The Portal: Volume 1
December 20, 2011 in newsletter
SciNet’s newsletter for 2011.
December 5, 2011 in for_researchers, for_users, newsletter
The SciNet Users Group (SNUG) meetings are every month on the second Wednesday, and involve pizza, user discussion, feedback, and a one or two short talks on topics or technologies of interest to the SciNet community.
This time, we will have
The goal of this course is for incoming students, new to GPGPU but familiar with scientific programming in C, to leave being able to start writing simple kernels for their own problems, and understand the tools, techniques and libraries that will be needed to improve and optimize the results.
More info and sign up at https://support.scinet.utoronto.ca/courses/?q=node/42
Extremely useful for new users of SciNet that are not yet familiar with the Linux shell or other unix prompt systems.
For more information and sign up, go to https://support.scinet.utoronto.ca/courses/?q=node/55
Learn what SciNet resources are available, how to recompile your code and how to use the batch system, in approximately 90 minutes.
Intended for new users, but experienced users may still pick up some valuable pointers.
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/56
Note that subsequently, at noon, there is a SciNet User group meeting (see below) that participants to the intro may be interested in too, but we do ask that you sign up for this separately.
We are still looking for users (students, postdocs, staff, faculty, it does not matter) willing to giving a short talk (20-30 minutes) about interesting work that they did on SciNet clusters and how they did it! If you are up for it, email support@scinet.utoronto.ca.
More info on future SNUGs and sign-up at https://support.scinet.utoronto.ca/courses/?q=node/47 (Jan) https://support.scinet.utoronto.ca/courses/?q=node/48 (Feb) https://support.scinet.utoronto.ca/courses/?q=node/49 (Mar) https://support.scinet.utoronto.ca/courses/?q=node/50 (Apr) https://support.scinet.utoronto.ca/courses/?q=node/51 (May)
Part II of SciNet’s Scientific Computing couse. These parts can be taken as “mini-courses” or “modular courses” by astrophysics and physics graduate students.
Topics of part II: Modelling, floating point computations, validation + verification, visualization, ODEs, Monte Carlo, linear algebra, FFT.
More info: https://support.scinet.utoronto.ca/courses/?q=node/39 Sign-up: https://support.scinet.utoronto.ca/courses/?q=node/44
Part III of SciNet’s Scientific Computing couse. These parts can be taken as “mini-courses” or “modular courses” by astrophysics and physics graduate students.
Topics of part II: Profiling, optimization, openmp, mpi and hybrid programming.
More info: https://support.scinet.utoronto.ca/courses/?q=node/39 Sign-up: https://support.scinet.utoronto.ca/courses/?q=node/45
The predefined variables $HOME, $SCRATCH, $PROJECT and $ARCHIVE point to the new directories.
All new wiki content below is listed and linked on the main page:
http://wiki.scinethpc.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
November 5, 2011 in for_researchers, for_users, newsletter
This is the first of two shutdowns intended to improve certain aspects of system performance and data centre stability. File systems are the focus of this first downtime. The most visible change for users is that their home and scratch directories will be moved. See “SYSTEM NEWS” below for details.
Note that all logins and jobs will be killed at that 9:00 am. We expect to be back in the evening.
The SciNet Users Group (SNUG) meetings are every month on the second Wednesday, and involve pizza, user discussion, feedback, and a one or two short talks on topics or technologies of interest to the SciNet community.
This time, we will have
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/35
We are still looking for users (students, postdocs, staff, faculty, it does not matter) willing to giving a short talk (20-30 minutes) about interesting work that they did on SciNet clusters and how they did it! If you are up for it, email support@scinet.utoronto.ca.
More info on future SNUGs and sign-up at https://support.scinet.utoronto.ca/courses/?q=SNUG_Meetings
ParaView is a powerful open-source tool for analyzing and visualizing large multi-dimensional datasets. It is based on the Visualization Toolkit (VTK) and can run on all major platforms (Linux, Mac, Windows) both as a standalone application and as a front-end client connecting to a remote parallel server. In this two-hour long introduction I will talk about the basic workflow of a ParaView session, importing datasets in various formats, using filters, and scripting for automating ParaView tasks. This tutorial will have many hands-on exercises, so attendees are encouraged to bring a laptop with the latest copy of ParaView installed (http://www.paraview.org/paraview/resources/software.html). All sample codes and data will be provided.
This workshop will be given at SciNet by our colleague from UOIT, Alex Razoumov.
Sign-up at https://support.scinet.utoronto.ca/courses/?q=node/46.
