Skip to content

m1nuzz/AutoGpuAffinity_Hyperthreading

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The screenshots below with the tests were taken on a 14900k processor. The tests were conducted with Hyperthreading enabled in the BIOS. When benchmarking through my fork, where two cores are tested simultaneously, it is noticeable that there is less stuttering and higher FPS:

Single-Thread: Original Program image

Hyperthreading: This fork image


AutoGpuAffinity_Hyperthreading

This fork of AutoGpuAffinity is designed to test CPU cores in hyperthreading pairs. The benchmarking process will run across pairs of logical processors: 0-1, 2-3, and so on.

Features

  • Assigns GPU driver affinity to specific CPU pairs.
  • Analyzes benchmark data from CSV files.
  • Supports logging and analysis with PresentMon and xperf.
  • Customizable benchmarking duration and CPU selection.

Installation

To set up the environment, follow these steps:

  1. Clone the repository.

  2. Install the necessary dependencies using the following command:

    pip install -r requirements.txt

Usage

Run the program using:

python main.py

About

Multi-core GPU driver affinity benchmarking

Resources

Stars

2 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors

Languages

  • Python 93.0%
  • Batchfile 7.0%