da4ml 0.3.1__tar.gz → 0.3.2__tar.gz

{da4ml-0.3.1 → da4ml-0.3.2}/.clang-format

@@ -8,17 +8,17 @@ AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
 BreakBeforeBraces: Custom
 BraceWrapping:
-  AfterClass: true
-  AfterControlStatement: true
-  AfterEnum: true
-  AfterFunction: true
-  AfterNamespace: true
-  AfterStruct: true
-  AfterUnion: true
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: false
+  AfterNamespace: false
+  AfterStruct: false
+  AfterUnion: false
   AfterExternBlock: true
   BeforeCatch: true
   BeforeElse: true
-  IndentBraces: true
+  IndentBraces: false
   SplitEmptyFunction: false
   SplitEmptyRecord: false
   SplitEmptyNamespace: false
@@ -28,11 +28,11 @@ Cpp11BracedListStyle: true
 KeepEmptyLinesAtTheStartOfBlocks: false
 Language: Cpp
 NamespaceIndentation: All
-PenaltyExcessCharacter: 100
+PenaltyExcessCharacter: 120
 PenaltyReturnTypeOnItsOwnLine: 1
 PointerAlignment: Right
 SortIncludes: false
-SpaceBeforeParens: Never
+SpaceBeforeParens: ControlStatements
 SpacesInContainerLiterals: false
 Standard: Cpp11
 BinPackArguments: false

da4ml-0.3.2/.github/workflows/sphinx-build.yml

@@ -0,0 +1,60 @@
+name: Documentation
+
+on:
+  # Runs on pushes targeting the default branch
+  push:
+    branches: ["master"]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  # Build job
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Setup Pages
+        uses: actions/configure-pages@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          pip3 install ".[docs]"
+          pip3 install jax
+      - name: Build
+        run: |
+          cd docs
+          KERAS_BACKEND=jax make html
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: "docs/_build/html"
+
+  # Deployment job
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

{da4ml-0.3.1 → da4ml-0.3.2}/.gitignore

@@ -1,3 +1,6 @@
+# autodoc
+docs/autodoc/
+
 # test files
 _*_codegen/
 

da4ml-0.3.2/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: da4ml
+Version: 0.3.2
+Summary: Digital Arithmetic for Machine Learning
+Author-email: Chang Sun <chsun@cern.ch>
+License: GNU Lesser General Public License v3 (LGPLv3)
+Project-URL: repository, https://github.com/calad0i/da4ml
+Keywords: CMVM,distributed arithmetic,hls4ml,MCM,subexpression elimination
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: llvmlite>=0.44
+Requires-Dist: numba>=0.61
+Provides-Extra: docs
+Requires-Dist: hgq2; extra == "docs"
+Requires-Dist: myst-parser; extra == "docs"
+Requires-Dist: pyparsing; extra == "docs"
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Dynamic: license-file
+
+# da4ml: Distributed Arithmetic for Machine Learning
+
+[![LGPLv3](https://img.shields.io/badge/License-LGPLv3-blue.svg)](https://www.gnu.org/licenses/lgpl-3.0)
+[![Documentation](https://github.com/calad0i/da4ml/actions/workflows/sphinx-build.yml/badge.svg)](https://calad0i.github.io/da4ml/)
+[![PyPI version](https://badge.fury.io/py/da4ml.svg)](https://badge.fury.io/py/da4ml)
+[![ArXiv](https://img.shields.io/badge/arXiv-2507.04535-b31b1b.svg)](https://arxiv.org/abs/2507.04535)
+
+da4ml is a library for implementing distributed arithmetic (DA) based algorithms for ultra-low latency machine learning (ML) applications on FPGAs. It as two major components:
+ - A fast and performant constant-matrix-vector multiplications (CMVM) optimizer to implement them as
+   efficient adder trees. Common sub-expressions elimination (CSE) with graph-based pre-optimization are
+   performed to reduce the firmware footprint and improve the performance.
+ - Low-level symbolic tracing frameworks for generating combinational/fully pipelined logics in HDL or HLS
+   code. For fully pipelined networks, da4ml can generate the firmware for the whole network standalone.
+   Alternatively, da4ml be used as a plugin in hls4ml to optimize the CMVM operations in the network.
+
+
+Key Features
+------------
+
+- **Optimized Algorithms**: Comparing to hls4ml's latency strategy, da4ml's CMVM implementation uses no DSO and consumes up to 50% less LUT usage.
+- **Fast code generation**: da4ml can generate HDL for a fully pipelined network in seconds. For the same models, high-level synthesis tools like Vivado/Vitis HLS can take up to days to generate the HDL code.
+- **Low-level symbolic tracing**: As long as the operation can be expressed by a combination of the low-level operations supported, adding new operations is straightforward by "replaying" the operation on the symbolic tensor provided. In most cases, adding support for a new operation/layer takes just a few lines of code in numpy flavor.
+- **Automatic model conversion**: da4ml can automatically convert models trained in `HGQ2 <https://github.com/calad0i/hgq2>`_.
+- **Bit-accurate Simulation**: All operation in da4ml is bit-accurate, meaning the generated HDL code will produce the same output as the original model. da4ml's computation is converted to a RISC-like, instruction set level intermediate representation, distributed arithmetic instruction set (DAIS), which can be easily simulated in multiple ways.
+- **hls4ml integration**: da4ml can be used as a plugin in hls4ml to optimize the CMVM operations in the network by setting `strategy='distributed_arithmetic'` for the strategy of the Dense, EinsumDense, or Conv1/2D layers.
+
+Installation
+------------
+
+```bash
+pip install da4ml
+```
+
+Getting Started
+---------------
+
+See the [Getting Started](https://calad0i.github.io/da4ml/getting_started.html) guide for a quick introduction to using da4ml.

