WIP: Quartus backend support for external weights #40
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
|
Will rebase this to the current quartus_new. |
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Outdated suggestions cannot be applied.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 is a first attempt to allow the option to provide externally updateable weights. The goal is to use this in an Arria10 SoC, where the weights could be updated from the HPS. This scheme uses Avalon MM stave interface connections for the weights and biases. (There was an alternate implementation with explicit Avalon streaming interfaces, which can allow quicker updates, but it is more complicated.) We want to use something like this to implement reinforcement learning for accelerator controls in Fermilab. This has been tested with csim, and cosim is currently running, but updating weights requires an HDL testbench, which I haven't yet done.
Anyway, I wanted to see if you have any suggestions.