https://github.com/atlarge-research/aie-blas

BLAS Implementation for AMD/Xilinx Versal Devices

https://github.com/atlarge-research/aie-blas

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (2.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

BLAS Implementation for AMD/Xilinx Versal Devices

Basic Info
  • Host: GitHub
  • Owner: atlarge-research
  • Language: C++
  • Default Branch: main
  • Size: 118 KB
Statistics
  • Stars: 0
  • Watchers: 9
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme

README.md

aieblas

This repository contains a BLAS implementation for the AMD AI Engine.

Note that the library is mostly a proof of concept and does not support all routines.

Supported routines

Level 1: - ASUM - AXPY - DOT - IAMAX - NRM2 - ROT - SCAL

Level 2: - GEMV

Supported devices

  • AMD Versal VCK5000

Compiling the library

To compile the code generator, run ./configure.sh && cmake --build build in the folder aieblas/.

Running the benchmarks

To run the benchmarks, first compile the code generator, and then build the benchmarks by running ./build-all.sh in the folder benchmark/util.

Owner

  • Name: @Large Research
  • Login: atlarge-research
  • Kind: organization
  • Email: info@atlarge-research.com

Massivizing Computer Systems

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2