Configurable sparse matrix - matrix multiplication accelerator on FPGA: A systematic design space exploration approach with quantization effects

High-performance sparse matrix multipliers are essential for deep learning applications, and as big data analytics continues to evolve, specialized accelerators are also needed to efficiently handle sparse matrix operations. This paper proposes a modified, configurable, outer product based architect...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	G. Noble, S. Nalesh, S. Kala, Akash Kumar
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	Elsevier 2024-03-01
Saila:	Alexandria Engineering Journal
Gaiak:	Accelerator FPGA Outer product Sparse matrix multiplication SpGEMM Quantization
Sarrera elektronikoa:	http://www.sciencedirect.com/science/article/pii/S1110016824001145
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!