Tag: c

  • New C test program for chastelib

    In my last post, I showed the test program for the Rust version of chastelib. I decided it would make sense to design a similar test program that uses the original C version of the library that I used when converting to Rust. Personally I like this version better. Global variables makes the code cleaner in my opinion because otherwise how would I choose which order the arguments to the functions would go in? This way, the radix and width of the integer string are set by global data before calling the putint function.

    Also notice that the b variable is set to an integer by a string using strint. This is only to demonstrate proper use of the function. Normally it would not be used unless getting string input from a user by command line argument such as was done in chastehex.

    In any case, this library controls all the integer and string conversion so that I can use it in larger projects. Because it is in ANSI C, it is portable to any machine that exists in modern times.

    main.c

    #include <stdio.h>
    #include <stdlib.h>
    #include "chastelib.h"
    
    int main(int argc, char *argv[])
    {
     int a=0,b;
    
     radix=16;
     int_width=1;
    
     putstring("This is the official test program for the C version of chastelib.\n");
     b=strint("100");
    
     putstring("Hello World!\n");
     
     while(a<b)
     {
      radix=2;
      int_width=8;
      putint(a);
      putstring(" ");
      radix=16;
      int_width=2;
      putint(a);
      putstring(" ");
      radix=10;
      int_width=3;
      putint(a);
    
      if(a>=0x20 && a<=0x7E)
      {
       putstring(" ");
       putchar(a);
      }
    
      putstring("\n");
      a+=1;
     }
      
     return 0;
    }
    

    Below is the command to compile and run it and the output.

    gcc -Wall -ansi -pedantic main.c -o main && ./main
    This is the official test program for the C version of chastelib.
    Hello World!
    00000000 00 000
    00000001 01 001
    00000010 02 002
    00000011 03 003
    00000100 04 004
    00000101 05 005
    00000110 06 006
    00000111 07 007
    00001000 08 008
    00001001 09 009
    00001010 0A 010
    00001011 0B 011
    00001100 0C 012
    00001101 0D 013
    00001110 0E 014
    00001111 0F 015
    00010000 10 016
    00010001 11 017
    00010010 12 018
    00010011 13 019
    00010100 14 020
    00010101 15 021
    00010110 16 022
    00010111 17 023
    00011000 18 024
    00011001 19 025
    00011010 1A 026
    00011011 1B 027
    00011100 1C 028
    00011101 1D 029
    00011110 1E 030
    00011111 1F 031
    00100000 20 032  
    00100001 21 033 !
    00100010 22 034 "
    00100011 23 035 #
    00100100 24 036 $
    00100101 25 037 %
    00100110 26 038 &
    00100111 27 039 '
    00101000 28 040 (
    00101001 29 041 )
    00101010 2A 042 *
    00101011 2B 043 +
    00101100 2C 044 ,
    00101101 2D 045 -
    00101110 2E 046 .
    00101111 2F 047 /
    00110000 30 048 0
    00110001 31 049 1
    00110010 32 050 2
    00110011 33 051 3
    00110100 34 052 4
    00110101 35 053 5
    00110110 36 054 6
    00110111 37 055 7
    00111000 38 056 8
    00111001 39 057 9
    00111010 3A 058 :
    00111011 3B 059 ;
    00111100 3C 060 <
    00111101 3D 061 =
    00111110 3E 062 >
    00111111 3F 063 ?
    01000000 40 064 @
    01000001 41 065 A
    01000010 42 066 B
    01000011 43 067 C
    01000100 44 068 D
    01000101 45 069 E
    01000110 46 070 F
    01000111 47 071 G
    01001000 48 072 H
    01001001 49 073 I
    01001010 4A 074 J
    01001011 4B 075 K
    01001100 4C 076 L
    01001101 4D 077 M
    01001110 4E 078 N
    01001111 4F 079 O
    01010000 50 080 P
    01010001 51 081 Q
    01010010 52 082 R
    01010011 53 083 S
    01010100 54 084 T
    01010101 55 085 U
    01010110 56 086 V
    01010111 57 087 W
    01011000 58 088 X
    01011001 59 089 Y
    01011010 5A 090 Z
    01011011 5B 091 [
    01011100 5C 092 \
    01011101 5D 093 ]
    01011110 5E 094 ^
    01011111 5F 095 _
    01100000 60 096 `
    01100001 61 097 a
    01100010 62 098 b
    01100011 63 099 c
    01100100 64 100 d
    01100101 65 101 e
    01100110 66 102 f
    01100111 67 103 g
    01101000 68 104 h
    01101001 69 105 i
    01101010 6A 106 j
    01101011 6B 107 k
    01101100 6C 108 l
    01101101 6D 109 m
    01101110 6E 110 n
    01101111 6F 111 o
    01110000 70 112 p
    01110001 71 113 q
    01110010 72 114 r
    01110011 73 115 s
    01110100 74 116 t
    01110101 75 117 u
    01110110 76 118 v
    01110111 77 119 w
    01111000 78 120 x
    01111001 79 121 y
    01111010 7A 122 z
    01111011 7B 123 {
    01111100 7C 124 |
    01111101 7D 125 }
    01111110 7E 126 ~
    01111111 7F 127
    10000000 80 128
    10000001 81 129
    10000010 82 130
    10000011 83 131
    10000100 84 132
    10000101 85 133
    10000110 86 134
    10000111 87 135
    10001000 88 136
    10001001 89 137
    10001010 8A 138
    10001011 8B 139
    10001100 8C 140
    10001101 8D 141
    10001110 8E 142
    10001111 8F 143
    10010000 90 144
    10010001 91 145
    10010010 92 146
    10010011 93 147
    10010100 94 148
    10010101 95 149
    10010110 96 150
    10010111 97 151
    10011000 98 152
    10011001 99 153
    10011010 9A 154
    10011011 9B 155
    10011100 9C 156
    10011101 9D 157
    10011110 9E 158
    10011111 9F 159
    10100000 A0 160
    10100001 A1 161
    10100010 A2 162
    10100011 A3 163
    10100100 A4 164
    10100101 A5 165
    10100110 A6 166
    10100111 A7 167
    10101000 A8 168
    10101001 A9 169
    10101010 AA 170
    10101011 AB 171
    10101100 AC 172
    10101101 AD 173
    10101110 AE 174
    10101111 AF 175
    10110000 B0 176
    10110001 B1 177
    10110010 B2 178
    10110011 B3 179
    10110100 B4 180
    10110101 B5 181
    10110110 B6 182
    10110111 B7 183
    10111000 B8 184
    10111001 B9 185
    10111010 BA 186
    10111011 BB 187
    10111100 BC 188
    10111101 BD 189
    10111110 BE 190
    10111111 BF 191
    11000000 C0 192
    11000001 C1 193
    11000010 C2 194
    11000011 C3 195
    11000100 C4 196
    11000101 C5 197
    11000110 C6 198
    11000111 C7 199
    11001000 C8 200
    11001001 C9 201
    11001010 CA 202
    11001011 CB 203
    11001100 CC 204
    11001101 CD 205
    11001110 CE 206
    11001111 CF 207
    11010000 D0 208
    11010001 D1 209
    11010010 D2 210
    11010011 D3 211
    11010100 D4 212
    11010101 D5 213
    11010110 D6 214
    11010111 D7 215
    11011000 D8 216
    11011001 D9 217
    11011010 DA 218
    11011011 DB 219
    11011100 DC 220
    11011101 DD 221
    11011110 DE 222
    11011111 DF 223
    11100000 E0 224
    11100001 E1 225
    11100010 E2 226
    11100011 E3 227
    11100100 E4 228
    11100101 E5 229
    11100110 E6 230
    11100111 E7 231
    11101000 E8 232
    11101001 E9 233
    11101010 EA 234
    11101011 EB 235
    11101100 EC 236
    11101101 ED 237
    11101110 EE 238
    11101111 EF 239
    11110000 F0 240
    11110001 F1 241
    11110010 F2 242
    11110011 F3 243
    11110100 F4 244
    11110101 F5 245
    11110110 F6 246
    11110111 F7 247
    11111000 F8 248
    11111001 F9 249
    11111010 FA 250
    11111011 FB 251
    11111100 FC 252
    11111101 FD 253
    11111110 FE 254
    11111111 FF 255
    