Note: in contrast to an earlier announcement, the lectures will be given on Fridays, from 9:30 to 11:30.
See below for more details of the course. Sign-up for this part of the course is now closed.
Many computational projects start off with knowledge of the science you want to do, and with a bit of programming experience. It can be an arduous journey to get to a (maintainable) piece of code which you trust to compute the right thing. This course is aimed at reducing your struggle, and make you a more efficient computational scientist. Topics include well-established best practices for developing software as it applies to scientific computations, common numerical techniques and packages (so you don’t reinvent the wheel), and aspects of high performance computing.
The course consists of three parts: Part 1: Scientific Software Development & Design (Nov 4,11,18,25) Part 2: Numerical Tools for Physical Scientists (Jan 13,20,27 & Feb 3) Part 3: High Performance Scientific Computing (Feb 10,17 & Mar 2,9) + A wrap-up lecture on Mar 16. Each part consists of four lectures of two hours. You can sign up for separate parts, or for the course as a whole.
More details, including the full syllabus, grading, and sign-up, can be found at
http://wiki.scinethpc.ca/wiki/index.php/Scientific_Software_Development_Course
Note that these parts can be taken as “mini-courses” (AST3100) by astrophysics graduate students and as “modular courses” (PHYS2109) by physics students.
Sign up for the full course and for part 1 is closed, but you can still sign up separately for parts 2 and 3 (see below) that will be give in the Winter.
The goal of this course is for incoming students, new to GPGPU but familiar with scientific programming in C, to leave being able to start writing simple kernels for their own problems, and understand the tools, techniques and libraries that will be needed to improve and optimize the results.
More info and sign up at https://support.scinet.utoronto.ca/courses/?q=node/42
Sign-up: https://support.scinet.utoronto.ca/courses/?q=node/44
Sign-up: https://support.scinet.utoronto.ca/courses/?q=node/45
Users are responsible for making sure all their scripts and applications only use relative paths, or use the predefined variables $HOME, $SCRATCH and $PROJECT.
Note that the TechTalk of the Nov 9 SNUG will address the issue how to deal with this new setup.
Come take a look at our new website!
All new wiki content below is listed and linked on the main page:
http://wiki.scinethpc.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
October 5, 2011 in for_researchers, for_users, newsletter
All logins and jobs will be killed at that time. Power may not be restored until midnight.
Meet with SciNet analysts to discuss your application for the yearly round of national resource allocations. The call for proposals can be found here: https://computecanada.org/?mod=cms&pageId=1663&lang=EN&
The SciNet Users Group (SNUG) meetings are every month on the second Wednesday, and involve pizza, user discussion, feedback, and a one or two short talks on topics or technologies of interest to the SciNet community.
This time, we will have
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/34
The application website is https://ccdb.computecanada.org/allocation/resource_applications. Note that an information session will be held on Oct 6 (see above).
This full-day course will demonstrate how to use modern features of Fortran. It will cover the use of modules to break code into type-safe pieces; optional arguments and the use of interface; portable ways of using different sizes of integers and reals; an introduction to object-oriented programming in Fortran 2003; and a preview of co-arrays for parallel programming in Fortran 2008.
More info and sign-up at https://support.scinet.utoronto.ca/courses/?q=node/41
We are still looking for users (students, postdocs, staff, faculty, it does not matter) willing to giving a short talk (20-30 minutes) about interesting work that they did on SciNet clusters and how they did it! If you are up for it, email support@scinet.utoronto.ca.
More info on future SNUGs and sign-up at https://support.scinet.utoronto.ca/courses/?q=SNUG_Meetings
Given at SciNet by our colleague from UOIT/SharcNet, Alex Razoumov.
More details to come soon at https://support.scinet.utoronto.ca/courses/?q=node/46.
Note: in contrast to an earlier announcement, the lectures will be given on Fridays, from 9:30 to 11:30.
See below for more details of the course.
Sign-up for this part only: https://support.scinet.utoronto.ca/courses/?q=node/43
You can also sign up for all three parts, see below.
Many computational projects start off with knowledge of the science you want to do, and with a bit of programming experience. It can be an arduous journey to get to a (maintainable) piece of code which you trust to compute the right thing. This course is aimed at reducing your struggle, and make you a more efficient computational scientist. Topics include well-established best practices for developing software as it applies to scientific computations, common numerical techniques and packages (so you don’t reinvent the wheel), and aspects of high performance computing.
