Skip to content

update OR submodule - #4779

Merged
maliberty merged 1 commit into
The-OpenROAD-Project:masterfrom
The-OpenROAD-Project-staging:update-or
Nov 3, 2026
Merged

maliberty merged 1 commit into
The-OpenROAD-Project:masterfrom
The-OpenROAD-Project-staging:update-or

Conversation

@maliberty

Copy link
Copy Markdown
Member

No description provided.

Signed-off-by: Matt Liberty <mliberty@precisioninno.com>
@maliberty maliberty self-assigned this Nov 2, 2026
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 2, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-02T01:53:33.265179Z 9a5c2f8 PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@gemini-code-assist gemini-code-assist Bot left a comment

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.

Code Review

This pull request updates the OpenROAD subproject commit to f3d27840b65a9571a808a19b06dc0b93b9d4423d. There are no review comments, and I have no feedback to provide.

@openroad-ci

Copy link
Copy Markdown
Member

🔍 QoR check

Metrics reflect the PR merge build — i.e. what will land on the target branch.

Commit 59a9dcf · Jenkins build #1 · Baseline: build · View build on dashboard

62 design(s) checked — 12 with regression(s), 1 without a comparable baseline.

❌ asap7/aes_lvt base — 1 failing metric(s)
Metric target base delta limit band
globalroute__timing__setup__tns -89.799 -5.730 -1467.245% -67.730 PeriodPadding 20.000%
❌ asap7/riscv32i base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -3773.900 -3011.110 -25.333% -3613.332 PeriodPadding 20.000%
❌ asap7/riscv32i-mock-sram base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -574.964 0.000 — -190.000 PeriodPadding 20.000%
❌ ihp-sg13g2/gcd base — 3 failing metric(s)
Metric target base delta limit band
cts__timing__setup__tns -5.875 -4.453 -31.951% -5.343 PeriodPadding 20.000%
finish__timing__setup__tns -5.666 -3.879 -46.058% -4.655 PeriodPadding 20.000%
globalroute__timing__setup__tns -7.591 -6.198 -22.485% -7.437 PeriodPadding 20.000%
❌ ihp-sg13g2/ibex base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -5.169 -0.0563 -9085.057% -1.656 PeriodPadding 20.000%
❌ ihp-sg13g2/jpeg base — 1 failing metric(s)
Metric target base delta limit band
detailedroute__antenna_diodes_count 102.000 100.000 2.000% 100.100 Metric 0.100%
❌ nangate45/tinyRocket base — 3 failing metric(s)
Metric target base delta limit band
cts__timing__setup__tns -35.451 -20.122 -76.184% -24.146 PeriodPadding 20.000%
finish__timing__setup__tns -41.380 -27.303 -51.559% -32.763 PeriodPadding 20.000%
globalroute__timing__setup__tns -39.238 -25.918 -51.396% -31.101 PeriodPadding 20.000%
❌ sky130hd/chameleon base — 5 failing metric(s)
Metric target base delta limit band
detailedroute__antenna__violating__nets 1.000 0.000 — 0.000 Padding 30.000%
finish__timing__setup__tns -7.251 -1.457 -397.779% -2.057 PeriodPadding 20.000%
finish__timing__setup__ws -0.627 -0.0723 -767.455% -0.222 PeriodPadding 5.000%
globalroute__antenna_diodes_count 125.000 99.000 26.263% 100.000 Metric 0.100%
globalroute__timing__setup__ws -0.292 -0.108 -170.509% -0.258 PeriodPadding 5.000%
❌ sky130hd/jpeg base — 3 failing metric(s)
Metric target base delta limit band
cts__timing__setup__tns -48.808 -33.127 -47.338% -39.752 PeriodPadding 20.000%
finish__timing__setup__tns -43.301 -25.244 -71.532% -30.293 PeriodPadding 20.000%
globalroute__timing__setup__tns -49.633 -28.998 -71.162% -34.797 PeriodPadding 20.000%
❌ sky130hd/microwatt base — 1 failing metric(s)
Metric target base delta limit band
globalroute__antenna_diodes_count 2150.000 2117.000 1.559% 2119.117 Metric 0.100%
❌ sky130hs/jpeg base — 2 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -1.060 -0.179 -490.950% -0.879 PeriodPadding 20.000%
globalroute__timing__setup__tns -6.332 -1.271 -398.071% -1.971 PeriodPadding 20.000%
❌ sky130hs/riscv32i base — 3 failing metric(s)
Metric target base delta limit band
cts__timing__setup__tns -50.333 -1.001 -4929.236% -1.801 PeriodPadding 20.000%
finish__timing__setup__tns -75.798 -37.351 -102.933% -44.822 PeriodPadding 20.000%
globalroute__timing__setup__tns -86.694 -42.113 -105.861% -50.535 PeriodPadding 20.000%