    

    Finally, here is the source to the library itself which was included by main.c at the top of the post.

    chastelib.h

    /*
    This file is a library of functions written by Chastity White Rose. The functions are for converting strings into integers and integers into strings. I did it partly for future programming plans and also because it helped me learn a lot in the process about how pointers work as well as which features the standard library provides and which things I need to write my own functions for.
    */
    
    /* These two lines define a static array with a size big enough to store the digits of an integer including padding it with extra zeroes. The function which follows always returns a pointer to this global string and this allows other standard library functions such as printf to display the integers to standard output or even possibly to files.*/
    
    #define usl 32
    char int_string[usl+1]; /*global string which will be used to store string of integers*/
    
     /*radix or base for integer output. 2=binary, 8=octal, 10=decimal, 16=hexadecimal*/
    int radix=2;
    /*default minimum digits for printing integers*/
    int int_width=1;
    
    /*
    This function is one that I wrote because the standard library can display integers as decimai, octai, or hexadecimal but not any other bases(including binary which is my favorite). My function corrects this and in my opinion such a function should have been part of the standard library but I'm not complaining because now I have my own which I can use forever!
    */
    
    char* intstr(unsigned int i)
    {
     int width=0;
     char *s=int_string+usl;
     *s=0;
     while(i!=0 || width<int_width)
     {
      s--;
      *s=i%radix;
      i/=radix;
      if(*s<10){*s+='0';}else{*s=*s+'A'-10;}
      width++;
     }
    
     return s;
    }
    
    /*
    This function is my own replacement for the strtol function from the C standard library. I didn't technically need to make this function because the functions from stdlib.h can already convert strings from bases 2 to 36 into integers. However my function is simpler because it only requires 2 arguments instead of three and it also does not handle negative numbers. Never have I needed negative integers but if I ever do I can use the standard functions or write my own in the future.
    */
    
    int strint(char *s)
    {
     int i=0;
     char c;
     if( radix<2 || radix>36 ){printf("Error: radix %i is out of range!\n",radix);return i;}
     while( *s == ' ' || *s == '\n' || *s == '\t' ){s++;} /*skip whitespace at beginning*/
     while(*s!=0)
     {
      c=*s;
      if( c >= '0' && c <= '9' ){c-='0';}
      else if( c >= 'A' && c <= 'Z' ){c-='A';c+=10;}
      else if( c >= 'a' && c <= 'z' ){c-='a';c+=10;}
      else if( c == ' ' || c == '\n' || c == '\t' ){return i;}
      else{printf("Error: %c is not an alphanumeric character!\n",c);return i;}
      if(c>=radix){printf("Error: %c is not a valid character for radix %i\n",*s,radix);return i;}
      i*=radix;
      i+=c;
      s++;
     }
     return i;
    }
    
