FSPA: An FeFET-based Sparse Matrix-Dense Vector Multiplication Accelerator

Sparse matrix-dense vector multiplication (SpMV) is widely used in various applications. The performance of traditional SpMV accelerators is bounded by memory. In-memory computing (IMC) is a promising technique to alleviate the memory bottleneck. The current IMC accelerator cannot support sparse sto...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autori: Zhang, Xiaoyu, Li, Zerun, Liu, Rui, Chen, Xiaoming, Han, Yinhe
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 09.07.2023
Predmet:
Design automation
Electric breakdown
FeFETs
ferroelectric field-effect transistor
Graphics processing units
In-memory computing
Sparse matrices
Sparse matrix multiplication
Transistors
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Sparse matrix-dense vector multiplication (SpMV) is widely used in various applications. The performance of traditional SpMV accelerators is bounded by memory. In-memory computing (IMC) is a promising technique to alleviate the memory bottleneck. The current IMC accelerator cannot support sparse storage format and in-situ floating-point multiplication at the same time. In this paper, we propose FSPA, an ferroelectric field-effect transistor (FeFET) based SpMV accelerator. FSPA integrates novel content-addressable memory (CAM) arrays and multiply-add computation (MAC) arrays to support sparse matrices represented in the floating-point format. FSPA achieves significant speedups and energy savings over CPU, GPU and two state-of-the-art IMC accelerators.
DOI:10.1109/DAC56929.2023.10247895