Custom kernels in GPULib 1.6

posted Wed 8 May 2013 by Michael Galloy under HPC, IDL

One of the features I’m most excited about in GPULib 1.6 is the ability to create your own kernel and call it from within the GPULib framework. Details and an example are on the GPULib blog. This feature requires CUDA programming knowledge, but makes it much easier to integrate custom CUDA code into IDL.

You can download a free version of GPULib which has basic features and includes a short term license for the full features of GPULib as well. Calling custom CUDA kernels requires the full version of GPULib.

Full disclosure: I work for Tech-X Corporation and I am the product manager for GPULib.

No Comments

michaelgalloy.com

Resources for IDL developers

Buy Modern IDL now!

Modern IDL offers IDL programmers one place to look for explanation, techniques, and reference material, for beginners and advanced users alike.

"... But I've always wanted a thorough, concise, up-to-date overview of the the IDL language and its vast capabilities. This is exactly what Mike's book provides in 464 very informative pages... Highly recommended!"
—Mort Canty

About me

I'm a software developer focusing on high-performance computing and visualization in scientific programming. I work mostly in IDL, but occasionally use C, CUDA, and Python.

I currently work for the National Center for Atmospheric Research (NCAR) at the Mauna Loa Solar Observatory. Previously, I worked for Tech-X Corporation, where I was the main developer for GPULib, a library of IDL bindings for GPU accelerated computation routines.

I am the creator and main developer for the open source projects IDLdoc, mgunit, and rIDL.

Contact me at Mastodon or via email at mgalloy at gmail dot com. For more details about me, see my CV/resume.

Need consulting/instruction? Contact me.

Other

Feeds

GPULib

GPULib enables IDL developers to access the high-performance capabilities of modern NVIDIA graphics cards without knowledge of CUDA programming.

TaskDL

TaskDL is a task-farming solution for IDL designed for problems with loosely-coupled, parallel applications where no communication between nodes of a cluster is required.

mpiDL

mpiDL is a library of IDL bindings for Message Passing Interface (MPI) used for tightly-coupled parallel applications.

Remote Data Toolkit

The Remote Data Toolkit is a library of IDL routines allowing for easy access to various scientific data in formats such as OPeNDAP, HDF 5, and netCDF.
Modern IDL

Modern IDL offers IDL programmers one place to look, for beginners and advanced users alike. This book also contains: a thorough tutorial on the core topics of IDL; a comprehensive introduction to the object graphics system; common problems and gotchas with many examples; advanced topics not normally found are discussed throughout the book: regular expressions, object graphics, advanced widget programming, performance, object-oriented programming, etc.
IDLdoc

IDLdoc is an open source utility for generating documentation from IDL source code and specially formatted comments.

mgunit

mgunit is an open source unit testing framework for IDL.

rIDL

rIDL is an open source IDL command line replacement.

mglib

mglib is an open source library of IDL routines in areas of visualization, application development, command line utilities, analysis, data access, etc.

Custom kernels in GPULib 1.6