Search

This paper presents a novel static digital pre-distortion (DPD) method for a current-steering digital-to-analog converter (CS-DAC). The proposed method utilizes the knowledge of the current cell array architecture to calculate the static mismatch currents of the cells. The mismatch values are stored in memory and added to the original input code to generate the new pre-distorted input word. The converter corrects the static error with its own current cells without incorporating an additional calibration DAC (CALDAC) or programmable current sources. This results in a reduction in area, power and simulation run times because of the simpler circuit design. An Overflow-Cell-Selection (OCS) is introduced as a novel solution to further enhance the static linearity of the converter. It also can be implemented as a software solution for already existing DAC designs which do not have an integrated DPD and lab/measurement equipment (e.g., arbitrary wave generator (AWG)). This poses as a strong differentiation factor compared to other state-of-the-art static DPD methods. The evaluation of the proposed DPD is done via simulations in MATLAB and on- chip measurements with a 14-bit CS-DAC in 16 nm. Single tone measurements show a performance gain of the total harmonic distortion (THD) of 12 dB. [ABSTRACT FROM AUTHOR]

This paper presents a high-current calibration-free analog-digital hybrid controlled LDO for large-area digital load. The proposed architecture has the advantages of an analog controller (continuous and high DC accuracy) with distributed digital power transistors (flexible and scalable for high current applications). Distinctive from the conventional digital LDOs that directly quantize the output voltage, the proposed LDO utilizes an error amplifier (EA) to pre-amplify the $\text{V}_{\mathrm {OUT}}$ error. Then, a 5-bit time-to-digital converter (TDC) quantizes the processed analog error signal subsequently transformed into a thermometer code that directly controls the distributed digital power transistors. This design can pull off high DC accuracy even without calibration. Besides, we implement an auxiliary constant current (ACC) circuit to solve reliability issues and to improve the stability under a large voltage dropout. Fabricated in a 28-nm bulk CMOS process with a 1.2-A load capability, the proposed LDO achieves 2- $\mu \text{V}$ /mA load regulation and close to 1.5% output accuracy. By employing a wide bandwidth EA and a fast TDC, the hybrid LDO can obtain a fast transient response. The measured undershoot is 70 mV with a 0.6-A load step within 10-ns edge time, and the output voltage can scale from 0.6 V to 0.9 V within 30 ns. [ABSTRACT FROM AUTHOR]

This paper presents a 7-bit digital to phase converter (DPC) for high speed clock and data recovery (CDR) applications which is capable of generating multi-phase clocks at 7-GHz frequency. Fabricated in a standard 65-nm CMOS technology, the design introduces a modified phase interpolator (PI) and a quadrature phase corrector (QPC) to reduce the effect of the circuit imperfections on the DPC’s resolution and linearity. Employing a 14-GHz quadrature reference clock, the DPC achieves DNL/INL of 0.7/6 LSB respectively while consuming 40.5 mW power from 1.05 V supply. [ABSTRACT FROM AUTHOR]

Residual block is a very common component in recent state-of-the art CNNs such as EfficientNet/EfficientDet. Shortcut data accounts for nearly 40% of feature-maps access in ResNet152. Most of the previous DNN compilers/accelerators ignore the shortcut data optimization. This paper presents ShortcutFusion, an optimization tool for FPGA-based accelerator with a reuse-aware static memory allocation for shortcut data, to maximize on-chip data reuse given resource constraints. From TensorFlow DNN models, the proposed design generates instruction sets for a group of nodes which uses an optimized data reuse for each residual block. The accelerator design implemented on the Xilinx KCU1500 FPGA card $2.8\times $ faster and $9.9\times $ more power efficient than NVIDIA RTX 2080 Ti for $256\times 256$ input size. Compared to the result from baseline, in which the weights/inputs/outputs are accessed from the off-chip memory exactly once per each layer, ShortcutFusion reduces the DRAM access by 47.8-84.8% for RetinaNet, Yolov3, ResNet152, and EfficientNet. Given a similar buffer size to ShortcutMining, which also “mine” the shortcut data in hardware, the proposed work reduces off-chip access for feature-maps $5.27\times $ while accessing weight from off-chip memory exactly once. [ABSTRACT FROM AUTHOR]

