GPU code addition. #23
Open
Conversation
This file contains 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
… the power operation support for tensors and matrices, working SGD support and a full working example of a neural network that trains successfuly to learn how to convert celcius to faranheit
…uilding cpu and gpu versions
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This pull request seeks to add building this project for the GPU. Currently, the kernel for the dot product is added (matrix multiplication).
To build for the GPU, the cuda compiler takes in
main.cuas the source file.main.cuincludesbuildTensorflowGpu.hinstead ofbuildTensorflow.h(as in themain.cppcase).The buildTensorflowGpu.h file inserts code for the CUDA kernels into the project by including the
gpu/defn.handgpu/impl.h.These two files contain the kernel code definitions and implementations respectively.
Finally to build for the cpu, we fire the make all command and to build for the GPU we fire the make gpu command.