    /*
    this function prints a string using fwrite
    This is the best C representation of how my Assembly programs also work/
    */
    
    void putstring(char *s)
    {
     int c=0;
     char *p=s;
     while(*p++){c++;} 
     fwrite(s,1,c,stdout);
    }
    
    void putint(unsigned int i)
    {
     putstring(intstr(i));
    }
    
    
  • Rust Programming Language: putint function

    I started learning the Rust programming language and so far I find it more difficult than assembly. However, I finally got a working prototype of my putint function that I have written using both C and Assembly before.

    fn main()
    {
     println!("This is a test of the putint function I wrote for the Rust programming language.");
     let mut i:i32=0;
     while i<256
     {
      putint(i,2,8);
      print!(" ");
      putint(i,16,2);
      print!(" ");
      putint(i,10,3);
      println!();
      i+=1;
     }
    }
    
    /*
     This is the putint function for printing an integer in any base from 2 to 36.
     It is the same function I wrote in C and Assembly but with some key differences for Rust.
    
     Rust doesn't allow global variables in "safe" mode. Therefore, the radix and the int_width must be passed to the function each time.
     I find this inefficient because usually I am just choosing one radix for the duration of the entire program.
     The width also typically stays the same unless I am doing something fancy, such as I did in chastehex.
    
     The first loop stores the correct ASCII numbers as unsigned bytes in an array by repeatedly dividing by the radix and converting the remainder of division into u8 (unsigned 8 bit integer) after adding the correct numbers based on the ASCII table.
    
     The second loop converts these ASCII numbers into the Rust (char) type and prints them in the reverse order of how they were stored.
    
     Most of the code in this function was required only because Rust imposes limitations on what I can do because strings are not simply mutable arrays of bytes like they are in C or Assembly. Additionally the char type is not the same as the char type in C. In C, chars are the same as 1 byte but in Rust they are actually unicode characters that are 4 bytes each.
    
    There is probably a better way to write this function in Rust but this is the first that has worked for me. The code is nearly twice the size of the C version of this function, but it will allow me to print my integers in any radix I want as I continue to learn the Rust programming language and see if it is worth the trouble of learning.
    
    */
    
    fn putint(mut i:i32,radix:i32,int_width:usize)
    {
     let mut a: [u8;32]=[0;32]; //create array of max size needed for 32 bit integer
     let mut width=0; //keeps track of current width of integer (how many digits in the chosen radix)
     let mut r:i32; //used to store the remainder of division
    
     while i!=0 || width<int_width
     {
      r=i%radix;
      i/=radix;
      if r<10 { r+=0x30 }
      else {r+=0x37}
      a[width]=r as u8;
      width+=1;
     }
    
     while width>0
     {
      width-=1;
      print!("{}", a[width] as char );
     }
    }
    

    The output of this program is the following. As you can see, it allows me to customize the radix/base and the width so that everything is lined up neatly in the autistic way I require.