Spatially coupled serially concatenated codes (SC-SCCs) are constructed by coupling several classical turbo-like component codes. The resulting spatially coupled codes provide a close-to-capacity performance and low error floor, which have attracted a lot of interest in the past few years. The aim of this paper is to perform a comprehensive design space exploration to reveal different aspects of SC-SCCs, which is missing in the literature. More specifically, we investigate the effect of block length, coupling memory, decoding window size, and number of iterations on the decoding performance, complexity, latency, and throughput of SC-SCCs. To this end, we propose two decoding algorithms for the SC-SCCs: block-wise and window-wise decoders. For these, we present VLSI architectural templates and explore them based on building blocks implemented in 12nm FinFET technology. Linking architectural templates with the new algorithms, we demonstrate various tradeoffs between throughput, silicon area, latency, and decoding performance. [ABSTRACT FROM AUTHOR]

Generalized integrated interleaved (GII) codes nest a set of linear block codewords to generate codewords belonging to stronger codes. They are among the best error-correcting codes for next-generation hyper-speed digital communications and storage. Serial encoders for GII codes based on BCH codes have been previous investigated. They consist of BCH encoders whose inputs and outputs are multiplied by vectors decided by the nesting scheme. However, parallel GII encoders for high-speed systems cannot be designed by directly extending serial encoders due to the unique feature that BCH codes of different error-correcting capabilities are involved. Moreover, GII decoder complexity and latency can be greatly reduced by sharing the encoder to compute short remainders for syndrome computation. Although previous resource-shareable BCH encoders can be utilized to implement resource-shareable GII encoders, they are all serial. This paper first proposes a low-complexity scheme to handle the different error-correcting capabilities of the involved codes and align the input and parity symbols for parallel processing. Then two efficient parallel resource-shareable BCH encoder architectures to be used as GII encoder components are developed. The first design is achieved by deriving parallel register state update formulas for concatenated linear-feedback shift registers (LFSRs). Through reformulating the remainder polynomial divisions, the second design allows the inputs to be added to different LFSR taps, and accordingly reduces the complexity by a significant portion. For an example 160-parallel GII-BCH encoder considered for Flash memory applications, the second proposed design requires 14% smaller area compared to the first one. Besides both of them lead to around 50% latency reduction in the nested syndrome computation with small area overheads compared to the best possible alternative design. [ABSTRACT FROM AUTHOR]

The required data rate of wireline communications has increased; however, channel attenuation limits the data bandwidth. Bit-efficient signaling is an effective and efficient solution because more data can be transmitted at the same Nyquist frequency. Several methods for increasing bit efficiency, such as multi-wire signaling, multi-level signaling, and symbol correlation schemes, have been proposed. Each scheme can generate additional codes by encoding the data. Additional codes can be used to transmit more data or to embed data transitions. In this study, the aforementioned schemes are analyzed, and a method is developed to combine them, maximize the bit efficiency, and ensure the data transition density. For the prototype transceiver, a 4-wire PAM-3 (4W3P) signaling scheme was adopted. The 4W3P signaling scheme can increase the bit efficiency to 200% while maintaining the DC-balanced characteristics. Transceiver building blocks, such as the TX driver, feed-forward equalizer, and analog front-end, were optimized for the proposed signaling scheme. The prototype transceiver was fabricated using 28 nm CMOS technology, occupying 0.012 mm2. The RX was measured using the TX and achieved a BER less than $10^{-12}$ at 40 Gb/s over the four wires, with a total transceiver energy efficiency of 1.52 pJ/bit. [ABSTRACT FROM AUTHOR]

Guessing Random Additive Noise Decoding (GRAND) is a universal decoding algorithm that has been recently proposed as a practical way to perform maximum likelihood decoding. It generates a sequence of possible error patterns and applies them to the received vector, checking if the result is a valid codeword. Ordered reliability bits GRAND (ORBGRAND) improves on GRAND by considering soft information received from the channel. Both GRAND and ORBGRAND have been implemented in hardware, focusing on average performance, sacrificing worst case throughput and latency. In this work, an improved pattern schedule for ORBGRAND is proposed. It provides $> 0.5$ dB gain over the standard schedule at a block error rate $\le 10^{-5}$ , and outperforms more complex GRAND flavors with a fraction of the complexity. The proposed schedule is used within a novel code-agnositic decoder architecture: the decoder guarantees fixed high throughput and low latency, making it attractive for latency-constrained applications. It outperforms the worst-case performance of decoders by orders of magnitude, and outperforms many best-case figures. Decoding a code of length 128, it achieves a throughput of 79.21 Gb/s with 58.49 ns latency, yielding better energy efficiency and comparable area efficiency with respect to the state of the art. [ABSTRACT FROM AUTHOR]