A 66-Gb/s/5.5-W RISC-V Many-Core Cluster for 5G+ Software-Defined Radio Uplinks

Following the scale-up of new radio (NR) complexity in 5G and beyond, the physical layer's computing load on base stations is increasing under a strictly constrained latency and power budget; base stations must process > 20-Gb/s uplink wireless data rate on the fly, in < 10 W. At the same time, the programmability and reconfigurability of base station components are the key requirements; it reduces the time and cost of new networks' deployment, it lowers the acceptance threshold for industry players to enter the market, and it ensures return on investments in a fast-paced evolution of standards. In this article, we present the design of a many-core cluster for 5G and beyond base station processing. Our design features 1024, streamlined RISC-V cores with domain-specific FP extensions, and 4-MiB shared memory. It provides the necessary computational capabilities for software-defined processing of the lower physical layer of 5G physical uplink shared channel (PUSCH), satisfying high-end throughput requirements (66 Gb/s for a transition time interval (TTI), 9.4-302 Gb/s depending on the processing stage). The throughput metrics for the implemented functions are ten times higher than in state-of-the-art (SoTA) application-specific instruction processors (ASIPs). The energy efficiency on key NR kernels (2-41 Gb/s/W), measured at 800 MHz, 25 {\deg}C, and 0.8 V, on a placed and routed instance in 12-nm CMOS technology, is competitive with SoTA architectures. The PUSCH processing runs end-to-end on a single cluster in 1.7 ms, at <6-W average power consumption, achieving 12 Gb/s/W.

Fast End-to-End Simulation and Exploration of Many-RISCV-Core Baseband Transceivers for Software-Defined Radio-Access Networks

The fast-rising demand for wireless bandwidth requires rapid evolution of high-performance baseband processing infrastructure. Programmable many-core processors for software-defined radio (SDR) have emerged as high-performance baseband processing engines, offering the flexibility required to capture evolving wireless standards and technologies. This trend must be supported by a design framework enabling functional validation and end-to-end performance analysis of SDR hardware within realistic radio environment models. We propose a static binary translation based simulator augmented with a fast, approximate timing model of the hardware and coupled to wireless channel models to simulate the most performance-critical physical layer functions implemented in software on a many (1024) RISC-V cores cluster customized for SDR. Our framework simulates the detection of a 5G OFDM-symbol on a server-class processor in 9.5s-3min, on a single thread, depending on the input MIMO size (three orders of magnitude faster than RTL simulation). The simulation is easily parallelized to 128 threads with 73-121x speedup compared to a single thread.

An SCMA Receiver for 6G NTN based on Multi-Task Learning

Future 6G networks are envisioned to enhance the user experience in a multitude of different ways. The unification of existing terrestrial networks with non-terrestrial network (NTN) components will provide users with ubiquitous connectivity. Multi-access edge computing (MEC) will enable low-latency services, with computations performed closer to the end users, and distributed learning paradigms. Advanced multiple access schemes, such as sparse code multiple access (SCMA), can be employed to efficiently move data from edge nodes to spaceborne MEC servers. However, the non-orthogonal nature of SCMA results in interference, limiting the effectiveness of traditional SCMA receivers. Hence, NTN links should be protected with robust channel codes, significantly reducing the uplink throughput. Thus, we investigate the application of artificial intelligence (AI) to SCMA receivers for 6G NTNs. We train an AI model with multi-task learning to optimally separate and receive superimposed SCMA signals. Through link level simulations, we evaluate the block error rate (BLER) and the aggregated theoretical throughput achieved by the AI model as a function of the received energy per bit over noise power spectral density ratio (Eb/N0). We show that the proposed receiver achieves a target 10% BLER with 3.5dB lower Eb/N0 with respect to the benchmark algorithm. We conclude the assessment discussing the complexity-related challenges to the implementation of the AI model on board of a low earth orbit satellite.

Uplink OFDM Channel Prediction with Hybrid CNN-LSTM for 6G Non-Terrestrial Networks

Wireless communications are typically subject to complex channel dynamics, requiring the transmission of pilot sequences to estimate and equalize such effects and correctly receive information bits. This is especially true in 6G non-terrestrial networks (NTNs) in low Earth orbit, where one end of the communication link orbits around the Earth at several kilometers per second, and a multi-carrier waveform, such as orthogonal frequency division multiplexing (OFDM), is employed. To minimize the pilot overhead, we remove pilot symbols every other OFDM slot and propose a channel predictor to obtain the channel frequency response (CFR) matrix in absence of pilots. The algorithm employs an encoder-decoder convolutional neural network and a long short-term memory layer, along with skip connections, to predict the CFR matrix on the upcoming slot based on the current one. We demonstrate the effectiveness of the proposed predictor through numerical simulations in tapped delay line channel models, highlighting the effective throughput improvement. We further assess the generalization capabilities of the model, showing minimal throughput degradation when testing under different Doppler spreads and in both line of sight (LoS) and non-LoS propagation conditions. Finally, we discuss computational-complexity-related aspects of the lightweight hybrid CNN-LSTM architecture.

