porffor 0.1.0 → 0.2.0-47b4f2e

package/compiler/2c.js

@@ -0,0 +1,380 @@
+import { read_ieee754_binary64, read_signedLEB128 } from './encoding.js';
+import { Blocktype, Opcodes, Valtype } from './wasmSpec.js';
+import { operatorOpcode } from './expression.js';
+import { log } from "./log.js";
+
+const CValtype = {
+  i8: 'char',
+  i16: 'unsigned short', // presume all i16 stuff is unsigned
+  i32: 'long',
+  i32_u: 'unsigned long',
+  i64: 'long long',
+  i64_u: 'unsigned long long',
+
+  f32: 'float',
+  f64: 'double',
+
+  undefined: 'void'
+};
+
+const inv = (obj, keyMap = x => x) => Object.keys(obj).reduce((acc, x) => { acc[keyMap(obj[x])] = x; return acc; }, {});
+const invOpcodes = inv(Opcodes);
+
+for (const x in CValtype) {
+  if (Valtype[x]) CValtype[Valtype[x]] = CValtype[x];
+}
+
+const todo = msg => {
+  class TodoError extends Error {
+    constructor(message) {
+      super(message);
+      this.name = 'TodoError';
+    }
+  }
+
+  throw new TodoError(`todo: ${msg}`);
+};
+
+const removeBrackets = str => {
+  if (str.startsWith('(long)(unsigned long)')) return '(long)(unsigned long)(' + removeBrackets(str.slice(22, -1)) + ')';
+  return str.startsWith('(') && str.endsWith(')') ? str.slice(1, -1) : str;
+};
+
+export default ({ funcs, globals, tags, exceptions, pages }) => {
+  const invOperatorOpcode = Object.values(operatorOpcode).reduce((acc, x) => {
+    for (const k in x) {
+      acc[x[k]] = k;
+    }
+    return acc;
+  }, {});
+  const invGlobals = inv(globals, x => x.idx);
+
+  const sanitize = str => str.replace(/[^0-9a-zA-Z_]/g, _ => String.fromCharCode(97 + _.charCodeAt(0) % 32));
+
+  for (const x in invGlobals) {
+    invGlobals[x] = sanitize(invGlobals[x]);
+  }
+
+  const includes = new Map(), unixIncludes = new Map(), winIncludes = new Map();
+
+  // TODO: make type i16
+  let out = `struct ReturnValue {
+  ${CValtype.f64} value;
+  ${CValtype.i32} type;
+};\n\n`;
+
+  for (const x in globals) {
+    const g = globals[x];
+
+    out += `${CValtype[g.type]} ${sanitize(x)} = ${g.init ?? 0}`;
+    out += ';\n';
+  }
+
+  // for (const [ x, p ] of pages) {
+    // out += `${CValtype[p.type]} ${x.replace(': ', '_').replace(/[^0-9a-zA-Z_]/g, '')}[100]`;
+    // out += ';\n';
+  // }
+
+  if (out) out += '\n';
+
+  let depth = 1;
+  const line = (str, semi = true) => out += `${' '.repeat(depth * 2)}${str}${semi ? ';' : ''}\n`;
+  const lines = lines => {
+    for (const x of lines) {
+      out += `${' '.repeat(depth * 2)}${x}\n`;
+    }
+  };
+
+  const platformSpecific = (win, unix, add = true) => {
+    let tmp = '';
+
+    if (win) {
+      if (add) out += '#ifdef _WIN32\n';
+        else tmp += '#ifdef _WIN32\n';
+
+      if (add) lines(win.split('\n'));
+        else tmp += win + (win.endsWith('\n') ? '' : '\n');
+    }
+
+    if (unix) {
+      if (add) out += (win ? '#else' : '#ifndef _WIN32') + '\n';
+        else tmp += (win ? '#else' : '#ifndef _WIN32') + '\n';
+
+      if (add) lines(unix.split('\n'));
+        else tmp += unix + (unix.endsWith('\n') ? '' : '\n');
+    }
+
+    if (win || unix)
+      if (add) out += '#endif\n';
+        else tmp += '#endif\n';
+
+    return tmp;
+  };
+
+  for (const f of funcs) {
+    depth = 1;
+
+    const invLocals = inv(f.locals, x => x.idx);
+    // if (f.returns.length > 1) todo('funcs returning >1 value unsupported');
+
+    for (const x in invLocals) {
+      invLocals[x] = sanitize(invLocals[x]);
+    }
+
+    const returns = f.returns.length > 0;
+
+    const shouldInline = f.internal;
+    out += `${f.name === 'main' ? 'int' : (f.internal ? 'double' : 'struct ReturnValue')} ${shouldInline ? 'inline ' : ''}${sanitize(f.name)}(${f.params.map((x, i) => `${CValtype[x]} ${invLocals[i]}`).join(', ')}) {\n`;
+
