porffor 0.2.0-536e463 → 0.2.0-5ac7ea0

package/compiler/precompile.js

@@ -0,0 +1,129 @@
+import { Opcodes } from './wasmSpec.js';
+
+import fs from 'node:fs';
+import { join } from 'node:path';
+
+import { fileURLToPath } from 'node:url';
+const __dirname = fileURLToPath(new URL('.', import.meta.url));
+
+const TYPES = {
+  number: 0x00,
+  boolean: 0x01,
+  string: 0x02,
+  undefined: 0x03,
+  object: 0x04,
+  function: 0x05,
+  symbol: 0x06,
+  bigint: 0x07,
+
+  // these are not "typeof" types but tracked internally
+  _array: 0x10,
+  _regexp: 0x11,
+  _bytestring: 0x12
+};
+
+// import porfParse from './parse.js';
+// import porfCodegen from './codeGen.js';
+
+const argv = process.argv.slice();
+
+const compile = async (file, [ _funcs, _globals ]) => {
+  const source = fs.readFileSync(file, 'utf8');
+  const first = source.slice(0, source.indexOf('\n'));
+
+  let args = ['-bytestring'];
+  if (file.endsWith('.ts')) args.push('-parse-types', '-opt-types');
+  if (first.startsWith('// @porf')) {
+    args = args.concat(first.slice('// @porf '.length).split(' '));
+  }
+  process.argv = argv.concat(args);
+
+  // const porfParse = (await import(`./parse.js?_=${Date.now()}`)).default;
+  // const porfCodegen = (await import(`./codeGen.js?_=${Date.now()}`)).default;
+
+  // let { funcs, globals, data } = porfCodegen(porfParse(source, ['module']));
+
+  const porfCompile = (await import(`./index.js?_=${Date.now()}`)).default;
+
+  let { funcs, globals, data, exceptions } = porfCompile(source, ['module']);
+
+  const allocated = new Set();
+
+  const exports = funcs.filter(x => x.export);
+  for (const x of exports) {
+    if (x.data) x.data = x.data.map(x => data[x]);
+    if (x.exceptions) x.exceptions = x.exceptions.map(x => {
+      const obj = exceptions[x];
+      if (obj) obj.exceptId = x;
+      return obj;
+    }).filter(x => x);
+
+    const locals = Object.keys(x.locals).reduce((acc, y) => {
+      acc[x.locals[y].idx] = { ...x.locals[y], name: y };
+      return acc;
+    }, {});
+
+    for (let i = 0; i < x.wasm.length; i++) {
+      const y = x.wasm[i];
+      const n = x.wasm[i + 1];
+      if (y[0] === Opcodes.call) {
+        const f = funcs.find(x => x.index === y[1]);
+        if (!f) continue;
+
+        y[1] = f.name;
+      }
+
+      if (y[0] === Opcodes.const && (n[0] === Opcodes.local_set || n[0] === Opcodes.local_tee)) {
+        const l = locals[n[1]];
+        if (!l) continue;
+        if (![TYPES.string, TYPES._array, TYPES._bytestring].includes(l.metadata?.type)) continue;
+        if (!x.pages) continue;
+
+        const pageName = [...x.pages.keys()].find(z => z.endsWith(l.name));
+        if (!pageName || allocated.has(pageName)) continue;
+        allocated.add(pageName);
+
+        y.splice(0, 10, 'alloc', pageName, x.pages.get(pageName).type);
+        // y.push(x.pages.get(pageName));
+      }
+    }
+  }
+
+  _funcs.push(...exports);
+  _globals.push(...Object.values(globals));
+};
+
+const precompile = async () => {
+  const dir = join(__dirname, 'builtins');
+
+  let funcs = [], globals = [];
+  for (const file of fs.readdirSync(dir)) {
+    if (file.endsWith('.d.ts')) continue;
+    await compile(join(dir, file), [ funcs, globals ]);
+  }
+
+  // ${x.pages && x.pages.size > 0 ? `    pages: ${JSON.stringify(Object.fromEntries(x.pages.entries()))},` : ''}
+  // ${x.used && x.used.length > 0 ? `    used: ${JSON.stringify(x.used)},` : ''}
+
+  return `// autogenerated by compiler/precompile.js
+import { number } from './embedding.js';
+
+export const BuiltinFuncs = function() {
+${funcs.map(x => `  this.${x.name} = {
+    wasm: (scope, { allocPage, builtin }) => ${JSON.stringify(x.wasm.filter(x => x.length && x[0] != null)).replace(/\["alloc","(.*?)","(.*?)"\]/g, (_, reason, type) => `...number(allocPage(scope, '${reason}', '${type}') * pageSize, ${valtypeBinary})`).replace(/\[16,"(.*?)"]/g, (_, name) => `[16, builtin('${name}')]`)},
+    params: ${JSON.stringify(x.params)},
+    typedParams: true,
+    returns: ${JSON.stringify(x.returns)},
+    typedReturns: true,
+    locals: ${JSON.stringify(Object.values(x.locals).slice(x.params.length).map(x => x.type))},
+    localNames: ${JSON.stringify(Object.keys(x.locals))},
+${x.data && x.data.length > 0 ? `    data: ${JSON.stringify(x.data)},` : ''}
+${x.exceptions && x.exceptions.length > 0 ? `    exceptions: ${JSON.stringify(x.exceptions)},` : ''}
+  };`.replaceAll('\n\n', '\n')).join('\n')}
+};`;
+};
+
+const code = await precompile();
+// console.log(code);
+
+fs.writeFileSync(join(__dirname, 'generated_builtins.js'), code);

