t-vi / Tensile

Stretching GPU performance for GEMMs and tensor contractions.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

A tool for creating a benchmark-driven backend library for GEMMs, GEMM-like problems (such as batched GEMM), N-dimensional tensor contractions, and anything else that multiplies two multi-dimensional objects together on a GPU.

See Tensile Wiki for documentation.

About

Stretching GPU performance for GEMMs and tensor contractions.

License:MIT License


Languages

Language:Python 55.9%Language:C++ 40.4%Language:CMake 2.1%Language:Shell 1.2%Language:Groovy 0.4%Language:Makefile 0.1%Language:Emacs Lisp 0.0%Language:Awk 0.0%Language:Dockerfile 0.0%