Difference between revisions of "CSC352 DT's Class Notes 2013"

From dftwiki3
Jump to: navigation, search
(DFT Class Notes for CSC352)
 
(11 intermediate revisions by the same user not shown)
Line 4: Line 4:
 
__TOC__
 
__TOC__
  
 +
<br />
 +
<center>
 +
'''PLEASE SEE [[CSC352_2017_DT%27s_Notes| THE 2017 NOTES PAGE FOR MORE INFO]]'''
 +
</center>
 +
<br />
 
==Threads==
 
==Threads==
 
* good example with multiple ping processes: [http://www.wellho.net/solutions/python-python-threads-a-first-example.html]
 
* good example with multiple ping processes: [http://www.wellho.net/solutions/python-python-threads-a-first-example.html]
Line 11: Line 16:
 
* [[NQueens.py | NQueens.py]]
 
* [[NQueens.py | NQueens.py]]
 
* [[threadedNQueens.py | threadedNQueens.py ]]
 
* [[threadedNQueens.py | threadedNQueens.py ]]
 +
* [[classExample1.py | classExample1.py ]]
 +
* [[classExample2.py | classExample2.py ]]
 +
* [[classExample3.py | classExample3.py ]]
 
* [[serialPing.py | serialPing.py ]]
 
* [[serialPing.py | serialPing.py ]]
 
* [[threadedPing.py | threadedPing.py ]]
 
* [[threadedPing.py | threadedPing.py ]]
 +
* [[searchKeywordsRetrieveEtexts.py | searchKeywordsRetrieveEtexts.py ]]
 +
* [[threadedSearchKeywordRetrieveEtexts.py | threadedSearchKeywordRetrieveEtexts.py ]]
  
 
===Setting up documents and swish-e===
 
===Setting up documents and swish-e===
Line 42: Line 52:
 
Where delay is number of 1/10s of a second to wait.  This is a bound as the true delay is random between 0.1 sec and the integer specified times 1/10 seconds.)
 
Where delay is number of 1/10s of a second to wait.  This is a bound as the true delay is random between 0.1 sec and the integer specified times 1/10 seconds.)
  
==Papers==
+
==Project==
===Landscape of parallel computing research: a view from berkeley===
+
 
----
+
;Project 1:
* good intro paper.
+
:Threading in Python: given two lists of keywords, List1 and List2, retrieve docs from a site (xgridmac.dyndns.org, yahoo, google) that respond/match List1.  Filter the docs received and keep only those that contain most of the words in List2.
* 3 sections
 
** software
 
** hardware
 
** performance/programming models
 
** conclusion
 
* probably cover 1st section w/ dwarfs, plus conclusion, although everything is good
 
----
 
* General introduction to world of // computing in 2006
 
* old wisdom/new wisdom ==> world of // computing is changing
 
* moore's law
 
:::"Key to this approach is a layer of libraries and programming frameworks centered on the 13 computational bottlenecks ("dwarfs") that we identified in the original Berkeley View report. "
 
* Page 7: we have been concentrating on massively parallel architectures, but this may apply to new forms of parallelism
 
* Page 7: good match between scientific // approaches and current parallel (non scientific) domains
 
* Page 7: 7 Dwarfs
 
** ==> question: what's a dwarf? (google berkeley + dwarf)
 
** high level of abstraction
 
* Page 11: 3 new areas for adoption as dwarf?
 
** machine learning
 
** database software
 
*** Page 12: map-reduce
 
** computer graphics
 
* Page 14: introduces 6 new dwarfs
 
* Page 19: End of software Dwarf section ==> Good place to break
 
* Page 20: beginning of hardware
 
** processor
 
** memory
 
** network
 
* Page 32: Programming  models
 
** Does not include threading
 
** MPI
 
** Map-REduce
 
* Page 36: system software
 
** '''Autotuner'''
 
* Page 40: virtual machines to the rescue
 
* Page 44: conclusion
 
  
 +
;Project 2:
 +
:XGrid: process a gzip xml dump of wikipedia and break it up into individual pages (9 million or so of them)!
  
 +
;Project 3:
 +
:Map-Reduce: process wikipedia pages and create an index of words and their associated categories
  
 +
==Papers==
  
 +
[[CSC352 Notes on A View From Berkeley| Notes]] on a View from Berkeley paper
  
  
 
</onlydft>
 
</onlydft>
 +
[[Category:CSC352]][[Category:Class Notes]]

Latest revision as of 15:01, 7 December 2016

DFT Class Notes for CSC352


...