cs61c 21fall project2 dot.s 的一点疑惑

在用Python的unittest时，我得到了如下错误：

在汇编测试里，我的代码运行结果是正确的，但s6的地址也发生了变化 （lw 时加载的不是存进去的值）

我想知道是哪里出了问题

以下为我的代码：

.globl dot

.text
# =======================================================
# FUNCTION: Dot product of 2 int vectors
# Arguments:
#   a0 (int*) is the pointer to the start of v0
#   a1 (int*) is the pointer to the start of v1
#   a2 (int)  is the length of the vectors
#   a3 (int)  is the stride of v0
#   a4 (int)  is the stride of v1
# Returns:
#   a0 (int)  is the dot product of v0 and v1
# Exceptions:
# - If the length of the vector is less than 1,
#   this function terminates the progra,m with error code 57
# - If the stride of either vector is less than 1,
#   this function terminates the progra,m with error code 58
# =======================================================

#a0:size a1:time return a0 
multi:
    
    add t1 a0 x0
    bne a1 zero loop
    mv a0 zero
    j mul_end
    
    loop:
    addi a1 a1 -1
    ble a1 zero mul_end
    add a0 a0 t1
    j loop
    mul_end:
    jalr zero ra 0

#ret a0; arg:a0,a1 find max value 
max:
    bge a0, a1, max_return # if a0 > a1 then max_return
    mv a0 a1

max_return:
    jalr zero ra 0

dot:
    addi sp sp -30
    sw s0 0(sp)
    sw s1 4(sp)
    sw s2 8(sp)
    sw s3 12(sp)
    sw s4 16(sp)
    sw s5 20(sp)
    sw s6 24(sp)
    sw ra, 26(sp)
    # Prologue
    ble a2, zero, error_len # if a2 <= zero then err
    ble a3, zero, error_str
    ble a4, zero, error_str
    jal zero loop_prepare
error_len:
    li a1 57
    call exit2
error_str:
    li a1 58
    call exit2

loop_prepare:
    #s0 - firstAdd
    #s1 - secAdd
    #s2 - firStr
    #s3 - secStr
    #s4 - largestStr
    #s5 - vecInd
    #s6 - sum

    mv s0 a0
    mv s1 a1
    mv s5 a2

    li a0 4
    mv a1 a3
    jal ra, multi
    mv s2 a0
    
    li a0 4
    mv a1 a4
    jal ra, multi
    mv s3 a0

    mv a0 a3
    mv a1 a4
    jal ra, max

    mv s4 a0
    li s6 0


    

loop_start:
    lw a0 0(s0)
    lw a1 0(s1)
    

    jal ra, multi

    add s6 s6 a0

loop_continue:
    sub s5 s5 s4
    ble s5 zero loop_end
    add s0 s0 s2 
    add s1 s1 s3 
    j loop_start

loop_end:
    mv a0 s6

    lw s0 0(sp)
    lw s1 4(sp)
    lw s2 8(sp)
    lw s3 12(sp)
    lw s4 16(sp)
    lw s5 20(sp)
    lw s6 24(sp)
    lw ra, 26(sp)
    addi sp sp 30

    # Epilogue

    jr ra

ps:感觉测试有个小坑

在变量表述中：a2 应该是2个数组的长度

但stride_test里，步长大的到了数组外依旧可以运算，以至于结果为22

实际上应该为7

MingLLuo .globl main

.text
# =======================================================
# FUNCTION: main product of 2 int vectors
# Arguments:
#   a0 (int*) is the pointer to the start of v0
#   a1 (int*) is the pointer to the start of v1
#   a2 (int)  is the length of the vectors
#   a3 (int)  is the stride of v0
#   a4 (int)  is the stride of v1
# Returns:
#   a0 (int)  is the main product of v0 and v1
# Exceptions:
# - If the length of the vector is less than 1,
#   this function terminates the progra,m with error code 57
# - If the stride of either vector is less than 1,
#   this function terminates the progra,m with error code 58
# =======================================================

#a0:size a1:time return a0 

main:
    
    addi sp sp -28
    sw s0 0(sp)
    sw s1 4(sp)
    sw s2 8(sp)
    sw s3 12(sp)
    sw s4 16(sp)
    sw s5 20(sp)
    sw ra, 24(sp)
    # Prologue
    ble a2, zero, error_len # if a2 <= zero then err
    ble a3, zero, error_str
    ble a4, zero, error_str
    jal zero loop_prepare
error_len:
    li a1 57
    # call exit2
error_str:
    li a1 58
    # call exit2

loop_prepare:
    #s0 - firstAdd
    #s1 - secAdd
    #s2 - firStr
    #s3 - secStr
    #s4 - vecInd
    #s5 - sum

    mv s0 a0
    mv s1 a1
    mv s4 a2

    li a0 4
    mv a1 a3
    jal ra, multi
    mv s2 a0
    
    li a0 4
    mv a1 a4
    jal ra, multi
    mv s3 a0

    li s5 0

loop_start:
    lw a0 0(s0)
    lw a1 0(s1)
    

    jal ra, multi

    add s5 s5 a0

loop_continue:
    addi s4 s4 -1
    ble s4 zero loop_end
    add s0 s0 s2 
    add s1 s1 s3 
    j loop_start

loop_end:
    mv a0 s5

    lw s0 0(sp)
    lw s1 4(sp)
    lw s2 8(sp)
    lw s3 12(sp)
    lw s4 16(sp)
    lw s5 20(sp)
    lw ra, 24(sp)
    addi sp sp 28

    # Epilogue

    jr ra

multi:
    add t1 a0 x0
    bne a1 zero loop
    mv a0 zero
    j mul_end
    
    loop:
    addi a1 a1 -1
    ble a1 zero mul_end
    add a0 a0 t1
    j loop
    mul_end:
    jalr zero ra 0