-
Notifications
You must be signed in to change notification settings - Fork 422
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
MLPerf Tiny developments #503
base: main
Are you sure you want to change the base?
MLPerf Tiny developments #503
Conversation
…into vivado-accel-concat
…vcd file. Next step -> add the parser, find the max for each fifo and set the new fifo depth
* fix conv1d io_parallel resource * replace tabs with spaces in modified code * Add test for Conv1D example model Co-authored-by: Sioni Summers <[email protected]>
Fix Dense ReLU merge bug
Patch: divide by 256
init commit of QDenseBN
Integration of features for EEMBC power analysis.
pass`hls_model` to `optimize_fifos_depth` + correct scopes for Arty
Enable 2nd counter in timer.
Hi @jmduarte, all the updates sounds good to me. I know @nicologhielmetti has begun the work to port the FIFO depth optimization to an optimizer pass on top of the current hls4ml framework. For the "ReLU merge optimizer" do you have any numbers for the savings (latency or resources) that result? |
@thesps Here is a table showing the resource utilization (estimated via csynth) before and after applying the "ReLU merge optimization" to an image classification model used for the tinyMLPerf submission. |
Not to be merged but simply to open discussion about which developments we should cherry-pick and rebase to hls4ml main branch. Based on a quick look, I can imagine a few separate PRs: