Skip to content

xvyv99/triton-benchmark

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

91 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

triton-benchmark

This project focuses on evaluating the tuning capabilities of triton-cpu for optimizing AI kernels on multicore CPUs. It compares triton-cpu's runtime auto-tuning with both compiler-based auto-tuning (e.g., GCC, Clang) and other runtime tuning frameworks (e.g., TVM, Hidet).

The benchmarks directory analyzes triton-cpu's runtime auto-tuning on multicore CPUs, comparing it with compiler-based auto-tuning to assess the impact of different tuning parameters.

The cases directory evaluates both the performance and tuning time of AI kernels optimized using different tuning frameworks on multi-core CPUs.

Refer to README in the directories above for environmental setup and more other details.

About

RISCV C and Triton AI-Benchmark

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C 36.9%
  • Python 36.0%
  • C++ 22.8%
  • Shell 4.3%