gerfin Sr. System Software Engineer Parallel Programming and Debugging with CUDA C Geoff Gerfin Sr. System Software Engineer CUDA - NVIDIA s Architecture for GPU Computing Broad Adoption Over 250M installed CUDA-enabled GPUs GPU Computing

More information

Titan - Early Experience with the Titan System at Oak Ridge National Laboratory

Titan - Early Experience with the Titan System at Oak Ridge National Laboratory Office of Science Titan - Early Experience with the Titan System at Oak Ridge National Laboratory Buddy Bland Project Director Oak Ridge Leadership Computing Facility November 13, 2012 ORNL s Titan Hybrid

More information

CUDA Development Using NVIDIA Nsight, Eclipse Edition. David Goodwin

CUDA Development Using NVIDIA Nsight, Eclipse Edition. David Goodwin CUDA Development Using NVIDIA Nsight, Eclipse Edition David Goodwin NVIDIA Nsight Eclipse Edition CUDA Integrated Development Environment Project Management Edit Build Debug Profile SC'12 2 Powered By

More information

How to write code that will survive the many-core revolution Write once, deploy many(-cores) F. Bodin, CTO

How to write code that will survive the many-core revolution Write once, deploy many(-cores) F. Bodin, CTO How to write code that will survive the many-core revolution Write once, deploy many(-cores) F. Bodin, CTO Foreword How to write code that will survive the many-core revolution? is being setup as a collective

More information

Introduction to CUDA Algoritmi e Calcolo Parallelo. Daniele Loiacono

Introduction to CUDA Algoritmi e Calcolo Parallelo. Daniele Loiacono Introduction to CUDA Algoritmi e Calcolo Parallelo References This set of slides is mainly based on: CUDA Technical Training, Dr. Antonino Tumeo, Pacific Northwest National Laboratory Slide of Applied

More information

STARTING THE DDT DEBUGGER ON MIO, AUN, & MC2. (Mouse over to the left to see thumbnails of all of the slides)

STARTING THE DDT DEBUGGER ON MIO, AUN, & MC2. (Mouse over to the left to see thumbnails of all of the slides) STARTING THE DDT DEBUGGER ON MIO, AUN, & MC2 (Mouse over to the left to see thumbnails of all of the slides) ALLINEA DDT Allinea DDT is a powerful, easy-to-use graphical debugger capable of debugging a

More information

GPU Technology Conference Three Ways to Debug Parallel CUDA Applications: Interactive, Batch, and Corefile

GPU Technology Conference Three Ways to Debug Parallel CUDA Applications: Interactive, Batch, and Corefile GPU Technology Conference 2015 Three Ways to Debug Parallel CUDA Applications: Interactive, Batch, and Corefile Three Ways to Debug Parallel CUDA Applications: Interactive, Batch, and Corefile What do

More information

Debugging with GDB and DDT

Debugging with GDB and DDT Debugging with GDB and DDT Ramses van Zon SciNet HPC Consortium University of Toronto June 13, 2014 1/41 Ontario HPC Summerschool 2014 Central Edition: Toronto Outline Debugging Basics Debugging with the

More information

Debugging with GDB and DDT

Debugging with GDB and DDT Debugging with GDB and DDT Ramses van Zon SciNet HPC Consortium University of Toronto June 28, 2012 1/41 Ontario HPC Summerschool 2012 Central Edition: Toronto Outline Debugging Basics Debugging with the

More information

Debugging Your CUDA Applications With CUDA-GDB

Debugging Your CUDA Applications With CUDA-GDB Debugging Your CUDA Applications With CUDA-GDB Outline Introduction Installation & Usage Program Execution Control Thread Focus Program State Inspection Run-Time Error Detection Tips & Miscellaneous Notes

More information

The Titan Tools Experience

The Titan Tools Experience The Titan Tools Experience Michael J. Brim, Ph.D. Computer Science Research, CSMD/NCCS Petascale Tools Workshop 213 Madison, WI July 15, 213 Overview of Titan Cray XK7 18,688+ compute nodes 16-core AMD

