Add language: Mojo

Add a new programming language to Linguist, named Mojo, for the file
extension `.mojo`. You can learn more about Mojo at
https://docs.modular.com/mojo/.

Co-authored-by: Chris Lattner <lattner@users.noreply.github.com>

.gitmodules

@@ -881,6 +881,9 @@
 [submodule "vendor/grammars/mlir-grammar"]
 	path = vendor/grammars/mlir-grammar
 	url = https://github.com/jpienaar/mlir-grammar
+[submodule "vendor/grammars/mojo-syntax"]
+	path = vendor/grammars/mojo-syntax
+	url = https://github.com/modularml/mojo-syntax.git
 [submodule "vendor/grammars/monkey"]
 	path = vendor/grammars/monkey
 	url = https://github.com/gingerbeardman/monkey.tmbundle

grammars.yml

@@ -832,6 +832,8 @@ vendor/grammars/mint-vscode:
 - source.mint
 vendor/grammars/mlir-grammar:
 - source.mlir
+vendor/grammars/mojo-syntax:
+- source.mojo
 vendor/grammars/monkey:
 - source.monkey
 vendor/grammars/moonscript-tmbundle:

lib/linguist/heuristics.yml

@@ -458,6 +458,12 @@ disambiguations:
   - language: Modula-2
     pattern: '^\s*(?i:MODULE|END) [\w\.]+;'
   - language: [Linux Kernel Module, AMPL]
+- extensions: ['.mojo']
+  rules:
+  - language: Mojo
+    pattern: '^\s*(alias|def|from|fn|import|struct)\s'
+  - language: XML
+    pattern: '^\s*<\?xml'
 - extensions: ['.ms']
   rules:
   - language: Roff

lib/linguist/languages.yml

@@ -4277,6 +4277,14 @@ Module Management System:
   tm_scope: none
   ace_mode: text
   language_id: 235
+Mojo:
+  type: programming
+  color: "#ff4c1f"
+  extensions:
+  - ".mojo"
+  ace_mode: python
+  tm_scope: source.mojo
+  language_id: 1045019587
 Monkey:
   type: programming
   extensions:
@@ -7751,6 +7759,7 @@ XML:
   - ".mjml"
   - ".mm"
   - ".mod"
+  - ".mojo"
   - ".mxml"
   - ".natvis"
   - ".ncl"

samples/Mojo/Bool.mojo

@@ -0,0 +1,31 @@
+alias OurTrue = OurBool(__mlir_attr.`true`)
+alias OurFalse: OurBool = __mlir_attr.`false`
+
+
+@register_passable("trivial")
+struct OurBool:
+    var value: __mlir_type.i1
+
+    fn __init__() -> Self:
+        return OurFalse
+
+    fn __init__(value: __mlir_type.i1) -> Self:
+        return Self {value: value}
+
+    fn __bool__(self) -> Bool:
+        return Bool(self.value)
+
+    fn __mlir_i1__(self) -> __mlir_type.i1:
+        return self.value
+
+    fn __eq__(self, rhs: OurBool) -> Self:
+        let lhsIndex = __mlir_op.`index.casts`[_type : __mlir_type.index](self.value)
+        let rhsIndex = __mlir_op.`index.casts`[_type : __mlir_type.index](rhs.value)
+        return Self(
+            __mlir_op.`index.cmp`[pred : __mlir_attr.`#index<cmp_predicate eq>`](
+                lhsIndex, rhsIndex
+            )
+        )
+
+    fn __invert__(self) -> Self:
+        return OurFalse if self == OurTrue else OurTrue

