https://github.com/rocm/tensile

Stretching GPU performance for GEMMs and tensor contractions.
https://github.com/rocm/tensile

amd assembly auto-tuning blas dnn gemm gpu gpu-acceleration gpu-computing hip machine-learning matrix-multiplication neural-networks opencl python radeon tensor-contraction tensors

Last synced: 3 days ago
JSON representation

Stretching GPU performance for GEMMs and tensor contractions.

• Host: GitHub
• URL: https://github.com/rocm/tensile
• Owner: ROCm
• License: mit
• Created: 2015-11-05T13:58:49.000Z (about 9 years ago)
• Default Branch: develop
• Last Pushed: 2024-06-04T19:03:45.000Z (8 months ago)
• Last Synced: 2024-06-04T19:05:17.825Z (8 months ago)
• Topics: amd, assembly, auto-tuning, blas, dnn, gemm, gpu, gpu-acceleration, gpu-computing, hip, machine-learning, matrix-multiplication, neural-networks, opencl, python, radeon, tensor-contraction, tensors
• Language: Python
• Homepage:
• Size: 92.8 MB
• Stars: 196
• Watchers: 55
• Forks: 136
• Open Issues: 25
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE.md
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

README

        
Tensile is a tool for creating benchmark-driven backend libraries for GEMMs, GEMM-like problems (such as batched GEMM), and general N-dimensional tensor contractions on a GPU.

The Tensile library is mainly used as a backend library for rocBLAS.

Tensile acts as the performance backbone for a wide variety of 'compute' applications running on AMD GPUs.

> [!NOTE]

> The published documentation is available at [Tensile](https://rocm.docs.amd.com/projects/Tensile/en/latest/index.html) in an organized, easy-to-read format, with search and a table of contents. The documentation source files reside in the `Tensile/docs/src` folder of this repository. As with all ROCm projects, the documentation is open source. For more information on contributing to the documentation, see [Contribute to ROCm documentation](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).