ninetoothed 0.1.0__tar.gz

ninetoothed-0.1.0/.github/workflows/ruff.yml

@@ -0,0 +1,11 @@
+name: Ruff
+on: [push, pull_request]
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1
+      - uses: chartboost/ruff-action@v1
+        with:
+          args: format --check

ninetoothed-0.1.0/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

ninetoothed-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

ninetoothed-0.1.0/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.3
+Name: ninetoothed
+Version: 0.1.0
+Summary: A domain-specific language based on Triton but providing higher-level abstraction.
+Project-URL: Homepage, https://github.com/InfiniTensor/ninetoothed
+Project-URL: Issues, https://github.com/InfiniTensor/ninetoothed/issues
+Author-email: Jiacheng Huang <huangjiacheng0709@outlook.com>
+License-File: LICENSE
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# Nine-Toothed
+
+A domain-specific language based on Triton but providing higher-level abstraction.
+
+**Read this in other languages: [English](README.md), [简体中文](docs/README.zh.md).**

ninetoothed-0.1.0/README.md

@@ -0,0 +1,5 @@
+# Nine-Toothed
+
+A domain-specific language based on Triton but providing higher-level abstraction.
+
+**Read this in other languages: [English](README.md), [简体中文](docs/README.zh.md).**

ninetoothed-0.1.0/docs/README.zh.md

@@ -0,0 +1,72 @@
+# 九齿
+
+一种基于 Triton 但提供更高层抽象的领域特定语言（DSL）。
+
+**其他语言版本: [English](../README.md)、[简体中文](README.zh.md)。**
+
+## 安装
+
+由于现在 `ninetoothed` 还没有进入到 PyPI，我们需要手动 `git clone` 本仓库，再 `pip install`。
+
+```shell
+git clone https://github.com/InfiniTensor/ninetoothed.git
+pip install ./ninetoothed
+```
+
+成功运行完以上两个命令之后，`ninetoothed` 就被安装好了。需要注意的是，我们目前还没有加入任何的依赖管理，所以如果想要运行 Triton 核函数，那么最起码应该再安装 Triton。
+
+```shell
+pip install triton
+```
+
+其余包可以根据需要自行安装，如 `torch`、`matplotlib`、`pandas` 等。
+
+## 使用
+
+目前，我们可以通过 `ninetoothed` 包当中的 `Tensor` 和 `Symbol` 类，进行 `tile` 和 `expand` 等元操作，从而简单地构建核函数。下面，我们将使用这些内容构建出向量加法和矩阵乘法核函数。
+
+### 向量加法
+
+```python
+BLOCK_SIZE = Symbol("BLOCK_SIZE", meta=True)
+
+@ninetoothed.jit
+def add_kernel(
+    x: Tensor(1).tile((BLOCK_SIZE,)),
+    y: Tensor(1).tile((BLOCK_SIZE,)),
+    z: Tensor(1).tile((BLOCK_SIZE,)),
+):
+    z = x + y
