Why does adding concurrency slow down this golang code?

The issue seems to come from your use of rand.Float64(), which uses a shared global object with a Mutex lock on it.

Instead, if for each CPU you create a separate rand.New(), pass it through to the interactions(), and use it to create the Float64(), there’s a massive improvement.

Update to show the changes to the new example code in the question that now uses rand.New()

The test() function was modified to either use a given channel, or return the result.

func test(n int, c chan []int) []int {
    source := rand.NewSource(time.Now().UnixNano())
    generator := rand.New(source)
    simulations := make([]int, n)
    for i := range simulations {
        for _, v := range simulation(NUMBER_OF_INTERACTIONS, generator) {
            simulations[i] += v
        }   
    }   
    if c == nil {
        return simulations
    }   
    c <- simulations
    return nil 
}

The main() function was updated to run both tests, and output the timed result.

func main() {
    rand.Seed(time.Now().UnixNano())

    nCPU := runtime.NumCPU()
    runtime.GOMAXPROCS(nCPU)
    fmt.Println("Number of CPUs: ", nCPU)

    start := time.Now()
    fmt.Println("Successful interactions: ", len(test(NUMBER_OF_SIMULATIONS, nil)))
    fmt.Println(time.Since(start))

    start = time.Now()
    tests := make([]chan []int, nCPU)
    for i := range tests {
        c := make(chan []int)
        go test(NUMBER_OF_SIMULATIONS/nCPU, c)
        tests[i] = c
    }

    // Concatentate the test results
    results := make([]int, NUMBER_OF_SIMULATIONS)
    for i, c := range tests {
        start := (NUMBER_OF_SIMULATIONS/nCPU) * i
        stop := (NUMBER_OF_SIMULATIONS/nCPU) * (i+1)
        copy(results[start:stop], <-c)
    }
    fmt.Println("Successful interactions: ", len(results))
    fmt.Println(time.Since(start))
}

The output is I received:

> Number of CPUs:  2 
>
> Successful interactions:  1000 
> 1m20.39959s
>
> Successful interactions:  1000
> 41.392299s