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
1255.1 ms
total CPU used
5309 ms
speedup
4.23×
vs serial
efficiency
84.6%
of 5× ideal
stream spawn ms spawned@ work start@ work end@ work ms reap wait ms
0 (main) 0 6.19 6.2 1254.83 1248.63 0
1 1.765 1.78 17.29 1020.3 1003.01 0.09
2 1.469 3.27 16.6 969.95 953.35 0.18
3 1.473 4.76 18.52 995.7 977.18 0.2
4 1.415 6.19 36.03 1162.86 1126.83 0.22
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.