    This is a test of the putint function I wrote for the Rust programming language.
    00000000 00 000
    00000001 01 001
    00000010 02 002
    00000011 03 003
    00000100 04 004
    00000101 05 005
    00000110 06 006
    00000111 07 007
    00001000 08 008
    00001001 09 009
    00001010 0A 010
    00001011 0B 011
    00001100 0C 012
    00001101 0D 013
    00001110 0E 014
    00001111 0F 015
    00010000 10 016
    00010001 11 017
    00010010 12 018
    00010011 13 019
    00010100 14 020
    00010101 15 021
    00010110 16 022
    00010111 17 023
    00011000 18 024
    00011001 19 025
    00011010 1A 026
    00011011 1B 027
    00011100 1C 028
    00011101 1D 029
    00011110 1E 030
    00011111 1F 031
    00100000 20 032
    00100001 21 033
    00100010 22 034
    00100011 23 035
    00100100 24 036
    00100101 25 037
    00100110 26 038
    00100111 27 039
    00101000 28 040
    00101001 29 041
    00101010 2A 042
    00101011 2B 043
    00101100 2C 044
    00101101 2D 045
    00101110 2E 046
    00101111 2F 047
    00110000 30 048
    00110001 31 049
    00110010 32 050
    00110011 33 051
    00110100 34 052
    00110101 35 053
    00110110 36 054
    00110111 37 055
    00111000 38 056
    00111001 39 057
    00111010 3A 058
    00111011 3B 059
    00111100 3C 060
    00111101 3D 061
    00111110 3E 062
    00111111 3F 063
    01000000 40 064
    01000001 41 065
    01000010 42 066
    01000011 43 067
    01000100 44 068
    01000101 45 069
    01000110 46 070
    01000111 47 071
    01001000 48 072
    01001001 49 073
    01001010 4A 074
    01001011 4B 075
    01001100 4C 076
    01001101 4D 077
    01001110 4E 078
    01001111 4F 079
    01010000 50 080
    01010001 51 081
    01010010 52 082
    01010011 53 083
    01010100 54 084
    01010101 55 085
    01010110 56 086
    01010111 57 087
    01011000 58 088
    01011001 59 089
    01011010 5A 090
    01011011 5B 091
    01011100 5C 092
    01011101 5D 093
    01011110 5E 094
    01011111 5F 095
    01100000 60 096
    01100001 61 097
    01100010 62 098
    01100011 63 099
    01100100 64 100
    01100101 65 101
    01100110 66 102
    01100111 67 103
    01101000 68 104
    01101001 69 105
    01101010 6A 106
    01101011 6B 107
    01101100 6C 108
    01101101 6D 109
    01101110 6E 110
    01101111 6F 111
    01110000 70 112
    01110001 71 113
    01110010 72 114
    01110011 73 115
    01110100 74 116
    01110101 75 117
    01110110 76 118
    01110111 77 119
    01111000 78 120
    01111001 79 121
    01111010 7A 122
    01111011 7B 123
    01111100 7C 124
    01111101 7D 125
    01111110 7E 126
    01111111 7F 127
    10000000 80 128
    10000001 81 129
    10000010 82 130
    10000011 83 131
    10000100 84 132
    10000101 85 133
    10000110 86 134
    10000111 87 135
    10001000 88 136
    10001001 89 137
    10001010 8A 138
    10001011 8B 139
    10001100 8C 140
    10001101 8D 141
    10001110 8E 142
    10001111 8F 143
    10010000 90 144
    10010001 91 145
    10010010 92 146
    10010011 93 147
    10010100 94 148
    10010101 95 149
    10010110 96 150
    10010111 97 151
    10011000 98 152
    10011001 99 153
    10011010 9A 154
    10011011 9B 155
    10011100 9C 156
    10011101 9D 157
    10011110 9E 158
    10011111 9F 159
    10100000 A0 160
    10100001 A1 161
    10100010 A2 162
    10100011 A3 163
    10100100 A4 164
    10100101 A5 165
    10100110 A6 166
    10100111 A7 167
    10101000 A8 168
    10101001 A9 169
    10101010 AA 170
    10101011 AB 171
    10101100 AC 172
    10101101 AD 173
    10101110 AE 174
    10101111 AF 175
    10110000 B0 176
    10110001 B1 177
    10110010 B2 178
    10110011 B3 179
    10110100 B4 180
    10110101 B5 181
    10110110 B6 182
    10110111 B7 183
    10111000 B8 184
    10111001 B9 185
    10111010 BA 186
    10111011 BB 187
    10111100 BC 188
    10111101 BD 189
    10111110 BE 190
    10111111 BF 191
    11000000 C0 192
    11000001 C1 193
    11000010 C2 194
    11000011 C3 195
    11000100 C4 196
    11000101 C5 197
    11000110 C6 198
    11000111 C7 199
    11001000 C8 200
    11001001 C9 201
    11001010 CA 202
    11001011 CB 203
    11001100 CC 204
    11001101 CD 205
    11001110 CE 206
    11001111 CF 207
    11010000 D0 208
    11010001 D1 209
    11010010 D2 210
    11010011 D3 211
    11010100 D4 212
    11010101 D5 213
    11010110 D6 214
    11010111 D7 215
    11011000 D8 216
    11011001 D9 217
    11011010 DA 218
    11011011 DB 219
    11011100 DC 220
    11011101 DD 221
    11011110 DE 222
    11011111 DF 223
    11100000 E0 224
    11100001 E1 225
    11100010 E2 226
    11100011 E3 227
    11100100 E4 228
    11100101 E5 229
    11100110 E6 230
    11100111 E7 231
    11101000 E8 232
    11101001 E9 233
    11101010 EA 234
    11101011 EB 235
    11101100 EC 236
    11101101 ED 237
    11101110 EE 238
    11101111 EF 239
    11110000 F0 240
    11110001 F1 241
    11110010 F2 242
    11110011 F3 243
    11110100 F4 244
    11110101 F5 245
    11110110 F6 246
    11110111 F7 247
    11111000 F8 248
    11111001 F9 249
    11111010 FA 250
    11111011 FB 251
    11111100 FC 252
    11111101 FD 253
    11111110 FE 254
    11111111 FF 255
    
    
  • Writing to video RAM

    One of the reasons DOS is the best platform for learning Intel Assembly language in my opinion is that it doesn’t prevent you from writing directly to video memory. People are unaware how much operating systems like Windows, and, to a lesser extent, Linux place limits on what you are allowed to do. The idea is that most people are not smart enough to be trusted with arbitrarily writing to video RAM, devices, etc.

    But that is where DOSBox comes in. Since it runs DOS inside an emulator, there is no danger. The program I am going to show you today is long and complicated but it does something that I can’t even do on Linux, write directly to video memory in multiple colors.

    Here is the source code that made all of that possible! I tested it to assemble with either FASM or NASM. If you assemble it and run it in DOSBox, or even a real DOS system, you will get something that looks like the picture above.

    org 100h
    
    main:
    
    ;set up the extra segment at the beginning of the program
    ;to point to the video memory segment in DOS text mode
    mov ax, 0xB800
    mov es, ax ; Or mov ds, ax
    
    
    ;80 columes times 25 rows is 2000 chars
    ;but since each character is two bytes
    ;4000 is the number of bytes to erase
    ;whatever character we write in this loop will fill the whole screen!
    
    mov bx,0
    screen_clear:
    mov [es:bx],word 0x0403
    add bx,2
    cmp bx,4000
    jnz screen_clear
    
    mov ax,title  ;the string we intend to write to video RAM
    mov ch,0x0F   ;the character attribute
    mov dx,0x0218
    call putstring_vram
    
    mov ax,v_str  ;the string we intend to write to video RAM
    mov ch,0x70   ;the character attribute
    mov dx,0x0401
    call putstring_vram
    
