FAST MATRIX MULTIPLICATION FOR BINARY AND TERNARY CONVOLUTIONAL NEURAL NETWORKS ON ARM CENTRAL PROCESSING UNIT

FAST MATRIX MULTIPLICATION FOR BINARY AND TERNARY CONVOLUTIONAL NEURAL NETWORKS ON ARM CENTRAL PROCESSING UNIT

No computationally efficient CPU-oriented algorithms of ternary and ternary-binary convolution and/or matrix multiplication are available. Accordingly, a microkernel is disclosed for high-performance matrix multiplication of binary, ternary, and ternary-binary matrices for central processing units (...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: TRUSOV, Anton Vsevolodovich, LIMONOVA, Elena Evgenyevna, NIKOLAEV, Dmitry Petrovich, ARLAZAROV, Vladimir Viktorovich
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:No computationally efficient CPU-oriented algorithms of ternary and ternary-binary convolution and/or matrix multiplication are available. Accordingly, a microkernel is disclosed for high-performance matrix multiplication of binary, ternary, and ternary-binary matrices for central processing units (CPUs) with the Advanced Reduced Instruction Set Computer (RISC) Machine (ARM) v8 architecture.