+```
+
+在这段代码当中，我们首先定义了 `BLOCK_SIZE`，它是一个 `Symbol`，我们可以把 `"BLOCK_SIZE"` 理解成它的名字。我们可以看到 `meta` 被设成了 `True`，这是在告诉编译器，它是一个元参数，可以由编译器决定它的取值。之后出现的 `Tensor(1)` 则是在构造一个一维的张量（向量），`Tensor(1).tile((BLOCK_SIZE,))` 的意思就是说，我们想要构造一个向量，并且把它分成大小为 `BLOCK_SIZE` 的块。假设这个向量的大小为 `8192`，而 `BLOCK_SIZE` 是 `1024`，那么这个向量就会被分成 `8` 块，每一块的大小都是 `1024`。
+
+我们通过类型标注的方式，告诉了编译器，我们将会有三个参数张量，并且每个参数张量，都会被按照这样的方式分块，而 `x`、`y`、`z` 就是被分成的块。这一点很重要，我们要意识到，`x`、`y`、`z` 是被分成的块，而不是被分块的张量本身，并且函数体当中的 `x`、`y`、`z` 也都是被分成的块。剩下的就很好理解了（也就剩下 `z = x + y` 一行了，哈哈哈），我们把每一块 `x` 和 `y` 相加，放到了 `z` 中，由于参数张量被分成的每一块都被执行了这样的操作，因此即便对于整体而言，加法也被完成了。
+
+### 矩阵乘法
+
+```python
+BLOCK_SIZE_M = Symbol("BLOCK_SIZE_M", meta=True)
+BLOCK_SIZE_N = Symbol("BLOCK_SIZE_N", meta=True)
+BLOCK_SIZE_K = Symbol("BLOCK_SIZE_K", meta=True)
+
+a_tiled = Tensor(2).tile((BLOCK_SIZE_M, BLOCK_SIZE_K)).tile((1, -1))
+b_tiled = Tensor(2).tile((BLOCK_SIZE_K, BLOCK_SIZE_N)).tile((-1, 1))
+c_tiled = Tensor(2).tile((BLOCK_SIZE_M, BLOCK_SIZE_N))
+
+a_tiled = a_tiled.expand((-1, c_tiled.shape[1]))
+b_tiled = b_tiled.expand((c_tiled.shape[0], -1))
+
+@ninetoothed.jit
+def matmul_kernel(a: a_tiled, b: b_tiled, c: c_tiled):
+    accumulator = ninetoothed.language.zeros(
+        c.shape, dtype=ninetoothed.language.float32
+    )
+    for k in range(a.shape[1]):
+        accumulator = ninetoothed.language.dot(a[0, k], b[k, 0], accumulator)
+    c = accumulator.to(ninetoothed.language.float16)
+```
+
+对于矩阵乘法来说，我们也有三个参数张量，但是分块的方式肯定比向量加法要复杂一些。我们将三个矩阵分别记作 A、B、C，其中 A 和 B 为输入，C 为输出。其中 C 的分块操作很简单，我们只需要按照行和列，将其分成大小为 `(BLOCK_SIZE_M, BLOCK_SIZE_N)` 的块即可，这样只要每个这样的块都算出了结果，整个 C 也就都算出了结果。那么该如何分 A 和 B 呢？答案是再引入一个元参数 `BLOCK_SIZE_K`，这样我们就可以把 A 分成 `(BLOCK_SIZE_M, BLOCK_SIZE_K)` 大小的块，把 B 分成 `(BLOCK_SIZE_K, BLOCK_SIZE_N)` 的块。但是对于矩阵乘法，A 和 B 并不是块块对应，而是需要对应 A 的每一行和 B 的每一列，所以我们还需要继续 `tile`，把 A 和 B 进一步分成以行为单位和以列为单位的块。到目前为止，我们有了一堆 A 的行块和 B 的列块，但是对于每一个 A 的行块，我们都要对应 B 的每一个列块。这个时候，我们就需要进行 `expand` 了，我们把 A 的行块沿着列 `expand` 成 C 的列数那么多列，把 B 的列块沿着行 `expand` 成 C 的行数那么多行。这样，我们就成功地将 A、B、C 三者都分好了块，并且对于每一个 C 的块，我们都有对应好的 A 的行块和 B 的列块。
+
+对应好了分块，后续的部分就简单多了。在函数体当中，我们定义了一个 `accumulator`，用于累加中间结果，之后就遍历了对应好的 A 的行块和 B 的列块，并且把他们相乘的结果累加到了 `accumulator` 当中，最后再将 `accumulator` 放到了对应的 C 的分块当中。由于参数张量被分成的每一块都被执行了这样的操作，因此即便对于整体而言，乘法也被完成了。

