Skip to content
forked from NVIDIA/warp

A Python framework for accelerated simulation, data generation and spatial computing.

License

Notifications You must be signed in to change notification settings

MetaX-MACA/hpc_warp

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6,115 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

MetaX Warp

| About MetaX | Documentation |


Latest News 🔥

  • [2026/1] Released hpc_warp v1.8.1 — aligned with Warp v1.8.1.

About

Warp is a Python framework for writing high-performance simulation and graphics code. Warp takes regular Python functions and JIT compiles them to efficient kernel code that can run on the CPU or GPU.

This project (hpc_warp) is based on Warp v1.8.1 release, and supports MetaX GPU.

Prerequisites

  • Hardware: MetaX C-series
  • OS: Linux
  • Software:
    • Python >= 3.10
    • Docker support

Getting Started

hpc_warp currently only supports starting on docker images release by MetaX develop community which works out of the box.

Setup environment variables

export MACA_PATH=/opt/maca
export CUCC_PATH=/opt/maca/tools/cu-bridge
export CUDA_PATH=/opt/maca/tools/cu-bridge
export PATH=${CUCC_PATH}/bin:${CUCC_PATH}/tools:${MACA_CLANG_PATH}:${MACA_PATH}/bin:${CUDA_PATH}/bin:$PATH
export LD_LIBRARY_PATH=${CUCC_PATH}/lib:${MACA_PATH}/lib:${MACA_PATH}/ompi/lib:${MACA_PATH}/ucx/lib:$LD_LIBRARY_PATH
export MACA_DIRECT_DISPATCH=1

Build

python build_lib.py --no_libmathdx

Install

python install -e .

Branches

Below are maintained branches:

Branch Status Note
master Maintained trying to support warp main, no gurantee on functionality
releases/v1.8.1 Maintained Released

License

Apache License 2.0, as found in the LICENSE file.

About

A Python framework for accelerated simulation, data generation and spatial computing.

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages

  • Python 77.5%
  • C++ 16.9%
  • Cuda 3.2%
  • Jupyter Notebook 1.1%
  • C 0.8%
  • Dockerfile 0.2%
  • Other 0.3%