    ;set the starting attribute for characters and location
    mov ch,0x01   ;the character attribute
    mov dx,0x0501 ;x,y position of where text should start on screen
    
    loop_vram:
    cmp ch,0x10
    jz loop_vram_end
    mov ax,v_str  ;the string we intend to write to video RAM
    call putstring_vram
    add dx,0x100
    inc ch
    jmp loop_vram
    loop_vram_end:
    
    mov ax,4C00h
    int 21h
    
    title db 'Chastity Video RAM Demonstration!',0
    v_str db 'Hello World! This string will be written to video RAM using Assembly language!',0
    
    ;Unlike previous functions I wrote that use DOS interrupts to write text to the screen
    ;this one makes use of several registers which are not meant to be preserved
    ;registers ax,cx,and dx must be set before calling this function
    
    ;ax = address of string to write
    ;bx = copied from ax and used to index the string
    ;cx = used for character attribute(ch) and value(cl)
    ;dx = column(x pos) and row(y pos) of where string should be printed
    
    ;For this routine, I chose to copy the dx register to memory locations for clarity
    ;Yes, it wastes some bytes but at least I can read it as I am familiar with x,y coordinates
    ;Most importantly, the dx register is never modified in this function
    ;This is important because the main program may need to modify it in a loop
    ;For writing data in consecutive rows (e.g. integer sequences)
    
    x db 0
    y db 0
    
    putstring_vram:
    
    mov bx,ax             ;copy ax to bx for use as index register
    
    ;get x and y positions from each byte of dx register
    mov [x],dl
    mov [y],dh
    
    mov ax,80  ;set ax to 80 because there are 80 chars per row in text mode
    mul byte [y]    ;multiply with the y value
    mov byte [y],0  ;zero the y byte so we can add a 16 bit x value to ax
    add ax, word [x]
    
    shl ax,1 ;shift left once to account for two bytes per character
    
    mov di,ax ;we will use di as our starting output location
    
    putstring_vram_strlen_start:    ;this loop finds the length of the string as part of the putstring function
    
    cmp [bx],byte 0                 ;compare this byte with 0
    jz putstring_vram_strlen_end    ;if comparison was zero, jump to loop end because we have found the length/end of string
    mov cl,[bx]                     ;mov this character to cl
    mov [es:di],cx                  ;mov character and attribute set in ch(before calling this function) to extra_segment+di
    add di,2                        ;each character contains two bytes (ASCII+Attribute). We must add two here.
    inc bx                          ;increment bx to point to next character
    jmp putstring_vram_strlen_start ;jump to the start of the loop and keep trying until we find a zero
    
    putstring_vram_strlen_end:
    
    ret
    
  • arithmetic by bitwise operators

    I have started a new programming library in C which simulates arithmetic using only bitwise operators. This is purely for computer science purposes and to prove that it can be done. The hardest part was getting the division function working correctly. I can prove that these functions work with another program I wrote, but I really want to record a video sometime to show the process of how these work.

    For now, here is the source of the 4 arithmetic functions and some global variables used in the division function.

    /*
     bitlib.h
    
     This library simulates the four arithmetic functions: ( addition, subtraction, multiplication, and division )
     Using only bitwise operations: ( AND, OR, XOR, SHL, SHR )
     
     Most of the time I would not need to do this, however, there exist applications where this information may prove useful.
     
     - Programming ARM CPUs which don't have a division instruction.
     - Arbitary Precision Arithmetic involving thousands of digits.
    
    */
    
    int add(int di,int si)
    {
     while(si!=0)
     {
      int ax=di;
      di^=si;
      si&=ax;
      si<<=1;
     }
     return di;
    }
    
    
    int sub(int di,int si)
    {
     while(si!=0)
     {
      di^=si;
      si&=di;
      si<<=1;
     }
     return di;
    }
    
    
    
    int mul(int di,int si)
    {
     int ax=0;
     while(si!=0)
     {
      if((si&1)!=0){ax=add(ax,di);}
      di<<=1;
      si>>=1;
     }
     return ax;
    }
    
    /*
    this division function returns the quotient, but also stores the remainder of division in a global variable
    */
    
    int sign_bit=1<<((sizeof(int)<<3)-1); /*used to extract the most significant bit during division function*/
    
    int mod=0; /*to store the modulus/remainder of the division function*/
    
    int bitdiv(int di,int si)
    {
     int ax=0,bx=0,cx=1;
     if(si==0){return 0;} /*division by zero is invalid*/
    
     while(cx!=0)
     {
      ax<<=1;
      bx<<=1;
      if(di&sign_bit){bx|=1;}
      di<<=1;
      
      if(bx>=si)
      {
       bx=sub(bx,si);
       ax|=1;
      }
     
      cx<<=1;
     }
    
     mod=bx;
     return ax;
    }
    
  • 64 bit Linux chastehex

    I used my previous 32 bit Linux program and translated it to use the “syscall” instruction and the new registers and functions numbers for 64 bit Linux programs.

    The behavior of the program is identical to the 32 bit version of chastehex, however this was a stepping stone into 64 bit development in Assembly for Linux. There could be some use for 64 bit programs, but none that I can think of right now. Still, it is good to be prepared. Also, there was quite a bit of research that went into learning how to do the system calls in 64 bit mode. Those who are interested in learning how to make console programs for Linux in 64 bit can ask me questions about my source.

    The reason chastehex makes such a good program to base my standard library design on is that it does all the basic things that are needed for most programs.