ninetoothed-0.1.0/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "ninetoothed"
+version = "0.1.0"
+authors = [{ name = "Jiacheng Huang", email = "huangjiacheng0709@outlook.com" }]
+description = "A domain-specific language based on Triton but providing higher-level abstraction."
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+Homepage = "https://github.com/InfiniTensor/ninetoothed"
+Issues = "https://github.com/InfiniTensor/ninetoothed/issues"

ninetoothed-0.1.0/src/ninetoothed/__init__.py

@@ -0,0 +1,5 @@
+from ninetoothed.jit import jit
+from ninetoothed.symbol import Symbol
+from ninetoothed.tensor import Tensor
+
+__all__ = ["Symbol", "Tensor", "jit"]

ninetoothed-0.1.0/src/ninetoothed/jit.py

@@ -0,0 +1,319 @@
+import ast
+import functools
+import inspect
+import itertools
+import math
+import tempfile
+import textwrap
+
+from ninetoothed.language import attribute, call
+from ninetoothed.symbol import Symbol
+from ninetoothed.tensor import Tensor
+from ninetoothed.torchifier import Torchifier
+
+
+class CodeGenerator(ast.NodeTransformer):
+    def __init__(self, context):
+        super().__init__()
+
+        self._context = context
+
+        self._args = list(self._context.values())
+
+        self._POWER_OF_TWOS = tuple(2**n for n in range(5, 11))
+
+        self._MIN_PRODUCT = 2**10
+
+        self._MAX_PRODUCT = 2**20
+
+    def visit_Module(self, node):
+        self.generic_visit(node)
+
+        node.body.append(self._launch)
+
+        return node
+
+    def visit_FunctionDef(self, node):
+        self._func_def = node
+
+        self.generic_visit(node)
+
+        return node
+
+    def visit_arguments(self, node):
+        self.generic_visit(node)
+
+        names_of_args = [arg.names() - {"ninetoothed"} for arg in self._args]
+        names = functools.reduce(lambda x, y: x | y, names_of_args)
+        meta_names = {name for name in names if Symbol.is_meta(name)}
+        non_meta_names = {name for name in names if name not in meta_names}
+
+        node.args = [
+            ast.arg(arg=name)
+            if not Symbol.is_constexpr(name)
+            else ast.arg(arg=name, annotation=attribute("constexpr"))
+            for name in non_meta_names
+        ] + [
+            ast.arg(arg=name, annotation=attribute("constexpr").node)
+            for name in meta_names
+        ]
+
+        autotune = self._generate_autotune(non_meta_names, meta_names)
+        self._func_def.decorator_list.insert(0, autotune)
+
+        self._launch = self._generate_launch(non_meta_names, meta_names)
+
+        return node
+
+    def visit_Subscript(self, node):
+        if (
+            isinstance(node.value, ast.Name)
+            and node.value.id in self._context
+            and isinstance(node.ctx, ast.Load)
+        ):
+            value = self._context[node.value.id]
+
+            if isinstance(value, Tensor):
+                if isinstance(node.slice, ast.Tuple):
+                    indices = value.indices() + tuple(node.slice.elts)
+                else:
+                    indices = value.indices() + (node.slice,)
+                offsets = value.offsets(indices)
+                pointers = value.pointers(offsets)
+
+                return call("load", pointers).node
+
+        self.generic_visit(node)
+
+        return node
+
+    def visit_Attribute(self, node):
+        if isinstance(node.value, ast.Name) and node.value.id in self._context:
+            value = self._context[node.value.id]
+
+            if isinstance(value, Tensor):
+                inner = value.dtype
+