More information

An Introduction to OpenACC

An Introduction to OpenACC An Introduction to OpenACC Alistair Hart Cray Exascale Research Initiative Europe 3 Timetable Day 1: Wednesday 29th August 2012 13:00 Welcome and overview 13:15 Session 1: An Introduction to OpenACC 13:15

More information

CUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav

CUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav CUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav CMPE655 - Multiple Processor Systems Fall 2015 Rochester Institute of Technology Contents What is GPGPU? What s the need? CUDA-Capable GPU Architecture

More information

OpenACC/CUDA/OpenMP... 1 Languages and Libraries... 3 Multi-GPU support... 4 How OpenACC Works... 4

OpenACC/CUDA/OpenMP... 1 Languages and Libraries... 3 Multi-GPU support... 4 How OpenACC Works... 4 OpenACC Course Class #1 Q&A Contents OpenACC/CUDA/OpenMP... 1 Languages and Libraries... 3 Multi-GPU support... 4 How OpenACC Works... 4 OpenACC/CUDA/OpenMP Q: Is OpenACC an NVIDIA standard or is it accepted

More information

Trends in HPC (hardware complexity and software challenges)

Trends in HPC (hardware complexity and software challenges) Trends in HPC (hardware complexity and software challenges) Mike Giles Oxford e-research Centre Mathematical Institute MIT seminar March 13th, 2013 Mike Giles (Oxford) HPC Trends March 13th, 2013 1 / 18

More information

Tesla GPU Computing A Revolution in High Performance Computing

Tesla GPU Computing A Revolution in High Performance Computing Tesla GPU Computing A Revolution in High Performance Computing Gernot Ziegler, Developer Technology (Compute) (Material by Thomas Bradley) Agenda Tesla GPU Computing CUDA Fermi What is GPU Computing? Introduction

More information

Overlapping Computation and Communication for Advection on Hybrid Parallel Computers

Overlapping Computation and Communication for Advection on Hybrid Parallel Computers Overlapping Computation and Communication for Advection on Hybrid Parallel Computers James B White III (Trey) trey@ucar.edu National Center for Atmospheric Research Jack Dongarra dongarra@eecs.utk.edu

More information

Introduction to CUDA Algoritmi e Calcolo Parallelo. Daniele Loiacono

Introduction to CUDA Algoritmi e Calcolo Parallelo. Daniele Loiacono Introduction to CUDA Algoritmi e Calcolo Parallelo References q This set of slides is mainly based on: " CUDA Technical Training, Dr. Antonino Tumeo, Pacific Northwest National Laboratory " Slide of Applied

More information

Improving the Productivity of Scalable Application Development with TotalView May 18th, 2010

Improving the Productivity of Scalable Application Development with TotalView May 18th, 2010 Improving the Productivity of Scalable Application Development with TotalView May 18th, 2010 Chris Gottbrath Principal Product Manager Rogue Wave Major Product Offerings 2 TotalView Technologies Family

More information

CUDA Programming Model

CUDA Programming Model CUDA Xing Zeng, Dongyue Mou Introduction Example Pro & Contra Trend Introduction Example Pro & Contra Trend Introduction What is CUDA? - Compute Unified Device Architecture. - A powerful parallel programming

More information

Hybrid KAUST Many Cores and OpenACC. Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS

Hybrid KAUST Many Cores and OpenACC. Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS + Hybrid Computing @ KAUST Many Cores and OpenACC Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS + Agenda Hybrid Computing n Hybrid Computing n From Multi-Physics

More information

Trends and Challenges in Multicore Programming

Trends and Challenges in Multicore Programming Trends and Challenges in Multicore Programming Eva Burrows Bergen Language Design Laboratory (BLDL) Department of Informatics, University of Bergen Bergen, March 17, 2010 Outline The Roadmap of Multicores