samples/Mojo/Matmul.mojo

@@ -0,0 +1,152 @@
+from autotune import autotune, search
+from algorithm import parallelize, Static2DTileUnitFunc as Tile2DFunc, vectorize_unroll
+from benchmark import Benchmark
+from sys.intrinsics import strided_load
+from utils.list import VariadicList
+from math import div_ceil, min
+from memory import memset_zero
+from memory.unsafe import DTypePointer, Pointer
+from random import rand, random_float64
+from sys.info import simdwidthof
+from time import now
+
+
+struct Matrix:
+    var data: DTypePointer[DType.float32]
+    var rows: Int
+    var cols: Int
+
+    fn __init__(inout self, rows: Int, cols: Int):
+        self.data = DTypePointer[DType.float32].alloc(rows * cols)
+        rand(self.data, rows * cols)
+        self.rows = rows
+        self.cols = cols
+
+    fn __del__(owned self):
+        self.data.free()
+
+    fn zero(inout self):
+        memset_zero(self.data, self.rows * self.cols)
+
+    @always_inline
+    fn __getitem__(self, y: Int, x: Int) -> Float32:
+        return self.load[1](y, x)
+
+    @always_inline
+    fn load[nelts: Int](self, y: Int, x: Int) -> SIMD[DType.float32, nelts]:
+        return self.data.simd_load[nelts](y * self.cols + x)
+
+    @always_inline
+    fn __setitem__(self, y: Int, x: Int, val: Float32):
+        return self.store[1](y, x, val)
+
+    @always_inline
+    fn store[nelts: Int](self, y: Int, x: Int, val: SIMD[DType.float32, nelts]):
+        self.data.simd_store[nelts](y * self.cols + x, val)
+
+
+alias matmul_fn_sig_type = fn (Matrix, Matrix, Matrix) -> None
+
+
+# Perform 2D tiling on the iteration space defined by end_x and end_y.
+fn tile[tiled_fn: Tile2DFunc, tile_x: Int, tile_y: Int](end_x: Int, end_y: Int):
+    # Note: this assumes that ends are multiples of the tiles.
+    for y in range(0, end_y, tile_y):
+        for x in range(0, end_x, tile_x):
+            tiled_fn[tile_x, tile_y](x, y)
+
+
+alias nelts = simdwidthof[DType.float32]()  # The SIMD vector width.
+
+
+# Autotune the tile size used in the matmul.
+@adaptive
+fn matmul_autotune_impl(C: Matrix, A: Matrix, B: Matrix):
+    @parameter
+    fn calc_row(m: Int):
+        @parameter
+        fn calc_tile[tile_x: Int, tile_y: Int](x: Int, y: Int):
+            for k in range(y, y + tile_y):
+
+                @parameter
+                fn dot[
+                    nelts: Int,
+                ](n: Int):
+                    C.store[nelts](
+                        m,
+                        n + x,
+                        C.load[nelts](m, n + x) + A[m, k] * B.load[nelts](k, n + x),
+                    )
+
+                vectorize_unroll[nelts, tile_x // nelts, dot](tile_x)
+
+        # Instead of hardcoding to tile_size = 4, search for the fastest
+        # tile size by evaluting this function as tile size varies.
+        alias tile_size = autotune(1, 2, 4, 8, 16, 32)
+        tile[calc_tile, nelts * tile_size, tile_size](A.cols, C.cols)
+
+    parallelize[calc_row](C.rows)
+
+
+fn matmul_evaluator(funcs: Pointer[matmul_fn_sig_type], size: Int) -> Int:
+    print("matmul_evaluator, number of candidates: ", size)
+
+    let eval_begin: Int = now()
+
+    # This size is picked at random, in real code we could use a real size
+    # distribution here.
+    let M = 512
+    let N = 512
+    let K = 512
+    print("Optimizing for size:", M, "x", N, "x", K)
+
+    var best_idx: Int = -1
+    var best_time: Int = -1
+
+    alias eval_iterations = 10
+    alias eval_samples = 10
+
+    var C = Matrix(M, N)
+    var A = Matrix(M, K)
+    var B = Matrix(K, N)
+    let Cptr = Pointer[Matrix].address_of(C).address
+    let Aptr = Pointer[Matrix].address_of(A).address
+    let Bptr = Pointer[Matrix].address_of(B).address
+
+    # Find the function that's the fastest on the size we're optimizing for
+    for f_idx in range(size):
+        let func = funcs.load(f_idx)
+
+        @always_inline
+        @parameter
+        fn wrapper():
+            func(C, A, B)
+
+        let cur_time = Benchmark(1, 100_000, 500_000_000, 1000_000_000).run[wrapper]()
+
+        if best_idx < 0:
+            best_idx = f_idx
+            best_time = cur_time
+        if best_time > cur_time:
+            best_idx = f_idx
+            best_time = cur_time
+
+    let eval_end: Int = now()
+    # Prevent matrices from being destroyed before we finished benchmarking them.
+    _ = A.data
+    _ = B.data
+    _ = C.data
+    print("Time spent in matmul_evaluator, ms:", (eval_end - eval_begin) // 1000000)
+    print("Best candidate idx:", best_idx)
+    return best_idx
+
+
+fn matmul_autotune(C: Matrix, A: Matrix, B: Matrix):
+    alias best_impl: matmul_fn_sig_type
+    search[
+        matmul_fn_sig_type,
+        VariadicList(matmul_autotune_impl.__adaptive_set),
+        matmul_evaluator -> best_impl
+    ]()
+    # Run the best candidate
+    return best_impl(C, A, B)