Faster-Than-Nyquist Equalization with Convolutional Neural Networks

Faster-than-Nyquist (FTN) signaling aims at improving the spectral efficiency of wireless communication systems by exceeding the boundaries set by the Nyquist-Shannon sampling theorem. 50 years after its first introduction in the scientific literature, wireless communications have significantly changed, but spectral efficiency remains one of the key challenges. To adopt FTN signaling, inter-symbol interference (ISI) patterns need to be equalized at the receiver. Motivated by the pattern recognition capabilities of convolutional neural networks with skip connections, we propose such deep learning architecture for ISI equalization and symbol demodulation in FTN receivers. We investigate the performance of the proposed model considering quadrature phase shift keying modulation and low density parity check coding, and compare it to a set of benchmarks, including frequency-domain equalization, a quadratic-programming-based receiver, and an equalization scheme based on a deep neural network. We show that our receiver outperforms any benchmark, achieving error rates comparable to those in additive white Gaussian noise channel, and higher effective throughput, thanks to the increased spectral efficiency of FTN signaling. With a compression factor of 60% and code rate 3/4, the proposed model achieves a peak effective throughput of 2.5 Mbps at just 10dB of energy per bit over noise power spectral density ratio, with other receivers being limited by error floors due to the strong inter-symbol interference. To promote reproducibility in deep learning for wireless communications, our code is open source at the repository provided in the references.

Federated Cell-Free MIMO in Non-Terrestrial Networks: Architectures and Performance

While 5G networks are being rolled out, the definition of the potential 5G-Advanced features and the identification of disruptive technologies for 6G systems are being addressed by the scientific and academic communities to tackle the challenges that 2030 communication systems will face, such as terabit-capacity and always-on networks. In this framework, it is globally recognised that Non-Terrestrial Networks (NTN) will play a fundamental role in support to a fully connected world, in which physical, human, and digital domains will converge. In this framework, one of the main challenges that NTN have to address is the provision of the high throughput requested by the new ecosystem. In this paper, we focus on Cell-Free Multiple Input Multiple Output (CF-MIMO) algorithms for NTN. In particular: i) we discuss the architecture design supporting centralised and federated CF-MIMO in NTN, with the latter implementing distributed MIMO algorithms from multiple satellites in the same formation (swarm); ii) propose a novel location-based CF-MIMO algorithm, which does not require Channel State Information (CSI) at the transmitter; and iii) design novel normalisation approaches for federated CF-MIMO in NTN, to cope with the constraints on non-colocated radiating elements. The numerical results substantiate the good performance of the proposed algorithm, also in the presence of non-ideal information.

Efficient Parallelization of 5G-PUSCH on a Scalable RISC-V Many-core Processor

5G Radio access network disaggregation and softwarization pose challenges in terms of computational performance to the processing units. At the physical layer level, the baseband processing computational effort is typically offloaded to specialized hardware accelerators. However, the trend toward software-defined radio-access networks demands flexible, programmable architectures. In this paper, we explore the software design, parallelization and optimization of the key kernels of the lower physical layer (PHY) for physical uplink shared channel (PUSCH) reception on MemPool and TeraPool, two manycore systems having respectively 256 and 1024 small and efficient RISC-V cores with a large shared L1 data memory. PUSCH processing is demanding and strictly time-constrained, it represents a challenge for the baseband processors, and it is also common to most of the uplink channels. Our analysis thus generalizes to the entire lower PHY of the uplink receiver at gNodeB (gNB). Based on the evaluation of the computational effort (in multiply-accumulate operations) required by the PUSCH algorithmic stages, we focus on the parallel implementation of the dominant kernels, namely fast Fourier transform, matrix-matrix multiplication, and matrix decomposition kernels for the solution of linear systems. Our optimized parallel kernels achieve respectively on MemPool and TeraPool speedups of 211, 225, 158, and 762, 880, 722, at high utilization (0.81, 0.89, 0.71, and 0.74, 0.88, 0.71), comparable a single-core serial execution, moving a step closer toward a full-software PUSCH implementation.