Scaled Population Arithmetic for Efficient Stochastic Computing

We propose a new Scaled Population (SP) based arithmetic computation approach that achieves considerable improvements over existing stochastic computing (SC) techniques. First, SP arithmetic introduces scaling operations that significantly reduce the numerical errors as compared to SC. Experiments show accuracy improvements of a single multiplication and addition operation by $6. 3 \times $ and $4. 0 \times $, respectively. Secondly, SP arithmetic erases the inherent serialization associated with stochastic computing, thereby significantly improves the computational delays. We design each of the operations of SP arithmetic to take $\mathcal{O}$(1) gate delays, and eliminate the need of serially iterating over the bits of the population vector. Our SP approach improves the area, delay and power compared with conventional stochastic computing on an FPGA-based implementation. We also apply our SP scheme on a handwritten digit recognition application (MNIST), improving the recognition accuracy by 32.79% compared to SC.