CPU scaling benchmark

W=0 W=1 W=2 W=3 W=4 W=6 W=8 W=9 W=10 W=12 W=16 iters: 100M 500M 1B 2B
workers
6 +1 main
iters total
500M
71428571/stream
elapsed
1156.46 ms
total CPU used
7104.22 ms
speedup
6.14×
vs serial
efficiency
87.7%
of 7× ideal
stream spawn ms spawned@ work start@ work end@ work ms reap wait ms
0 (main) 0 10.71 10.72 1138.07 1127.35 0
1 2.029 2.05 18.38 1149.03 1130.65 11.1
2 1.556 3.63 24.17 1018.7 994.53 0.17
3 1.667 5.32 20.88 770.47 749.59 0.23
4 2.098 7.45 38.74 1038.18 999.44 0.26
5 1.815 9.28 38.7 1153.98 1115.28 16.02
6 1.403 10.7 42.39 1029.77 987.38 0.27
main
w1
w2
w3
w4
w5
w6
    fork+handshake      CPU work      parent reap wait
what this measures
Each stream runs a tight integer LCG loop — working set is one CPU register, no memory access, no shared data. Speedup = sum(stream CPU time) / wall-clock elapsed. Efficiency = speedup / (workers+1). 100% efficiency means perfect linear scaling; less than 100% is the cost of serial fork setup, reap tail, SMT/core contention.