Phase 67a: Layout tax forensics foundation (SSOT + measurement box)
Changes: - scripts/box/layout_tax_forensics_box.sh: New measurement harness * Baseline vs treatment 10-run throughput comparison * Automated perf stat collection (cycles, IPC, branches, misses, TLB) * Binary metadata (size, section info) * Output to results/layout_tax_forensics/ - docs/analysis/PHASE67A_LAYOUT_TAX_FORENSICS_SSOT.md: Diagnostic reference * Decision tree: GO/NEUTRAL/NO-GO classification * Symptom→root-cause mapping (IPC/branch-miss/dTLB/cache-miss) * Phase 64 case study analysis (IPC 2.05→1.98) * Operational guidelines for Phase 67b+ optimizations - CURRENT_TASK.md: Phase 67a marked complete, operational Outcome: - Layout tax diagnosis now reproducible in single measurement pass - Enables fast GO/NO-GO decision for future code removal/reordering attempts - Foundation for M2 (55% target) structural exploration without regression risk 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
Moe Charm (CI)
150
scripts/box/layout_tax_forensics_box.sh
Executable file
150
scripts/box/layout_tax_forensics_box.sh
Executable file
@ -0,0 +1,150 @@
|
||||
#!/bin/bash
|
||||
# Layout Tax Forensics Box
|
||||
# Purpose: Compare baseline vs treatment binaries to isolate layout tax causes
|
||||
# Usage: ./scripts/box/layout_tax_forensics_box.sh <baseline_binary> <treatment_binary>
|
||||
# Example: ./scripts/box/layout_tax_forensics_box.sh ./bench_random_mixed_hakmem_minimal_pgo ./bench_random_mixed_hakmem_fast_pruned
|
||||
|
||||
set -e
|
||||
|
||||
BASELINE_BIN="${1:-./.bench_random_mixed_hakmem_minimal_pgo}"
|
||||
TREATMENT_BIN="${2:-./.bench_random_mixed_hakmem_fast_pruned}"
|
||||
ITERS=20000000
|
||||
WS=400
|
||||
RUNS=10
|
||||
RESULT_DIR="./results/layout_tax_forensics"
|
||||
|
||||
# Ensure binaries exist
|
||||
if [ ! -f "$BASELINE_BIN" ]; then
|
||||
echo "ERROR: Baseline binary not found: $BASELINE_BIN"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ ! -f "$TREATMENT_BIN" ]; then
|
||||
echo "ERROR: Treatment binary not found: $TREATMENT_BIN"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
mkdir -p "$RESULT_DIR"
|
||||
|
||||
# Metrics to collect
|
||||
PERF_EVENTS="cycles,instructions,branches,branch-misses,cache-misses,iTLB-loads,iTLB-load-misses,dTLB-loads,dTLB-load-misses,L1-dcache-loads,L1-dcache-load-misses,LLC-loads,LLC-load-misses"
|
||||
|
||||
echo "=========================================="
|
||||
echo "Layout Tax Forensics Box"
|
||||
echo "=========================================="
|
||||
echo "Baseline binary: $BASELINE_BIN"
|
||||
echo "Treatment binary: $TREATMENT_BIN"
|
||||
echo "Workload: Mixed, ITERS=$ITERS, WS=$WS, RUNS=$RUNS"
|
||||
echo "Metrics: $PERF_EVENTS"
|
||||
echo "Output: $RESULT_DIR"
|
||||
echo ""
|
||||
|
||||
# Throughput 10-run (baseline)
|
||||
echo "=== BASELINE: Throughput (10-run) ==="
|
||||
BASELINE_THROUGHPUT_FILE="$RESULT_DIR/baseline_throughput.txt"
|
||||
> "$BASELINE_THROUGHPUT_FILE"
|
||||
for i in $(seq 1 $RUNS); do
|
||||
# Use cleanenv to match canonical benchmark
|
||||
HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE RUNS=1 ITERS=$ITERS WS=$WS BENCH_BIN="$BASELINE_BIN" \
|
||||
bash -c 'source scripts/run_mixed_10_cleanenv.sh' 2>/dev/null | grep -oP "Throughput = +\K[0-9.]+" >> "$BASELINE_THROUGHPUT_FILE" || true
|
||||
done
|
||||
|
||||
BASELINE_MEAN=$(awk '{sum+=$1; count++} END {print sum/count}' "$BASELINE_THROUGHPUT_FILE")
|
||||
BASELINE_MEDIAN=$(sort -n "$BASELINE_THROUGHPUT_FILE" | awk 'NR==('$(($RUNS/2))')' | head -1)
|
||||
BASELINE_STDDEV=$(awk -v mean="$BASELINE_MEAN" '{sum+=($1-mean)^2; count++} END {print sqrt(sum/count)}' "$BASELINE_THROUGHPUT_FILE")
|
||||
BASELINE_CV=$(awk -v mean="$BASELINE_MEAN" -v sd="$BASELINE_STDDEV" 'BEGIN {print (sd/mean)*100}')
|
||||
|
||||
echo "Baseline throughput (M ops/s):"
|
||||
cat "$BASELINE_THROUGHPUT_FILE" | nl
|
||||
echo "Mean: $BASELINE_MEAN"
|
||||
echo "Median: $BASELINE_MEDIAN"
|
||||
echo "CV: $BASELINE_CV %"
|
||||
echo ""
|
||||
|
||||
# Throughput 10-run (treatment)
|
||||
echo "=== TREATMENT: Throughput (10-run) ==="
|
||||