package/compiler/prefs.js

@@ -0,0 +1,26 @@
+const onByDefault = [ 'bytestring' ];
+
+const cache = {};
+const obj = new Proxy({}, {
+  get(_, p) {
+    // intentionally misses with undefined values cached
+    if (cache[p]) return cache[p];
+
+    return cache[p] = (() => {
+      // fooBar -> foo-bar
+      const name = p[0] === '_' ? p : p.replace(/[A-Z]/g, c => `-${c.toLowerCase()}`);
+      if (process.argv.includes('-' + name)) return true;
+      if (process.argv.includes('-no-' + name)) return false;
+
+      const valArg = process.argv.find(x => x.startsWith(`-${name}=`));
+      if (valArg) return valArg.slice(name.length + 2);
+
+      if (onByDefault.includes(p)) return true;
+      return undefined;
+    })();
+  }
+});
+
+obj.uncache = () => cache = {};
+
+export default obj;

package/compiler/prototype.js

@@ -2,6 +2,7 @@ import { Opcodes, Blocktype, Valtype, ValtypeSize, PageSize } from "./wasmSpec.j
 import { number } from "./embedding.js";
 import { unsignedLEB128 } from "./encoding.js";
 import { UNDEFINED } from "./builtins.js";
+import Prefs from './prefs.js';
 
 // todo: do not duplicate this
 const TYPES = {
@@ -16,15 +17,17 @@ const TYPES = {
 
   // these are not "typeof" types but tracked internally
   _array: 0x10,
-  _regexp: 0x11
+  _regexp: 0x11,
+  _bytestring: 0x12
 };
 
 // todo: turn these into built-ins once arrays and these become less hacky
 
 export const PrototypeFuncs = function() {
-  const noUnlikelyChecks = process.argv.includes('-funsafe-no-unlikely-proto-checks');
-  let zeroChecks = process.argv.find(x => x.startsWith('-funsafe-zero-proto-checks='));
-  if (zeroChecks) zeroChecks = zeroChecks.split('=')[1].split(',').reduce((acc, x) => { acc[x.toLowerCase()] = true; return acc; }, {});
+  const noUnlikelyChecks = Prefs.funsafeNoUnlikelyProtoChecks;
+
+  let zeroChecks;
+  if (Prefs.zeroChecks) zeroChecks = Prefs.zeroChecks.split('=')[1].split(',').reduce((acc, x) => { acc[x.toLowerCase()] = true; return acc; }, {});
     else zeroChecks = {};
 
   this[TYPES._array] = {
@@ -71,7 +74,7 @@ export const PrototypeFuncs = function() {
     ],
 
     // todo: only for 1 argument
-    push: (pointer, length, wNewMember) => [
+    push: (pointer, length, wNewMember, _1, _2, _3, unusedValue) => [
       // get memory offset of array at last index (length)
       ...length.getCachedI32(),
       ...number(ValtypeSize[valtype], Valtype.i32),
@@ -92,22 +95,28 @@ export const PrototypeFuncs = function() {
         ...number(1, Valtype.i32),
         [ Opcodes.i32_add ],
 
-        ...length.setCachedI32(),
-        ...length.getCachedI32(),
+        ...(unusedValue() ? [] : [
+          ...length.setCachedI32(),
+          ...length.getCachedI32(),
+        ])
       ]),
 
-      ...length.getCachedI32(),
-      Opcodes.i32_from_u
+      ...(unusedValue() ? [] : [
+        ...length.getCachedI32(),
+        Opcodes.i32_from_u
+      ])
 