+    const localKeys = Object.keys(f.locals).sort((a, b) => f.locals[a].idx - f.locals[b].idx).slice(f.params.length).sort((a, b) => f.locals[a].idx - f.locals[b].idx);
+    for (const x of localKeys) {
+      const l = f.locals[x];
+      line(`${CValtype[l.type]} ${sanitize(x)} = 0`);
+    }
+
+    if (localKeys.length !== 0) out += '\n';
+
+    let vals = [];
+    const endNeedsCurly = [], ignoreEnd = [];
+    let beginLoop = false, lastCond = false, ifTernary = false;
+    for (let _ = 0; _ < f.wasm.length; _++) {
+      const i = f.wasm[_];
+
+      if (invOperatorOpcode[i[0]]) {
+        const b = vals.pop();
+        const a = vals.pop();
+
+        let op = invOperatorOpcode[i[0]];
+        if (op.length === 3) op = op.slice(0, 2);
+
+        if (['==', '!=', '>', '>=', '<', '<='].includes(op)) lastCond = true;
+          else lastCond = false;
+
+        // vals.push(`(${removeBrackets(a)} ${op} ${b})`);
+        vals.push(`(${a} ${op} ${b})`);
+        continue;
+      }
+
+      // misc insts
+      if (i[0] === 0xfc) {
+        switch (i[1]) {
+          // i32_trunc_sat_f64_s
+          case 0x02:
+            vals.push(`(${CValtype.i32})${vals.pop()}`);
+            break;
+
+          // i32_trunc_sat_f64_u
+          case 0x03:
+            vals.push(`(${CValtype.i32})(${CValtype.i32_u})${vals.pop()}`);
+            break;
+        }
+
+        lastCond = false;
+        continue;
+      }
+
+      switch (i[0]) {
+        case Opcodes.i32_const:
+        case Opcodes.i64_const:
+          vals.push(read_signedLEB128(i.slice(1)).toString());
+          break;
+
+        case Opcodes.f64_const:
+          vals.push(read_ieee754_binary64(i.slice(1)).toExponential());
+          break;
+
+        case Opcodes.local_get:
+          vals.push(`${invLocals[i[1]]}`);
+          break;
+
+        case Opcodes.local_set:
+          line(`${invLocals[i[1]]} = ${removeBrackets(vals.pop())}`);
+          break;
+
+        case Opcodes.local_tee:
+          // line(`${invLocals[i[1]]} = ${removeBrackets(vals.pop())}`);
+          // vals.push(`${invLocals[i[1]]}`);
+          vals.push(`((${invLocals[i[1]]} = ${vals.pop()}))`);
+          break;
+
+        case Opcodes.global_get:
+          vals.push(`${invGlobals[i[1]]}`);
+          break;
+
+        case Opcodes.global_set:
+          line(`${invGlobals[i[1]]} = ${removeBrackets(vals.pop())}`);
+          break;
+
+        case Opcodes.f64_trunc:
+          // vals.push(`trunc(${vals.pop()})`);
+          vals.push(`(int)(${removeBrackets(vals.pop())})`); // this is ~10x faster with clang??
+          break;
+
+        case Opcodes.f64_convert_i32_u:
+        case Opcodes.f64_convert_i32_s:
+        case Opcodes.f64_convert_i64_u:
+        case Opcodes.f64_convert_i64_s:
+          // int to double
+          vals.push(`(double)${vals.pop()}`);
+          break;
+
+        case Opcodes.return:
+          // line(`return${returns ? ` ${removeBrackets(vals.pop())}` : ''}`);
+          line(`return${returns ? ` (struct ReturnValue){ ${removeBrackets(vals.pop())}, ${removeBrackets(vals.pop())} }` : ''}`);
+          break;
+
+        case Opcodes.if:
+          let cond = removeBrackets(vals.pop());
+          if (!lastCond) {
+            if (cond.startsWith('(long)')) cond = `${cond.slice(6)} == 1e+0`;
+              else cond += ' == 1';
+          }
+
+          ifTernary = i[1] !== Blocktype.void;
+          if (ifTernary) {
+            ifTernary = cond;
+            break;
+          }
+
+          if (beginLoop) {
+            beginLoop = false;
+            line(`while (${cond}) {`, false);
+
+            depth++;
+            endNeedsCurly.push(true);
+            ignoreEnd.push(false, true);
+            break;
+          }
+
+          line(`if (${cond}) {`, false);
+
+          depth++;
+          endNeedsCurly.push(true);
