Difference between revisions of "CSC352 Class Page 2017"

From dftwiki3
Jump to: navigation, search
( )
( )
 
(12 intermediate revisions by the same user not shown)
Line 527: Line 527:
 
::* <font color="magenta">Paper Presentations: Wikipedia dumps (Angie), and Can Cloud Reach Top500 (Vega)</font>
 
::* <font color="magenta">Paper Presentations: Wikipedia dumps (Angie), and Can Cloud Reach Top500 (Vega)</font>
 
::* Map-Reduce
 
::* Map-Reduce
:::* Implementing Map-Reduce in Python
+
:::* Implementing Map-Reduce in Python: various problems solved with Map-Reduce
:::* [[Tutorial:_Creating_a_Hadoop_Cluster_on_Amazon_AWS | Lab 1: Hadoop on AWS]]
+
::::* [[Map-Reduce_Examples| Example page]]
:::* [[Hadoop_Tutorial_2.3_--_Running_WordCount_in_Python_on_AWS | Hadoop on AWS: streaming Python]]
+
::::* [[CSC352_Game_of_Life_in_Map-Reduce| Solving Conway's Game of Life with Map-Reduce]]
:::* [[Hadoop_Tutorial_1.1_--_Generating_Task_Timelines | Lab 2: Creating Task Graphs]]
+
 
::* [[Media:CSC352_Week11_MapReduce.pdf | Map-Reduce slides (pdf)]]
+
::* [[Media:CSC352_Week12_MapReduce.pdf | Map-Reduce slides (pdf)]]
  
 
|
 
|
Line 557: Line 557:
 
|
 
|
 
* '''Tuesday'''
 
* '''Tuesday'''
::* Project Presentations:  
+
::* Labs
:::* _______
+
:::* [[Tutorial:_Creating_a_Hadoop_Cluster_on_Amazon_AWS | Lab 1: Hadoop on AWS]]
 +
:::* [[Hadoop_Tutorial_2.3_--_Running_WordCount_in_Python_on_AWS | Lab 2:Hadoop on AWS: streaming Python]]
 +
:::* [[Hadoop_Tutorial_1.1_--_Generating_Task_Timelines | Lab 3: Creating Task Graphs]]
 +
 
 
* '''Thursday'''
 
* '''Thursday'''
 
::*  Project Presentations:  
 
::*  Project Presentations:  
:::* Isaiah & Muriel
+
:::* Isaiah
:::* Sam & Angie
 
 
|
 
|
*  
+
* [[CSC352 Homework 4 2017| Homework 4, Game of Life using Map-Reduce on AWS]]
 
|
 
|
 
*  
 
*  
Line 588: Line 590:
 
* '''Tuesday'''
 
* '''Tuesday'''
 
::* Project Presentations:   
 
::* Project Presentations:   
 +
:::* Grace (lunch time)
 
:::* Kathleen
 
:::* Kathleen
 
:::* Riley
 
:::* Riley
 
* '''Thursday'''
 
* '''Thursday'''
::* Project Presentations:  
+
::* Project Presentations:
 +
:::* Sam & Angie (lunch time)
 
:::* Lujun & Vega
 
:::* Lujun & Vega
 
:::* Youyou and Zainab
 
:::* Youyou and Zainab
Line 615: Line 619:
 
|
 
|
 
* '''Friday, May 12, 4:00 p.m.''': pdf of project due on Moodle.
 
