CPU scaling benchmark

workers
2 +1 main
iters total
500M
166666666/stream
elapsed
1471.25 ms
total CPU used
4343.14 ms
speedup
2.95×
vs serial
efficiency
98.3%
of 3× ideal
stream spawn ms spawned@ work start@ work end@ work ms reap wait ms
0 (main) 0 3.58 3.59 1443.65 1440.06 0
1 1.969 1.98 15.48 1466.65 1451.17 23.13
2 1.556 3.56 16.52 1468.43 1451.91 25.81
main
w1
w2
    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.