More information

It s not my fault! Finding errors in parallel codes 找並行程序的錯誤

It s not my fault! Finding errors in parallel codes 找並行程序的錯誤 It s not my fault! Finding errors in parallel codes 找並行程序的錯誤 David Abramson Minh Dinh (UQ) Chao Jin (UQ) Research Computing Centre, University of Queensland, Brisbane Australia Luiz DeRose (Cray) Bob Moench

More information

ECMWF Workshop on High Performance Computing in Meteorology. 3 rd November Dean Stewart

ECMWF Workshop on High Performance Computing in Meteorology. 3 rd November Dean Stewart ECMWF Workshop on High Performance Computing in Meteorology 3 rd November 2010 Dean Stewart Agenda Company Overview Rogue Wave Product Overview IMSL Fortran TotalView Debugger Acumem ThreadSpotter 1 Copyright

More information

CUDA. Matthew Joyner, Jeremy Williams

CUDA. Matthew Joyner, Jeremy Williams CUDA Matthew Joyner, Jeremy Williams Agenda What is CUDA? CUDA GPU Architecture CPU/GPU Communication Coding in CUDA Use cases of CUDA Comparison to OpenCL What is CUDA? What is CUDA? CUDA is a parallel

More information

Introduction to GPU hardware and to CUDA

Introduction to GPU hardware and to CUDA Introduction to GPU hardware and to CUDA Philip Blakely Laboratory for Scientific Computing, University of Cambridge Philip Blakely (LSC) GPU introduction 1 / 35 Course outline Introduction to GPU hardware

More information

Introduction to MPI. EAS 520 High Performance Scientific Computing. University of Massachusetts Dartmouth. Spring 2014

Introduction to MPI. EAS 520 High Performance Scientific Computing. University of Massachusetts Dartmouth. Spring 2014 Introduction to MPI EAS 520 High Performance Scientific Computing University of Massachusetts Dartmouth Spring 2014 References This presentation is almost an exact copy of Dartmouth College's Introduction

More information

Addressing Heterogeneity in Manycore Applications

Addressing Heterogeneity in Manycore Applications Addressing Heterogeneity in Manycore Applications RTM Simulation Use Case stephane.bihan@caps-entreprise.com Oil&Gas HPC Workshop Rice University, Houston, March 2008 www.caps-entreprise.com Introduction

More information

Guillimin HPC Users Meeting July 14, 2016

Guillimin HPC Users Meeting July 14, 2016 Guillimin HPC Users Meeting July 14, 2016 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Outline Compute Canada News System Status Software Updates Training

More information

OpenACC Course. Office Hour #2 Q&A

OpenACC Course. Office Hour #2 Q&A OpenACC Course Office Hour #2 Q&A Q1: How many threads does each GPU core have? A: GPU cores execute arithmetic instructions. Each core can execute one single precision floating point instruction per cycle

More information

Welcome. HRSK Practical on Debugging, Zellescher Weg 12 Willers-Bau A106 Tel

Welcome. HRSK Practical on Debugging, Zellescher Weg 12 Willers-Bau A106 Tel Center for Information Services and High Performance Computing (ZIH) Welcome HRSK Practical on Debugging, 03.04.2009 Zellescher Weg 12 Willers-Bau A106 Tel. +49 351-463 - 31945 Matthias Lieber (matthias.lieber@tu-dresden.de)

More information

CUDA GPGPU Workshop 2012

CUDA GPGPU Workshop 2012 CUDA GPGPU Workshop 2012 Parallel Programming: C thread, Open MP, and Open MPI Presenter: Nasrin Sultana Wichita State University 07/10/2012 Parallel Programming: Open MP, MPI, Open MPI & CUDA Outline

More information

How to Write Code that Will Survive the Many-Core Revolution

How to Write Code that Will Survive the Many-Core Revolution How to Write Code that Will Survive the Many-Core Revolution Write Once, Deploy Many(-Cores) Guillaume BARAT, EMEA Sales Manager CAPS worldwide ecosystem Customers Business Partners Involved in many European

