1 January 2018 in IEEE Journal of Selected Topics in Signal Processing
The problem of low complexity, close to optimal, channel decoding of linear codes with short to moderate block length is considered. It is shown that deep learning methods can be used to improve a standard belief propagation decoder, despite the large example space. Similar improvements are obtained for the min-sum algorithm. It is also shown that tying the parameters of the decoders across iterations, so as to form a recurrent neural network architecture, can be implemented with comparable results. The advantage is that significantly less parameters are required. We also introduce a recurrent neural decoder architecture based on the method of successive relaxation. Improvements over standard belief propagation are also observed on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the neural belief propagation decoder can be used to improve the performance, or alternatively reduce the computational complexity, of a close to optimal decoder of short BCH codes.
9 March 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Ultrareliable low-latency communication (URLLC), a major 5G new-radio (NR) use case, is the key enabler for applications with strict reliability and latency requirements. These applications necessitate the use of short-length and high-rate channel codes. Guessing random additive noise decoding (GRAND) is a recently proposed maximum likelihood (ML) decoding technique for these short-length and high-rate codes. Rather than decoding the received vector, GRAND tries to infer the noise that corrupted the transmitted codeword during transmission through the communication channel. As a result, GRAND can decode any code, structured or unstructured. GRAND has hard-input as well as soft-input variants. Among these variants, ordered reliability bits GRAND (ORBGRAND) is a soft-input variant that outperforms hard-input GRAND and is suitable for parallel hardware implementation. This work reports the first hardware architecture for ORBGRAND, which achieves an average throughput of up to 42.5 Gb/s for a code length of 128 at a target frame error rate (FER) of 10−7. Furthermore, the proposed hardware can be used to decode any code as long as the length and rate constraints are met. In comparison to the GRAND with ABandonment (GRANDAB), a hard-input variant of GRAND, the proposed architecture enhances decoding performance by at least 2 dB. When compared to the state-of-the-art fast dynamic successive cancellation flip decoder (Fast-DSCF) using a 5G polar code (PC) (128, 105), the proposed ORBGRAND VLSI implementation has $49\times $ higher average throughput, $32\times $ times more energy efficiency, and $5\times $ more area efficiency while maintaining similar decoding performance.
11 January 2019 in IEEE Transactions on Circuits and Systems I: Regular Papers
Invertible logic can operate in one of two modes: 1) a forward mode, in which inputs are presented and a single, correct output is produced, and 2) a reverse mode, in which the output is fixed and the inputs take on values consistent with the output. It is possible to create invertible logic using various Boltzmann machine configurations. Such systems have been shown to solve certain challenging problems quickly, such as factorization and combinatorial optimization. In this paper, we show that invertible logic can be implemented using simple spiking neural networks based on stochastic computing. We present a design methodology for invertible stochastic gates, which can be implemented using a small amount of CMOS hardware. We demonstrate that our design can not only correctly implement the basic gates with invertible capability but can also be extended to construct invertible stochastic adder and multiplier circuits. The experimental results are presented, which demonstrate the correct operation of synthesizable invertible circuitry performing both multiplication and factorization, along with fabricated ASIC measurement results for an invertible multiplier circuit.
11 July 2012 in Journal of Signal Processing Systems
28 November 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Guessing random additive noise decoding (GRAND) is a recently proposed universal maximum likelihood (ML) decoder for short-length and high-rate linear block codes. Soft-GRAND (SGRAND) is a prominent soft-input GRAND variant, outperforming the other GRAND variants in decoding performance; nevertheless, SGRAND is not suitable for parallel hardware implementation. Ordered Reliability Bits-GRAND (ORBGRAND) is another soft-input GRAND variant that is suitable for parallel hardware implementation; however, it has lower decoding performance than SGRAND. In this article, we propose List-GRAND (LGRAND), a technique for enhancing the decoding performance of ORBGRAND to match the ML decoding performance of SGRAND. Numerical simulation results show that LGRAND enhances ORBGRAND’s decoding performance by 0.5–0.75 dB for channel codes of various classes at a target frame error rate (FER) of 10−7. For linear block codes of length 127/128 and different code rates, LGRAND’s VLSI implementation can achieve an average information throughput of 47.27–51.36 Gb/s. In comparison to ORBGRAND’s VLSI implementation, the proposed LGRAND hardware has a 4.84% area overhead.
1 January 2020 in IEEE Transactions on Computers
Convolutional neural networks (CNNs) are a vital approach in machine learning. However, their high complexity and energy consumption make them challenging to embed in mobile applications at the edge requiring real-time processes such as smart phones. In order to meet the real-time constraint of edge devices, recently proposed custom hardware CNN accelerators have exploited parallel processing elements (PEs) to increase throughput. However, this straightforward parallelization of PEs and high memory bandwidth require high data movement, leading to large energy consumption. As a result, only a certain number of PEs can be instantiated when designing bandwidth-limited custom accelerators targeting edge devices. While most bandwidth-limited designs claim a peak performance of a few hundred giga operations per second, their average runtime performance is substantially lower than their roofline when applied to state-of-the-art CNNs such as AlexNet, VGGNet and ResNet, as a result of low resource utilization and arithmetic intensity. In this work, we propose a zero-activation-skipping convolutional accelerator (ZASCA) that avoids noncontributory multiplications with zero-valued activations. ZASCA employs a dataflow that minimizes the gap between its average and peak performances while maximizing its arithmetic intensity for both sparse and dense representations of activations, targeting the bandwidth-limited edge computing scenario. More precisely, ZASCA achieves a performance efficiency of up to 94% over a set of state-of-the-art CNNs for image classification with dense representation where the performance efficiency is the ratio between the average runtime performance and the peak performance. Using its zero-skipping feature, ZASCA can further improve the performance efficiency of the state-of-theart CNNs by up to 1.9× depending on the sparsity degree of activations. The implementation results in 65-nm TSMC CMOS technology show that, compared to the most energy-efficient accelerator, ZASCA can process convolutions from 5.5× to 17.5× faster, and is between 2.1× and 4.5× more energy efficient while occupying 2.1× less silicon area.