Skip to main content

A Python package for program analysis and custom instruction generation

Project description

Pixi (Pass for Instruction eXtraction and Inference)

License: MIT Python 3.8+ Publish Python Package

Pixi is a tool for analyzing LLVM IR and generating custom hardware instructions to optimize performance-critical code sections in the von-Neumann pipeline. The project follows the idea of everything is computation both hardware and software but they come with different computational cost models.

Requirements

  • Python 3.10+
  • LLVM and Clang (automatically set up by the installation process)
  • Ninja build system
  • CMake 3.13.4+

Installation

# Clone the repository
git clone https://github.com/JoyenBenitto/Pixi.git
cd Pixi

# Install the package in development mode
pip install -e .

# Set up LLVM dependencies
pixi setup -c <jobs>

[!Note] The setup process clones and configures the LLVM project, which may take some time during the initial setup. Subsequent setups will be much faster.

Usage

Pixi provides a comprehensive command-line interface for analyzing code, generating LLVM IR, and creating custom hardware instructions.

Command Reference

Command Description
setup Sets up the LLVM environment for Pixi

License

This project is licensed under the MIT License - see the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

py-pixi-0.0.0.tar.gz (8.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

py_pixi-0.0.0-py3-none-any.whl (9.3 kB view details)

Uploaded Python 3

File details

Details for the file py-pixi-0.0.0.tar.gz.

File metadata

  • Download URL: py-pixi-0.0.0.tar.gz
  • Upload date:
  • Size: 8.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for py-pixi-0.0.0.tar.gz
Algorithm Hash digest
SHA256 9d538a9e2e596558a4d7b7e2e3c85f62870344c8e81ee9f1ec5772e6f9497827
MD5 ba2639892bbf6a502877385d20e23456
BLAKE2b-256 153ecc4def3d7020a231c544d1e49ef000218054d208fc57e74c73c967ab6d46

See more details on using hashes here.

File details

Details for the file py_pixi-0.0.0-py3-none-any.whl.

File metadata

  • Download URL: py_pixi-0.0.0-py3-none-any.whl
  • Upload date:
  • Size: 9.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for py_pixi-0.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a35740846e62366d84162af73d06757e7243f9028613fbc980d22fb126544814
MD5 68157c06ca089a4f6b2add402820e432
BLAKE2b-256 a1bd57547225260781d4bd22ffd061185b9c1b9085a7269efc72a270e622af2f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page