More information

Practical Introduction to CUDA and GPU

Practical Introduction to CUDA and GPU Practical Introduction to CUDA and GPU Charlie Tang Centre for Theoretical Neuroscience October 9, 2009 Overview CUDA - stands for Compute Unified Device Architecture Introduced Nov. 2006, a parallel computing

More information

Progress on GPU Parallelization of the NIM Prototype Numerical Weather Prediction Dynamical Core

Progress on GPU Parallelization of the NIM Prototype Numerical Weather Prediction Dynamical Core Progress on GPU Parallelization of the NIM Prototype Numerical Weather Prediction Dynamical Core Tom Henderson NOAA/OAR/ESRL/GSD/ACE Thomas.B.Henderson@noaa.gov Mark Govett, Jacques Middlecoff Paul Madden,

More information

The Use of Cloud Computing Resources in an HPC Environment

The Use of Cloud Computing Resources in an HPC Environment The Use of Cloud Computing Resources in an HPC Environment Bill, Labate, UCLA Office of Information Technology Prakashan Korambath, UCLA Institute for Digital Research & Education Cloud computing becomes

More information

Incremental Migration of C and Fortran Applications to GPGPU using HMPP HPC Advisory Council China Conference 2010

Incremental Migration of C and Fortran Applications to GPGPU using HMPP HPC Advisory Council China Conference 2010 Innovative software for manycore paradigms Incremental Migration of C and Fortran Applications to GPGPU using HMPP HPC Advisory Council China Conference 2010 Introduction Many applications can benefit

More information

Overview of research activities Toward portability of performance

Overview of research activities Toward portability of performance Overview of research activities Toward portability of performance Do dynamically what can t be done statically Understand evolution of architectures Enable new programming models Put intelligence into

More information

TotalView. Debugging Tool Presentation. Josip Jakić

TotalView. Debugging Tool Presentation. Josip Jakić TotalView Debugging Tool Presentation Josip Jakić josipjakic@ipb.ac.rs Agenda Introduction Getting started with TotalView Primary windows Basic functions Further functions Debugging parallel programs Topics

More information

Introduction CPS343. Spring Parallel and High Performance Computing. CPS343 (Parallel and HPC) Introduction Spring / 29

Introduction CPS343. Spring Parallel and High Performance Computing. CPS343 (Parallel and HPC) Introduction Spring / 29 Introduction CPS343 Parallel and High Performance Computing Spring 2018 CPS343 (Parallel and HPC) Introduction Spring 2018 1 / 29 Outline 1 Preface Course Details Course Requirements 2 Background Definitions

More information

ET International HPC Runtime Software. ET International Rishi Khan SC 11. Copyright 2011 ET International, Inc.

ET International HPC Runtime Software. ET International Rishi Khan SC 11. Copyright 2011 ET International, Inc. HPC Runtime Software Rishi Khan SC 11 Current Programming Models Shared Memory Multiprocessing OpenMP fork/join model Pthreads Arbitrary SMP parallelism (but hard to program/ debug) Cilk Work Stealing

More information

Steve Scott, Tesla CTO SC 11 November 15, 2011

Steve Scott, Tesla CTO SC 11 November 15, 2011 Steve Scott, Tesla CTO SC 11 November 15, 2011 What goal do these products have in common? Performance / W Exaflop Expectations First Exaflop Computer K Computer ~10 MW CM5 ~200 KW Not constant size, cost

More information

IBM High Performance Computing Toolkit

IBM High Performance Computing Toolkit IBM High Performance Computing Toolkit Pidad D'Souza (pidsouza@in.ibm.com) IBM, India Software Labs Top 500 : Application areas (November 2011) Systems Performance Source : http://www.top500.org/charts/list/34/apparea

More information

Chapter 3 Parallel Software

Chapter 3 Parallel Software Chapter 3 Parallel Software Part I. Preliminaries Chapter 1. What Is Parallel Computing? Chapter 2. Parallel Hardware Chapter 3. Parallel Software Chapter 4. Parallel Applications Chapter 5. Supercomputers