@oharboe

oharboe commented Nov 3, 2026

Copy link
Copy Markdown
Collaborator

@maliberty Merge?

@dsengupta0628

Copy link
Copy Markdown
Contributor

I am debugging the QoR regressions in the designs to investigate before this is merged.
All 10 designs that failed on setup TNS or WNS set SETUP_REPAIR_PHASES = PARALLEL_EVAL, either directly or through an include:

aes_lvt, riscv32i, riscv32i-mock-sram (includes the riscv32i config), ihp gcd, ihp ibex, nangate45 tinyRocket, sky130hd chameleon, sky130hd jpeg, sky130hs jpeg, sky130hs riscv32i.

The other two failures are tiny antenna-diode count changes (ihp jpeg 100→102, microwatt 2117→2150). Those designs don't use PARALLEL_EVAL and are probably just noise from the placement and routing changes.

TNS already gets worse at CTS in several designs (sky130hs/riscv32i goes from −1.0 to −50.3). ORFS runs repair_timing_helper in cts.tcl, so the damage happens in setup repair.

Suspect OR commits in the bump (98c6045c72 → f3d27840b)

These two only affect PARALLEL_EVAL runs:

  1. #12029 (2f0c402b11), "rsz: Add UnbufferMove to PARALLEL_EVAL policy". It puts kUnbuffer first in the default PE move sequence in SetupParallelEvalPolicy.cc. It also removes repair_design_->init() from estimateSlewsAfterBufferRemoval. This is the most likely cause: it changes which moves run first in every PE design.
  2. #11974 (1740e32a2e), PARALLEL_EVAL stall and checkpoint rework. The WNS thresholds used to be a percentage of WNS and are now a percentage of the clock period:
    • Checkpoint WNS tolerance: 1% of WNS → 0.02% of the period.
    • progress_wns: 0.1% of WNS → 0.04% of the period.
    • The stall window rule is new.
    • The WNS tail gain threshold is now 0.1% of the period.

AI ruled these out:

  • STA bump: it only touches PrimaDelayCalc, which is not the default delay calculator, plus power and the SAIF lexer.
  • CTS useful-skew (#11930): -useful_skew defaults to off.
  • #12030 skew restore: it only matters when there are pin clock latency annotations.
  • The GRT resistance-mode fix: it only matters when resistance-aware routing is enabled.

@oharboe

oharboe commented Nov 3, 2026

Copy link
Copy Markdown
Collaborator

@dsengupta0628 @maliberty Can you debug this after the merge? Its going to take more updates to OpenROAD anyway. That should get us unstuck.

@dsengupta0628

dsengupta0628 commented Nov 3, 2026 •

Copy link
Copy Markdown
Contributor

I debugged ihp-sg13g2/gcd as this was the smallest. The regression comes from #11974 (1740e32a2e, "rsz: Scale the PARALLEL_EVAL WNS thresholds by the clock period"). The commit changes the floorplan-stage result slightly, and that difference grows through placement.

Adding @jhkim-pii Are there changes in your pipeline to address the QoR changes outlined here (is this going to help The-OpenROAD-Project/OpenROAD#12027 for example)?
Also #11974 makes the checkpoint WNS tolerance about 8× stricter for gcd (2.3 ps → 0.3 ps); probably intended?

The open PARALLEL_EVAL PRs (#12027 and others) will move these numbers again, so my be worth merging and recalibrating the baselines after those PRs land?

I cannot override to merge this PR unfortunately.

@maliberty
maliberty merged commit 3ff0197 into The-OpenROAD-Project:master Nov 3, 2026
10 of 12 checks passed
@maliberty
maliberty deleted the update-or branch November 3, 2026 16:36
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.

4 participants