+                return Symbol(inner.__dict__[node.attr]).node
+
+        self.generic_visit(node)
+
+        return node
+
+    def visit_Name(self, node):
+        self.generic_visit(node)
+
+        if node.id in self._context and isinstance(node.ctx, ast.Load):
+            return call("load", self._context[node.id].pointers().node).node
+
+        return node
+
+    def visit_Assign(self, node):
+        if len(node.targets) == 1:
+            target = node.targets[0]
+
+            if isinstance(target, ast.Name) and target.id in self._context:
+                self.generic_visit(node)
+
+                return ast.Expr(
+                    call(
+                        "store",
+                        self._context[target.id].pointers().node,
+                        node.value,
+                    ).node
+                )
+            elif (
+                isinstance(target, ast.Subscript)
+                and isinstance(target.value, ast.Name)
+                and target.value.id in self._context
+                and isinstance(target.ctx, ast.Store)
+            ):
+                value = self._context[target.value.id]
+
+                if isinstance(value, Tensor):
+                    self.generic_visit(node)
+
+                    indices = value.indices() + tuple(
+                        target.slice.elts
+                        if isinstance(target.slice, ast.Tuple)
+                        else target.slice
+                    )
+                    offsets = value.offsets(indices)
+                    pointers = value.pointers(offsets)
+
+                    return ast.Expr(
+                        call(
+                            "store",
+                            pointers.node,
+                            node.value,
+                        ).node
+                    )
+
+        self.generic_visit(node)
+
+        return node
+
+    def _generate_autotune(self, params, meta):
+        configs = [
+            ast.Call(
+                func=ast.Attribute(
+                    value=ast.Name(id="ninetoothed", ctx=ast.Load()),
+                    attr="Config",
+                    ctx=ast.Load(),
+                ),
+                args=[
+                    ast.Dict(
+                        keys=[ast.Constant(value=param) for param in meta],
+                        values=[ast.Constant(value=value) for value in values],
+                    )
+                ],
+                keywords=[],
+            )
+            for values in itertools.product(self._POWER_OF_TWOS, repeat=len(meta))
+            if self._MIN_PRODUCT <= math.prod(values) <= self._MAX_PRODUCT
+        ]
+
+        return ast.Call(
+            func=ast.Attribute(
+                value=ast.Name(id="ninetoothed", ctx=ast.Load()),
+                attr="autotune",
+                ctx=ast.Load(),
+            ),
+            args=[],
+            keywords=[
+                ast.keyword(
+                    arg="configs",
+                    value=ast.List(
+                        elts=configs,
+                        ctx=ast.Load(),
+                    ),
+                ),
+                ast.keyword(
+                    arg="key",
+                    value=ast.List(
+                        elts=[
+                            ast.Constant(value=param)
+                            for param in params
+                            if not Tensor.is_pointer(param)
+                        ],
+                        ctx=ast.Load(),
+                    ),
+                ),
+            ],
+        )
+
+    def _generate_launch(self, params, meta):