    • Writes strings and numbers to standard output
    • opens and closes a file and reads or writes to it
    • accepts command line arguments and changes behavior accordingly
    • displays a message of how to use it if it is launched with no arguments
    • uses only functions supplied by the Linux kernel

    This post contains the full source for the 64 bit version of chastehex. You can also see the FASM forum thread about it here:

    https://board.flatassembler.net/topic.php?p=246358

    main.asm

    ;Linux 64-bit Assembly Source for chastehex
    ;a special tool originally written in C
    format ELF64 executable
    entry main
    
    include 'chastelib64.asm'
    include "chasteio64.asm"
    
    main:
    
    ;radix will be 16 because this whole program is about hexadecimal
    mov [radix],16 ; can choose radix for integer input/output!
    mov [int_newline],0 ;disable automatic printing of newlines after putint
    ;we will be manually printing spaces or newlines depending on context
    
    pop rax
    mov [argc],rax ;save the argument count for later
    
    ;first arg is the name of the program. we skip past it
    pop rax
    dec [argc]
    
    ;before we try to get the first argument as a filename, we must check if it exists
    cmp [argc],0
    jnz arg_open_file
    
    help:
    mov rax,help_message
    call putstring
    jmp main_end
    
    arg_open_file:
    
    pop rax
    dec [argc]
    mov [filename],rax ; save the name of the file we will open to read
    call putstring
    call putline
    
    call open
    
    cmp rax,0
    js main_end
    
    mov [filedesc],rax ; save the file descriptor number for later use
    mov [file_offset],0 ;assume the offset is 0,beginning of file
    
    ;check next arg
    cmp [argc],0 ;if there are no more args after filename, just hexdump it
    jnz next_arg_address ;but if there are more, jump to the next argument to process it as address
    
    hexdump:
    
    mov rdx,0x10         ;number of bytes to read
    mov rsi,byte_array   ;address to store the bytes
    mov rdi,[filedesc]   ;move the opened file descriptor into rdi
    mov rax,0            ;invoke SYS_READ (kernel opcode 0 on 64 bit Intel)
    syscall              ;call the kernel
    
    mov [bytes_read],rax
    
    ; call putint
    
    cmp rax,0
    jnz file_success ;if more than zero bytes read, proceed to display
    
    ;if the offset is zero, display EOF to indicate empty file
    ;otherwise, end without displaying this because there should already be bytes printed to the display
    cmp [file_offset],0
    jnz main_end
    
    call show_eof
    
    jmp main_end
    
    ; this point is reached if file was read from successfully
    
    file_success:
    ;mov rax,[filename]
    ;call putstring
    ;mov rax,file_opened_string
    ;call putstring
    
    mov rax,byte_array
    ;call putstring
    
    call print_bytes_row
    
    cmp [bytes_read],1 
    jl main_end ;if less than one bytes read, there is an error
    jmp hexdump
    
    ;address argument section
    next_arg_address:
    
    ;if there is at least one more arg
    pop rax ;pop the argument into rax and process it as a hex number
    dec [argc]
    call strint
    
    mov rdx,0          ;whence argument (SEEK_SET)
    mov rsi,rax        ;move the file cursor to this address
    mov rdi,[filedesc] ;move the opened file descriptor into rdi
    mov rax,8          ;invoke SYS_LSEEK (kernel opcode 8 on 64 bit Intel)
    syscall            ;call the kernel
    
    mov [file_offset],rax ;move the new offset
    
    ;check the number of args still remaining
    cmp [argc],0
    jnz next_arg_write ; if there are still arguments, skip this read section and enter writing mode
    
    read_one_byte:
    mov rdx,1            ;number of bytes to read
    mov rsi,byte_array   ;address to store the bytes
    mov rdi,[filedesc]   ;move the opened file descriptor into rdi
    mov rax,0            ;invoke SYS_READ (kernel opcode 0 on 64 bit Intel)
    syscall              ;call the kernel
    
    
    ;rax will have the number of bytes read after system call
    cmp rax,1
    jz print_byte_read ;if exactly 1 byte was read, proceed to print info
    
    call show_eof
    
    jmp main_end ;go to end of program
    
    ;print the address and the byte at that address
    print_byte_read:
    call print_byte_info
    
    ;this section interprets the rest of the args as bytes to write
    next_arg_write:
    cmp [argc],0
    jz main_end
    
    pop rax
    dec [argc]
    call strint ;try to convert string to a hex number
    
    ;write that number as a byte value to the file
    
    mov [byte_array],al
    
    mov rdx,1          ;write 1 byte
    mov rsi,byte_array ;pointer/address of byte to write
    mov rdi,[filedesc] ;write to this file descriptor
    mov rax,1          ;invoke SYS_WRITE (kernel opcode 1 on 64 bit systems)
    syscall            ;system call to write the message
    
    call print_byte_info
    inc [file_offset]
    
    jmp next_arg_write
    
    main_end:
    
    ;this is the end of the program
    ;we close the open file and then use the exit call
    
    mov rax,[filedesc] ;file number to close
    call close
    
    mov rax, 0x3C ; invoke SYS_EXIT (kernel opcode 0x3C (60 decimal) on 64 bit systems)
    mov rdi,0   ; return 0 status on exit - 'No Errors'
    syscall
    
    
    ;this function prints a row of hex bytes
    ;each row is 16 bytes
    print_bytes_row:
    mov rax,[file_offset]
    mov [int_width],8
    call putint
    call putspace
    
    mov rbx,byte_array
    mov rcx,[bytes_read]
    add [file_offset],rcx
    next_byte:
    mov rax,0
    mov al,[rbx]
    mov [int_width],2
    call putint
    call putspace
    
    inc rbx
    dec rcx
    cmp rcx,0
    jnz next_byte
    
    mov rcx,[bytes_read]
    pad_spaces:
    cmp rcx,0x10
    jz pad_spaces_end
    mov rax,space_three
    call putstring
    inc rcx
    jmp pad_spaces
    pad_spaces_end:
    