The course consists of three parts: Part 1: Scientific Software Development & Design (Nov 4,11,18,25) Part 2: Numerical Tools for Physical Scientists (Jan 13,20,27 & Feb 3) Part 3: High Performance Scientific Computing (Feb 10,17 & Mar 2,9) + A wrap-up lecture on Mar 16. Each part consists of four lectures of two hours. You can sign up for separate parts, or for the course as a whole.
More details, including the full syllabus, grading, and signup, can be found at https://support.scinet.utoronto.ca/courses/?q=node/39
Note that these parts can be taken as “mini-courses” by astrophysics graduate students; we are talking to other departments to see if this can be extended to their grad students as well.
The goal of this course is for incoming students, new to GPGPU but familiar with scientific programming in C, to leave being able to start writing simple kernels for their own problems, and understand the tools, techniques and libraries that will be needed to improve and optimize the results.
More info and sign up at https://support.scinet.utoronto.ca/courses/?q=node/42
To facilitate the transition, we ask the user’s cooperation in making sure all their scripts and applications only use relative paths, or use the predefined variables $HOME, $SCRATCH and $PROJECT.
All new wiki content below is listed and linked on the main page:
http://wiki.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
September 5, 2011 in for_researchers, for_users, newsletter
Learn what SciNet resources are available and how to use them, in approximately 90 minutes. Extremely useful for new users, but experienced users may still pick up some valuable pointers. This is a repeat of the Aug 26 session.
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/32.
The SciNet Users Group (SNUG) meetings are every month on the second Wednesday, and involve pizza, user discussion, feedback, and a one or two short talks on topics or technologies of interest to the SciNet community.
This time, we will have
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/33
We are still looking for users (students, postdocs, staff, faculty, it does not matter) willing to giving a short talk (20-30 minutes) about interesting work that they did on SciNet clusters and how they did it! If you are up for it, email support@scinet.utoronto.ca.
More info on future SNUGs and sign-up at https://support.scinet.utoronto.ca/courses/?q=SNUG_Meetings
SciNet presentation:
Research talks:
More info and sign-up at https://support.scinet.utoronto.ca/courses/?q=node/38
Thinking of starting a compute-intensive research project? In the middle of one but stuck on what technique or method to use?
Once a month, the experts at SciNet, Canada’s largest supercomputing centre, will have a consulting desk open for all research members of the larger University community to help them design and make decisions about their computational research tools. These clinics will usually be held on the days of the SciNet users group meetings, the 3rd Wednesday of the month, which attendees are welcome to attend.
To mark the start of the school year, this month’s clinic will be at a special date: Wed, 28 Sept, 10am-4:30pm. For the rest of the semester, it will be held at the third Wednesday of the month, 10am-12pm, 1:30pm-3:30pm.
Learn how to avoid I/O becoming the bottleneck in your large-scale computation; general strategies as well as true parallel I/O techniques (MPI-IO, HDF5, and NetCDF) will be covered in this one-day course.
More info and sign-up at https://support.scinet.utoronto.ca/courses/?q=node/40
This full-day course will demonstrate how to use modern features of Fortran. It will cover the use of modules to break code into type-safe pieces; optional arguments and the use of interface; portable ways of using different sizes of integers and reals; an introduction to object-oriented programming in Fortran 2003; and a preview of co-arrays for parallel programming in Fortran 2008.
More info and sign-up at https://support.scinet.utoronto.ca/courses/?q=node/41
Many computational projects start off with knowledge of the science you want to do, and with a bit of programming experience. It can be an arduous journey to get to a (maintainable) piece of code which you trust to compute the right thing. This course is aimed at reducing your struggle, and make you a more efficient computational scientist. Topics include well-established best practices for developing software as it applies to scientific computations, common numerical techniques and packages (so you don’t reinvent the wheel), and aspects of high performance computing.
The course consists of three parts: Part 1: Scientific Software Development & Design (Nov 3,10,17,24) Part 2: Numerical Tools for Physical Scientists (Jan 13,20,27 & Feb 3) Part 3: High Performance Scientific Computing (Feb 10,17 & Mar 2,9) + A wrap-up lecture on Mar 16. Each part consists of four lectures of two hours. You can sign up for separate parts, or for the course as a whole.
More details, including the full syllabus, grading, etc., can be found at https://support.scinet.utoronto.ca/courses/?q=node/39
Note that these parts can be taken as “mini-courses” by astrophysics graduate students; we are talking to other departments to see if this can be extended to their grad students as well.
The goal of this course is for incoming students, new to GPGPU but familiar with scientific programming in C, to leave being able to start writing simple kernels for their own problems, and understand the tools, techniques and libraries that will be needed to improve and optimize the results.
