Repository navigation
rsz, gpl: Fold duplicate ports before swapping arithmetic modules and update the GPL incremental mode - #12391
Open
LucasYuki wants to merge 10 commits into
Conversation
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
… phase 2 Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Signed-off-by: LucasYuki <lucasyuki@yahoo.com.br>
Contributor
|
This PR exceeds the recommended size of 1000 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size. |
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces enhancements to the global placement (gpl) and resizer (rsz) modules, including options to skip phase 2 of incremental placement, set a separate phase 2 overflow target, and fold duplicate ports during arithmetic module swapping. The review feedback identifies two key issues in the cell-spreading search logic: an integer division truncation when computing grid step sizes, and the lack of a search iteration limit, which can lead to severe runtime regressions.
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
replace_arith_modulesrefuses to swap a module instance that has ports the replacement module lacks (ODB-0453). Hierarchical buffering adds such ports, for example during timing-driven global placement. This PR removes them before the swap when each one only carries a copy of a signal that already crosses a port the replacement has. On the public designs this removes all 16 swaps master refuses.It also changes incremental global placement, which places the swapped modules' new cells, to keep those cells in the space the replaced cells left.
Type of Change
Impact
rsz
removeBufferIfPossible, along with the buffers feeding them while those are left without loads (RSZ-0172).replace_arith_modulesreturns 1 if any module was swapped and 0 otherwise (documented in the rsz README).gpl: incremental placement
-skip_incremental_phase2keeps the existing instances where they are and leaves any remaining overflow to detailed placement (GPL-0197).-incremental_phase2_overflowsets a separate overflow target for phase 2, so phase 1 can stop at a looser one.QoR
Run with the ORFS branch of the same name (companion PR under Related Issues) against master at the same base, OpenROAD 4543b6b and ORFS 25331f78fe. That is OpenROAD-flow-scripts-Private » r2_swap_fix_unl_nop2_rtall #7 vs Nightly-Public #7774, all 62 public designs. All designs finish, and the Jenkins QoR check passes.
The 55 designs that swap nothing end with identical WS and TNS. The 7 that swap (master → branch):
Verification
./etc/Build.sh).At 9b1585a, with Bazel, all gpl and rsz tests pass (402 passed, 4 GPU tests skipped), and so does
odb/replace_hier_mod1.//test:flow_testspasses (14 designs). clang-format 23.1.2 and tclfmt/tclint 0.7.0, the versions CI uses, report nothing on the changed files.New and updated tests:
rsz/replace_arith_modules4: extra inputs that duplicate existing inputs are removed. Of the buffers that drove them, the one left without loads is removed and the one with another load is kept. A port carrying another signal still refuses the swap.rsz/replace_arith_modules5: extra inputs that bring the module's own outputs back in, directly and through a buffer in the parent, are removed, along with the buffer left without loads. A module whose looped-back signal leaves through an extra output port the replacement lacks still refuses the swap.gpl/incremental04andgpl/incremental05(pass/fail) cover phase 2 after a missed target, the separate phase 2 target, and the option checks.gpl/incremental03now covers the divergence path with-skip_incremental_phase2.odb/replace_hier_mod1.okis updated for the new phase 1 overflow.gpl/incremental02.okand.defokare regenerated. incremental02 is a pass/fail test, so CI compares neither file. They are most of this PR's line count.Related Issues
Should be merged at the same time as ORFS PR: The-OpenROAD-Project/OpenROAD-flow-scripts#4861