我有下面的代码使用Go语言的矩阵乘法

func main() {
    var wg sync.WaitGroup
    var col = 100
    var row = 150
    var randMatrixA [][]int
    var randMatrixB [][]int
    chA := make(chan [][]int)
    chB := make(chan [][]int)
    wg.Add(1)
    go genMat(row, col, chA, &wg)
    wg.Add(1)
    go genMat(col, row, chB, &wg)
    wg.Wait()
    randMatrixA = <-chA
    randMatrixB = <-chB
    fmt.Println(randMatrixA)
    fmt.Println(randMatrixB)
    fmt.Println("The Go Result of Matrix Multiplication = ")
    start := time.Now()
    c := doCalc(randMatrixA, randMatrixB)
    elapsed := time.Since(start)
    fmt.Println(c)
    fmt.Printf("Time taken to calculate %s \n", elapsed)
}
func genMat(row int, col int, ch chan<- [][]int, wg *sync.WaitGroup) {
    nM := make([][]int, col)
    for i := 0; i < col; i++ {
        nM[i] = make([]int, row)
    }
    generateNums(nM)
    wg.Done()
    ch <- nM
}
func generateNums(randMatrix [][]int) {
    for i, innerArray := range randMatrix {
        for j := range innerArray {
            randMatrix[i][j] = rand.Intn(100)
        }
    }
}
func rowCount(inM [][]int) int {
    return (len(inM))
}
func colCount(inM [][]int) int {
    return (len(inM[0]))
}
func doCalc(inA [][]int, inB [][]int) [][]int {
    var i, j int
    var wg sync.WaitGroup
    chC := make(chan [][]int)
    m := rowCount(inA) // number of rows the first matrix
    p := rowCount(inB) // number of rows the second matrix
    q := colCount(inB) // number of columns the second matrix
    k := 0
    total := 0
    var nM [][]int
    wg.Add(1)
    go genMat(m, q, chC, &wg)
    nM = <-chC
    wg.Wait()
    for i = 0; i < m; i++ {
        for j = 0; j < q; j++ {
            for k = 0; k < p; k++ {
                total = total + inA[i][k]*inB[k][j]
            }
            nM[i][j] = total
            total = 0
        }
        fmt.Println()
    }
    return nM
}

字符集
我使用Go例程来优化执行。两个go例程随机生成matrixA和MatrixB，另一个计算结果MatrixC
总执行时间平均约为2.4 ms，但我希望它在1到2 ms之间，甚至更短。
有没有人可以通过使用go例程而不使用内置函数来建议代码中的优化区域：）