LIBXSMM

All repositories

Overview

HEALTH SCORE

Healthy

80out of 100

Solid maintainer coverage and security posture. Development cadence keeps the score from reaching Excellent.

LIFECYCLE

Active

Consistent commits, responsive maintainers, regular releases, and healthy issue triage.

Display your project Health score on your GitHub page.

Health breakdown

Healthy(80/100)

Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.

Maintainer responsiveness

Median response time is 0 days.

Bus factor

3 active maintainers currently have merge rights.

Organization Diversity

Contributors span 27 organizations.

Project Achievements

Leaderboards

About

LIBXSMM is a high-performance library for small matrix-matrix multiplications targeting Intel processors. It specializes in optimizing dense and sparse matrix operations, particularly for deep learning and HPC workloads, generating specialized code for small matrix sizes to achieve maximum performance.

First commit

April 2014

Software value

$6.3M