# some utilities for converting numbers from hex # lowercase letters only for now == code # instruction effective address register displacement immediate # . op subop mod rm32 base index scale r32 # . 1-3 bytes 3 bits 2 bits 3 bits 3 bits 3 bits 2 bits 2 bits 0/1/2/4 bytes 0/1/2/4 bytes hex-int?: # in: (addr slice) -> result/eax: boolean # . prologue 55/push-ebp 89/copy 3/mod/direct 5/rm32/ebp . . . 4/r32/esp . . # copy esp to ebp # . save registers 51/push-ecx 52/push-edx 53/push-ebx # ecx = s 8b/copy 1/mod/*+disp8 5/rm32/ebp . . . 1/r32/ecx 8/disp8 . # copy *(ebp+8) to ecx # edx = s->end 8b/copy 1/mod/*+disp8 1/rm32/ecx . . . 2/r32/edx 4/disp8 . # copy *(ecx+4) to edx # var curr/ecx: (addr byte) = s->start 8b/copy 0/mod/indirect 1/rm32/ecx . . . 1/r32/ecx . . # copy *ecx to ecx # if s is empty return false b8/copy-to-eax 0/imm32/false 39/compare 3/mod/direct 1/rm32/ecx . . . 2/r32/edx . . # compare ecx with edx 73/jump-if-addr>= $hex-int?:end/disp8 # skip past leading '-' # . if (*curr == '-') ++curr 31/xor 3/mod/direct 3/rm32/ebx . . . 3/r32/ebx . . # clear ebx 8a/copy-byte 0/mod/indirect 1/rm32/ecx . . . 3/r32/BL . . # copy byte at *ecx to BL 81 7/subop/compare 3/mod/direct 3/rm32/ebx . . . . . 0x2d/imm32/- # compare ebx 75/jump-if-!= $hex-int?:initial-0/disp8 # . ++curr 41/increment-ecx # skip past leading '0x' $hex-int?:initial-0: # . if (*curr != '0') jump to loop 31/xor 3/mod/direct 3/rm32/ebx . . . 3/r32/ebx . . # clear ebx 8a/copy-byte 0/mod/indirect 1/rm32/ecx . . . 3/r32/BL . . # copy byte at *ecx to BL 81 7/subop/compare 3/mod/direct 3/rm32/ebx . . . . . 0x30/imm32/0 # compare ebx 75/jump-if-!= $hex-int?:loop/disp8 # . ++curr 41/increment-ecx $hex-int?:initial-0x: # . if (curr >= in->end) return true 39/compare 3/mod/direct 1/rm32/ecx . . . 2/r32/edx . . # compare ecx with edx 73/jump-if-addr>= $hex-int?:true/disp8 # . if (*curr != 'x') jump to loop # the previous '0' is still valid so doesn't need to be checked again 31/xor 3/mod/direct 3/rm32/ebx . . . 3/r32/ebx . . # clear ebx 8a/copy-byte 0/mod/indirect 1/rm32/ecx . . . 3/r32/BL . . # copy byte at *ecx to BL 81 7/subop/compare 3/mod/direct 3/rm32/ebx . . . . . 0x78/imm32/x # compare ebx 75/jump-if-!= $hex-int?:loop/disp8 # . ++curr 41/increment-ecx $hex-int?:loop: # if (curr >= in->end) return true 39/compare 3/mod/direct 1/rm32/ecx . . . 2/r32/edx . . # compare ecx with edx 73/jump-if-addr>= $hex-int?:true/disp8 # var eax: boolean = hex-digit?(*curr) # . . push args 8a/copy-byte 0/mod/indirect 1/rm32/ecx . . . 0/r32/AL . . # copy byte at *ecx to AL 50/push-eax # . . call e8/call hex-digit?/disp32 # . . discard args 81 0/subop/add 3/mod/direct 4/rm32/esp . . . . . 