More information

CUDA PROGRAMMING MODEL. Carlo Nardone Sr. Solution Architect, NVIDIA EMEA

CUDA PROGRAMMING MODEL. Carlo Nardone Sr. Solution Architect, NVIDIA EMEA CUDA PROGRAMMING MODEL Carlo Nardone Sr. Solution Architect, NVIDIA EMEA CUDA: COMMON UNIFIED DEVICE ARCHITECTURE Parallel computing architecture and programming model GPU Computing Application Includes

More information

High-Performance and Parallel Computing

High-Performance and Parallel Computing 9 High-Performance and Parallel Computing 9.1 Code optimization To use resources efficiently, the time saved through optimizing code has to be weighed against the human resources required to implement

More information

GPU Computing with NVIDIA s new Kepler Architecture

GPU Computing with NVIDIA s new Kepler Architecture GPU Computing with NVIDIA s new Kepler Architecture Axel Koehler Sr. Solution Architect HPC HPC Advisory Council Meeting, March 13-15 2013, Lugano 1 NVIDIA: Parallel Computing Company GPUs: GeForce, Quadro,

More information

Pedraforca: a First ARM + GPU Cluster for HPC

Pedraforca: a First ARM + GPU Cluster for HPC www.bsc.es Pedraforca: a First ARM + GPU Cluster for HPC Nikola Puzovic, Alex Ramirez We ve hit the power wall ALL computers are limited by power consumption Energy-efficient approaches Multi-core Fujitsu

More information

COMP528: Multi-core and Multi-Processor Computing

COMP528: Multi-core and Multi-Processor Computing COMP528: Multi-core and Multi-Processor Computing Dr Michael K Bane, G14, Computer Science, University of Liverpool m.k.bane@liverpool.ac.uk https://cgi.csc.liv.ac.uk/~mkbane/comp528 2X So far Why and

More information

Allinea DDT Debugger. Dan Mazur, McGill HPC March 5,

Allinea DDT Debugger. Dan Mazur, McGill HPC  March 5, Allinea DDT Debugger Dan Mazur, McGill HPC daniel.mazur@mcgill.ca guillimin@calculquebec.ca March 5, 2015 1 Outline Introduction and motivation Guillimin login and DDT configuration Compiling for a debugger

More information

MIGRATION OF LEGACY APPLICATIONS TO HETEROGENEOUS ARCHITECTURES Francois Bodin, CTO, CAPS Entreprise. June 2011

MIGRATION OF LEGACY APPLICATIONS TO HETEROGENEOUS ARCHITECTURES Francois Bodin, CTO, CAPS Entreprise. June 2011 MIGRATION OF LEGACY APPLICATIONS TO HETEROGENEOUS ARCHITECTURES Francois Bodin, CTO, CAPS Entreprise June 2011 FREE LUNCH IS OVER, CODES HAVE TO MIGRATE! Many existing legacy codes needs to migrate to

More information

Tesla Architecture, CUDA and Optimization Strategies

Tesla Architecture, CUDA and Optimization Strategies Tesla Architecture, CUDA and Optimization Strategies Lan Shi, Li Yi & Liyuan Zhang Hauptseminar: Multicore Architectures and Programming Page 1 Outline Tesla Architecture & CUDA CUDA Programming Optimization

More information

DDT Debugging Techniques

DDT Debugging Techniques DDT Debugging Techniques Carlos Rosales carlos@tacc.utexas.edu Scaling to Petascale 2010 July 7, 2010 Debugging Parallel Programs Usual problems Memory access issues Special cases not accounted for in

More information

GPU Programming Using NVIDIA CUDA

GPU Programming Using NVIDIA CUDA GPU Programming Using NVIDIA CUDA Siddhante Nangla 1, Professor Chetna Achar 2 1, 2 MET s Institute of Computer Science, Bandra Mumbai University Abstract: GPGPU or General-Purpose Computing on Graphics

