Skip to content

Placement optimization (CPU, primary) and optional GPU implementation#57

Open
agamdamaraju wants to merge 8 commits intopartcleda:mainfrom
agamdamaraju:main
Open

Placement optimization (CPU, primary) and optional GPU implementation#57
agamdamaraju wants to merge 8 commits intopartcleda:mainfrom
agamdamaraju:main

Conversation

@agamdamaraju
Copy link
Copy Markdown

Summary

  • Implemented placement optimization improvements in placement.py
  • Added CPU test harness updates in test.py
  • Added optional GPU versions: placement_gpu.py, test_gpu.py (for test11)
  • Added requirements.txt and updated leaderboard entry in README.md

Results (CPU, tests 1-10)

  • Average Overlap: 0.0000
  • Average Wirelength: 0.2502
  • Total Runtime: 107.09 s

Notes

  • CPU path is primary for submission.
  • GPU files are optional for extra credit.
  • Test 11/12 is extra credit.

Comment thread placement.py Outdated
# Total wirelength
total_wirelength = torch.sum(smooth_manhattan)
# Average-axis routing distance keeps objective scale stable and smooth.
total_wirelength = torch.sum(0.5 * (smooth_dx + smooth_dy))
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

here.

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants