Repository navigation
Conversation
The ASAP7 1x tech LEFs (asap7_tech_1x_201209.lef and asap7_tech_1x_260907.lef) declare DATABASE MICRONS 1000 but write several rule values on a quarter nanometre. OpenROAD stores them as lround(value * 1000), and three of them then stop the rule doing what it was written to do: - M1 EOLKEEPOUT 0.01825 becomes 18 nm. The EOL test is length < width, so no 18 nm (minimum-width) tip is a line end and the keep-out never applies. Now 0.019. - M4/M5 EOLKEEPOUT side extension 0.02425 becomes 24 nm and M6/M7's 0.03225 becomes 32 nm, exactly the edge of the wire on the adjacent track. The CORNERONLY check needs the corner strictly inside, so adjacent-track tips are never caught. Now 0.025 and 0.033. - M8/M9 SPACINGTABLE thresholds (0.05975 ... 0.99975, 0.39975, 1.19975, 1.79975) round up, so a width or run exactly on the intended 60 ... 1000 nm or 400/1200/1800 nm threshold falls in the row below. Now rounded down (0.059 ... 0.999, 0.399, 1.199, 1.799). On a routed SHA-256, OpenROAD's check_drc reported no M1 or M4/M5 keep-out violations with the stored values; with the M1 width at 19 and the M4/M5 side extension at 25 it reported 1164 on M1 and 249 + 2 on M4/M5. The other quarter-nanometre values (M2/M3 0.0125, M6/M7 ENDOFLINE 0.0375, V3/V5 EOL enclosure 0.02425, M6/M7 AREA, M4_M3widePWR0p864 width ranges) round to values that behave the same on a 1 nm grid and are unchanged. The 4x LEF holds these values as whole nanometres and is unaffected. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: jeffhsu3 <jeffhsu3@gmail.com>
There was a problem hiding this comment.
Code Review
This pull request updates the LEF technology files (asap7_tech_1x_201209.lef and asap7_tech_1x_260907.lef) to adjust spacing and EOL keepout rules. The modifications address rounding issues introduced by the DATABASE MICRONS 1000 setting, ensuring that values do not round to exact grid boundaries or incorrect thresholds. Specifically, keepout and extension values for layers M1, M4, M5, M6, and M7 are slightly increased, and parallel run lengths and widths in the spacing tables for M8 and M9 are adjusted. No review comments were provided, and there is no additional feedback.
§6 now traces where LambdaPDK's ASAP7 tech LEF comes from. asap7sc7p5t_28's techlef_misc copy is byte-identical, and ORFS's platform LEF matches it apart from implant layers. It also lists the same fix proposed at every copy, covering both the 201209 LEF and the newer 260907 LEF: - siliconcompiler/lambdapdk#246 - The-OpenROAD-Project/OpenROAD-flow-scripts#4663 - The-OpenROAD-Project/asap7sc7p5t_28#10 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
🔍 QoR checkMetrics reflect the PR merge build — i.e. what will land on the target branch. Commit 62 design(s) checked — 3 with regression(s), 1 without a comparable baseline. ❌ asap7/aes-mbff base — 1 failing metric(s)
❌ asap7/riscv32i base — 3 failing metric(s)
❌ asap7/uart base — 2 failing metric(s)
|
Both 1x tech LEFs declare DATABASE MICRONS 1000 but write several rule values on a quarter nanometre, which a 1 nm database rounds off. OpenROAD stores lround(value * dbu), and then no 18 nm M1 tip is a line end for EOLKEEPOUT (0.01825 -> 18, the test being length < width), the M4-M7 corner keep-out's side extension (0.02425, 0.03225 -> 24, 32) ends exactly on the adjacent track's wire edge, which a corner must lie strictly inside, and the M8/M9 SPACINGTABLE thresholds (0.05975 ... 1.79975) round up past the manual's. At 4000 units per micron every value in both files is exact, so the rules hold as ASAP7 wrote them: the stored M1 line-end width is 73 against a minimum width of 72, the side extensions 97 and 129 against adjacent edges at 96 and 128, and M6/M7's AREA 0.0021875 is 35000 rather than 2188. The manufacturing grid stays 0.001, now 4 units, so geometry is still on the nanometre. The platform's cell, DFF and SRAM LEFs carry no UNITS block and load unchanged. This replaces the earlier whole-nanometre substitutes, as the review of siliconcompiler/lambdapdk#246 asked; that copy and The-OpenROAD-Project/asap7sc7p5t_28#10 now make the same change, and The-OpenROAD-Project/OpenROAD#11695 made it to OpenROAD's own copies of this LEF and warns when a LEF value rounds (ODB-1220). Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Signed-off-by: jeffhsu3 <jeffhsu3@gmail.com>
Summary
Both 1x tech LEFs (
flow/platforms/asap7/lef/asap7_tech_1x_201209.lefandasap7_tech_1x_260907.lef) declareDATABASE MICRONS 1000but write several rule values on a quarter nanometre. OpenROAD stores LEF distances aslround(value * dbu), so those values are rounded to whole nanometres, and for three of them the rounded value stops the rule from doing what it was written to do. This PR changes the unit toDATABASE MICRONS 4000in both files, at which every value is exact, and leaves the rule values as ASAP7 wrote them.Revised from an earlier version that substituted whole-nanometre values instead. The review of the same change in siliconcompiler/lambdapdk#246 asked for the unit instead, and The-OpenROAD-Project/OpenROAD#11695 (merged) already made this change to OpenROAD's own copies of the 201209 LEF under
test/asap7.LEF58_EOLKEEPOUTEOL widthlength < eolWidthLEF58_EOLKEEPOUTside extensionLEF58_EOLKEEPOUTside extensionSPACINGTABLEthresholdsAlso now exact: M6/M7
AREA 0.0021875(35000 units², was rounded to 2188 nm²) and the remaining quarter-nanometre values (M2/M3 and M30.0125, M6/M7ENDOFLINE 0.0375, V3/V5 enclosure0.02425, theM4_M3widePWR0p864width ranges), which rounded harmlessly before.MANUFACTURINGGRID 0.001is unchanged (now 4 units), so routed geometry stays on the nanometre; the router checks shapes, not rule values, against that grid. The platform's cell, DFF and SRAM LEFs carry noUNITSblock and load unchanged (asap7sc7p5tsite 216 x 1080 units, i.e. 0.054 x 0.27 µm).Evidence
EOLKEEPOUTrules gives M1 EOL width 18, M4/M5 side extension 24 and M6/M7 32 at 1000; with this patch 73, 97 and 129. A scan of every number in both files finds all exact at 4000.check_drcon a routed SHA-256 (stock 201209 LEF, SiliconCompiler 0.38.10 / OpenROAD 26Q3).drt::check_drcreports no M1 or M4/M5 keep-out violations on that database. Raising the stored M1 EOL width above 18 makes it report 1,164 M1 keep-out violations; raising the M4/M5 side extension above 24 makes it report 249 on M4 and 2 on M5.The investigation is written up in ASAP7_ECOSYSTEM_DISCREPANCIES.md, sections 5–7.
Notes
ODB-1220warning fires on these files at 1000 and not at 4000.🤖 Generated with Claude Code