Skip to content
/ CAPA Public
forked from oclint/oclint

CAPA is a static code analysis tool for identifying possibly parallel algorithm implementations within your C codebase that may be re-implemented on GPU hardware.

Notifications You must be signed in to change notification settings

Jhana1/CAPA

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CAPA - C Algorithm Parallelisation Analyser

CAPA is a static code analysis tool for identifying possibly parallel algorithm implementations within your C codebase that may be re-implemented on GPU hardware.

It looks for potential speedups including:

  • Map Operations - Neighbour Invariant 1->1 transformations
  • Reduce Operations - Highly Efficient N->1 transformations
  • Scan (Prefix Sum) - N->N transformations
  • Matrix Multiplication - Quadratic complexity with superior GPU implementations
  • Vectorisable Function Declarations - Functions which appear to operate over vectors
  • Generally Vectorisable Regions of Code - A catch all for when specific cases aren't met

About

CAPA is a static code analysis tool for identifying possibly parallel algorithm implementations within your C codebase that may be re-implemented on GPU hardware.

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 92.3%
  • Python 5.4%
  • CMake 2.2%
  • Shell 0.1%