Skip to main content
In the News

A custom RISC-V vector instruction to accelerate structured-sparse matrix multiplications

By March 20, 2024March 26th, 2024No Comments

A novel AI-acceleration paper presents a method to optimize sparse matrix multiplication for machine learning models, particularly focusing on structured sparsity. Structured sparsity involves a predefined pattern of zero values in the matrix, unlike unstructured sparsity where zeros can occur anywhere. The research was conducted by Democritus University of Thrace (DUTH) in Greece and was sponsored by Codasip University Program.

Read the full article.

Stay Connected With RISC-V

We send occasional news about RISC-V technical progress, news, and events.