+          ignoreEnd.push(false);
+          break;
+
+        case Opcodes.else:
+          if (ifTernary) break;
+
+          depth--;
+          line(`} else {`, false);
+          depth++;
+          break;
+
+        case Opcodes.loop:
+          // not doing properly, fake a while loop
+          beginLoop = true;
+          break;
+
+        case Opcodes.end:
+          if (ignoreEnd.pop()) break;
+
+          if (ifTernary) {
+            const b = vals.pop();
+            const a = vals.pop();
+            vals.push(`${ifTernary} ? ${a} : ${b}`);
+            break;
+          }
+
+          depth--;
+          if (endNeedsCurly.pop() === true) line('}', false);
+          break;
+
+        case Opcodes.call:
+          let func = funcs.find(x => x.index === i[1]);
+          if (!func) {
+            const importFunc = importFuncs[i[1]];
+            switch (importFunc.name) {
+              case 'print':
+                line(`printf("%f\\n", ${vals.pop()})`);
+                includes.set('stdio.h', true);
+                break;
+              case 'printChar':
+                line(`printf("%c", (int)(${vals.pop()}))`);
+                includes.set('stdio.h', true);
+                break;
+
+              case 'time':
+                line(`double _time_out`);
+                /* platformSpecific(
+`FILETIME _time_filetime;
+GetSystemTimeAsFileTime(&_time_filetime);
+
+ULARGE_INTEGER _time_ularge;
+_time_ularge.LowPart = _time_filetime.dwLowDateTime;
+_time_ularge.HighPart = _time_filetime.dwHighDateTime;
+_time_out = (_time_ularge.QuadPart - 116444736000000000i64) / 10000.;`,
+`struct timespec _time;
+clock_gettime(CLOCK_MONOTONIC, &_time);
+_time_out = _time.tv_nsec / 1000000.;`); */
+                platformSpecific(
+`LARGE_INTEGER _time_freq, _time_t;
+QueryPerformanceFrequency(&_time_freq);
+QueryPerformanceCounter(&_time_t);
+_time_out = ((double)_time_t.QuadPart / _time_freq.QuadPart) * 1000.;`,
+`struct timespec _time;
+clock_gettime(CLOCK_MONOTONIC, &_time);
+_time_out = _time.tv_nsec / 1000000. + _time.tv_sec * 1000.;`);
+                vals.push(`_time_out`);
+
+                unixIncludes.set('time.h', true);
+                winIncludes.set('windows.h', true);
+                break;
+
+              default:
+                log.warning('2c', `unimplemented import: ${importFunc.name}`);
+                break;
+            }
+
+            break;
+          }
+
+          let args = [];
+          for (let j = 0; j < func.params.length; j++) args.unshift(removeBrackets(vals.pop()));
+
+          if (func.returns.length > 0) {
+            if (func.internal) {
+              vals.push(`${sanitize(func.name)}(${args.join(', ')})`);
+            } else {
+              line(`const struct ReturnValue _ = ${sanitize(func.name)}(${args.join(', ')})`);
+              vals.push(`_.value`);
+              vals.push(`_.type`);
+            }
+          } else line(`${sanitize(func.name)}(${args.join(', ')})`);
+
+          break;
+
+        case Opcodes.drop:
+          // line(vals.pop());
+          vals.pop();
+          break;
+
+        case Opcodes.br:
+          // ignore
+          // reset "stack"
+          vals = [];
+          break;
+
+        default:
+          log.warning('2c', `unimplemented op: ${invOpcodes[i[0]]}`);
+          // todo(`unimplemented op: ${invOpcodes[i[0]]}`);
+      }
+
+      lastCond = false;
+    }
+
+    if (vals.length === 1 && returns) {
+      line(`return ${vals.pop()}`);
+    }
+
+    out += '}\n\n';
+  }
+
+  depth = 0;
+
+  const makeIncludes = includes => [...includes.keys()].map(x => `#include <${x}>\n`).join('');
+
+  out = platformSpecific(makeIncludes(winIncludes), makeIncludes(unixIncludes), false) + '\n' + makeIncludes(includes) + '\n' + out;
+
+  return out;
+};

