porffor 0.2.0-09999e8 → 0.2.0-15592d6

package/compiler/decompile.js

@@ -15,7 +15,7 @@ export default (wasm, name = '', ind = 0, locals = {}, params = [], returns = []
   if (name) out += `${makeSignature(params, returns)} ;; $${name} (${ind})\n`;
 
   const justLocals = Object.values(locals).sort((a, b) => a.idx - b.idx).slice(params.length);
-  if (justLocals.length > 0) out += `  local ${justLocals.map(x => invValtype[x.type]).join(' ')}\n`;
+  if (name && justLocals.length > 0) out += `  local ${justLocals.map(x => invValtype[x.type]).join(' ')}\n`;
 
   let i = -1, lastInst;
   let byte = 0;
@@ -32,7 +32,7 @@ export default (wasm, name = '', ind = 0, locals = {}, params = [], returns = []
       inst = [ [ inst[0], inst[1] ], ...inst.slice(2) ];
     }
 
-    if (inst[0] === Opcodes.end || inst[0] === Opcodes.else || inst[0] === Opcodes.catch_all) depth--;
+    if (depth > 0 && (inst[0] === Opcodes.end || inst[0] === Opcodes.else || inst[0] === Opcodes.catch_all)) depth--;
 
     out += ' '.repeat(Math.max(0, depth * 2));
 
@@ -119,7 +119,7 @@ export default (wasm, name = '', ind = 0, locals = {}, params = [], returns = []
 export const highlightAsm = asm => asm
   .replace(/(local|global|memory)\.[^\s]*/g, _ => `\x1B[31m${_}\x1B[0m`)
   .replace(/(i(8|16|32|64)x[0-9]+|v128)(\.[^\s]*)?/g, _ => `\x1B[34m${_}\x1B[0m`)
-  .replace(/[^m](i32|i64|f32|f64|drop)(\.[^\s]*)?/g, _ => `${_[0]}\x1B[36m${_.slice(1)}\x1B[0m`)
+  .replace(/(i32|i64|f32|f64|drop)(\.[^\s]*)?/g, _ => `\x1B[36m${_}\x1B[0m`)
   .replace(/(return_call|call|br_if|br|return|rethrow|throw)/g, _ => `\x1B[35m${_}\x1B[0m`)
   .replace(/(block|loop|if|end|else|try|catch_all|catch|delegate)/g, _ => `\x1B[95m${_}\x1B[0m`)
   .replace(/unreachable/g, _ => `\x1B[91m${_}\x1B[0m`)

package/compiler/generated_builtins.js

@@ -0,0 +1,3 @@
+
+export const BuiltinFuncs = function() {
+};

package/compiler/index.js

@@ -4,7 +4,6 @@ import codeGen from './codeGen.js';
 import opt from './opt.js';
 import produceSections from './sections.js';
 import decompile from './decompile.js';
-import { BuiltinPreludes } from './builtins.js';
 import toc from './2c.js';
 
 globalThis.decompile = decompile;
@@ -37,10 +36,6 @@ export default (code, flags) => {
   globalThis.allocLog = process.argv.includes('-alloc-log');
   globalThis.regexLog = process.argv.includes('-regex-log');
 
-  for (const x in BuiltinPreludes) {
-    if (code.indexOf(x + '(') !== -1) code = BuiltinPreludes[x] + code;
-  }
-
   const t0 = performance.now();
   const program = parse(code, flags);
   if (flags.includes('info')) console.log(`1. parsed in ${(performance.now() - t0).toFixed(2)}ms`);
@@ -52,7 +47,7 @@ export default (code, flags) => {
   if (process.argv.includes('-funcs')) logFuncs(funcs, globals, exceptions);
 
   const t2 = performance.now();
-  opt(funcs, globals, pages);
+  opt(funcs, globals, pages, tags, exceptions);
   if (flags.includes('info')) console.log(`3. optimized code in ${(performance.now() - t2).toFixed(2)}ms`);
 
   if (process.argv.includes('-opt-funcs')) logFuncs(funcs, globals, exceptions);
@@ -68,11 +63,17 @@ export default (code, flags) => {
     console.log([...pages.keys()].map(x => `\x1B[36m - ${x}\x1B[0m`).join('\n') + '\n');
   }
 
-  const out = { wasm: sections, funcs, globals, tags, exceptions, pages };
+  const out = { wasm: sections, funcs, globals, tags, exceptions, pages, data };
 
   const target = getArg('target') ?? getArg('t') ?? 'wasm';
   const outFile = getArg('o');
 