4/imm32 # add to esp # if (eax == false) return false 3d/compare-eax-and 0/imm32/false 74/jump-if-= $hex-int?:end/disp8 # ++curr 41/increment-ecx # loop eb/jump $hex-int?:loop/disp8 $hex-int?:true: # return true b8/copy-to-eax 1/imm32/true $hex-int?:end: # . restore registers 5b/pop-to-ebx 5a/pop-to-edx 59/pop-to-ecx # . epilogue 89/copy 3/mod/direct 4/rm32/esp . . . 5/r32/ebp . . # copy ebp to esp 5d/pop-to-ebp c3/return test-hex-int: # . prologue 55/push-ebp 89/copy 3/mod/direct 5/rm32/ebp . . . 4/r32/esp . . # copy esp to ebp # (eax..ecx) = "34" b8/copy-to-eax "34"/imm32 8b/copy 0/mod/indirect 0/rm32/eax . . . 1/r32/ecx . . # copy *eax to ecx 8d/copy-address 1/mod/*+disp8 4/rm32/sib 0/base/eax 1/index/ecx . 1/r32/ecx 4/disp8 . # copy eax+ecx+4 to ecx 05/add-to-eax 4/imm32 # var slice/ecx: slice = {eax, ecx} 51/push-ecx 50/push-eax 89/copy 3/mod/direct 1/rm32/ecx . . . 4/r32/esp . . # copy esp to ecx # eax = hex-int?(slice) # . . push args 51/push-ecx # . . call e8/call hex-int?/disp32 # . . discard args 81 0/subop/add 3/mod/direct 4/rm32/esp . . . . . 4/imm32 # add to esp # check-ints-equal(eax, 1, msg) # . . push args 68/push "F - test-hex-int"/imm32 68/push 1/imm32/true 50/push-eax # . . call e8/call check-ints-equal/disp32 # . . discard args 81 0/subop/add 3/mod/direct 4/rm32/esp . . . . . 0xc/imm32 # add to esp # . epilogue 89/copy 3/mod/direct 4/rm32/esp . . . 5/r32/ebp . . # copy ebp to esp 5d/pop-to-ebp c3/return test-hex-int-handles-letters: # . prologue 55/push-ebp 89/copy 3/mod/direct 5/r
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<title>Mu - 302stack_allocate.subx</title>
<meta name="Generator" content="Vim/8.1">
<meta name="plugin-version" content="vim8.1_v1">
<meta name="syntax" content="none">
<meta name="settings" content="number_lines,use_css,pre_wrap,no_foldcolumn,expand_tabs,line_ids,prevent_copy=">
<meta name="colorscheme" content="minimal-light">
<style type="text/css">
<!--
pre { white-space: pre-wrap; font-family: monospace; color: #000000; background-color: #ffffd7; }
body { font-size:12pt; font-family: monospace; color: #000000; background-color: #ffffd7; }
a { color:inherit; }
* { font-size:12pt; font-size: 1em; }
.subxComment { color: #005faf; }
.LineNr { }
.SpecialChar { color: #d70000; }
.CommentedCode { color: #8a8a8a; }
.subxFunction { color: #af5f00; text-decoration: underline; }
.Constant { color: #008787; }
-->
</style>

<script type='text/javascript'>
<!--

/* function to open any folds containing a jumped-to line before jumping to it */
function JumpToLine()
{
  var lineNum;
  lineNum = window.location.hash;
  lineNum = lineNum.substr(1); /* strip off '#' */

  if (lineNum.indexOf('L') == -1) {
    lineNum = 'L'+lineNum;
  }
  var lineElem = document.getElementById(lineNum);
  /* Always jump to new location even if the line was hidden inside a fold, or
   * we corrected the raw number to a line ID.
