This skill should be used when measuring RTL throughput and latency against BFM baselines. Flags deviations exceeding 10%.
<Use_When>
<Do_Not_Use_When>
<Execution_Policy>
skills/rtl-p5s-perf-verify/templates/perf-monitor-template.sv as measurement harness scaffold
</Execution_Policy><Why_This_Exists> RTL that is functionally correct may still fail performance targets due to unexpected stalls, backpressure, or pipeline bubbles. BFM provides the performance baseline; RTL must match it. </Why_This_Exists>
RTL modules and BFM baseline required:
rtl/**/*.sv files must existbfm/perf_baseline.json must existIf prerequisites are missing: WARNING — recommend running /rtl-agent-team:rtl-p5s-func-verify
and /rtl-agent-team:bfm-develop first. Orchestrator will adapt scope with available artifacts.
Task(subagent_type="rtl-agent-team:p5s-perf-orchestrator", prompt="Execute performance verification. User input: $ARGUMENTS")
Do not perform any work directly. The orchestrator agent manages performance simulation, BFM baseline comparison, throughput/latency/stall measurement, and deviation flagging.
reviews/phase-5-verify/{module}-performance-report.md — throughput and latency measurements vs BFM baseline, with PASS if deviation is within 10%sim/{module}/{module}_perf.json — raw measured vs expected metric values