+        launch = ast.FunctionDef(
+            name=f"launch_{self._func_def.name}",
+            args=ast.arguments(
+                posonlyargs=[],
+                args=[ast.arg(arg.name) for arg in self._args],
+                kwonlyargs=[],
+                defaults=[],
+            ),
+            body=[
+                ast.Expr(
+                    ast.Call(
+                        func=ast.Subscript(
+                            value=ast.Name(id=self._func_def.name, ctx=ast.Load()),
+                            slice=self._generate_grid(),
+                            ctx=ast.Load(),
+                        ),
+                        args=[ast.Name(id=param, ctx=ast.Load()) for param in params],
+                        keywords=[],
+                    )
+                )
+            ],
+            decorator_list=[],
+        )
+
+        class MetaEncloser(ast.NodeTransformer):
+            def __init__(self, meta):
+                self._meta = meta
+
+            def visit_Name(self, node):
+                self.generic_visit(node)
+
+                if node.id in self._meta:
+                    return ast.Subscript(
+                        value=ast.Name(id="meta", ctx=ast.Load()),
+                        slice=ast.Constant(value=node.id),
+                        ctx=ast.Load(),
+                    )
+
+                return node
+
+        MetaEncloser(meta).visit(launch)
+
+        Torchifier().visit(launch)
+
+        return launch
+
+    def _generate_grid(self):
+        num_elements = functools.reduce(lambda x, y: x * y, self._args[0].shape)
+
+        return ast.parse(f"lambda meta: ({num_elements},)", mode="eval").body
+
+
+class Tritonizer(ast.NodeTransformer):
+    def visit_Module(self, node):
+        self.generic_visit(node)
+
+        node.body.insert(0, ast.Import(names=[ast.alias(name="triton.language")]))
+        node.body.insert(0, ast.Import(names=[ast.alias(name="triton")]))
+
+        return node
+
+    def visit_Name(self, node):
+        self.generic_visit(node)
+
+        if node.id == "ninetoothed":
+            node.id = "triton"
+
+        return node
+
+    def visit_Call(self, node):
+        self.generic_visit(node)
+
+        if (
+            isinstance(node.func, ast.Attribute)
+            and isinstance(node.func.value, ast.Name)
+            and node.func.value.id == "triton"
+            and node.func.attr == "jit"
+        ):
+            return ast.Attribute(
+                value=ast.Name(id="triton", ctx=ast.Load()), attr="jit", ctx=ast.Load()
+            )
+
+        return node
+
+
+def jit(func):
+    source = textwrap.dedent(inspect.getsource(func))
+    tree = ast.parse(source)
+
+    CodeGenerator(func.__annotations__).visit(tree)
+    Tritonizer().visit(tree)
+    ast.fix_missing_locations(tree)
+
+    unparsed = ast.unparse(tree).replace("None:", ":").replace(":None", ":")
+
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".py") as temp_file:
+        temp_file.write(unparsed.encode("utf-8"))
+        temp_file_name = temp_file.name
+
+    with open(temp_file_name, "r") as temp_file:
+        code = compile(source=temp_file.read(), filename=temp_file_name, mode="exec")
+
+    namespace = {}
+    exec(code, namespace)
+
+    class Handle:
+        def __init__(self, kernel, launch):
+            self._kernel = kernel
+            self._launch = launch
+
+        def __call__(self, *args, **kwargs):
+            return self._launch(*args, **kwargs)
+
+    return Handle(namespace[func.__name__], namespace[f"launch_{func.__name__}"])

