IEEE journal of solid-state circuits, 2021-09, Vol.56 (9), p.2817-2831
2021
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- A Local Computing Cell and 6T SRAM-Based Computing-in-Memory Macro With 8-b MAC Operation for Edge AI Chips
- Ist Teil von
- IEEE journal of solid-state circuits, 2021-09, Vol.56 (9), p.2817-2831
- Ort / Verlag
- New York: IEEE
- Erscheinungsjahr
- 2021
- Quelle
- IEEE Xplore
- Beschreibungen/Notizen
- This article presents a computing-in-memory (CIM) structure aimed at improving the energy efficiency of edge devices running multi-bit multiply-and-accumulate (MAC) operations. The proposed scheme includes a 6T SRAM-based CIM (SRAM-CIM) macro capable of: 1) weight-bitwise MAC (WbwMAC) operations to expand the sensing margin and improve the readout accuracy for high-precision MAC operations; 2) a compact 6T local computing cell to perform multiplication with suppressed sensitivity to process variation; 3) an algorithm-adaptive low MAC-aware readout scheme to improve energy efficiency; 4) a bitline header selection scheme to enlarge signal margin; and 5) a small-offset margin-enhanced sense amplifier for robust read operations against process variation. A fabricated 28-nm 64-kb SRAM-CIM macro achieved access times of 4.1-8.4 ns with energy efficiency of 11.5-68.4 TOPS/W, while performing MAC operations with 4- or 8-b input and weight precision.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 0018-9200eISSN: 1558-173XDOI: 10.1109/JSSC.2021.3073254Titel-ID: cdi_ieee_primary_9416993
- Format
- –
- Schlagworte
- Adaptive algorithms, Artificial intelligence (AI), Common Information Model (computing), Computation, Computer architecture, computing-in-memory, Energy efficiency, local computing cell (LCC), Microprocessors, Multiplication, Neural networks, random access memory, Sense amplifiers, Software, SRAM cells, Static random access memory, Transistors, Weight, weight-bitwise MAC (WbwMAC) operation