nsys-analyze

nsys export --type=sqlite -o profile.sqlite profile.nsys-rep --force-overwrite=true

sqlite3 -header -column profile.sqlite "
WITH frames AS (
  SELECT ROW_NUMBER() OVER (ORDER BY e.start) as n,
         e.start, e.end, (e.end - e.start) as dur_ns
  FROM NVTX_EVENTS e LEFT JOIN StringIds s ON e.textId = s.id
  WHERE COALESCE(e.text, s.value) = 'App Update' AND e.end IS NOT NULL
),
frame_med AS (
  SELECT dur_ns as med FROM frames ORDER BY dur_ns
  LIMIT 1 OFFSET (SELECT COUNT(*)/2 FROM frames)
),
runtime AS (
  SELECT dur_ns FROM frames, frame_med WHERE dur_ns <= med * 5 ORDER BY dur_ns
)
SELECT
  ROUND((SELECT (MIN(start) - (SELECT MIN(start) FROM NVTX_EVENTS)) / 1e9 FROM frames), 2) as startup_sec,
  ROUND((SELECT (MAX(end) - MIN(start)) / 1e9 FROM frames), 2) as total_sec,
  (SELECT COUNT(*) FROM frames) as total_frames,
  (SELECT COUNT(*) FROM frames, frame_med WHERE dur_ns > med * 5) as loading_frames,
  COUNT(*) as runtime_frames,
  ROUND(AVG(dur_ns)/1e6, 2) as mean_ms,
  (SELECT ROUND(dur_ns/1e6,2) FROM runtime LIMIT 1 OFFSET (SELECT COUNT(*)/2 FROM runtime)) as p50_ms,
  (SELECT ROUND(dur_ns/1e6,2) FROM runtime LIMIT 1 OFFSET (SELECT CAST(COUNT(*)*0.95 AS INT) FROM runtime)) as p95_ms,
  ROUND(MIN(dur_ns)/1e6, 2) as min_ms,
  ROUND(MAX(dur_ns)/1e6, 2) as max_ms,
  ROUND(1000.0/(AVG(dur_ns)/1e6), 1) as fps
FROM runtime;
"

sqlite3 -header -column profile.sqlite "
WITH frames AS (
  SELECT ROW_NUMBER() OVER (ORDER BY e.start) as n,
         e.start, e.end, (e.end - e.start) as dur_ns
  FROM NVTX_EVENTS e LEFT JOIN StringIds s ON e.textId = s.id
  WHERE COALESCE(e.text, s.value) = 'App Update' AND e.end IS NOT NULL
),
frame_med AS (
  SELECT dur_ns as med FROM frames ORDER BY dur_ns
  LIMIT 1 OFFSET (SELECT COUNT(*)/2 FROM frames)
),
runtime_frames AS (
  -- Keep only frames classified as steady-state runtime. Do not collapse to
  -- one min/max span, because loading spikes can occur between runtime frames.
  SELECT f.start, f.end
  FROM frames f, frame_med m
  WHERE f.dur_ns <= m.med * 5
)
SELECT
  COALESCE(e.text, s.value) as zone_name,
  COUNT(*) as cnt,
  ROUND(AVG(e.end - e.start)/1e6, 3) as avg_ms,
  ROUND(SUM(e.end - e.start)/1e6, 2) as total_ms,
  ROUND(MAX(e.end - e.start)/1e6, 3) as max_ms
FROM NVTX_EVENTS e
LEFT JOIN StringIds s ON e.textId = s.id
WHERE EXISTS (
    SELECT 1 FROM runtime_frames rf
    WHERE e.start >= rf.start AND e.start < rf.end
  )
  AND e.end IS NOT NULL AND (e.end - e.start) > 0
  AND COALESCE(e.text, s.value) NOT LIKE '%Thread waiting%'
  AND COALESCE(e.text, s.value) NOT LIKE 'Carbonite::%'
  AND COALESCE(e.text, s.value) NOT LIKE 'carb::%'
  AND COALESCE(e.text, s.value) NOT IN ('Executing task','Running fiber')
GROUP BY zone_name
HAVING total_ms > 1
ORDER BY total_ms DESC LIMIT 30;
"

csvexport profile.tracy > zones.csv

head -1 zones.csv

nsys export --type=sqlite -o v1.sqlite v1.nsys-rep --force-overwrite=true
nsys export --type=sqlite -o v2.sqlite v2.nsys-rep --force-overwrite=true

csvexport v1.tracy > v1_zones.csv
csvexport v2.tracy > v2_zones.csv

import csv
 
def number(row, *names):
    for name in names:
        value = row.get(name)
        if value not in (None, ""):
            return float(value)
    return 0.0
 
def load_zones(path):
    zones = {}
    with open(path) as f:
        for row in csv.DictReader(f):
            name = row.get('name') or row.get('zone_name')
            if not name:
                continue
            zones[name] = {
                'total_ms': number(row, 'total_ns', 'total_time') / 1e6,
                'count': int(number(row, 'counts', 'count')),
                'mean_ms': number(row, 'mean_ns', 'mean') / 1e6,
            }
    return zones
 
v1, v2 = load_zones('v1_zones.csv'), load_zones('v2_zones.csv')
 
diffs = []
for name in set(v1) | set(v2):
    t1 = v1.get(name, {}).get('total_ms', 0)
    t2 = v2.get(name, {}).get('total_ms', 0)
    if t1 > 0.1 or t2 > 0.1:  # skip trivial zones
        diffs.append((name, t1, t2, t2 - t1))
 
print("=== Top Regressions (slower in v2) ===")
for name, t1, t2, d in sorted(diffs, key=lambda x: -x[3])[:15]:
    print(f"  {d:+10.1f}ms  {name}  (v1={t1:.1f}, v2={t2:.1f})")
 
print("\n=== Top Improvements (faster in v2) ===")
for name, t1, t2, d in sorted(diffs, key=lambda x: x[3])[:15]:
    print(f"  {d:+10.1f}ms  {name}  (v1={t1:.1f}, v2={t2:.1f})")