ninetoothed-0.1.0/src/ninetoothed/language.py

@@ -0,0 +1,19 @@
+import ast
+
+from ninetoothed.symbol import Symbol
+
+LANGUAGE = "ninetoothed.language"
+
+
+def call(func, *args, **kwargs):
+    return Symbol(
+        ast.Call(
+            func=attribute(func).node,
+            args=[Symbol(arg).node for arg in args],
+            keywords=[(kwarg, Symbol(kwargs[kwarg]).node) for kwarg in kwargs],
+        )
+    )
+
+
+def attribute(attr):
+    return Symbol(ast.parse(f"{LANGUAGE}.{attr}", mode="eval").body)

ninetoothed-0.1.0/src/ninetoothed/symbol.py

@@ -0,0 +1,109 @@
+import ast
+import inspect
+import types
+
+
+class Symbol:
+    def __init__(self, expr, constexpr=None, meta=None):
+        if isinstance(expr, type(self)):
+            self._node = expr._node
+            return
+
+        if isinstance(expr, ast.AST):
+            self._node = expr
+            return
+
+        if isinstance(expr, types.CodeType):
+            expr = inspect.getsource(expr)
+
+        if not isinstance(expr, str):
+            expr = str(expr)
+
+        self._node = ast.parse(expr, mode="eval").body
+
+        if (constexpr or meta) and not isinstance(self._node, ast.Name):
+            raise ValueError("`constexpr` and `meta` are properties of name symbols.")
+
+        if meta:
+            if constexpr is False:
+                raise ValueError("Non-constexpr meta symbol is not supported.")
+
+            self._node.id = type(self)._create_meta(self._node.id)
+
+        if constexpr:
+            self._node.id = type(self)._create_constexpr(self._node.id)
+
+    def __add__(self, other):
+        return type(self)(
+            ast.BinOp(left=self._node, op=ast.Add(), right=type(self)(other)._node)
+        )
+
+    def __radd__(self, other):
+        return self.__add__(other)
+
+    def __mul__(self, other):
+        return type(self)(
+            ast.BinOp(left=self._node, op=ast.Mult(), right=type(self)(other)._node)
+        )
+
+    def __rmul__(self, other):
+        return self.__mul__(other)
+
+    def __floordiv__(self, other):
+        return type(self)(
+            ast.BinOp(left=self._node, op=ast.FloorDiv(), right=type(self)(other)._node)
+        )
+
+    def __mod__(self, other):
+        return type(self)(
+            ast.BinOp(left=self._node, op=ast.Mod(), right=type(self)(other)._node)
+        )
+
+    def __getitem__(self, key):
+        return type(self)(ast.Subscript(value=self._node, slice=type(self)(key)._node))
+
+    def __repr__(self):
+        return ast.unparse(self._node)
+
+    def names(self):
+        class NameCollector(ast.NodeVisitor):
+            def __init__(self):
+                self.names = set()
+
+            def visit_Name(self, node):
+                self.generic_visit(node)
+
+                self.names.add(node.id)
+
+        name_collector = NameCollector()
+
+        name_collector.visit(self._node)
+
+        return name_collector.names
+
+    @property
+    def node(self):
+        class SliceSimplifier(ast.NodeTransformer):
+            def visit_Call(self, node):
+                if isinstance(node.func, ast.Name) and node.func.id == "slice":
+                    return ast.Slice(*node.args)
+
+                return node
+
+        return SliceSimplifier().visit(self._node)
+
+    @staticmethod
+    def is_constexpr(name):
+        return name.startswith("_ninetoothed_constexpr_") or Symbol.is_meta(name)
+
+    @staticmethod
+    def is_meta(name):
+        return name.startswith("_ninetoothed_meta_")
+
+    @staticmethod
+    def _create_constexpr(name):
+        return f"_ninetoothed_constexpr_{name}"
+
+    @staticmethod
+    def _create_meta(name):
+        return f"_ninetoothed_meta_{name}"