    ;optionally, print chars after hex bytes
    call print_bytes_row_text
    call putline
    
    ret
    
    space_three db '   ',0
    
    print_bytes_row_text:
    mov rbx,byte_array
    mov rcx,[bytes_read]
    next_char:
    mov rax,0
    mov al,[rbx]
    
    ;if char is below '0' or above '9', it is outside the range of these and is not a digit
    cmp al,0x20
    jb not_printable
    cmp al,0x7E
    ja not_printable
    
    printable:
    ;if char is in printable range,copy as is and proceed to next index
    jmp next_index
    
    not_printable:
    mov al,'.' ;otherwise replace with placeholder value
    
    next_index:
    mov [rbx],al
    inc rbx
    dec rcx
    cmp rcx,0
    jnz next_char
    mov [rbx],byte 0 ;make sure string is zero terminated
    
    mov rax,byte_array
    call putstring
    
    ret
    
    
    ;function to display EOF with address
    show_eof:
    
    mov rax,[file_offset]
    mov [int_width],8
    call putint
    call putspace
    mov rax,end_of_file_string
    call putstring
    call putline
    
    ret
    
    ;print the address and the byte at that address
    print_byte_info:
    mov rax,[file_offset]
    mov [int_width],8
    call putint
    call putspace
    mov rax,0
    mov al,[byte_array]
    mov [int_width],2
    call putint
    call putline
    
    ret
    
    end_of_file_string db 'EOF',0
    
    help_message db 'Welcome to chastehex! The tool for reading and writing bytes of a file!',0Ah,0Ah
    db 'To hexdump an entire file:',0Ah,0Ah,9,'chastehex file',0Ah,0Ah
    db 'To read a single byte at an address:',0Ah,0Ah,9,'chastehex file address',0Ah,0Ah
    db 'To write a single byte at an address:',0Ah,0Ah,9,'chastehex file address value',0Ah,0Ah,0
    
    ;variables for managing arguments
    argc dq 0
    filename dq 0 ; name of the file to be opened
    filedesc dq 0 ; file descriptor
    bytes_read dq 0
    file_offset dq 0
    
    
    
    
    ;where we will store data from the file
    byte_array db 17 dup ?
    

    chastelib64.asm

    ; This file is where I keep my function definitions.
    ; These are usually my string and integer output routines.
    
    ; function to print zero terminated string pointed to by register rax
    
    stdout dq 1 ; variable for standard output so that it can theoretically be redirected
    
    putstring:
    
    push rax
    push rbx
    push rcx
    push rdx
    
    mov rbx,rax ; copy rax to rbx as well. Now both registers have the address of the main_string
    
    putstring_strlen_start: ; this loop finds the lenge of the string as part of the putstring function
    
    cmp [rbx],byte 0 ; compare byte at address rdx with 0
    jz putstring_strlen_end ; if comparison was zero, jump to loop end because we have found the length
    inc rbx
    jmp putstring_strlen_start
    
    putstring_strlen_end:
    sub rbx,rax ;rbx will now have correct number of bytes
    
    ;write string using Linux Write system call
    ;https://www.chromium.org/chromium-os/developer-library/reference/linux-constants/syscalls/#x86_64-64-bit
    
    
    mov rdx,rbx      ;number of bytes to write
    mov rsi,rax      ;pointer/address of string to write
    mov rdi,[stdout] ;write to the STDOUT file
    mov rax,1        ;invoke SYS_WRITE (kernel opcode 1 on 64 bit systems)
    syscall          ;system call to write the message
    
    
    pop rdx
    pop rcx
    pop rbx
    pop rax
    
    ret ; this is the end of the putstring function return to calling location
    
    ;this is the location in memory where digits are written to by the putint function
    int_string     db 64 dup '?' ;enough bytes to hold maximum size 64-bit binary integer
    ; this is the end of the integer string optional line feed and terminating zero
    ; clever use of this label can change the ending to be a different character when needed 
    int_newline db 0Ah,0
    
    radix dq 2 ;radix or base for integer output. 2=binary, 8=octal, 10=decimal, 16=hexadecimal
    int_width dq 8
    
    ;this function creates a string of the integer in rax
    ;it uses the above radix variable to determine base from 2 to 36
    ;it then loads rax with the address of the string
    ;this means that it can be used with the putstring function
    
    intstr:
    
    mov rbx,int_newline-1 ;find address of lowest digit(just before the newline 0Ah)
    mov rcx,1
    
    digits_start:
    
    mov rdx,0;
    div qword [radix]
    cmp rdx,10
    jb decimal_digit
    jge hexadecimal_digit
    
    decimal_digit: ;we go here if it is only a digit 0 to 9
    add rdx,'0'
    jmp save_digit
    
    hexadecimal_digit:
    sub rdx,10
    add rdx,'A'
    
    save_digit:
    
    mov [rbx],dl
    cmp rax,0
    jz intstr_end
    dec rbx
    inc rcx
    jmp digits_start
    
    intstr_end:
    
    prefix_zeros:
    cmp rcx,[int_width]
    jnb end_zeros
    dec rbx
    mov [rbx],byte '0'
    inc rcx
    jmp prefix_zeros
    end_zeros:
    
    mov rax,rbx ; now that the digits have been written to the string, display it!
    