package/compiler/builtins/base64.js

@@ -1,92 +1,92 @@
-var btoa_a = str => {
-  // todo: throw invalid character for unicode
-
-  const chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/';
-  const mask = (1 << 6) - 1;
-
-  let out = '';
-  let bits = 0, buffer = 0;
-  for (let i = 0; i < str.length; i++) {
-    buffer = (buffer << 8) | (0xff & str.charCodeAt(i));
-    bits += 8;
-
-    while (bits > 6) {
-      bits -= 6;
-      out += chars[mask & (buffer >> bits)];
-    }
-  }
-
-  if (bits) {
-    out += chars[mask & (buffer << (6 - bits))]
-  }
-
-  while ((out.length * 6) & 7) {
-    out += '=';
-  }
-
-  return out;
-};
-
-var btoa = function (input) {
-  // todo: throw invalid character for unicode
-  const keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
-
-  let output = "";
-  let chr1, chr2, chr3, enc1, enc2, enc3, enc4;
-  let i = 0;
-
-  while (i < input.length) {
-    chr1 = input.charCodeAt(i++);
-    chr2 = input.charCodeAt(i++);
-    chr3 = input.charCodeAt(i++);
-
-    enc1 = chr1 >> 2;
-    enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
-    enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
-    enc4 = chr3 & 63;
-
-    if (isNaN(chr2)) {
-      enc3 = enc4 = 64;
-    } else if (isNaN(chr3)) {
-      enc4 = 64;
-    }
-
-    output += keyStr.charAt(enc1);
-    output += keyStr.charAt(enc2);
-    output += keyStr.charAt(enc3);
-    output += keyStr.charAt(enc4);
-  }
-
-  return output;
-};
-
-var atob_b = function (input) {
-  const keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
-
-  let output = "";
-  let chr1, chr2, chr3;
-  let enc1, enc2, enc3, enc4;
-  let i = 0;
-
-  while (i < input.length) {
-    enc1 = keyStr.indexOf(input.charAt(i++));
-    enc2 = keyStr.indexOf(input.charAt(i++));
-    enc3 = keyStr.indexOf(input.charAt(i++));
-    enc4 = keyStr.indexOf(input.charAt(i++));
-
-    chr1 = (enc1 << 2) | (enc2 >> 4);
-    chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
-    chr3 = ((enc3 & 3) << 6) | enc4;
-
-    output += String.fromCharCode(chr1);
-
-    if (enc3 != 64) {
-      output += String.fromCharCode(chr2);
-    }
-    if (enc4 != 64) {
-      output += String.fromCharCode(chr3);
-    }
-  }
-
-  return output;
+var btoa_a = str => {
+  // todo: throw invalid character for unicode
+
+  const chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/';
+  const mask = (1 << 6) - 1;
+
+  let out = '';
+  let bits = 0, buffer = 0;
+  for (let i = 0; i < str.length; i++) {
+    buffer = (buffer << 8) | (0xff & str.charCodeAt(i));
+    bits += 8;
+
+    while (bits > 6) {
+      bits -= 6;
+      out += chars[mask & (buffer >> bits)];
+    }
+  }
+
+  if (bits) {
+    out += chars[mask & (buffer << (6 - bits))]
+  }
+
+  while ((out.length * 6) & 7) {
+    out += '=';
+  }
+
+  return out;
+};
+
+var btoa = function (input) {
+  // todo: throw invalid character for unicode
+  const keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
+
+  let output = "";
+  let chr1, chr2, chr3, enc1, enc2, enc3, enc4;
+  let i = 0;
+
+  while (i < input.length) {
+    chr1 = input.charCodeAt(i++);
+    chr2 = input.charCodeAt(i++);
+    chr3 = input.charCodeAt(i++);
+
+    enc1 = chr1 >> 2;
+    enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
+    enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
+    enc4 = chr3 & 63;
+
+    if (isNaN(chr2)) {
+      enc3 = enc4 = 64;
+    } else if (isNaN(chr3)) {
+      enc4 = 64;
+    }
+
+    output += keyStr.charAt(enc1);
+    output += keyStr.charAt(enc2);
+    output += keyStr.charAt(enc3);
+    output += keyStr.charAt(enc4);
+  }
+
+  return output;
+};
+
+var atob_b = function (input) {
+  const keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
+
+  let output = "";
+  let chr1, chr2, chr3;
+  let enc1, enc2, enc3, enc4;
+  let i = 0;
+
+  while (i < input.length) {
+    enc1 = keyStr.indexOf(input.charAt(i++));
+    enc2 = keyStr.indexOf(input.charAt(i++));
+    enc3 = keyStr.indexOf(input.charAt(i++));
+    enc4 = keyStr.indexOf(input.charAt(i++));
+
+    chr1 = (enc1 << 2) | (enc2 >> 4);
+    chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
+    chr3 = ((enc3 & 3) << 6) | enc4;
+
+    output += String.fromCharCode(chr1);
+
+    if (enc3 != 64) {
+      output += String.fromCharCode(chr2);
+    }
+    if (enc4 != 64) {
+      output += String.fromCharCode(chr3);
+    }
+  }
+
+  return output;
 };