ninetoothed-0.1.0/src/ninetoothed/tensor.py

@@ -0,0 +1,165 @@
+import itertools
+
+from ninetoothed.language import call
+from ninetoothed.symbol import Symbol
+
+
+class Tensor:
+    num_instances = 0
+
+    def __init__(self, ndim=None, shape=None, dtype=None, strides=None, name=None):
+        type(self).num_instances += 1
+
+        self.dtype = dtype
+
+        if name is not None:
+            self.name = name
+        else:
+            self.name = f"tensor_{type(self).num_instances}"
+
+        if ndim is not None:
+            self.shape = [Symbol(f"{self.name}_size_{i}") for i in range(ndim)]
+            self.strides = [Symbol(f"{self.name}_stride_{i}") for i in range(ndim)]
+        else:
+            self.shape = shape
+
+            if strides is not None:
+                self.strides = strides
+            else:
+                self.strides = self._calculate_default_strides(shape)
+
+    def tile(self, tile_shape, tile_strides=None):
+        if tile_strides is None:
+            tile_strides = [1 for _ in tile_shape]
+
+        outer_shape = []
+        outer_strides = []
+        inner_shape = []
+        inner_strides = []
+
+        for size, stride, tile_size, tile_stride in zip(
+            self.shape, self.strides, tile_shape, tile_strides
+        ):
+            if tile_size == -1:
+                tile_size = size
+
+            new_size = call("cdiv", size, tile_size)
+            outer_shape.append(new_size)
+
+            new_stride = call("cdiv", stride * size, (new_size * tile_stride))
+            outer_strides.append(new_stride)
+
+            inner_shape.append(tile_size)
+            next_stride = stride * tile_stride
+            inner_strides.append(next_stride)
+
+        return type(self)(
+            shape=outer_shape,
+            dtype=type(self)(
+                shape=inner_shape,
+                dtype=self.dtype,
+                strides=inner_strides,
+                name=self.name,
+            ),
+            strides=outer_strides,
+            name=self.name,
+        )
+
+    def expand(self, shape):
+        # TODO: Add error handling.
+        return type(self)(
+            shape=[
+                new_size if new_size != -1 else size
+                for size, new_size in zip(self.shape, shape)
+            ],
+            dtype=self.dtype,
+            strides=[
+                stride if new_size == -1 else 0
+                for new_size, stride in zip(shape, self.strides)
+            ],
+            name=self.name,
+        )
+
+    def names(self):
+        return (
+            {self._pointer()}
+            | {
+                name
+                for value in itertools.chain(self.shape, self.strides)
+                if isinstance(value, Symbol)
+                for name in value.names()
+            }
+            | (self.dtype.names() if isinstance(self.dtype, type(self)) else set())
+        )
+
+    def pointers(self, offsets=None):
+        if offsets is None:
+            offsets = self.offsets()
+
+        return self._pointer() + offsets
+
+    def offsets(self, indices=None):
+        if indices is None:
+            indices = self.indices()
+
+        if not isinstance(self.dtype, type(self)):
+            if indices:
+                raise IndexError("Incorrect number of indices.")
+
+            return sum(
+                self.stride(idx)
+                * call("arange", 0, self.size(idx))[
+                    tuple(slice(None) if i == idx else None for i in range(self.ndim()))
+                ]
+                for idx in range(self.ndim())
+            )
+
+        outer_indices = indices[: self.ndim()]
+        inner_indices = indices[self.ndim() :]
+
+        return sum(
+            index * stride for index, stride in zip(outer_indices, self.strides)
+        ) + self.dtype.offsets(inner_indices)
+
+    def indices(self, index=None):
+        if index is None:
+            index = call("program_id", 0)
+
+        indices = []
+
+        for stride in type(self)(shape=self.shape, name=self.name).strides:
+            indices.append(index // stride)
+            index %= stride
+
+        return tuple(indices)
+
+    def ndim(self):
+        return len(self.shape)
+
+    def size(self, dim=None):
+        if dim is None:
+            return self.shape
+
+        return self.shape[dim]
+
+    def stride(self, dim=None):
+        if dim is None:
+            return self.strides
+
+        return self.strides[dim]
+
+    @staticmethod
+    def is_pointer(name):
+        return name.endswith("_ptr")
+
+    def _pointer(self):
+        return f"{self.name}_ptr"
+
+    @staticmethod
+    def _calculate_default_strides(shape):
+        strides = [1]
+
+        for size in shape[1:]:
+            strides.append(size * strides[-1])
+
+        return reversed(strides)

ninetoothed-0.1.0/src/ninetoothed/torchifier.py

@@ -0,0 +1,34 @@
+import ast
+import re
+
+
+class Torchifier(ast.NodeTransformer):
+    def visit_Name(self, node):
+        self.generic_visit(node)
+
+        pattern = re.compile(r"([a-zA-Z_][a-zA-Z0-9_]*)_(size|stride)_(.+)")
+
+        node.id = node.id.replace("_ptr", "")
+
+        if re.fullmatch(pattern, node.id):
+            return ast.parse(
+                pattern.sub(
+                    lambda match: f"{match.group(1)}.{match.group(2)}({match.group(3)})",
+                    node.id,
+                ),
+                mode="eval",
+            ).body
+
+        return node
+
+    def visit_Attribute(self, node):
+        self.generic_visit(node)
+
+        if (
+            isinstance(node.value, ast.Name)
+            and node.value.id == "ninetoothed"
+            and node.attr == "language"
+        ):
+            return node.value
+
+        return node