More info and sign up at https://support.scinet.utoronto.ca/courses/?q=node/42
(All new wiki content below is listed and linked on the main page: http://wiki.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
August 5, 2011 in for_researchers, for_users, newsletter
EVENTS COMING UP
The goal of this one-day course is for incoming students, new to GPGPU but familiar with scientific programming in C, to leave being able to start writing simple kernels for their own problems, and understand the tools, techniques and libraries that will be needed to improve and optimize the results.
For more information and to sign up, see: https://support.scinet.utoronto.ca/courses/?q=node/37
Learn how to use SciNet systems in approximately 90 minutes. Extremely useful for new users, but experienced users may still pick up some valuable pointers.
More sessions may be given throughout the year depending on user interest, but only the first one (Aug 25) will feature pizza!
Sign up on https://support.scinet.utoronto.ca/courses/?q=node/31.
A GPGPU workshop at SciNet in which representatives from research groups will give short talks, and then we discuss.
More info coming soon at https://support.scinet.utoronto.ca/courses/?q=node/38
A repeat of the Aug 26 session, but without the distraction of pizza.
Sign up on https://support.scinet.utoronto.ca/courses/?q=node/32.
Sign up on https://support.scinet.utoronto.ca/courses/?q=node/33
This course will likely follow the format of a weekly 3-hour session. It will consist of three parts: Part 1: Scientific Software Development & Design Part 2: Numerical Tools for Physical Scientists Part 3: High Performance Scientific Computing Each part consists of 4 lectures, which include hands-on, and can be taken separately.
More details (including whether you can get credit for this course!) will soon be available on the courses website: https://support.scinet.utoronto.ca/courses.
(All new wiki content below is listed and linked on the main page: http://wiki.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
July 5, 2011 in for_researchers, for_users, newsletter
Practical Parallel Programming With OpenMP and MPI HPCVL Training Room, 115-993 Princess St., Kingston, Ontario
Schedule: Mon July 11, 2011: OpenMP Tue July 12, 2011: MPI Wed July 13, 2011: Hybrid Time: 9:00 am – 4:00 pm (EST)
Lecturers: Hartmut Schmider and Gang Liu (HPCVL, Queen’s University, Kingston, Ontario)
Also available via video conferencing at SciNet. Contact us if you want to participate remotely (support@scinet.utoronto.ca), or see https://support.scinet.utoronto.ca/courses/?q=node/29.
Speaker: Isaac Ye, HPTC Analyst
An introductory seminar on Linux usage, aimed specifically at users new to the Linux operating system, and with an emphasis on usage typical to a user of the SHARCNET systems. Topics will include basic concepts related to the filesystem, shell usage and basic commands to help a new user be productive on SHARCNET clusters; key activities such as compilation, modules and the job scheduler will also be covered.
Registration for this event is not necessary, just point your web browser at http://my.dimdim.com/sharcnet just before the talk.
Learn how to use SciNet systems in approximately 90 minutes. Extremely useful for new users, but experienced users may still pick up some valuable pointers.
More sessions may be given throughout the year depending on user interest, but only the first one (Aug 25) will feature pizza!
Sign up on https://support.scinet.utoronto.ca/courses.
Sign up on https://support.scinet.utoronto.ca/courses/?q=node/33
(All new wiki content below is listed and linked on the main page: http://wiki.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
June 5, 2011 in for_researchers, for_users, newsletter
This event takes place at the SciNet Headquarters, Rm 235 of 256 McCaul Street, Toronto.
Sign up if you are planning to come (so we won’t run out of pizza), at https://support.scinet.utoronto.ca/courses/?q=node/26
HPCS2011 is a multidisciplinary conference that focuses on research involving High Performance Computing and its application.
This year it is given in Montreal, and focuses on HPC in medical science.
The actual symposium is from June 15 to 17. There are very worthwhile tutorial sessions on the two days before.
More info can be found at http://2011.hpcs.ca.
(All new wiki content below is listed and linked on the main page: http://wiki.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
May 5, 2011 in for_researchers, for_users, newsletter
“Scripting HALMD with Lua and Luabind”
Lua is a lightweight, embeddable scripting language. Luabind is a library that exposes C++ classes and functions to Lua. HALMD, a highly accelerated large-scale molecular dynamics package for GPUs, uses Lua and Luabind to couple a set of high-performance C++ and CUDA modules in a flexible and extensible manner.
