Personal tools

ThreadScope Tour

From HaskellWiki

(Difference between revisions)
Jump to: navigation, search
(tidy up requirements section a bit)
(bookmark chapter)
Line 28: Line 28:
 
<li>[[ThreadScope_Tour/Profile|Profile]]: examine the profile for a real program </li>
 
<li>[[ThreadScope_Tour/Profile|Profile]]: examine the profile for a real program </li>
 
<li>[[ThreadScope_Tour/Profile2|Profile 2]]: examine the profile for an improved program</li>
 
<li>[[ThreadScope_Tour/Profile2|Profile 2]]: examine the profile for an improved program</li>
<li>[[ThreadScope_Tour/Zoom|Zoom]]: zooming and bookmarking</li>
+
<li>[[ThreadScope_Tour/Zoom|Zoom]]: zoom in to see performance behaviour at a finer resolution</li>
  +
<li>[[ThreadScope_Tour/Bookmark|Bookmark]]: place a temporary marker in the eventlog</li>
 
<li>[[ThreadScope_Tour/Consolidate|Consolidate]]: tease out the sequential parts of code</li></ol>
 
<li>[[ThreadScope_Tour/Consolidate|Consolidate]]: tease out the sequential parts of code</li></ol>
   
Line 35: Line 35:
 
[[Image:spark-lifecycle.png|thumb]]
 
[[Image:spark-lifecycle.png|thumb]]
   
<ol start="8" style="list-style-type: decimal;">
+
<ol start="9" style="list-style-type: decimal;">
 
<li>[[ThreadScope_Tour/SparkOverview|Spark overview]]
 
<li>[[ThreadScope_Tour/SparkOverview|Spark overview]]
 
<ul>
 
<ul>

Revision as of 19:50, 9 December 2011

A guided tour of ThreadScope

In this tutorial, we'll be working through concrete examples on using ThreadScope to debug the performance of parallel programs.

We aim to keep each module in the tutorial self-contained, so you can either follow the progression suggested or jump to just the sections we need.

Software

This tutorial is written with the following software versions in mind.

  • ThreadScope 0.2.1
  • GHC 7.4. (earlier versions work, but lack more advanced features like spark events)
Getting started
ThreadScope-ch8.png
  1. Installation: install ThreadScope and run a sample trace
  2. Hello world: run ThreadScope on a small test program
Basic skills
ThreadScope-sudoku2.png
  1. Initial statistics: collect some simple statistics
  2. Profile: examine the profile for a real program
  3. Profile 2: examine the profile for an improved program
  4. Zoom: zoom in to see performance behaviour at a finer resolution
  5. Bookmark: place a temporary marker in the eventlog
  6. Consolidate: tease out the sequential parts of code
Digging into a program with spark events
Spark-lifecycle.png
  1. Spark overview
  2. Spark rates: study spark creation/conversion
  3. Spark rates 2: spark debugging continued
Reference

This tutorial was initially written by Well-Typed in the context of the Parallel GHC Project. Feedback would be most appreciated!