Sorry, you need to enable JavaScript to visit this website.

With the advent of Big Data application domains, several Machine Learning (ML) signal-processing algorithms such as Convolutional Neural Networks (CNNs) are required to process progressively larger datasets at a great cost in terms of both compute power and memory bandwidth. Although dedicated accelerators have been developed targeting this issue, they usually require moving massive amounts of data across the memory hierarchy to the processing cores and low-level knowledge of how data is stored in the memory devices to enable in-/near-memory processing solutions.


SC-Flip (SCF) decoding is a low-complexity polar code decoding algorithm alternative to SC-List (SCL) algorithm with small list sizes. To achieve the performance of the SCL algorithm with large list sizes, the Dynamic SC-Flip (DSCF) algorithm was proposed. However, DSCF involves logarithmic and exponential computations that are not suitable for practical hardware implementations. In this work, we propose a simple approximation that replaces the transcendental computations of DSCF decoding. Moreover, we show how to incorporate fast decoding techniques with the DSCF algorithm.


Custom hardware accelerators of Convolutional Neural Networks (CNN) provide a promising solution to meet real-time constraints for a wide range of applications on low-cost embedded devices. In this work, we aim to lower the dynamic power of a stream-based CNN hardware accelerator by reducing the computational redundancies in the CNN layers. In particular, we investigate the redundancies due to the downsampling effect of max pooling layers which are prevalent in state-of-the-art CNNs, and propose an approximation method to reduce the overall computations.


This paper describes a low-power processor tailored for fast Fourier transform computations where transport triggering template is exploited. The processor is software-programmable while retaining an energy-efficiency comparable to existing fixed-function implementations. The power savings are achieved by compressing the computation kernel into one instruction word. The word is stored in an instruction loop buffer, which is more power-efficient than regular instruction memory storage.