Difference between revisions of "GPU610/DPS915"

From CDOT Wiki
Jump to: navigation, search
(→‎The Workshops)
(→‎Resources)
 
(36 intermediate revisions by the same user not shown)
Line 1: Line 1:
−
{{GPU610/DPS915 Index | 20123}}
+
{{GPU610/DPS915 Index | 20191}}
  
 
Please help make this page resourceful for all GPU610/DPS915 students to use!
 
Please help make this page resourceful for all GPU610/DPS915 students to use!
  
−
= Course Descriptions =
+
= Course Material =
  
 
== GPU610 - Parallel Programming Fundamentals ==
 
== GPU610 - Parallel Programming Fundamentals ==
 +
<table>
 +
<tr valign=top>
 +
<td>
 +
 
*Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming.  
 
*Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming.  
−
* [https://scs.senecac.on.ca/course/gpu610 Course Outline]
+
* [https://ict.senecacollege.ca/course/gpu610 Course Outline]
 +
</td>
 +
<td>
 +
[[Image:NV_CUDA_Teaching_Center_Small.jpg]]
 +
</td>
 +
</tr>
 +
</table>
  
 
== DPS915 - Introduction to Parallel Programming ==
 
== DPS915 - Introduction to Parallel Programming ==
 +
<table>
 +
<tr valign=top>
 +
<td>
 +
 
*Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming and develop a CPU+GPU application for a client.
 
*Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming and develop a CPU+GPU application for a client.
  
−
* [https://scs.senecac.on.ca/course/dps915 Course Outline]
+
* [https://ict.senecacollege.ca/course/dps915 Course Outline]
 +
</td>
 +
<td>
 +
[[Image:NV_CUDA_Teaching_Center_Small.jpg]]
 +
</td>
 +
</tr>
 +
</table>
  
−
= Common Material =
 
 
== External Links ==
 
== External Links ==
 
* [https://scs.senecac.on.ca/~gpu610/pages/content/index.html Course Web Site – Lecture Notes]
 
* [https://scs.senecac.on.ca/~gpu610/pages/content/index.html Course Web Site – Lecture Notes]
 
* [https://cs.senecac.on.ca/~gpu610/pages/timeline.html Course Web Site – Timeline]
 
* [https://cs.senecac.on.ca/~gpu610/pages/timeline.html Course Web Site – Timeline]
 +
<!--
 
* [svn://zenit.senecac.on.ca/dpsgpu/trunk Class Samples]
 
* [svn://zenit.senecac.on.ca/dpsgpu/trunk Class Samples]
 +
-->
  
−
== The Workshops ==
+
== Workshops ==
−
* The workshops provide timely opportunities to implement some of the material covered during the lectures. Each workshop is graded and all submissions are through [https://open.senecac.on.ca/cms/course/view.php?id=342 Moodle].
+
* The workshops provide timely opportunities to implement some of the material covered during the lectures. Each workshop is graded and all submissions are through [https://open.senecac.on.ca/cms/course/view.php?id=536 Moodle].
 
* Detail Specifications
 
* Detail Specifications
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w1.html Initial Assessment]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w1.html Initial Profile]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w2.html Linear Algebra using BLAS]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w2.html BLAS]
 
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w3.html Device Query and Selection]
 
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w3.html Device Query and Selection]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w4.html A Simple Device Operation]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w4.html cuBLAS]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w5.html Dot Product]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w5.html Thrust]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w6.html Matrix Product]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w6.html A Simple Kernel]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w7.html Matrix Product using Thrust]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w7.html Reduction]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w8.html Matrix Product using cuBlas]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w8.html Thread Divergence]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w9.html Matrix Product using Streams]
+
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w9.html Coalesced Memory Access]
 
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w10.html CUDA to OpenCL]
 
*# [https://scs.senecac.on.ca/~gpu610/pages/workshops/w10.html CUDA to OpenCL]
−
* Grading
+
* Grading - The due date for each workshop is noted in MySeneca. The penalty for late submission is 20% of the workshop mark; 50% for very late submission.
−
The window for submission of each workshop is two weeks. The penalty for late submission is 50% of the workshop mark.
 
−
 
 
−
== The Project  ==
 
−
<table>
 
−
<tr>
 
−
<td>
 
  
−
* The course project is a three-stage, team assignment. Each team consists of 3 members.  In the first stage your team evaluates 6 applications and selects 3 for continued work.  The evaluation includes profiling to identify the hot spots in each application. Each team member is responsible for 2 of the candidate applications. The second stage refactors the applications to use the GPU, including shared memory.  The third and final stage optimizes the performance.  Each team presents the results of its work during the final week of the semester.
+
== Assignments ==
−
* Detail Specifications
+
# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a1.html Select and Assess]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a1.html Selection and Assessment]
+
# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a2.html Parallelize]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a2.html GPU Programming]
+
# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a3.html Optimize]
−
*# [https://scs.senecac.on.ca/~gpu610/pages/assignments/a3.html Optimization]
 
−
* Grading
 
−
The penalty for late submission is 30% of the assignment mark. The penalty for resubmission, in the event that the original submission was not workable is 50%. The due dates are posted in [https://open.senecac.on.ca/cms/course/view.php?id=342 Moodle]. All submissions are to be made through [https://open.senecac.on.ca/cms/course/view.php?id=342 Moodle].&nbsp; 
 
−
</td>
 
−
<td>
 
−
[[Image:NV_CUDA_Teaching_Center_Small.jpg]]
 
−
</td>
 
−
</tr>
 
−
</table>
 
  
 
== Evaluation ==
 
== Evaluation ==
  
−
* Assignment 30%
+
* Assignments and Presentation 20%
−
* Workshops 20%
+
* Workshops 30%
−
* Test 20%
+
* Option 1: Tests 50%
−
* Exam 30%
+
* Option 2: Tests 35% + Exam 15%
−
 
 
−
== Final Submission Requirements ==
 
−
* Under construction
 
−
<!-- When ready to submit your project:
 
−
# Finalize your modifications in trunk.
 
