Abstract | ||
---|---|---|
Memory array architecture based on emerging non-volatile memory devices have been proposed for on-chip acceleration of dot-product computation in neural networks. As recent advances in machine learning have shown that precision reduction is a useful technique to reduce the computation and memory storage, it is desired to evaluate their hardware cost. In this paper, we use a circuit-level macro model, i.e. NeuroSim, to benchmark the circuit-level performance metrics, such as chip area, latency, and dynamic energy for the XNOR-RRAM and conventional 8-bit RRAM architectures. Both architectures are implemented to process the dot-product operation of a 512×512 synaptic matrix in sequential row-by-row and parallel read-out fashion separately. The simulation results are based on RRAM models and 32nm CMOS PDK, the energy-efficiency of the parallel XNOR-RRAM architecture could achieve 311 TOPS/W, showing at least ~15× and ~621× improvement compared to the parallel and sequential conventional 8-bit RRAM architectures respectively. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/APCCAS.2018.8605606 | 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) |
Keywords | Field | DocType |
non-volatile memory,machine learning,hardware accelerator,neuromorphic computing | Computer science,Parallel computing,Neuromorphic engineering,Electronic engineering,Chip,Non-volatile memory,Hardware acceleration,Artificial neural network,Benchmark (computing),Resistive random-access memory,Computation | Conference |
ISBN | Citations | PageRank |
978-1-5386-8241-8 | 0 | 0.34 |
References | Authors | |
2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaochen Peng | 1 | 61 | 12.17 |
Shimeng Yu | 2 | 490 | 56.22 |