18 August 2020 in IEEE Transactions on Communications
Since the inherent serial nature of successive cancellation list (SCL) decoding results in a long latency, belief propagation (BP) decoding for polar codes has drawn attention for high-throughput applications. However, its error correction performance is inferior to that of SCL decoding. Therefore, the bit-flipping strategy has been recently applied to BP decoding, which can approach the SCL decoding performance through multiple additional decoding attempts. The original BP flip (BPF) decoding suffers from an inaccurate identification of erroneous bits by a fixed flip set (FS), which has been improved by the generalized BPF (GBPF) decoding. In this paper, the GBPF decoding is extended to support multiple bits being flipped in one decoding attempt. In addition, for two types of decoding errors: detected errors and undetected errors, we propose two novel methods to more effectively identify erroneous bits. For detected errors, the concept of loop sets is defined and a loop-based identification method is introduced based on the study of error patterns of BP decoding. On the other hand, a method to generate a more accurate fixed FS is proposed for undetected errors, which considers the bit error distribution under BP decoding. Combining the two methods, the GBPF with merged sets (GBPF-MS) decoding can achieve the SCL-8 performance and outperforms the state-of-the-art BPF, BP list, and SC flip (SCF) decoding, for polar codes with length 1024 and information rate 1/2. Implemented by 40 nm CMOS technology, the proposed GBPF-MS decoder with ten flips exhibits an average throughput of 4.19 Gbps at 2.5 dB, which is 1.6× and 1.72× faster than the state-of-the-art SCL-4 and SCF decoders, respectively.
10 March 2021 in IEEE Transactions on Signal Processing
Massive multiple-input multiple-output (M-MIMO) brings better robustness and spectral efficiency but higher computational challenges compared to small-scale MIMO. One of the key challenges is the large-scale matrix inversion, as widely employed in channel estimation and detection. Traditionally, to address the issue, several low-complexity matrix inversion methods have been proposed, including the tri-diagonal matrix approximation (TMA) and the Neumann-series approximation (NSA). Although the previous methods effectively alleviate the computational cost, they all fail to exploit the typical properties of channel matrices, leading to unsatisfactory error-rate performance in some non-ideal scenarios. To solve the issue, in this paper, a two-level and block diagonal based improved Neumann series approximation (TL-BD-INSA) algorithm is proposed, which is suitable for both ideal uncorrelated channels and the correlated channels with multiple-antenna user equipment (MAUE) system. First, a two-level block diagonal iteration based on matrix partition is employed, which exhibits performance comparable to the exact method while having a lower computational load. An improved normalization factor is then introduced to accelerate convergence. Numerical results show that, for 128×32 MIMO with MAUE non-ideal channel, the proposed algorithm performs only 0.25 dB away from the exact matrix inversion when bit error rate (BER) = 10 -3 . The implementation on Xilinx Virtex-7 FPGA and ASIC with TSMC 45 nm shows that the proposed detector can achieve 1731 bps/slices and 0.463 Gbps/mm 2 hardware efficiency, respectively, demonstrating that the proposed system can achieve a well trade-off between error performance and implementation efficiency.
23 January 2020 in IEEE Transactions on Vehicular Technology
4 March 2020 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Convolutional neural networks (CNNs) have emerged as one of the most popular ways applied in many fields. These networks deliver better performance when going deeper and larger. However, the complicated computation and huge storage impede hardware implementation. To address the problem, quantized networks are proposed. Besides, various convolutional structures are designed to meet the requirements of different applications. For example, compared with the traditional convolutions (CONVs) for image classification, CONVs for image generation are usually composed of traditional CONVs, dilated CONVs, and transposed CONVs, leading to a difficult hardware mapping problem. In this brief, we translate the difficult mapping problem into the sparsity problem and propose an efficient hardware architecture for sparse binary and ternary CNNs by exploiting the sparsity and low bit-width characteristics. To this end, we propose an ineffectual data removing (IDR) mechanism to remove both the regular and irregular sparsity based on dual-channel processing elements (PEs). Besides, a flexible layered load balance (LLB) mechanism is introduced to alleviate the load imbalance. The accelerator is implemented with 65-nm technology with a core size of 2.56 mm^2. It can achieve 3.72-TOPS/W energy efficiency at 50.1 mW, which makes it a promising design for embedded devices.
8 January 2021 in IEEE Transactions on Circuits and Systems I: Regular Papers
We propose a new method and hardware architecture to compute the functions expressed as $X^{Y}$ ( $X$ and $Y$ are arbitrary floating-point numbers), which can support arbitrary Nth root, exponential and power operations. Because of the complexity of direct computation, we usually convert it to logarithm, multiplication, and antilogarithm operations. Traditional approaches suffer from long latency, large area and high power consumption. To solve this problem, we propose a symmetric-mapping lookup table (SM-LUT) to be capable of computing $\log _{2}x$ ( $x\in [{1, 2}]$ ) and $2^{x}$ ( $x\in [{0, 1}]$ ) simultaneously. It lays the foundation for computing $X^{Y}$ . To further improve hardware performance of our architecture, we propose a multi-region address searcher to speed up the calculation of SM-LUT. In addition, we use an optimized Vedic multiplier to shorten the critical path and improve the efficiency of multiplication, which is included in computing $X^{Y}$ . Under the TSMC 40nm CMOS technology, we design and synthesize a reference circuit to compute $X^{Y}$ with a maximum relative error of 10 −3 . The report shows that the reference circuit achieves the area of $14338.50~\mu \text {m}^{2}$ and the power consumption of 4.59 mW at the frequency of 1 GHz. In comparison with the state-of-the-art work under the same input range and similar precision, it saves 78.57% area and 80.42% power consumption for $\sqrt [N]{R}$ computation and 82.89% area and 81.89% power consumption for $R^{N}$ computation averagely. On top of that, our architecture reduces the computation latency by 62.77% averagely and has one more order of magnitude of energy efficiency than others.
15 November 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
The wireless baseband processing algorithms are still developing and show a great diversity. The development of ASIC implementations cannot quickly adapt to the evolution of algorithms and standards. Meanwhile, the general-purpose processors cannot meet the real-time requirements in some scenarios. This paper proposes a DSP-purposed REconfigurable Acceleration Machine (DREAM) core for wireless baseband digital signal processing, which has a good trade-off between flexibility and performance. First, we abstract a set of shared operators with a moderate granularity from a variety of wireless MIMO signal processing algorithms. Then, we propose a two-step configuration process to reduce the size of the required reconfiguration bits. Besides, we design a conflict-free address generator to transfer data between the on-chip scratchpad memory and reconfiguration processing elements with high efficiency and high throughput. Finally, the prototype DREAM core has been implemented in TSMC CMOS 28 nm, and its area and power consumption have been analyzed. The chip has great flexibility in supporting a variety of wireless MIMO processing algorithms and a wide range of MIMO scales. The proposed DREAM core can achieve the normalized area efficiency and the normalized energy efficiency of $0.67~Gbps/MGE$ and $15.05~Gbps/W$ , which are $1.56\times $ and $4.18\times $ those of state-of-the-art reconfigurable implementations when running the WeJi-based MIMO detection algorithm.