* '''Friday, May 12, 4:00 p.m.''': pdf of project due on Moodle.
 +
* '''Friday, May 12, 4:00 p.m.''': Hadoop Game of Life due.
 
|}
 
|}
 
<br />
 
<br />

Latest revision as of 11:50, 25 April 2017

--D. Thiebaut (talk) 10:37, 2 December 2016 (EST)



Home | Syllabus | Schedule | Links & Resources | Final Project


Topics to be covered: Week (approx)
  • Syllabus
  • Parallelism
  • Interrupts
  • Processes/Threads
  • Latex

Week 1

  • Performance
  • Speedup
  • Amdhal's Law
  • Java threads + Synchronization

Week 2

  • Java Thread-Safe Libraries
  • Static Variables

Week 3

  • Introduction to C

Week 4
Week 5

  • MPI

Week 6
Week 7

  • AWS
  • MySQL + MPI
  • MPI Clusters on AWS

Week 8
Week 9

  • MapReduce
  • Hadoop, Java
  • Hadoop, Python
  • Hadoop AWS

Week 10
Week 11

  • Apache Spark

Week 12

  • GPU

Week 13


 


Week 1 Jan 26, 27    


Topics: Lab/Hw Reading
  • Thursday
  • Syllabus
  • papers
  • Biweekly newsletters in Latex
  • Parallelism: going to the source: Interrupts!
    • 8086 type of interrupts (simplified)
    • Interrupt Vector
    • Interrupt Priority


 


Week 2 Jan 31, Feb 2    


Topics: Lab/Hw Reading
  • Tuesday

  • Newsletter
  • The format should be similar to the ACM Tech News format.
  • The header should contain a title, your name, the class (CSC352) and the date
  • Each paragraph should have a header with a title, the source of news, the date, and possibly a link to the full article.
  • The paragraph describing a news item should be between 3 to 10 lines, give or take.
  • Write 1 full page to 2 pages, depending on the richness of events in the technology field
  • Feel free to present N-1 topics with just 3 lines, and 1 topic which you highlight with a longer paragraph.
  • Topics: anything related to parallelism: computers, mobile platforms, cloud, companies, new software, new algorithms, conferences, people in the field, etc.
  • Good sources of information to get started:
  • Recommendation for news aggregator: Feedly.com

  • Introduction to Latex

  • Thursday



 


Week 3 Feb 7, 9    


Topics: Lab/Hw Reading
  • Tuesday
  • Thursday
  • Paper Presentation: Berkeley
  • Newsletter due


 


Week 4 Feb 14, 16    


Topics: Lab/Hw Reading
  • Tuesday
  • Discussion of View from Berkeley paper. Many concepts to revisit
  • Thursday
  • Rocco Piccinino: presentation on Library Resources. You can find a link to Rocco's presentation here
  • Paper Presentations: Patterns + Framework (presented by Riley), and Throughput Oriented Architectures
  • Game of Life?

Two papers to read for Thrusday. In class discussion.


 


Week 5 Feb 21    


Topics: Lab/Hw Reading
  • Tuesday
  • Thursday: Rally Day
  • Newsletter due on Moodle, at 1:00 p.m., just before Rally Day events.
  • Requirements for newsletter: Add an image or figure to your newsletter. It could be a photo of you at the top, as the author, or a graph, or a logo. You pick the jpeg or png, and incorporate it in your newsletter.


 


Week 6 Feb 28, Mar 2    


Topics: Lab/Hw Reading
  • Tuesday
  • Thursday
  • Paper Presentation: Unreasonable (Lujun), and Top500
  • Homework 2, due Thursday after the break, 3/23/17, at 1:00 p.m.


 


Week 7 Mar 7, 9    


Topics: Lab/Hw Reading
  • Tuesday


  • Thursday
  • A word about the final project
  • Paper Presentation: Success of MPI (Zainab), and General purpose vs GPU
  • Newsletter due. This week, add a sentence to each summary that explains why you picked this news item. Why does the news you reported matters? How is it important to you? Does it connect in any way to something you have read or programmed? Also, this week, add an a section to your newsletter that refers to Amdahl's law. The purpose of this is to have you create an equation with Latex. So, you can simply explain what Amdahl's law is, or you can find a bit of news in the past year that mentions Amdahl's Law, and take this opportunity to create an equation: Speedup = T(1)/T(N).
  • Prepare a 1-page description of the project you will present at the end of the semester. Submit it before March 21, 1:00 p.m. to Moodle. See this page for information.


