例外4：inst / data fetch中的未对齐地址：0x100100bb

Question

我正试图在MIPS模拟器（QtMips）中使用Assembly进行4x4矩阵乘法。 QtMips给了我Exception 4: Unaligned Address in inst/data fetch: 0x100100bb

这是我单步时出错的地方。

    [00400070] c52b0000  lwc1 $f11, 0($9) ; 80: lwc1 $f11 0($t1) #load float from array1

当计数器k = 2时发生错误，这意味着当它处于第三个循环时。我假设第三次加载时，32位对齐有问题，lwc1

这是我尝试/阅读但不起作用的内容：

This建议我在.data中的数组（矩阵）声明之前放置.align 2或.align 4。没工作。
This建议它可能是size值的问题（在array3之后定义）。但我正在通过lw $s1 size将其加载到s1，所以我不认为这对我来说是一个真正的问题。

我很失落怎么办。请给我一些智慧。

以下是我的全部代码：

    # here's our array data, two args and a result
    .data
    .globl array1
    .globl array2
    .globl array3

    .align 5 #align the data set
array1: .float 1.00, 0.00, 3.14, 2.72, 2.72, 1.00, 0.00, 3.14, 1.00, 1.00, 1.00, 1.00, 1.00, 2.00, 3.00, 4.00
    .align 5 #align the data set
array2: .float 1.00, 1.00, 0.00, 3.14, 0.00, 1.00, 3.14, 2.72, 0.00, 1.00, 1.00, 0.00, 4.00, 3.00, 2.00, 1.00
    .align 5 #align the data set
array3: .float 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00

size: .word 4 #store float in s2

    .text
    .globl main
main:
    sw $31 saved_ret_pc

    .data
lb_:    .asciiz "Vector Multiplication
"
lbd_:   .byte 1, -1, 0, 128
lbd1_:  .word 0x76543210, 0xfedcba98
    .text
    li $v0 4    # syscall 4 (print_str)
    la $a0 lb_
    syscall

# main program: multiply matrix 1 and 2, store in array3

la $t1 array1
la $t2 array2
la $t3 array3 ###load arrrays to registers


li $t4 4 # i loop counter    -> I changed addi to li
li $t5 4 # j loop counter
li $t6 4 # k loop counter

lw $s1 size # load matrix(array) size


i_loop:
    j j_loop
j_loop:
    j k_loop
k_loop:
    #f0 and f1 - float func return values
    #f10 - multiplication return values
    #f4, f5 - register to store addr offset

    lwc1 $f11 0($t1) #load float from array1
    lwc1 $f12 0($t2) #load float from array2
    lwc1 $f13 0($t3) #load float from result array3
    nop 
    mul.s $f10 $f11 $f12 #multiply floats, store result as temp in $f10
    nop

    add.s $f13 $f13 $f10 #add to multiplication result to resulting array3

    swc1 $f13 0($t3) #store the resulting float in array3

#call index_of_A
    move $s0 $ra    #save return address into s0
    nop
    jal index_of_A  #get addr offset for array1
    nop
    move $ra $s0    #restore return address that was saved into s0

#call index_of_B
    move $s0 $ra    #save return address into s0
    nop
    jal index_of_B  #get addr offset for array2
    nop
    move $ra $s0    #restore return address that was saved into s0

    add $t1 $t1 $s2 # next address in the array1
    add $t2 $t2 $s3 # next address in the array2
    addi $t3 $t3 4 # next address in the array3

    addi $t6 $t6 -1 #decrease k counter
    bne $t6 $0 k_loop #repeat k_loop

    addi $t5 $t5 -1 #decrease j counter
    bne $t5 $0 j_loop #repeat j_loop

    addi $t4 $t4 -1 #decrease i counter
    bne $t4 $0 i_loop #repeat i_loop

#used regs: f0-f5, f10-13
index_of_A: #function for array1 addr offset    #may need to convert all to float first
    #size*i + k #$f20*i + k
    mul $s2 $s1 $t4 # 4*i, 
    add $s2 $s2 $t6 # + k, store in $s2
    jr $ra #jump back to the caller


index_of_B: #function for array2 addr offset
    #4*k + j
    mul $s3 $s1 $t6 # 4*k, 
    add $s3 $s3 $t5 # + j, store in $s3
    jr $ra #jump back to the caller


# Done multiplying...
    .data
sm: .asciiz "Done multiplying
"
    .text
print_and_end:
    li $v0 4    # syscall 4 (print_str)
    la $a0 sm
    syscall

# Done with the program!
    lw $31 saved_ret_pc
    jr $31      # Return from main

#Terminate the program
    li $v0, 10
    syscall

.end main

但是我不明白什么是错的，因为同样的代码在我的另一个例子中起作用：