Abstract
This letter presents C3SRAM, an in-memory-computing SRAM macro, which utilizes analog-mixed-signal capacitive-coupling computing to perform XNOR-and-accumulate operations for binary deep neural networks. The 256 × 64 C3SRAM macro asserts all 256 rows simultaneously and equips one ADC per column, realizing fully parallel vector-matrix multiplication in one cycle. C3SRAM demonstrates 672 TOPS/W and 1638 GOPS, and achieves 98.3% accuracy for MNIST and 85.5% for CIFAR-10 dataset. It achieves 3975 × smaller energy-delay product than conventional digital processors.
Original language | English (US) |
---|---|
Article number | 8877969 |
Pages (from-to) | 131-134 |
Number of pages | 4 |
Journal | IEEE Solid-State Circuits Letters |
Volume | 2 |
Issue number | 9 |
DOIs | |
State | Published - Sep 2019 |
Keywords
- Capacitive coupling
- In-memory-computing (IMC)
- Machine learning accelerator
- Mixed-signal processingc
- Neural network
ASJC Scopus subject areas
- Electrical and Electronic Engineering