Achieving Native GPU Performance for Out-of-Card Large Dense Matrix Multiplication
From MaRDI portal
Publication:4598919
DOI10.1142/S0129626416500079zbMath1376.65075OpenAlexW2416378570MaRDI QIDQ4598919
Publication date: 15 December 2017
Published in: Parallel Processing Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1142/s0129626416500079
Complexity and performance of numerical algorithms (65Y20) Numerical algorithms for specific classes of architectures (65Y10)