   */
  if (lineElem) {
    lineElem.scrollIntoView(true);
  }
  return true;
}
if ('onhashchange' in window) {
  window.onhashchange = JumpToLine;
}

-->
</script>
</head>
<body onload='JumpToLine();'>
<a href='https://github.com/akkartik/mu/blob/main/302stack_allocate.subx'>https://github.com/akkartik/mu/blob/main/302stack_allocate.subx</a>
<pre id='vimCodeElement'>
<span id="L1" class="LineNr"> 1 </span><span class="subxComment"># A function which pushes n zeros on the stack.</span>
<span id="L2" class="LineNr"> 2 </span><span class="subxComment"># Really only intended to be called from code generated by mu.subx (for array</span>
<span id="L3" class="LineNr"> 3 </span><span class="subxComment"># vars on the stack).</span>
<span id="L4" class="LineNr"> 4 </span>
<span id="L5" class="LineNr"> 5 </span>== code
<span id="L6" class="LineNr"> 6 </span>
<span id="L7" class="LineNr"> 7 </span><span class="CommentedCode">#? Entry:</span>
<span id="L8" class="LineNr"> 8 </span><span class="CommentedCode">#?     # . prologue</span>
<span id="L9" class="LineNr"> 9 </span><span class="CommentedCode">#?     89/&lt;- %ebp 4/r32/esp</span>
<span id="L10" class="LineNr">10 </span><span class="CommentedCode">#?     #</span>
<span id="L11" class="LineNr">11 </span><span class="CommentedCode">#?     68/push 0xfcfdfeff/imm32</span>
<span id="L12" class="LineNr">12 </span><span class="CommentedCode">#?     b8/copy-to-eax 0x34353637/imm32</span>
<span id="L13" class="LineNr">13 </span><span class="CommentedCode">#? $dump-stack0:</span>
<span id="L14" class="LineNr">14 </span><span class="CommentedCode">#?     (push-n-zero-bytes 4)</span>
<span id="L15" class="LineNr">15 </span><span class="CommentedCode">#?     68/push 0x20/imm32</span>
<span id="L16" class="LineNr">16 </span><span class="CommentedCode">#? $dump-stack9:</span>
<span id="L17" class="LineNr">17 </span><span class="CommentedCode">#?     b8/copy-to-eax 1/imm32/exit</span>
<span id="L18" class="LineNr">18 </span><span class="CommentedCode">#?     cd/syscall 0x80/imm8</span>
<span id="L19" class="LineNr">19 </span>
<span id="L20" class="LineNr">20 </span><span class="subxComment"># This is not a regular function, so it won't be idiomatic.</span>
<span id="L21" class="LineNr">21 </span><span class="subxComment"># Registers must be properly restored.</span>
<span id="L22" class="LineNr">22 </span><span class="subxComment"># Registers can be spilled, but that modifies the stack and needs to be</span>
<span id="L23" class="LineNr">23 </span><span class="subxComment"># cleaned up.</span>
<span id="L24" class="LineNr">24 </span>
<span id="L25" class="LineNr">25 </span><span class="subxComment"># Overhead:</span>
<span id="L26" class="LineNr">26 </span><span class="subxComment">#   62 + n*6 instructions to push n bytes.</span>
<span id="L27" class="LineNr">27 </span><span class="subxComment"># If we just emitted code to push n zeroes, it would be:</span>
<span id="L28" class="LineNr">28 </span><span class="subxComment">#   5 bytes for 4 zero bytes, so 1.25 bytes per zero. And that's not even</span>
<span id="L29" class="LineNr">29 </span><span class="subxComment">#   instructions.</span>
<span id="L30" class="LineNr">30 </span><span class="subxComment"># But on the other hand it would destroy the instruction cache, where this</span>
<span id="L31" class="LineNr">31 </span><span class="subxComment"># approach requires 15 instructions, fixed.</span>
<span id="L32" class="LineNr">32 </span>
<span id="L33" class="LineNr">33 </span><span class="subxComment"># n must be positive</span>
<span id="L34" class="LineNr">34 </span><span class="subxFunction">push-n-zero-bytes</span>:  <span class="subxComment"># n: int</span>
<span id="L35" class="LineNr">35 </span><span class="Constant">$push-n-zero-bytes:prologue</span>:
<span id="L36" class="LineNr">36 </span>    89/&lt;- *<span class="SpecialChar"><a href='302stack_allocate.subx.html#L56'>Push-n-zero-bytes-ebp</a></span> 5/r32/ebp  <span class="subxComment"># spill ebp without affecting stack</span>
<span id="L37" class="LineNr">37 </span>    89/&lt;- %ebp 4/r32/esp
<span id="L38" class="LineNr">38