Skip to content

Code for trying to optimize GEMM operation by trading for accuracy

License

Notifications You must be signed in to change notification settings

ankdesh/ApproxGemmOCL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

ApproxGemmOCL

Code for optimizing GEMM operation by trading for accuracy on GPU using OpenCL.

Building -

To build the simple matrix multiplication with g++, use following command

$ g++ -I<Path to CL include folder> simpleMatMul.cpp -lOpenCL -o simpleMatMul

Note -

This project is still in nascent state. Keep tuned for interesting work

About

Code for trying to optimize GEMM operation by trading for accuracy

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages