Assembly-level Feature Extraction #16
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
* fix typo (tlc-pack#12) * update gpu dataset version * Few-shot learning for end-to-end search; graph embedding; mlp model (tlc-pack#7) * add few shot learning * embedding * embedding * embedding * embedding * excluded certain networks * excluded certain networks * mlp * mlp * mlp * Update dataset.py * split dataset * exclude dataset * exclude dataset * dataset * add vgg * a * mlp * mlp models * mlp models * a * mlp model in eval * plot * eval model * plot mlp * mlp * mlp load + vgg * two mlp models * mlp loss func by group * remove vgg add eval gpu * mlp loss by group * mlp loss by group * mlp loss by group multiple loaders * plot * mlp lambda rank remove device * plot * mlp * plot * weight by flop cnt * delete plots * plot * plot * weight by ctn * mlp shuffle tasks * renext * mlp debug * plots * plots * random from top two * random from top two * plots * plot * plot * beam search * random wearch debug * plots * plot debugger * make plot * plots * eval model * a * eval model * eval model * eval model * eval model * eval * comment out stuff * get backstuff * remove meta * revert * revert * a model * clean up mlp * embedding * a model * clean up mlp * clean up mlp * hold out * model * a * metrics * models * a * eval model * a * dataset * mlp debug * lstm * lstm * lstm * lstm * lstm * average top score * lstm * hold out all resnet50 * model * target embedding * multiple target * a * timestamp * timestamp * timestamp * timestamp * timestamp * timestamp * timestamp * timestamp * mlp * cross platform * minor bugs fixed * local * wrap up * wrap up * wrap up * wrap up * wrap up * wrap up * delete binary * merge * Update xgb_model.py * Update dataset.py * Update dataset.py * Update dataset.py * Update dispatcher.py * Update task_scheduler.py * remove binary * Update workload_registry.py * doc * Delete graph_embedding.py Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> Co-authored-by: ruochen99 <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Ubuntu <[email protected]>
|
This PR is ready for review. |
merrymercy
force-pushed
the
main
branch
4 times, most recently
from
b4070bf to
a3f54d7
Compare
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.
Known records that results in OOM/Segfault on
e5-2673:Time taken roughly on a 64-core machine: 100 hours
Full-scale results on e5:
Model: xgb
RMSE: 0.0775
R^2: 0.7641
pairwise comparision accuracy: 0.8556
mape: 10064628454.7681
average peak score@1: 0.8368
average peak score@5: 0.9098
Model: lgbm
RMSE: 0.0727
R^2: 0.7928
pairwise comparision accuracy: 0.8665
mape: 10188322169.1727
average peak score@1: 0.8467
average peak score@5: 0.9203
e2e results:
XGB:
Estimated total latency: 17.791 ms Trials: 102 Used time : 18696 s Next ID: -1
Mean inference time (std dev): 15.84 ms (0.01 ms)
LightGBM:
Estimated total latency: 16.897 ms Trials: 102 Used time : 35345 s Next ID: -1
Mean inference time (std dev): 14.88 ms (0.02 ms)