More information

TOOLS FOR IMPROVING CROSS-PLATFORM SOFTWARE DEVELOPMENT

TOOLS FOR IMPROVING CROSS-PLATFORM SOFTWARE DEVELOPMENT TOOLS FOR IMPROVING CROSS-PLATFORM SOFTWARE DEVELOPMENT Eric Kelmelis 28 March 2018 OVERVIEW BACKGROUND Evolution of processing hardware CROSS-PLATFORM KERNEL DEVELOPMENT Write once, target multiple hardware

More information

Towards a codelet-based runtime for exascale computing. Chris Lauderdale ET International, Inc.

Towards a codelet-based runtime for exascale computing. Chris Lauderdale ET International, Inc. Towards a codelet-based runtime for exascale computing Chris Lauderdale ET International, Inc. What will be covered Slide 2 of 24 Problems & motivation Codelet runtime overview Codelets & complexes Dealing

More information

HPC with GPU and its applications from Inspur. Haibo Xie, Ph.D

HPC with GPU and its applications from Inspur. Haibo Xie, Ph.D HPC with GPU and its applications from Inspur Haibo Xie, Ph.D xiehb@inspur.com 2 Agenda I. HPC with GPU II. YITIAN solution and application 3 New Moore s Law 4 HPC? HPC stands for High Heterogeneous Performance

More information

Particle-in-Cell Simulations on Modern Computing Platforms. Viktor K. Decyk and Tajendra V. Singh UCLA

Particle-in-Cell Simulations on Modern Computing Platforms. Viktor K. Decyk and Tajendra V. Singh UCLA Particle-in-Cell Simulations on Modern Computing Platforms Viktor K. Decyk and Tajendra V. Singh UCLA Outline of Presentation Abstraction of future computer hardware PIC on GPUs OpenCL and Cuda Fortran

More information

Advanced CUDA Optimizations. Umar Arshad ArrayFire

Advanced CUDA Optimizations. Umar Arshad ArrayFire Advanced CUDA Optimizations Umar Arshad (@arshad_umar) ArrayFire (@arrayfire) ArrayFire World s leading GPU experts In the industry since 2007 NVIDIA Partner Deep experience working with thousands of customers

More information

DDT: A visual, parallel debugger on Ra

DDT: A visual, parallel debugger on Ra DDT: A visual, parallel debugger on Ra David M. Larue dlarue@mines.edu High Performance & Research Computing Campus Computing, Communications, and Information Technologies Colorado School of Mines March,

More information

The Eclipse Parallel Tools Platform

The Eclipse Parallel Tools Platform May 1, 2012 Toward an Integrated Development Environment for Improved Software Engineering on Crays Agenda 1. What is the Eclipse Parallel Tools Platform (PTP) 2. Tour of features available in Eclipse/PTP

More information

Scalable Debugging with TotalView on Blue Gene. John DelSignore, CTO TotalView Technologies

Scalable Debugging with TotalView on Blue Gene. John DelSignore, CTO TotalView Technologies Scalable Debugging with TotalView on Blue Gene John DelSignore, CTO TotalView Technologies Agenda TotalView on Blue Gene A little history Current status Recent TotalView improvements ReplayEngine (reverse

More information

Accelerate HPC Development with Allinea Performance Tools

Accelerate HPC Development with Allinea Performance Tools Accelerate HPC Development with Allinea Performance Tools 19 April 2016 VI-HPS, LRZ Florent Lebeau / Ryan Hulguin flebeau@allinea.com / rhulguin@allinea.com Agenda 09:00 09:15 Introduction 09:15 09:45

More information

CRAY XK6 REDEFINING SUPERCOMPUTING. - Sanjana Rakhecha - Nishad Nerurkar

CRAY XK6 REDEFINING SUPERCOMPUTING. - Sanjana Rakhecha - Nishad Nerurkar CRAY XK6 REDEFINING SUPERCOMPUTING - Sanjana Rakhecha - Nishad Nerurkar CONTENTS Introduction History Specifications Cray XK6 Architecture Performance Industry acceptance and applications Summary INTRODUCTION

More information

Open Compute Stack (OpenCS) Overview. D.D. Nikolić Updated: 20 August 2018 DAE Tools Project,

Open Compute Stack (OpenCS) Overview. D.D. Nikolić Updated: 20 August 2018 DAE Tools Project, Open Compute Stack (OpenCS) Overview D.D. Nikolić Updated: 20 August 2018 DAE Tools Project, http://www.daetools.com/opencs What is OpenCS? A framework for: Platform-independent model specification 1.