TREATMENT_THROUGHPUT_FILE="$RESULT_DIR/treatment_throughput.txt"
|
||||
> "$TREATMENT_THROUGHPUT_FILE"
|
||||
for i in $(seq 1 $RUNS); do
|
||||
HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE RUNS=1 ITERS=$ITERS WS=$WS BENCH_BIN="$TREATMENT_BIN" \
|
||||
bash -c 'source scripts/run_mixed_10_cleanenv.sh' 2>/dev/null | grep -oP "Throughput = +\K[0-9.]+" >> "$TREATMENT_THROUGHPUT_FILE" || true
|
||||
done
|
||||
|
||||
TREATMENT_MEAN=$(awk '{sum+=$1; count++} END {print sum/count}' "$TREATMENT_THROUGHPUT_FILE")
|
||||
TREATMENT_MEDIAN=$(sort -n "$TREATMENT_THROUGHPUT_FILE" | awk 'NR==('$(($RUNS/2))')' | head -1)
|
||||
TREATMENT_STDDEV=$(awk -v mean="$TREATMENT_MEAN" '{sum+=($1-mean)^2; count++} END {print sqrt(sum/count)}' "$TREATMENT_THROUGHPUT_FILE")
|
||||
TREATMENT_CV=$(awk -v mean="$TREATMENT_MEAN" -v sd="$TREATMENT_STDDEV" 'BEGIN {print (sd/mean)*100}')
|
||||
|
||||
echo "Treatment throughput (M ops/s):"
|
||||
cat "$TREATMENT_THROUGHPUT_FILE" | nl
|
||||
echo "Mean: $TREATMENT_MEAN"
|
||||
echo "Median: $TREATMENT_MEDIAN"
|
||||
echo "CV: $TREATMENT_CV %"
|
||||
echo ""
|
||||
|
||||
# Calculate delta
|
||||
DELTA=$(awk -v b="$BASELINE_MEAN" -v t="$TREATMENT_MEAN" 'BEGIN {print ((t-b)/b)*100}')
|
||||
echo "Performance delta: $DELTA % ($(awk -v t="$TREATMENT_MEAN" -v b="$BASELINE_MEAN" 'BEGIN {print t-b}' | cut -c1-6)M ops/s)"
|
||||
echo ""
|
||||
|
||||
# perf stat: single representative runs (baseline)
|
||||
echo "=== BASELINE: perf stat (representative run) ==="
|
||||
BASELINE_PERF_FILE="$RESULT_DIR/baseline_perf.txt"
|
||||
perf stat -e "$PERF_EVENTS" -o "$BASELINE_PERF_FILE" \
|
||||
bash -c "HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE RUNS=1 ITERS=$ITERS WS=$WS BENCH_BIN='$BASELINE_BIN' source scripts/run_mixed_10_cleanenv.sh" 2>&1 || true
|
||||
cat "$BASELINE_PERF_FILE"
|
||||
echo ""
|
||||
|
||||
# perf stat: single representative runs (treatment)
|
||||
echo "=== TREATMENT: perf stat (representative run) ==="
|
||||
TREATMENT_PERF_FILE="$RESULT_DIR/treatment_perf.txt"
|
||||
perf stat -e "$PERF_EVENTS" -o "$TREATMENT_PERF_FILE" \
|
||||
bash -c "HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE RUNS=1 ITERS=$ITERS WS=$WS BENCH_BIN='$TREATMENT_BIN' source scripts/run_mixed_10_cleanenv.sh" 2>&1 || true
|
||||
cat "$TREATMENT_PERF_FILE"
|
||||
echo ""
|
||||
|
||||
# Binary metadata
|
||||
echo "=== Binary Metadata ==="
|
||||
echo "Baseline:"
|
||||
ls -lh "$BASELINE_BIN" | awk '{print " Size:", $5}'
|
||||
size "$BASELINE_BIN" 2>/dev/null | tail -1 || echo " (size info not available)"
|
||||
echo ""
|
||||
echo "Treatment:"
|
||||
ls -lh "$TREATMENT_BIN" | awk '{print " Size:", $5}'
|
||||
size "$TREATMENT_BIN" 2>/dev/null | tail -1 || echo " (size info not available)"
|
||||
echo ""
|
||||
|
||||
# Summary report
|
||||
SUMMARY_FILE="$RESULT_DIR/layout_tax_forensics_summary.txt"
|
||||
cat > "$SUMMARY_FILE" << EOF
|
||||
================================================================================
|
||||
Layout Tax Forensics Summary
|
||||
================================================================================
|
||||
|
||||
Baseline: $BASELINE_BIN
|
||||
Treatment: $TREATMENT_BIN
|
||||
Workload: Mixed (ITERS=$ITERS, WS=$WS)
|
||||
|
||||
THROUGHPUT RESULTS
|
||||
==================
|
||||
Baseline Mean: $BASELINE_MEAN M ops/s (CV: $BASELINE_CV %)
|
||||
Treatment Mean: $TREATMENT_MEAN M ops/s (CV: $TREATMENT_CV %)
|
||||
Delta: $DELTA %
|
||||
|
||||
DETAILED OUTPUT
|
||||
================
|
||||
- Throughput samples: $BASELINE_THROUGHPUT_FILE, $TREATMENT_THROUGHPUT_FILE
|
||||
- perf stat: $BASELINE_PERF_FILE, $TREATMENT_PERF_FILE
|
||||
|
||||
NEXT STEPS
|
||||
==========
|
||||
Use PHASE67A_LAYOUT_TAX_FORENSICS_SSOT.md to:
|
||||
1. Categorize delta as GO/NEUTRAL/NO-GO
|
||||
2. Map perf metrics to root causes (IPC/cache/iTLB/branch-miss)
|
||||
3. Document symptoms and remediation strategies
|
||||
================================================================================
|
||||
EOF
|
||||
|
||||
cat "$SUMMARY_FILE"
|
||||
echo ""
|
||||
echo "Results saved to: $RESULT_DIR"
|
||||
Reference in New Issue
Block a user