打印转置矩阵时出现的问题

问：

我的问题是，在转置后打印出矩阵的第一行后，我收到一个错误，告诉我我试图访问无法访问的位置

第一篇文章与 asm 讨论，如果我没有告诉可能需要的东西文本 我在 C++ 中调用了一个用 asm 编写的转置函数

#include <iostream>
#include <windows.h>

extern "C" void transpose(INT64**, INT64);

// Function for displaying the matrix
void printMatrix(INT64** matrix, INT64 n) {
    for (INT64 i = 0; i < n; ++i) {
        for (INT64 j = 0; j < n; ++j) {
            std::cout << matrix[i][j] << " ";
        }
        std::cout << std::endl;
    }
}

int main() {
    INT64 n = 8; // Matrix size

    // Initialization of matrix A
    INT64** A = new INT64 * [n];
    for (INT64 i = 0; i < n; ++i) {
        A[i] = new INT64[n];
        for (INT64 j = 0; j < n; ++j) {
            A[i][j] = i * n + j; // Filling matrix A
        }
    }

    std::cout << "Matrix before transposition:" << std::endl;
    printMatrix(A, n); // Display the matrix before transposition

    // Calling the transpose function
    transpose(A, n);

    std::cout << "Matrix after transposition:" << std::endl;
    printMatrix(A, n); // Display the matrix after transposition

    // Deallocate memory
    for (INT64 i = 0; i < n; ++i) {
        delete[] A[i];
    }
    delete[] A;

    return 0;
}

这是我的代码最后一次迭代中使用的 asm 函数

; TransposeSquareMatrix(A, n)
    mov     rdi, rcx
    mov     rsi, rdx
    mov     rbx, rdi        ; Address A is in RDI
    mov     rcx, rsi        ; Dimension n is in RSI
    imul    r8, rsi, 8      ; Step between rows
    dec     rcx
    jz      .c              ; It's a (1 x 1) matrix
.a: push    rcx             ; (1)
    mov     rsi, rbx        ; Column address
    mov     rdi, rbx        ; Row address
.b: add     rsi, 8          ; To next element in this row
    add     rdi, r8         ; To next element in this column
    mov     rax, [rsi]      ; Swap 2 elements
    mov     rdx, [rdi]
    mov     [rdi], rax
    mov     [rsi], rdx
    dec     rcx
    jnz     .b
    lea     rbx, [rbx + r8 + 8] ; To next element on main diagonal
    pop     rcx             ; (1)
    dec     rcx
    jnz     .a              ; Continu until (1 x 1) matrix
.c: ret

有什么问题？是 c++ 代码还是其他东西？