More information

OVERVIEW OF MPC JUNE 24 TH LLNL Meeting June 15th, 2015 PAGE 1

OVERVIEW OF MPC JUNE 24 TH LLNL Meeting June 15th, 2015 PAGE 1 OVERVIEW OF MPC Forum Teratec Patrick CARRIBA ULT, Julien JAEGER, Marc PERACHE CEA, DAM, DIF, F-91297 Arpajon, France www.cea.fr www.cea.fr JUNE 24 TH 2015 LLNL Meeting June 15th, 2015 PAGE 1 Context Starting

More information

HPC Architectures. Types of resource currently in use

HPC Architectures. Types of resource currently in use HPC Architectures Types of resource currently in use Reusing this material This work is licensed under a Creative Commons Attribution- NonCommercial-ShareAlike 4.0 International License. http://creativecommons.org/licenses/by-nc-sa/4.0/deed.en_us

More information

Parallelism. Parallel Hardware. Introduction to Computer Systems

Parallelism. Parallel Hardware. Introduction to Computer Systems Parallelism We have been discussing the abstractions and implementations that make up an individual computer system in considerable detail up to this point. Our model has been a largely sequential one,

More information

Debugging, benchmarking, tuning i.e. software development tools. Martin Čuma Center for High Performance Computing University of Utah

Debugging, benchmarking, tuning i.e. software development tools. Martin Čuma Center for High Performance Computing University of Utah Debugging, benchmarking, tuning i.e. software development tools Martin Čuma Center for High Performance Computing University of Utah m.cuma@utah.edu SW development tools Development environments Compilers

More information

Introduction to Multicore Programming

Introduction to Multicore Programming Introduction to Multicore Programming Minsoo Ryu Department of Computer Science and Engineering 2 1 Multithreaded Programming 2 Synchronization 3 Automatic Parallelization and OpenMP 4 GPGPU 5 Q& A 2 Multithreaded

More information

Pragma-based GPU Programming and HMPP Workbench. Scott Grauer-Gray

Pragma-based GPU Programming and HMPP Workbench. Scott Grauer-Gray Pragma-based GPU Programming and HMPP Workbench Scott Grauer-Gray Pragma-based GPU programming Write programs for GPU processing without (directly) using CUDA/OpenCL Place pragmas to drive processing on

More information

Present and Future Leadership Computers at OLCF

Present and Future Leadership Computers at OLCF Present and Future Leadership Computers at OLCF Al Geist ORNL Corporate Fellow DOE Data/Viz PI Meeting January 13-15, 2015 Walnut Creek, CA ORNL is managed by UT-Battelle for the US Department of Energy

More information

April 4-7, 2016 Silicon Valley. CUDA DEBUGGING TOOLS IN CUDA8 Vyas Venkataraman, Kudbudeen Jalaludeen, April 6, 2016

April 4-7, 2016 Silicon Valley. CUDA DEBUGGING TOOLS IN CUDA8 Vyas Venkataraman, Kudbudeen Jalaludeen, April 6, 2016 April 4-7, 2016 Silicon Valley CUDA DEBUGGING TOOLS IN CUDA8 Vyas Venkataraman, Kudbudeen Jalaludeen, April 6, 2016 AGENDA General debugging approaches Cuda-gdb Demo 2 CUDA API CHECKING CUDA calls are

More information

Fahad Zafar, Dibyajyoti Ghosh, Lawrence Sebald, Shujia Zhou. University of Maryland Baltimore County

