这是我的.CPP文件

#include <iostream>
using namespace std;

extern "C" void KeysAsm(int arr[], int n, int thetha, int rho);

// Keep this and call it from assembler
extern "C"
void crim(int *xp, int *yp) {
    int temp = *xp;
    *xp = *yp;
    *yp = temp+2;
}

// Translate this into Intel assembler
void KeysCpp(int arr[], int n, int thetha, int rho){
    for (int i = 0; i < n - 1; i++) {
        for (int j = 0; j < n - i - 1; j++) {
            if (arr[j] > arr[j + 1]) {
                crim(&arr[j], &arr[j + 1]);
            }
        }
        arr[i]= arr[i] + thetha / rho * 2 - 4;
    }
}

// Function to print an array 
void printArray(int arr[], int size){
    int i;
    for (i = 0; i < size; i++)
        cout << arr[i] << "\n";
    cout << endl;
}

int main() {
    int gamma1[]{
        9,
        270,
        88,
        -12,
        456,
        80,
        45,
        123,
        427,
        999
    };

    int gamma2[]{
        900,
        312,
        542,
        234,
        234,
        1,
        566,
        123,
        427,
        111
    };

    printf("Array:\n");
    printArray(gamma1, 10);

    KeysAsm(gamma1, 10, 5, 6);
    printf("Array Result Asm:\n");
    printArray(gamma1, 10);

    KeysCpp(gamma2, 10, 5, 6);
    printf("Array Result Cpp:\n");
    printArray(gamma2, 10);
}

我想做的是，将 KeysCpp 函数转换为汇编语言，并从这个.CPP文件中调用它。我想保留.CPP中的 crim 函数，而只转换 KeysCpp。
这是我的.ASM文件

PUBLIC KeysAsm

includelib kernel32.lib

_DATA   SEGMENT
EXTERN crim:PROC
_DATA ENDS

_TEXT   SEGMENT

KeysAsm PROC
    push    rbp
    mov     rbp, rsp
    sub     rsp, 40
    mov     QWORD PTR [rbp-24], rdi
    mov     DWORD PTR [rbp-28], esi
    mov     DWORD PTR [rbp-32], edx
    mov     DWORD PTR [rbp-36], ecx
    mov     DWORD PTR [rbp-4], 0
    jmp      L3

 L3:
    mov     eax, DWORD PTR [rbp-28]
    sub     eax, 1
    cmp     DWORD PTR [rbp-4], eax
    jl       L7

 L4:
    mov     eax, DWORD PTR [rbp-28]
    sub     eax, DWORD PTR [rbp-4]
    sub     eax, 1
    cmp     DWORD PTR [rbp-8], eax
    jl       L6

 L5:
    add     DWORD PTR [rbp-8], 1

 L6:
    mov     eax, DWORD PTR [rbp-8]
    cdqe
    lea     rdx, [0+rax*4]
    mov     rax, QWORD PTR [rbp-24]
    add     rax, rdx
    mov     edx, DWORD PTR [rax]
    mov     eax, DWORD PTR [rbp-8]
    cdqe
    add     rax, 1
    lea     rcx, [0+rax*4]
    mov     rax, QWORD PTR [rbp-24]
    add     rax, rcx
    mov     eax, DWORD PTR [rax]
    cmp     edx, eax
    jle      L5
    mov     eax, DWORD PTR [rbp-8]
    cdqe
    add     rax, 1
    lea     rdx, [0+rax*4]
    mov     rax, QWORD PTR [rbp-24]
    add     rdx, rax
    mov     eax, DWORD PTR [rbp-8]
    cdqe
    lea     rcx, [0+rax*4]
    mov     rax, QWORD PTR [rbp-24]
    add     rax, rcx
    mov     rsi, rdx
    mov     rdi, rax
    call    crim

 L7:
    mov     DWORD PTR [rbp-8], 0
    jmp      L4

KeysAsm ENDP

_TEXT   ENDS


END

我正在使用Visual Studio 2017运行此项目。
运行此代码时出现下一个错误。
MatrixMultiplication.exe中0x00007FF74B0E429C处的未处理异常：堆栈Cookie检测代码检测到基于堆栈的缓冲区溢出。发生