       // ...length.get()
     ],
 
-    pop: (pointer, length) => [
+    pop: (pointer, length, _1, _2, _3, _4, unusedValue) => [
       // if length == 0, noop
       ...length.getCachedI32(),
       [ Opcodes.i32_eqz ],
       [ Opcodes.if, Blocktype.void ],
-      ...number(UNDEFINED),
+      ...(unusedValue() ? [] : [
+        ...number(UNDEFINED),
+      ]),
       [ Opcodes.br, 1 ],
       [ Opcodes.end ],
 
@@ -119,19 +128,23 @@ export const PrototypeFuncs = function() {
         ...number(1, Valtype.i32),
         [ Opcodes.i32_sub ],
 
-        ...length.setCachedI32(),
-        ...length.getCachedI32(),
+        ...(unusedValue() ? [] : [
+          ...length.setCachedI32(),
+          ...length.getCachedI32(),
+        ])
       ]),
 
       // load last element
-      ...length.getCachedI32(),
-      ...number(ValtypeSize[valtype], Valtype.i32),
-      [ Opcodes.i32_mul ],
+      ...(unusedValue() ? [] : [
+        ...length.getCachedI32(),
+        ...number(ValtypeSize[valtype], Valtype.i32),
+        [ Opcodes.i32_mul ],
 
-      ...pointer,
-      [ Opcodes.i32_add ],
+        ...pointer,
+        [ Opcodes.i32_add ],
 
-      [ Opcodes.load, Math.log2(ValtypeSize[valtype]) - 1, ...unsignedLEB128(ValtypeSize.i32) ]
+        [ Opcodes.load, Math.log2(ValtypeSize[valtype]) - 1, ...unsignedLEB128(ValtypeSize.i32) ]
+      ])
     ],
 
     shift: (pointer, length) => [
@@ -331,8 +344,8 @@ export const PrototypeFuncs = function() {
         ...number(0, Valtype.i32), // base 0 for store later
 
         ...wIndex,
-
         Opcodes.i32_to,
+
         ...number(ValtypeSize.i16, Valtype.i32),
         [ Opcodes.i32_mul ],
 
@@ -372,7 +385,7 @@ export const PrototypeFuncs = function() {
 
           ...(noUnlikelyChecks ? [] : [ [ Opcodes.i32_or ] ]),
           [ Opcodes.if, Blocktype.void ],
-          ...number(NaN),
+          ...number(valtype === 'i32' ? -1 : NaN),
           [ Opcodes.br, 1 ],
           [ Opcodes.end ],
 
@@ -472,8 +485,151 @@ export const PrototypeFuncs = function() {
   this[TYPES.string].at.returnType = TYPES.string;
   this[TYPES.string].charAt.returnType = TYPES.string;
   this[TYPES.string].charCodeAt.local = Valtype.i32;
+  this[TYPES.string].charCodeAt.noPointerCache = zeroChecks.charcodeat;
 