+  if (target === 'wasm' && outFile) {
+    writeFileSync(outFile, Buffer.from(sections));
+
+    if (process.version) process.exit();
+  }
+
   if (target === 'c') {
     const c = toc(out);
     out.c = c;
@@ -87,11 +88,16 @@ export default (code, flags) => {
   }
 
   if (target === 'native') {
-    const compiler = getArg('compiler') ?? 'clang';
+    let compiler = getArg('compiler') ?? 'clang';
     const cO = getArg('cO') ?? 'Ofast';
 
+    if (compiler === 'zig') compiler = [ 'zig', 'cc' ];
+      else compiler = [ compiler ];
+
     const tmpfile = 'tmp.c';
-    const args = [ compiler, tmpfile, '-o', outFile ?? (process.platform === 'win32' ? 'out.exe' : 'out'), '-' + cO, '-march=native' ];
+    // const args = [ compiler, tmpfile, '-o', outFile ?? (process.platform === 'win32' ? 'out.exe' : 'out'), '-' + cO, '-march=native', '-s', '-fno-unwind-tables', '-fno-asynchronous-unwind-tables', '-ffunction-sections', '-fdata-sections', '-Wl', '-fno-ident', '-fno-exceptions', '-ffast-math' ];
+    // const args = [ ...compiler, tmpfile, '-o', outFile ?? (process.platform === 'win32' ? 'out.exe' : 'out'), '-' + cO, '-march=native', '-s', '-ffast-math', '-fno-exceptions', '-target', 'x86_64-linux' ];
+    const args = [ ...compiler, tmpfile, '-o', outFile ?? (process.platform === 'win32' ? 'out.exe' : 'out'), '-' + cO, '-march=native', '-s', '-ffast-math', '-fno-exceptions' ];
 
     const c = toc(out);
     writeFileSync(tmpfile, c);

package/compiler/opt.js

@@ -11,7 +11,7 @@ const performWasmOp = (op, a, b) => {
   }
 };
 
-export default (funcs, globals, pages) => {
+export default (funcs, globals, pages, tags, exceptions) => {
   const optLevel = parseInt(process.argv.find(x => x.startsWith('-O'))?.[2] ?? 1);
   if (optLevel === 0) return;
 
@@ -99,6 +99,9 @@ export default (funcs, globals, pages) => {
 
   if (process.argv.includes('-opt-inline-only')) return;
 
+  const tagUse = tags.reduce((acc, x) => { acc[x.idx] = 0; return acc; }, {});
+  const exceptionUse = exceptions.reduce((acc, _, i) => { acc[i] = 0; return acc; }, {});
+
   // wasm transform pass
   for (const f of funcs) {
     const wasm = f.wasm;
@@ -127,6 +130,13 @@ export default (funcs, globals, pages) => {
         if (inst[0] === Opcodes.local_get) getCount[inst[1]]++;
         if (inst[0] === Opcodes.local_set || inst[0] === Opcodes.local_tee) setCount[inst[1]]++;
 
+        if (inst[0] === Opcodes.throw) {
+          tagUse[inst[1]]++;
+
+          const exceptId = read_signedLEB128(wasm[i - 1].slice(1));
+          exceptionUse[exceptId]++;
+        }
+
         if (inst[0] === Opcodes.block) {
           // remove unneeded blocks (no brs inside)
           // block
@@ -143,7 +153,7 @@ export default (funcs, globals, pages) => {
               depth--;
               if (depth <= 0) break;
             }
-            if (op === Opcodes.br || op === Opcodes.br_if) {
+            if (op === Opcodes.br || op === Opcodes.br_if || op === Opcodes.br_table) {
               hasBranch = true;
               break;
             }
@@ -188,6 +198,7 @@ export default (funcs, globals, pages) => {
           let missing = false;
           if (type === 'Array') missing = !pages.hasArray;
           if (type === 'String') missing = !pages.hasString;
+          if (type === 'ByteString') missing = !pages.hasByteString;
 
           if (missing) {
             let j = i, depth = 0;
@@ -235,7 +246,7 @@ export default (funcs, globals, pages) => {
         }
 