    ret
    
    
    ; function to print string form of whatever integer is in rax
    ; The radix determines which number base the string form takes.
    ; Anything from 2 to 36 is a valid radix
    ; in practice though, only bases 2,8,10,and 16 will make sense to other programmers
    ; this function does not process anything by itself but calls the combination of my other
    ; functions in the order I intended them to be used.
    
    putint: 
    
    push rax
    push rbx
    push rcx
    push rdx
    
    call intstr
    
    call putstring
    
    pop rdx
    pop rcx
    pop rbx
    pop rax
    
    ret
    
    ;this function converts a string pointed to by rax into an integer returned in rax instead
    ;it is a little complicated because it has to account for whether the character in
    ;a string is a decimal digit 0 to 9, or an alphabet character for bases higher than ten
    ;it also checks for both uppercase and lowercase letters for bases 11 to 36
    ;finally, it checks if that letter makes sense for the base.
    ;For example, G to Z cannot be used in hexadecimal, only A to F can
    ;The purpose of writing this function was to be able to accept user input as integers
    
    strint:
    
    mov rbx,rax ;copy string address from rax to esi because rax will be replaced soon!
    mov rax,0
    
    read_strint:
    mov rcx,0 ; zero rcx so only lower 8 bits are used
    mov cl,[rbx]
    inc rbx
    cmp cl,0 ; compare byte at address rdx with 0
    jz strint_end ; if comparison was zero, this is the end of string
    
    ;if char is below '0' or above '9', it is outside the range of these and is not a digit
    cmp cl,'0'
    jb not_digit
    cmp cl,'9'
    ja not_digit
    
    ;but if it is a digit, then correct and process the character
    is_digit:
    sub cl,'0'
    jmp process_char
    
    not_digit:
    ;it isn't a digit, but it could be perhaps and alphabet character
    ;which is a digit in a higher base
    
    ;if char is below 'A' or above 'Z', it is outside the range of these and is not capital letter
    cmp cl,'A'
    jb not_upper
    cmp cl,'Z'
    ja not_upper
    
    is_upper:
    sub cl,'A'
    add cl,10
    jmp process_char
    
    not_upper:
    
    ;if char is below 'a' or above 'z', it is outside the range of these and is not lowercase letter
    cmp cl,'a'
    jb not_lower
    cmp cl,'z'
    ja not_lower
    
    is_lower:
    sub cl,'a'
    add cl,10
    jmp process_char
    
    not_lower:
    
    ;if we have reached this point, result invalid and end function
    jmp strint_end
    
    process_char:
    
    cmp rcx,[radix] ;compare char with radix
    jae strint_end ;if this value is above or equal to radix, it is too high despite being a valid digit/alpha
    
    mov rdx,0 ;zero rdx because it is used in mul sometimes
    mul [radix]    ;mul rax with radix
    add rax,rcx
    
    jmp read_strint ;jump back and continue the loop if nothing has exited it
    
    strint_end:
    
    ret
    ;the next utility functions simply print a space or a newline
    ;these help me save code when printing lots of things for debugging
    
    space db ' ',0
    line db 0Dh,0Ah,0
    
    putspace:
    push rax
    mov rax,space
    call putstring
    pop rax
    ret
    
    putline:
    push rax
    mov rax,line
    call putstring
    pop rax
    ret
    

    chasteio64.asm

    ;this file is for managing the advanced Input and Output situations that occur when opening and closing files.
    ;I use the following references when using system calls.
    
    
    ;https://www.chromium.org/chromium-os/developer-library/reference/linux-constants/syscalls/#x86-32-bit
    ;https://www.chromium.org/chromium-os/developer-library/reference/linux-constants/errnos/
    
    
    ;before calling this function, make sure the rax register points to an address containing the filename as a zero terminated string
    ;this function opens a file for both reading and writing handle is returned in rax
    ;this function design is consistent with my other functions by using only rax as the input and output
    ;because it opens files for reading and writing, I do not need to be concerned with passing another argument for access mode
    
    ;However, this function actually does a whole lot more. It detects error codes by testing the sign bit and jumping to an error display system if rax is less than 0; Negative numbers are how errors are indicated on Linux. By turning the numbers positive, we get the actual error codes. The most common error codes that would occur are the following, either because a file doesn't exist, or because the user doesn't have permissions to read or write it.
    
    ; 2 0x02 ENOENT No such file or directory
    ;13 0x0d EACCES Permission denied
    
    open_error_message db 'File Error Code: ',0
    
    open:
    
    mov rsi,2   ;open file in read and write mode 
    mov rdi,rax ;filename should be in rax before this function was called
    mov rax,2   ;invoke SYS_OPEN (kernel opcode 2 on 64 bit systems)
    syscall     ;call the kernel
    
    cmp rax,0
    js open_error
    jmp open_end
    
    open_error:
    
    neg rax ;invert sign to get errno code
    push rax
    mov rax,open_error_message
    call putstring
    pop rax
    call putint
    call putline
    neg rax ;return rax to original sign
    
    open_end:
    
    ret
    
    ;this is the equivalent close call that expects rax to have the file handle we are closing
    ;technically it just passes it on to rdi but it is easier for me to remember if I use rax for everything
    
    close:
    
    mov rdi,rax ;file number to close
    mov rax,3   ;invoke SYS_CLOSE (kernel opcode 3 for 64 bit Intel)
    syscall     ;call the kernel
    
    ret