−
# Create a directory in trunk called: '''"SubmissionLogs"'''
 
−
# For each member of the team create a text file named as '''"YourSenecaEmailId.txt"''' in the '''"SubmissionLogs"''' directory. In this text file, in a point form, specify in detail, all the tasks you have done for the group project.
 
−
# Branch (copy) the whole project including the SubmissionLogs directory and its text files into tags directory under '''"prj1.0"'''.
 
−
# If final adjustments are needed after these steps, repeat everything from step one but branch the trunk into a new directory in tags as '''prj1.1, prj1.2''', etc.
 
−
#:(for marking purposes, your instructor will consider your last revision as your submission)
 
−
-->
 
  
 
= Resources =
 
= Resources =
 
* Software Support
 
* Software Support
−
** [https://acs.senecac.on.ca/pages/index.php Microsoft Visual Studio 2010 Pro]
 
 
** [http://developer.nvidia.com/cuda-downloads CUDA Toolkit]
 
** [http://developer.nvidia.com/cuda-downloads CUDA Toolkit]
 +
** Get [https://inside.senecacollege.ca/its/software/index.html Visual Studio 2017] | Select Software Downloads | Go To Visual Studio 2013 Ultimate 2.82GB | Download iso | Burn, if error burn again | Finally, install
 +
 +
<!--
 
** [http://developer.nvidia.com/nvidia-nsight-visual-studio-edition NSight Visual Studio Edition]
 
** [http://developer.nvidia.com/nvidia-nsight-visual-studio-edition NSight Visual Studio Edition]
 
** [http://developer.nvidia.com/nsight-eclipse-edition NSight Eclipse Edition]
 
** [http://developer.nvidia.com/nsight-eclipse-edition NSight Eclipse Edition]
 +
-->
 
* Wikis
 
* Wikis
 
** [http://en.wikipedia.org/wiki/Wikipedia:How_to_edit_a_page How To edit Wiki pages]
 
** [http://en.wikipedia.org/wiki/Wikipedia:How_to_edit_a_page How To edit Wiki pages]
 
** [http://en.wikipedia.org/wiki/Wikipedia:Cheatsheet How To edit Wiki Cheatsheet]
 
** [http://en.wikipedia.org/wiki/Wikipedia:Cheatsheet How To edit Wiki Cheatsheet]
 +
<!--
 
* Subversion
 
* Subversion
 
** [http://subversion.tigris.org/ Subversion (SVN)]
 
** [http://subversion.tigris.org/ Subversion (SVN)]
Line 87: Line 86:
 
** [http://tortoisesvn.net/docs/release/TortoiseSVN_en/index.html TortoiseSVN Documentation]
 
** [http://tortoisesvn.net/docs/release/TortoiseSVN_en/index.html TortoiseSVN Documentation]
 
** [http://svnbook.red-bean.com/ SVN book at red-bean.com] or download [https://cs.senecac.on.ca/~fardad.soleimanloo/oop344/notes/svn-book.pdf the PDF from here].
 
** [http://svnbook.red-bean.com/ SVN book at red-bean.com] or download [https://cs.senecac.on.ca/~fardad.soleimanloo/oop344/notes/svn-book.pdf the PDF from here].
−
<!--
+
** [http://ankhsvn.open.collab.net/ AnkhSVN - Free Visual Studio SVN Integration Alternative To VisualSVN]
−
* [http://zenit.senecac.on.ca/wiki/index.php/OOP344_Student_Resources#The_Basics_of_IRC IRC Basics]
 
−
 
 
−
* [http://irchelp.org/irchelp/irctutorial.html IRC Tutorial]
 
 
-->
 
-->
−
** [http://ankhsvn.open.collab.net/ AnkhSVN - Free Visual Studio SVN Integration Alternative To VisualSVN]
 
  
 +
<!--
 
= Archives =
 
= Archives =
 +
-->

Latest revision as of 17:17, 6 January 2019


GPU610/DPS915 | Student List | Group and Project Index | Student Resources | Glossary

Please help make this page resourceful for all GPU610/DPS915 students to use!

Course Material

GPU610 - Parallel Programming Fundamentals

  • Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming.
  • Course Outline

NV CUDA Teaching Center Small.jpg

DPS915 - Introduction to Parallel Programming

  • Modern GPU (Graphics Processing Unit) technology supports massively parallel computations, which complements the serial processing capabilities of CPU technology. This course teaches students how to read, write, and debug programs that use both CPU and GPU technology. Students learn to reorganize existing programs into serial code that runs on the CPU and parallel code that runs on the GPU. Students also study cases that have benefited from CPU+GPU programming and develop a CPU+GPU application for a client.

NV CUDA Teaching Center Small.jpg

External Links

Workshops

Assignments

  1. Select and Assess
  2. Parallelize
  3. Optimize

Evaluation

  • Assignments and Presentation 20%
  • Workshops 30%
  • Option 1: Tests 50%
  • Option 2: Tests 35% + Exam 15%

Resources

  • Software Support
    • CUDA Toolkit
    • Get Visual Studio 2017 | Select Software Downloads | Go To Visual Studio 2013 Ultimate 2.82GB | Download iso | Burn, if error burn again | Finally, install


Retrieved from "https://wiki.cdot.senecapolytechnic.ca/w/index.php?title=GPU610/DPS915&oldid=137032"