SPRING BREAK


 


Week 8 Mar 21, 23    


Topics: Lab/Hw Reading
  • Tuesday
  • Thursday
  • StarCluster overview: must read. StarCluster is a set of Python programs that one installs on one's laptop to control clusters on Amazon Web Services (AWS). StarCluster can easily setup MPI and Hadoop clusters.


 


Week 9 Mar 28, 30    


Topics: Lab/Hw Reading
  • Tuesday
  • Thursday


 


Week 10 Apr 4, 6    


Topics: MPI, AWS Lab/Hw Reading
  • Tuesday
  • Thursday
  • Paper Presentations: Spark (Youyou), and Microsoft Bet Future (Isaiah & Muriel)


 


Week 11 Apr 11, 13    


Topics: Lab/Hw Reading
  • Tuesday
  • Introduction to Functional Programming
  • Implementing Map-Reduce in Python
  • Thursday
  • Class cancelled


 


Week 12 Apr 18, 20    


Topics: Lab/Hw Reading
  • Tuesday/Thursday
  • Paper Presentations: Wikipedia dumps (Angie), and Can Cloud Reach Top500 (Vega)
  • Map-Reduce
  • Implementing Map-Reduce in Python: various problems solved with Map-Reduce


 


Week 13 Apr 25, 27    


Topics: Lab/Hw Reading
  • Tuesday
  • Labs
  • Thursday
  • Project Presentations:
  • Isaiah


 


Week 14 May 2, 4    


Topics: Lab/Hw Reading
  • Tuesday
  • Project Presentations:
  • Grace (lunch time)
  • Kathleen
  • Riley
  • Thursday
  • Project Presentations:
  • Sam & Angie (lunch time)
  • Lujun & Vega
  • Youyou and Zainab

 


Exam Week May 9, 12    


Final Exam Week
  • Friday, May 12, 4:00 p.m.: pdf of project due on Moodle.
  • Friday, May 12, 4:00 p.m.: Hadoop Game of Life due.


Links & Resources


Map-Reduce



Final Project


Go to the project page for information on the projects.


Links and Resources


Cloud Services

Cloud Services
Name Description

bitfusion.io

Provides AMIs on AWS with GPUs attached. The AMIs are already loaded with tensorflow and python, as well as Jupyter for remote development of Python programs. They offer a 5-day free trial.

Digital Ocean

A whole cloud infrastructure similar to AWS, but (apparently) not running on AWS. Offers a cluster infrastructure with many packages preloaded, including Node.js, Rails, Redis, MongoDB, Cassandra, Docker, MediaWiki, Django, Drupal, Drone, LAMP, LEMP, Ruby, etc. Offers a $10 credit when first signing up.

Latex


Here are some nice video tutorials on using Latex to write papers.


Smith Elements of Style



On-Line Resources

MPI

Hadoop

Microprocessors



Papers

This is a tentative and non exhaustive list of papers scheduled for reading this semester.

Introduction

Paper Pages

50

2

General/Parallelism

Paper Pages

5

7

5

  • Top500 Versus Sustained Performance, by William Kramer, 21st International Conference On Parallel Architectures And Compilation Techniques (PACT12), 19–23 September 2012, Minneapolis, MN, US

8

MPI

Paper Pages
  • Learning from the Success of MPI, by WIlliam D. Gropp, Argonne National Lab, 2002.                                             

11

GPUs

Paper Pages

6

Virtualization

Paper Pages

5

Cloud

Paper Pages

1.5

  • A View of Cloud Computing, 2010, By Armbrust, Michael and Fox, Armando and Griffith, Rean and Joseph, Anthony D. and Katz, Randy and Konwinski, Andy and Lee, Gunho and Patterson, David and Rabkin, Ariel and Stoica, Ion and Zaharia, Matei.

9

13

5

2

10

19

8

  • Can Cloud Computing Reach the Top500?, by Jeffrey Napper and Paolo Bientinesi, Proceeding of UCHPC-MAW '09 on UnConventional high performance computing workshop plus memory access workshop,

Ischia, Italy — May 18 - 20, 2009.

4