package/compiler/builtins.js

@@ -1,6 +1,5 @@
 import { Blocktype, Opcodes, Valtype } from "./wasmSpec.js";
 import { number, i32x4 } from "./embedding.js";
-import { signedLEB128 } from "./encoding.js";
 
 export const importedFuncs = [
   {
@@ -15,12 +14,6 @@ export const importedFuncs = [
     params: 1,
     returns: 0
   },
-  {
-    name: 'assert',
-    import: 'a',
-    params: 1,
-    returns: 0
-  },
   {
     name: 'time',
     import: 't',
@@ -402,7 +395,7 @@ export const BuiltinFuncs = function() {
 
   // this is an implementation of xorshift128+ (in wasm bytecode)
   // fun fact: v8, SM, JSC also use this (you will need this fun fact to maintain your sanity reading this code)
-  const prngSeed0 = Math.floor(Math.random() * (2 ** 30)), prngSeed1 = Math.floor(Math.random() * (2 ** 30));
+  const prngSeed0 = Math.floor(Math.random() * Number.MAX_SAFE_INTEGER), prngSeed1 = Math.floor(Math.random() * Number.MAX_SAFE_INTEGER);
 
   this.__Math_random = {
     floatOnly: true,
@@ -416,13 +409,13 @@ export const BuiltinFuncs = function() {
     wasm: [
       // setup: s1 = state0, s0 = state1, state0 = s0
       [ Opcodes.global_get, 0 ], // state0
-      [ Opcodes.local_set, 0 ], // s1
+      [ Opcodes.local_tee, 0 ], // s1
       [ Opcodes.global_get, 1 ], // state1
       [ Opcodes.local_tee, 1, ], // s0
       [ Opcodes.global_set, 0 ], // state0
 
       // s1 ^= s1 << 23
-      [ Opcodes.local_get, 0 ], // s1
+      // [ Opcodes.local_get, 0 ], // s1
       [ Opcodes.local_get, 0 ], // s1
       [ Opcodes.i64_const, 23 ],
       [ Opcodes.i64_shl ], // <<
@@ -452,12 +445,26 @@ export const BuiltinFuncs = function() {
 
       // you thought it was over? now we need the result as a f64 between 0-1 :)
 
-      // mantissa = (state1 + s0) & ((1 << 53) - 1)
+      // state1 + s0
       [ Opcodes.global_get, 1 ], // state1
       [ Opcodes.local_get, 1 ], // s0
       [ Opcodes.i64_add ],
 
-      [ Opcodes.i64_const, ...signedLEB128((1 << 53) - 1) ],
+      // should we >> 12 here?
+      // it feels like it but it breaks values
+
+      // | 0x3FF0000000000000
+      // [ Opcodes.i64_const, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0xf8, 0x3f ],
+      // [ Opcodes.i64_or ],
+
+      // bit cast as f64
+      // [ Opcodes.f64_reinterpret_i64 ],
+
+      // - 1
+      // ...number(1),
+      // [ Opcodes.f64_sub ],
+
+      ...number((1 << 53) - 1, Valtype.i64),
       [ Opcodes.i64_and ],
 
       // double(mantissa)
@@ -568,7 +575,6 @@ export const BuiltinFuncs = function() {
     params: [ Valtype.i32 ],
     locals: [],
     returns: [ Valtype.v128 ],
-    memory: true,
     wasm: [
       [ Opcodes.local_get, 0 ],
       [ ...Opcodes.v128_load, 0, 0 ]