gpuocelot  by gtcasl

Dynamic compilation framework for PTX

Created 10 years ago
288 stars

Top 91.2% on SourcePulse

GitHubView on GitHub
Project Summary

GPUOCelot is a modular dynamic compilation framework for heterogeneous systems, designed to execute CUDA programs on NVIDIA GPUs, AMD GPUs, and x86-CPUs without recompilation. It targets researchers and developers working with parallel computing and GPU architectures who need a flexible platform for analyzing and executing CUDA code across diverse hardware.

How It Works

GPUOCelot employs a dynamic compilation approach, analyzing and transforming PTX (Parallel Thread Execution) virtual instruction sets. This allows for runtime adaptation and execution on different hardware backends, including NVIDIA GPUs, AMD GPUs, and x86 CPUs, aiming for full execution speed.

Quick Start & Requirements

Installation instructions are available at https://github.com/gtcasl/gpuocelot/wiki/Installation.

Highlighted Details

  • Enables CUDA program execution on NVIDIA GPUs, AMD GPUs, and x86-CPUs without recompilation.
  • Provides analysis modules for the PTX virtual instruction set.
  • Aims for full execution speed across supported platforms.

Maintenance & Community

The project is no longer actively maintained. The last news update was in March 2013, seeking developers for AMD and Intel GPU backends. A mailing list is available at http://groups.google.com/group/gpuocelot.

Licensing & Compatibility

The README does not specify a license.

Limitations & Caveats

The project is explicitly stated as no longer actively maintained, indicating a lack of ongoing development, bug fixes, or support for newer hardware architectures or CUDA versions. Documentation for installation and common usage is also noted as lacking.

Health Check
Last Commit

2 years ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
0 stars in the last 30 days

Explore Similar Projects

Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Jason Knight Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML), and
3 more.

gpu.cpp by AnswerDotAI

0%
4k
C++ library for portable GPU computation using WebGPU
Created 1 year ago
Updated 2 months ago
Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems") and Ying Sheng Ying Sheng(Coauthor of SGLang).

fastllm by ztxz16

0.4%
4k
High-performance C++ LLM inference library
Created 2 years ago
Updated 1 week ago
Starred by David Cournapeau David Cournapeau(Author of scikit-learn), Stas Bekman Stas Bekman(Author of "Machine Learning Engineering Open Book"; Research Engineer at Snowflake), and
5 more.

lectures by gpu-mode

0.8%
5k
Lecture series for GPU-accelerated computing
Created 1 year ago
Updated 4 days ago
Feedback? Help us improve.