samples/XML/Example.mojo

@@ -0,0 +1,3 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project name="Example" board="Mojo V3" language="Lucid">
+</project>

test/test_heuristics.rb

@@ -681,6 +681,13 @@ def test_mod_by_heuristics
     })
   end
 
+  def test_mojo_by_heuristics
+    assert_heuristics({
+      "Mojo" => all_fixtures("Mojo", "*.mojo"),
+      "XML" => all_fixtures("XML", "*.mojo"),
+    })
+  end
+
   def test_ms_by_heuristics
     assert_heuristics({
       "Roff" => all_fixtures("Roff", "*.ms"),

vendor/README.md

@@ -342,6 +342,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Modelica:** [BorisChumichev/modelicaSublimeTextPackage](https://github.com/BorisChumichev/modelicaSublimeTextPackage)
 - **Modula-2:** [harogaston/Sublime-Modula-2](https://github.com/harogaston/Sublime-Modula-2)
 - **Modula-3:** [newgrammars/m3](https://github.com/newgrammars/m3)
+- **Mojo:** [modularml/mojo-syntax](https://github.com/modularml/mojo-syntax)
 - **Monkey:** [gingerbeardman/monkey.tmbundle](https://github.com/gingerbeardman/monkey.tmbundle)
 - **Monkey C:** [ghisguth/vscode-monkey-c](https://github.com/ghisguth/vscode-monkey-c)
 - **MoonScript:** [leafo/moonscript-tmbundle](https://github.com/leafo/moonscript-tmbundle)

vendor/licenses/git_submodule/mojo-syntax.dep.yml

@@ -0,0 +1,33 @@
+---
+name: mojo-syntax
+version: 81cf73ef2d4a1b149d58b4e7fab2f1acf4edde2d
+type: git_submodule
+homepage: https://github.com/modularml/mojo-syntax.git
+license: mit
+licenses:
+- sources: LICENSE
+  text: |
+    The MIT License
+
+    Copyright (c) 2022-present Modular Inc.  https://www.modular.com
+    Copyright (c) 2015-present MagicStack Inc.  http://magic.io
+    Copyright (c) 2015-present Microsoft Corporation
+
+    Permission is hereby granted, free of charge, to any person obtaining a copy
+    of this software and associated documentation files (the "Software"), to deal
+    in the Software without restriction, including without limitation the rights
+    to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+    copies of the Software, and to permit persons to whom the Software is
+    furnished to do so, subject to the following conditions:
+
+    The above copyright notice and this permission notice shall be included in
+    all copies or substantial portions of the Software.
+
+    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+    AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+    LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+    OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+    THE SOFTWARE.
+notices: []