Optimize power, performance, and area for HighTide designs by tuning flow parameters.
npx skills add https://github.com/VLSIDA/HighTide --skill optimize-ppa
Please help me install this Agent Skill. Skill: optimize-ppa Source: https://github.com/VLSIDA/HighTide/tree/main/.claude/skills/optimize-ppa Command: npx skills add https://github.com/VLSIDA/HighTide --skill optimize-ppa
This Skill helps engineers wring out higher utilization, faster Fmax, and cleaner DRC-free flows from HighTide benchmark builds without ever editing upstream RTL by focusing on stats-driven flow, timing, IO, and PDN tuning.
Ask the skill to review the last build metrics for designs/asap7/lfsr, adjust config.mk/constraint.sdc/io.tcl/pdn.tcl to increase utilization and tighten timing, then rerun the flow and compare the new die area, Fmax, and DRC status against the baseline.
High-intent search queries and answers about installing and using this skill.
To optimize PPA without modifying RTL, analyze build reports and tune flow parameters like utilization, clock period, and IO placement in config.mk and constraint.sdc files. Iterate by rerunning the flow and monitoring 6_report.json metrics.
To increase core utilization without causing routing congestion, incrementally raise CORE_UTILIZATION and PLACE_DENSITY while mitigating congestion using IO pin scripts, macro halos, and pin spacing. Monitor routing heatmaps and runtime to prevent flow failures.
The best way to tighten timing constraints for ASAP7 and Sky130HD benchmarks is to read timing reports, adjust clock periods and IO delays in constraint.sdc, rerun the flow, and monitor CTS and routing stages until negative timing margins appear.
Yes, you can use Bazel or Make to run HighTide PPA optimization flows. The process extracts baseline die area, power, and timing metrics from bazel-bin or legacy logs, applies parameter tuning, and reruns the build to compare new metrics.
To reduce IR drop and improve power delivery, tighten power configurations using IR-drop-aware PDN scripts and ABC_AREA settings. Generate IR drop images via Docker and OpenROAD, compare metrics across runs, and iterate until congestion or negative margins occur.
Your HighTide flow fails after increasing placement density because aggressive utilization triggers routing congestion and runtime blowup. You must monitor DRC reports and RUDY images, adjusting macro halos and pin spacing to mitigate the physical design bottlenecks.
VLSIDADiagnose failing HighTide designs by correlating build artifacts, logs, and configuration files.
loujcAutomates iterative design-space exploration for software/hardware optimization.
xsw632Automate the ORFS place-and-route flow for sky130hd designs with PPA reporting.
chuanseng-ngOrchestrate SoC physical design from gate-level netlist to GDS-II.