   this[TYPES.string].isWellFormed.local = Valtype.i32;
   this[TYPES.string].isWellFormed.local2 = Valtype.i32;
   this[TYPES.string].isWellFormed.returnType = TYPES.boolean;
+
+  if (Prefs.bytestring) {
+    this[TYPES._bytestring] = {
+      at: (pointer, length, wIndex, iTmp, _, arrayShell) => {
+        const [ newOut, newPointer ] = arrayShell(1, 'i8');
+
+        return [
+          // setup new/out array
+          ...newOut,
+          [ Opcodes.drop ],
+
+          ...number(0, Valtype.i32), // base 0 for store later
+
+          ...wIndex,
+          Opcodes.i32_to_u,
+          [ Opcodes.local_tee, iTmp ],
+
+          // if index < 0: access index + array length
+          ...number(0, Valtype.i32),
+          [ Opcodes.i32_lt_s ],
+          [ Opcodes.if, Blocktype.void ],
+          [ Opcodes.local_get, iTmp ],
+          ...length.getCachedI32(),
+          [ Opcodes.i32_add ],
+          [ Opcodes.local_set, iTmp ],
+          [ Opcodes.end ],
+
+          // if still < 0 or >= length: return undefined
+          [ Opcodes.local_get, iTmp ],
+          ...number(0, Valtype.i32),
+          [ Opcodes.i32_lt_s ],
+
+          [ Opcodes.local_get, iTmp ],
+          ...length.getCachedI32(),
+          [ Opcodes.i32_ge_s ],
+          [ Opcodes.i32_or ],
+
+          [ Opcodes.if, Blocktype.void ],
+          ...number(UNDEFINED),
+          [ Opcodes.br, 1 ],
+          [ Opcodes.end ],
+
+          [ Opcodes.local_get, iTmp ],
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+
+          // store to new string ind 0
+          [ Opcodes.i32_store8, 0, ...unsignedLEB128(newPointer + ValtypeSize.i32) ],
+
+          // return new string (pointer)
+          ...number(newPointer)
+        ];
+      },
+
+      // todo: out of bounds properly
+      charAt: (pointer, length, wIndex, _1, _2, arrayShell) => {
+        const [ newOut, newPointer ] = arrayShell(1, 'i8');
+
+        return [
+          // setup new/out array
+          ...newOut,
+          [ Opcodes.drop ],
+
+          ...number(0, Valtype.i32), // base 0 for store later
+
+          ...wIndex,
+          Opcodes.i32_to,
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+
+          // store to new string ind 0
+          [ Opcodes.i32_store8, 0, ...unsignedLEB128(newPointer + ValtypeSize.i32) ],
+
+          // return new string (page)
+          ...number(newPointer)
+        ];
+      },
+
+      charCodeAt: (pointer, length, wIndex, iTmp) => {
+        return [
+          ...wIndex,
+          Opcodes.i32_to,
+
+          ...(zeroChecks.charcodeat ? [] : [
+            [ Opcodes.local_set, iTmp ],
+
+            // index < 0
+            ...(noUnlikelyChecks ? [] : [
+              [ Opcodes.local_get, iTmp ],
+              ...number(0, Valtype.i32),
+              [ Opcodes.i32_lt_s ],
+            ]),
+
+            // index >= length
+            [ Opcodes.local_get, iTmp ],
+            ...length.getCachedI32(),
+            [ Opcodes.i32_ge_s ],
+
+            ...(noUnlikelyChecks ? [] : [ [ Opcodes.i32_or ] ]),
+            [ Opcodes.if, Blocktype.void ],
+            ...number(valtype === 'i32' ? -1 : NaN),
+            [ Opcodes.br, 1 ],
+            [ Opcodes.end ],
+
+            [ Opcodes.local_get, iTmp ],
+          ]),
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+          Opcodes.i32_from_u
+        ];
+      },
+
+      isWellFormed: () => {
+        return [
+          // we know it must be true as it is a bytestring lol
+          ...number(1)
+        ]
+      }
+    };
+
+    this[TYPES._bytestring].at.local = Valtype.i32;
+    this[TYPES._bytestring].at.returnType = TYPES._bytestring;
+    this[TYPES._bytestring].charAt.returnType = TYPES._bytestring;
+    this[TYPES._bytestring].charCodeAt.local = Valtype.i32;
+    this[TYPES._bytestring].charCodeAt.noPointerCache = zeroChecks.charcodeat;
+
+    this[TYPES._bytestring].isWellFormed.local = Valtype.i32;
+    this[TYPES._bytestring].isWellFormed.local2 = Valtype.i32;
+    this[TYPES._bytestring].isWellFormed.returnType = TYPES.boolean;
+  }
 };

package/compiler/sections.js

@@ -3,6 +3,7 @@ import { encodeVector, encodeString, encodeLocal, unsignedLEB128, signedLEB128 }
 import { number } from './embedding.js';
 import { importedFuncs } from './builtins.js';
 import { log } from "./log.js";
+import Prefs from './prefs.js';
 
 const createSection = (type, data) => [
   type,
@@ -26,12 +27,12 @@ export default (funcs, globals, tags, pages, data, flags) => {
 
   const optLevel = parseInt(process.argv.find(x => x.startsWith('-O'))?.[2] ?? 1);
 
-  const compileHints = process.argv.includes('-compile-hints');
+  const compileHints = Prefs.compileHints;
   if (compileHints) log.warning('sections', 'compile hints is V8 only w/ experimental arg! (you used -compile-hints)');
 
   const getType = (params, returns) => {
     const hash = `${params.join(',')}_${returns.join(',')}`;
-    if (optLog) log('sections', `getType(${JSON.stringify(params)}, ${JSON.stringify(returns)}) -> ${hash} | cache: ${typeCache[hash]}`);
+    if (Prefs.optLog) log('sections', `getType(${JSON.stringify(params)}, ${JSON.stringify(returns)}) -> ${hash} | cache: ${typeCache[hash]}`);
     if (optLevel >= 1 && typeCache[hash] !== undefined) return typeCache[hash];
 
     const type = [ FuncType, ...encodeVector(params), ...encodeVector(returns) ];
@@ -79,7 +80,7 @@ export default (funcs, globals, tags, pages, data, flags) => {
   }
   globalThis.importFuncs = importFuncs;
 
