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
4 +1 main
iters total
500M
100000000/stream
elapsed
1209.51 ms
total CPU used
5373.21 ms
speedup
4.44×
vs serial
efficiency
88.8%
of 5× ideal
stream spawn ms spawned@ work start@ work end@ work ms reap wait ms
0 (main) 0 6.45 6.46 1037.7 1031.24 0
1 1.838 1.85 16.16 1106.01 1089.85 68.44
2 1.471 3.34 45.19 1206.71 1161.52 169.15
3 1.58 4.94 20.31 990.74 970.43 0.08
4 1.487 6.43 42.39 1162.56 1120.17 125.03
main
w1
w2
w3
w4
    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.