         // remove setting last type if it is never gotten
-        if (!f.gotLastType && inst[0] === Opcodes.local_set && inst[1] === lastType.idx) {
+        if (!f.gotLastType && inst[0] === Opcodes.local_set && inst[1] === lastType?.idx) {
           // replace this inst with drop
           wasm.splice(i, 1, [ Opcodes.drop ]); // remove this and last inst
           if (i > 0) i--;
@@ -541,5 +552,18 @@ export default (funcs, globals, pages) => {
     }
   }
 
+  for (const x in tagUse) {
+    if (tagUse[x] === 0) {
+      const el = tags.find(y => y.idx === x);
+      tags.splice(tags.indexOf(el), 1);
+    }
+  }
+
+  for (const x of Object.keys(exceptionUse).sort((a, b) => b - a)) {
+    if (exceptionUse[x] === 0) {
+      exceptions.splice(+x, 1);
+    }
+  }
+
   // return funcs;
 };

package/compiler/precompile.js

@@ -0,0 +1,79 @@
+import fs from 'node:fs';
+import { join } from 'node:path';
+
+import { fileURLToPath } from 'node:url';
+const __dirname = fileURLToPath(new URL('.', import.meta.url));
+
+// 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);
+
+  // globalThis.optLog = process.argv.includes('-opt-log');
+  // globalThis.codeLog = process.argv.includes('-code-log');
+  // globalThis.allocLog = process.argv.includes('-alloc-log');
+  // globalThis.regexLog = process.argv.includes('-regex-log');
+
+  // 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?_=${Date.now()}`)).default;
+
+  let { funcs, globals, data, exceptions } = porfCompile(source, ['module']);
+
+  funcs = funcs.filter(x => x.export);
+  for (const x of funcs) {
+    if (x.data) x.data = x.data.map(x => data[x]);
+    if (x.exceptions) x.exceptions = x.exceptions.map(x => {
+      const obj = exceptions[x];
+      if (obj) obj.exceptId = x;
+      return obj;
+    }).filter(x => x);
+  }
+
+  _funcs.push(...funcs);
+  _globals.push(...Object.values(globals));
+};
+
+const precompile = async () => {
+  const dir = join(__dirname, 'builtins');
+
+  let funcs = [], globals = [];
+  for (const file of fs.readdirSync(dir)) {
+    if (file.endsWith('.d.ts')) continue;
+    await compile(join(dir, file), [ funcs, globals ]);
+  }
+
+  // todo: globals, exceptions, pages per func
+
+  return `// autogenerated by precompile.js
+
+export const BuiltinFuncs = function() {
+${funcs.map(x => `  this.${x.name} = {
+    wasm: ${JSON.stringify(x.wasm)},
+    params: ${JSON.stringify(x.params)},
+    typedParams: true,
+    returns: ${JSON.stringify(x.returns)},
+    typedReturns: true,
+    locals: ${JSON.stringify(Object.values(x.locals).slice(x.params.length * 2).map(x => x.type))},
+${x.pages && x.pages.size > 0 ? `    pages: ${JSON.stringify(Object.fromEntries(x.pages.entries()))},` : ''}
+${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')}
+}`;
+};
+
+console.log(await precompile());

package/compiler/prototype.js

@@ -16,7 +16,8 @@ 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
@@ -71,7 +72,7 @@ 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 +93,28 @@ 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 +126,23 @@ 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 +342,8 @@ 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 ],
 
@@ -472,8 +483,151 @@ 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 (process.argv.includes('-bytestring')) {
+    this[TYPES._bytestring] = {
+      at: (pointer, length, wIndex, iTmp, _, arrayShell) => {
+        const [ newOut, newPointer ] = arrayShell(1, 'i16');
+
+        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, 'i16');
+
+        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(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

@@ -95,7 +95,7 @@ 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)))
   );
 
@@ -150,7 +150,7 @@ 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 ]);
     }))
   );
 

package/compiler/wasmSpec.js

@@ -32,8 +32,6 @@ export const Opcodes = {
   throw: 0x08,
   rethrow: 0x09,
 
-  return: 0x0F,
-
   call: 0x10,
   call_indirect: 0x11,
   return_call: 0x12,
@@ -42,7 +40,10 @@ export const Opcodes = {
   end: 0x0b,
   br: 0x0c,
   br_if: 0x0d,
+  br_table: 0x0e,
+  return: 0x0f,
   call: 0x10,
+
   drop: 0x1a,
 
   local_get: 0x20,
@@ -56,9 +57,12 @@ 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_store8: 0x3a,
   i32_store16: 0x3b,
 
   i32_store: 0x36,