Skip to content

asap7: keep the PDN on the routing grid and tracks - #4668

Draft
jeffhsu3 wants to merge 1 commit into
The-OpenROAD-Project:masterfrom
jeffhsu3:asap7-pdn-ongrid
Draft

jeffhsu3 wants to merge 1 commit into
The-OpenROAD-Project:masterfrom
jeffhsu3:asap7-pdn-ongrid

Conversation

@jeffhsu3

Copy link
Copy Markdown

Summary

The ASAP7 PDN scripts place power vias and stripes where the design rule manual's grid, track and via-width rules cannot hold. This changes all three (grid_strategy-M1-M2-M5-M6.tcl, BLOCKS_grid_strategy.tcl, BLOCK_grid_strategy.tcl) so the PDN stays on the routing grid and tracks. Part of the divergences listed in #4667.

  • M2-to-M5 stacks: pdngen stacks them on the M2 rails, every 270 nm, which is off M4's 24 nm grid, and the M3/M4 pads are wider than their cuts. Now -min_width_layers {M3 M4} -ongrid {M4}.
  • M5 straps: 0.12 um straps take V4 cuts narrower than the strap. They are now minimum width (0.024 um) with -snap_to_grid, at a fifth of the pitch (1.08 um; 0.432 um at the BLOCKS top level), so the M5 metal is unchanged. M6 straps are -snap_to_grid too.
  • Rings: a new ring_offsets.tcl computes per-side -core_offsets that put every ring wire on its layer's tracks. The BLOCKS ring's M5 is 0.408 um (0.504 is over M5's 0.48 um maximum) and its M6 0.288 um, the one width M6_M5widePWR1p152 makes a flush V5 for. The BLOCK ring's M5 is minimum width for the V4s at its corners.

Type of Change

  • Bug fix

Impact

Checked with gdscheck's asap7 openroad suite: the DRM's rules less the ones the tech LEF does not give the router, so a marker is a DRM violation of a rule the flow could have kept. ORFS's KLayout deck has its grid checks off (OFFGRID = false), so it does not see these.

Design DRM markers (openroad suite) Worst static IR drop, VDD Setup WNS
asap7/gcd 602 -> 0 0.61% -> 0.40%
asap7/aes 14,449 -> 0 4.56% -> 2.80% -2.57 -> -2.95 ps
asap7/aes-block 114,821 -> 15,756 0.44% -> 0.17%

What remains on aes-block is not the PDN: macros placed off the fin/gate grid, and tech LEF via and M8/M9 width gaps (see #4667).

The strap pitch is set by IR drop: minimum-width straps at the old 5.4 um pitch raised aes to 11.6%; 2.16 um gave 5.2%, 1.08 um 2.8%. Denser straps take M5 tracks, so congestion-sensitive designs are worth watching in the QoR check.

Verification

  • gcd, aes and aes-block run to completion; detailed routing has 0 DRC errors on all three, and aes-block's VDD/VSS are fully connected (PSM).
  • IR drop from the flow's own analyze_power_grid (aes-block with PWR_NETS_VOLTAGES/GND_NETS_VOLTAGES set, as its config clears them).
  • gcd and aes were built with SYNTH_USE_SYN=0: syn currently writes DEF at 100 units per micron, which rounds the GDS to 10 nm (syn: give the exported block the tech's DEF units OpenROAD#11700). QoR metrics are not affected.
  • Other ASAP7 designs: left to the CI QoR check.

Related Issues

#4667

🤖 Co-authored with Claude Code

The ASAP7 PDN scripts place power vias and stripes where the design rule
manual's grid, track and via-width rules cannot hold:

- pdngen stacks the M2-to-M5 connections on the M2 rails, every 270 nm,
  which is off M4's 24 nm grid; the stacked M3/M4 pads are wider than
  their cuts. Now -min_width_layers {M3 M4} -ongrid {M4}.
- 0.12 um M5 straps take V4 cuts narrower than the strap. The straps are
  now minimum width (0.024 um) and -snap_to_grid, at a fifth of the pitch
  (1.08 um, 0.432 um at the BLOCKS top level) so the M5 metal is the same.
  M6 straps are -snap_to_grid too.
- Rings: the new ring_offsets.tcl computes per-side core offsets that put
  every ring wire on its layer's tracks. The BLOCKS ring's M5 is 0.408
  (0.504 is over M5's 0.48 maximum) and its M6 0.288, the width
  M6_M5widePWR1p152 makes a flush V5 for; BLOCK's ring M5 is minimum width
  for the V4s at its corners.

Checked with gdscheck's asap7 openroad suite (the DRM, less the rules the
tech LEF does not give the router): gcd 602 -> 0, aes 14449 -> 0, aes-block
114821 -> 15756 (what remains is macro placement off the fin/gate grid and
tech LEF via and width gaps). Detailed routing has no DRC errors on all
three. Worst-case static IR drop (VDD) is lower than before:

  gcd        0.61% -> 0.40%
  aes        4.56% -> 2.80%
  aes-block  0.44% -> 0.17%

gcd and aes built with SYNTH_USE_SYN=0; syn currently writes DEF at 100
units per micron, which rounds the GDS to 10 nm.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: jeffhsu3 <jeffhsu3@gmail.com>

@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 introduces a new Tcl utility ring_offsets.tcl with the asap7_ring_core_offsets procedure to dynamically calculate core offsets for PDN rings on routing tracks. It also updates several PDN grid strategy files (BLOCKS_grid_strategy.tcl, BLOCK_grid_strategy.tcl, and grid_strategy-M1-M2-M5-M6.tcl) to use this utility and adjusts various stripe widths, pitches, and connection parameters to ensure proper grid alignment. However, there is a critical issue in both BLOCKS_grid_strategy.tcl and BLOCK_grid_strategy.tcl where the horizontal and vertical layer arguments passed to asap7_ring_core_offsets are swapped, which will result in incorrect offset calculations and off-grid wires.

@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 f2751ed · Jenkins build #1 · Baseline: build · View build on dashboard

62 design(s) checked — 3 with regression(s), 0 without a comparable baseline.

❌ asap7/cva6 base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -501.291 -9.79672 -5016.926889816184% -191.79672 PeriodPadding 20%
❌ asap7/riscv32i-mock-sram base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -500.597 -130.364 -283.99941701696787% -320.364 PeriodPadding 20%
❌ asap7/swerv_wrapper base — 1 failing metric(s)
Metric target base delta limit band
finish__timing__setup__tns -1929.07 -1551.92 -24.302154750244856% -1862.304 PeriodPadding 20%

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