DLX汇编矩阵相乘：程序调试与流水线优化

.data
;*** Prompts for input  ;输入提示部分
A:      .space     64
B:      .space     64
C:      .space     64
Prompt1:     .asciiz       "Please input the row of Matrix A:"
Prompt2:     .asciiz       "Please input the column of Matrix A and the row of Matrix B: "
Prompt3:     .asciiz         "Please input the column of Matrix B:"
Prompt4:     .asciiz         "Please input the elements of Matrix A:"
Prompt5:     .asciiz         "Please input the elements of Matrix B:" 
Prompt6:     .asciiz         "Do you want to continue(Y:1,N:0)? Making a decision:"           
;*** Data for printf-Trap       ;输出数据设置部分
PrintfFormat: .asciiz         "%d "
        .align 2
PrintfPar: .word PrintfFormat
PrintfValue:  .space 4
PrintfFormat1: .asciiz    "\n"    
.align 2
PrintfPar1: .word PrintfFormat1

PrintfFormat_1: .asciiz    "\n"    
.align 2
PrintfPar_1: .word PrintfFormat_1

PrintfValue1: .space 4
PrintfFormat2: .asciiz    "Output the Matrix A:\n "
.align 2
PrintfPar2: .word PrintfFormat2
PrintfValue2: .space 4
PrintfFormat3: .asciiz    "Output the Matrix B:\n "

.align          2
PrintfPar3: .word PrintfFormat3
PrintfValue3: .space 4
PrintfFormat4: .asciiz  "Output the Matrix C:\n "
.align 2
PrintfPar4: .word PrintfFormat4
PrintfValue4: .space 4

.text
.global main
main:
       addi     r1,r0,Prompt1
       jal      InputUnsigned
       movi2fp  f1,r1       ;矩阵A的行数
       addi     r1,r0,Prompt2
       jal InputUnsigned
       movi2fp  f2,r1       ;矩阵A的列数，矩阵B的行数
       addi     r1,r0,Prompt3
       jal      InputUnsigned
       movi2fp  f3,r1       ;矩阵B的列数
                
       movfp2i  r8,f1
       movfp2i  r6,f2
       multu    r4,r6,r8     ;总的矩阵A的元素个数r4
       addi     r2,r10,A  ;指向A的首地址
 loop1:      
       add      r1,r0,Prompt4   ;分别读入矩阵A的元素值
       jal      InputUnsigned
       sb       0(r2),r1        ;储存字节，读入元素
       addi     r2,r2,1         ;元素个数加一