-  if (optLog) log('sections', `treeshake: using ${importFuncs.length}/${importedFuncs.length} imports`);
+  if (Prefs.optLog) log('sections', `treeshake: using ${importFuncs.length}/${importedFuncs.length} imports`);
 
   const importSection = importFuncs.length === 0 ? [] : createSection(
     Section.import,
@@ -95,7 +96,7 @@ export default (funcs, globals, tags, pages, data, flags) => {
   // https://github.com/WebAssembly/design/issues/1473#issuecomment-1431274746
   const chSection = !compileHints ? [] : customSection(
     'compilationHints',
-    // for now just do everything as optimise eager
+    // for now just do everything as optimize eager
     encodeVector(funcs.map(_ => chHint(0x02, 0x02, 0x02)))
   );
 
@@ -106,7 +107,7 @@ export default (funcs, globals, tags, pages, data, flags) => {
 
   const exports = funcs.filter(x => x.export).map((x, i) => [ ...encodeString(x.name === 'main' ? 'm' : x.name), ExportDesc.func, x.index ]);
 
-  if (process.argv.includes('-always-memory') && pages.size === 0) pages.set('-always-memory', 0);
+  if (Prefs.alwaysMemory && pages.size === 0) pages.set('-always-memory', 0);
   if (optLevel === 0) pages.set('O0 precaution', 0);
 
   const usesMemory = pages.size > 0;
@@ -150,7 +151,7 @@ export default (funcs, globals, tags, pages, data, flags) => {
 
       if (typeCount !== 0) localDecl.push(encodeLocal(typeCount, lastType));
 
-      return encodeVector([ ...encodeVector(localDecl), ...x.wasm.flat().filter(x => x <= 0xff), Opcodes.end ]);
+      return encodeVector([ ...encodeVector(localDecl), ...x.wasm.flat().filter(x => x != null && x <= 0xff), Opcodes.end ]);
     }))
   );
 
@@ -169,7 +170,7 @@ export default (funcs, globals, tags, pages, data, flags) => {
     unsignedLEB128(data.length)
   );
 
-  if (process.argv.includes('-sections')) console.log({
+  if (Prefs.sections) console.log({
     typeSection: typeSection.map(x => x.toString(16)),
     importSection: importSection.map(x => x.toString(16)),
     funcSection: funcSection.map(x => x.toString(16)),

package/compiler/wasmSpec.js

@@ -32,17 +32,17 @@ export const Opcodes = {
   throw: 0x08,
   rethrow: 0x09,
 
-  return: 0x0F,
+  end: 0x0b,
+  br: 0x0c,
+  br_if: 0x0d,
+  br_table: 0x0e,
+  return: 0x0f,
 
   call: 0x10,
   call_indirect: 0x11,
   return_call: 0x12,
   return_call_indirect: 0x13,
 
-  end: 0x0b,
-  br: 0x0c,
-  br_if: 0x0d,
-  call: 0x10,
   drop: 0x1a,
 
   local_get: 0x20,
@@ -56,15 +56,26 @@ export const Opcodes = {
   i64_load: 0x29,
   f64_load: 0x2b,
 
+  i32_load8_s: 0x2c,
+  i32_load8_u: 0x2d,
   i32_load16_s: 0x2e,
   i32_load16_u: 0x2f,
 
-  i32_store16: 0x3b,
+  i64_load8_s: 0x30,
+  i64_load8_u: 0x31,
+  i64_load16_s: 0x32,
+  i64_load16_u: 0x33,
 
   i32_store: 0x36,
   i64_store: 0x37,
   f64_store: 0x39,
 
+  i32_store8: 0x3a,
+  i32_store16: 0x3b,
+
+  i64_store8: 0x3c,
+  i64_store16: 0x3d,
+
   memory_grow: 0x40,
 
   i32_const: 0x41,
@@ -96,6 +107,8 @@ export const Opcodes = {
   i32_shl: 0x74,
   i32_shr_s: 0x75,
   i32_shr_u: 0x76,
+  i32_rotl: 0x77,
+  i32_rotr: 0x78,
 
   i64_eqz: 0x50,
   i64_eq: 0x51,
@@ -119,6 +132,7 @@ export const Opcodes = {
   i64_shr_s: 0x87,
   i64_shr_u: 0x88,
   i64_rotl: 0x89,
+  i64_rotr: 0x8a,
 
   f64_eq: 0x61,
   f64_ne: 0x62,