da4ml-0.3.2/README.md

@@ -0,0 +1,37 @@
+# da4ml: Distributed Arithmetic for Machine Learning
+
+[![LGPLv3](https://img.shields.io/badge/License-LGPLv3-blue.svg)](https://www.gnu.org/licenses/lgpl-3.0)
+[![Documentation](https://github.com/calad0i/da4ml/actions/workflows/sphinx-build.yml/badge.svg)](https://calad0i.github.io/da4ml/)
+[![PyPI version](https://badge.fury.io/py/da4ml.svg)](https://badge.fury.io/py/da4ml)
+[![ArXiv](https://img.shields.io/badge/arXiv-2507.04535-b31b1b.svg)](https://arxiv.org/abs/2507.04535)
+
+da4ml is a library for implementing distributed arithmetic (DA) based algorithms for ultra-low latency machine learning (ML) applications on FPGAs. It as two major components:
+ - A fast and performant constant-matrix-vector multiplications (CMVM) optimizer to implement them as
+   efficient adder trees. Common sub-expressions elimination (CSE) with graph-based pre-optimization are
+   performed to reduce the firmware footprint and improve the performance.
+ - Low-level symbolic tracing frameworks for generating combinational/fully pipelined logics in HDL or HLS
+   code. For fully pipelined networks, da4ml can generate the firmware for the whole network standalone.
+   Alternatively, da4ml be used as a plugin in hls4ml to optimize the CMVM operations in the network.
+
+
+Key Features
+------------
+
+- **Optimized Algorithms**: Comparing to hls4ml's latency strategy, da4ml's CMVM implementation uses no DSO and consumes up to 50% less LUT usage.
+- **Fast code generation**: da4ml can generate HDL for a fully pipelined network in seconds. For the same models, high-level synthesis tools like Vivado/Vitis HLS can take up to days to generate the HDL code.
+- **Low-level symbolic tracing**: As long as the operation can be expressed by a combination of the low-level operations supported, adding new operations is straightforward by "replaying" the operation on the symbolic tensor provided. In most cases, adding support for a new operation/layer takes just a few lines of code in numpy flavor.
+- **Automatic model conversion**: da4ml can automatically convert models trained in `HGQ2 <https://github.com/calad0i/hgq2>`_.
+- **Bit-accurate Simulation**: All operation in da4ml is bit-accurate, meaning the generated HDL code will produce the same output as the original model. da4ml's computation is converted to a RISC-like, instruction set level intermediate representation, distributed arithmetic instruction set (DAIS), which can be easily simulated in multiple ways.
+- **hls4ml integration**: da4ml can be used as a plugin in hls4ml to optimize the CMVM operations in the network by setting `strategy='distributed_arithmetic'` for the strategy of the Dense, EinsumDense, or Conv1/2D layers.
+
+Installation
+------------
+
+```bash
+pip install da4ml
+```
+
+Getting Started
+---------------
+
+See the [Getting Started](https://calad0i.github.io/da4ml/getting_started.html) guide for a quick introduction to using da4ml.

da4ml-0.3.2/docs/Makefile

@@ -0,0 +1,21 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@sphinx-apidoc -f -o autodoc/ ../src/da4ml
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)