Fahad Zafar, Dibyajyoti Ghosh, Lawrence Sebald, Shujia Zhou. University of Maryland Baltimore County Accelerating a climate physics model with OpenCL Fahad Zafar, Dibyajyoti Ghosh, Lawrence Sebald, Shujia Zhou University of Maryland Baltimore County Introduction The demand to increase forecast predictability

More information

GPUs and Emerging Architectures

GPUs and Emerging Architectures GPUs and Emerging Architectures Mike Giles mike.giles@maths.ox.ac.uk Mathematical Institute, Oxford University e-infrastructure South Consortium Oxford e-research Centre Emerging Architectures p. 1 CPUs

More information

Introduction to Parallel and Distributed Computing. Linh B. Ngo CPSC 3620

Introduction to Parallel and Distributed Computing. Linh B. Ngo CPSC 3620 Introduction to Parallel and Distributed Computing Linh B. Ngo CPSC 3620 Overview: What is Parallel Computing To be run using multiple processors A problem is broken into discrete parts that can be solved

More information

Performance Tools for Technical Computing

Performance Tools for Technical Computing Christian Terboven terboven@rz.rwth-aachen.de Center for Computing and Communication RWTH Aachen University Intel Software Conference 2010 April 13th, Barcelona, Spain Agenda o Motivation and Methodology

More information

The Cray Programming Environment. An Introduction

The Cray Programming Environment. An Introduction The Cray Programming Environment An Introduction Vision Cray systems are designed to be High Productivity as well as High Performance Computers The Cray Programming Environment (PE) provides a simple consistent

More information

Preparing GPU-Accelerated Applications for the Summit Supercomputer

Preparing GPU-Accelerated Applications for the Summit Supercomputer Preparing GPU-Accelerated Applications for the Summit Supercomputer Fernanda Foertter HPC User Assistance Group Training Lead foertterfs@ornl.gov This research used resources of the Oak Ridge Leadership

More information

High Performance Computing. Introduction to Parallel Computing

High Performance Computing. Introduction to Parallel Computing High Performance Computing Introduction to Parallel Computing Acknowledgements Content of the following presentation is borrowed from The Lawrence Livermore National Laboratory https://hpc.llnl.gov/training/tutorials

More information

Programmer's View of Execution Teminology Summary

Programmer's View of Execution Teminology Summary CS 61C: Great Ideas in Computer Architecture (Machine Structures) Lecture 28: GP-GPU Programming GPUs Hardware specialized for graphics calculations Originally developed to facilitate the use of CAD programs

More information

CS 220: Introduction to Parallel Computing. Introduction to CUDA. Lecture 28

CS 220: Introduction to Parallel Computing. Introduction to CUDA. Lecture 28 CS 220: Introduction to Parallel Computing Introduction to CUDA Lecture 28 Today s Schedule Project 4 Read-Write Locks Introduction to CUDA 5/2/18 CS 220: Parallel Computing 2 Today s Schedule Project

More information

Parallel Programming Libraries and implementations

Parallel Programming Libraries and implementations Parallel Programming Libraries and implementations Partners Funding Reusing this material This work is licensed under a Creative Commons Attribution- NonCommercial-ShareAlike 4.0 International License.

More information

GPU Fundamentals Jeff Larkin November 14, 2016

GPU Fundamentals Jeff Larkin November 14, 2016 GPU Fundamentals Jeff Larkin , November 4, 206 Who Am I? 2002 B.S. Computer Science Furman University 2005 M.S. Computer Science UT Knoxville 2002 Graduate Teaching Assistant 2005 Graduate

More information

Parallel Debugging with TotalView BSC-CNS

Parallel Debugging with TotalView BSC-CNS Parallel Debugging with TotalView BSC-CNS AGENDA What debugging means? Debugging Tools in the RES Allinea DDT as alternative (RogueWave Software) What is TotalView Compiling Your Program Starting totalview

More information