Sign up if you are planning to come, at https://support.scinet.utoronto.ca/courses/?q=node/25
The goal of the workshop is to enable young researchers already experienced in scientific computing to leave with the knowledge necessary to begin writing the parallel codes needed for their research. The workshop will be a mix of lectures and immediate feedback on practical assignments, designed to ensure that students leave with significant experience in both OpenMP and MPI, two of the standards for parallel computing today. We aim for this workshop to be useful for graduate students and postdocs for a wide range of disciplines.
The course will be given in a yet-to-be determined location on the St. George Campus.
There will be NO FEE, but you are responsible to get the recommended BOOKS, and your own COFFEE and LUNCH.
There is LIMITED AVAILABILITY, so please only register if you are serious about attending. Registration and further details (topics, books, location) are (or will be) available at
https://support.scinet.utoronto.ca/courses/?q=node/23
This Summer School is jointly sponsored by SHARCNET, SciNet and HPCVL — your Ontario HPC consortia. It is held at the Sheridan Institute of Technology and Advanced Learning in Trafalgar, Oakville, Ontario.
This annual, intensive education event offers a week-long program of hands-on courses covering introductory HPC materials, programming for distributed systems (MPI) and shared memory environments (OpenMP), GPU programming, software best practices, debugging and much more.
To maximize the ability for persons from the widest range of SHARCNET, SciNet and HPCVL institutions to attend, a subsidized rate will be available for those traveling a reasonable distance which includes up to 4 nights accommodation in the on-site residence, and a limited number of travel subsidies will be available, reserved for those traveling very long distances (Lakehead for example).
Please watch the website (http://ss2011.sharcnet.ca) over the coming days as more information is put in place, and registration opens. Note that spaces are limited so register early!
If you have additional questions in the meantime, please e-mail ss2011@sharcnet.ca .
Let us know (support@scinet) if you’re interested in giving a TechTalk.
Sign up if you are planning to come, at https://support.scinet.utoronto.ca/courses/?q=node/26
HPCS2011 is a multidisciplinary conference that focuses on research involving High Performance Computing and its application.
This year it is given in Montreal, and focuses on HPC in medical science.
The actual symposium is from June 15 to 17. There are very worthwhile tutorial sessions on the two days before.
More info can be found at at http://2011.hpcs.ca
(All new wiki content below is listed and linked on the main page: https://support.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)
April 5, 2011 in for_researchers, for_users, newsletter
“Scripting HALMD with Lua and Luabind”
Lua is a lightweight, embeddable scripting language. Luabind is a library that exposes C++ classes and functions to Lua. HALMD, a highly accelerated large-scale molecular dynamics packqage for GPUs, uses Lua and Luabind to couple a set of high-performance C++ and CUDA modules in a flexible and extensible manner.
Sign up if you are planning to come, at https://support.scinet.utoronto.ca/courses/?q=node/18
Fortran, as the only major programming language designed explicitly for scientific programming, has come a long way since it’s 1977 version which was sensitive to spacing layout, used computed gotos and with only arrays whose sizes could only be changed by recompiling.
This is a full-day course which will will demonstrate the use of modules to break code into type-safe pieces; optional arguments and the use of interface; portable ways of using different sizes of integers and reals; an introduction to object-oriented programming in Fortran 2003.; and a preview of co-arrays for parallel programming in Fortran 2008.
Prerequisite is a significant experience in scientific programming with FORTRAN. If you are unsure about the prerequisites, contact us at support@scinet.utoronto.ca.
Sign up at https://support.scinet.utoronto.ca/courses/?q=node/21
Sign up if you are planning to come, at https://support.scinet.utoronto.ca/courses/?q=node/25
The goal of the workshop is to enable young researchers already experienced in scientific computing to leave with the knowledge necessary to begin writing the parallel codes needed for their research. The workshop will be a mix of lectures and immediate feedback on practical assignments, designed to ensure that students leave with significant experience in both OpenMP and MPI, two of the standards for parallel computing today. We aim for this workshop to be useful for graduate students and postdocs for a wide range of disciplines.
The course will be given in a yet-to-be determined location on the St. George Campus.
There will be NO FEE, but you are responsible to get the recommended BOOKS, and your own COFFEE and LUNCH.
There is LIMITED AVAILABILITY, so please only register if you are serious about attending. Registration and further details (topics, books, location) are (or will be) available at
Sign up if you are planning to come, at https://support.scinet.utoronto.ca/courses/?q=node/26
(All new wiki content below is listed and linked on the main page: https://support.scinet.utoronto.ca/wiki/index.php/SciNet_User_Support_Library#What.27s_New_On_The_Wiki)