Adding the OpenCL runtime compilation method#5
Open
davidcastells wants to merge 25 commits intoljbade:masterfrom
Open
Adding the OpenCL runtime compilation method#5davidcastells wants to merge 25 commits intoljbade:masterfrom
davidcastells wants to merge 25 commits intoljbade:masterfrom
Conversation
new usage function to give some more info about the possible parameters print log if verbose, even when compilation is successful
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I was interested in compiling and testing OpenCL kernels on different platforms and especially receive feedback about the used resources.
I noticed that NVIDIA OpenCL gives different information wether it is executed from the former clcc implementation and the OpenCL runtime compiler clBuildProgram logs.
So I added a way to select wether Leith direct shared library access method is used or classic OpenCL runtime.
I also modified the command line interface adding new flags (I understand @MichaelE1000 you worked on that), and did some code refactoring in the argument parsing to be easier to support new flags.
I also modified a bit cmake files (implemented by @debdattabasu ) to support cygwin (from Netbeans 8.2) in Windows and Linux. I tested it in Cygwin and Ubuntu Linux.
Finally I moved from C to C++, to reuse OpenCL functions that use STL classes.
@ljbade I am very curious on how did you obtain the function signature of the NVIDIA functions.
It would be interesting to do the same experiment with the libnvidia-ptxjitcompiler.so.1 library (which I have in my system).
I don't know how this compare with the clcc maintained in sourceforge... I would appreciate your comments.
BR