Abstract | ||
---|---|---|
A 65nm XNOR-SRAM macro is presented for binary deep neural network (DNN) accelerator. It features 1) a custom XNOR-SRAM bit-cell design with 8 transistors (8T); 2) a fully parallel compute-in-memory capability of XNOR bit-counting for the inference. Multi-level sense amplifier is employed as Flash analog-to-digital converter (ADC) at edge of the array. The impact of ADC offset on the algorithm-level accuracy is statistically evaluated on a VGG-like XNOR-Net with the CIFAR-10 dataset, showing a marginal degradation ~1.77%. Read-disturb of SRAM bit-cell during parallel computation is also evaluated and its impact is minimized by lowering the word-line (WL) voltage. Silicon measurement results show that the proposed XNOR-SRAM unit-macro achieves a fast access time (2.3 ns) for parallel bit-counting and a high energy efficiency (44.8-62.8) TOPS/W depending on the WL voltage. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/MWSCAS48704.2020.9184455 | 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS) |
Keywords | DocType | ISSN |
parallel compute-in-memory,binary deep neural network accelerator,compute-in-memory,XNOR bit-counting,multilevel sense amplifier,Flash analog-to-digital converter,ADC,VGG-like XNOR-Net,CIFAR-10 dataset,parallel bit-counting,XNOR-SRAM bit-cell design | Conference | 1548-3746 |
ISBN | Citations | PageRank |
978-1-7281-8059-5 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongwu Jiang | 1 | 16 | 6.77 |
Rui Liu | 2 | 47 | 5.32 |
Shimeng Yu | 3 | 490 | 56.22 |