MBMarco Bertuletti

Marco Bertuletti

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Marco Bertuletti has a total of 50 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Buckbeak: A 1.2 TFLOPS/W Reconfigurable Vector/Scalar RISC-V Processor for Precision Scalable Near-Sensor Computing in 22-nm FDSOI Technology

    by Marco Bertuletti, Amirhossein Kiamarzi, Mattia Sinigaglia, Gianmarco Ottavi, Matteo Perotti, Giuseppe Tagliavini, Luca Benini, Davide Rossi

    Near-sensor computing requires concurrent execution of data-parallel and control-intensive tasks under tight latency and power constraints. Vector processors excel on data-parallel tasks, thanks to their single-instruction multiple-data (SIMD) execution model. However, scalar control-intensive processing can still saturate their instruction fetch frontend, undermining utilization and efficiency. To address this challenge without compromising flexibility and efficiency for data-parallel computations, we present a runtime-configurable dual-core RISC-V vector processor that switches in 5 cycles between Split Mode (two independent vector engines) and Merge Mode (one wide vector plus a scalar programmable core). On a sensor fusion pipeline that mixes scalar-vector workloads, data parallel tasks can be executed on the wide SIMD processor, while the programmable core, decoupled from the vector engines, takes care of scalar tasks, achieving up to 1.47× speedup over Split Mode. The dual-core reconfigurability allows Split Mode performance optimality on homogeneous tasks with modest data parallelism, delivering up to 1.93× speedup over Merge Mode. Implemented in GF22FDX technology, the processor delivers 10.78 GFLOPS@FP64 to 85.64 GFLOPS@FP8 peak performance (at 1 V) and 1.2 TFLOPS@FP8/W peak energy efficiency (at 0.65 V). Thanks to the vector ISA semantics and underlying architecture, Buckbeak is up to 4× more energy-efficient than state-of-the-art multi-core accelerators implemented in the same node. The streamlined reconfigurable design and lightweight instruction fetch frontend yield up to 14.5× better energy efficiency and 15× better area efficiency compared to larger vector processors for edge processing application.

  • Open Access

    A 8.4 TFLOPS@16b/4.3W General-Purpose Programmable Accelerated Cluster for AI-Native RAN

    by Marco Bertuletti, Yichao Zhang, Alessandro Vanelli-Coralli, Luca Benini

  • Open Access

    A 410GFLOP/s, 64 RISC-V Cores, 204.8GBps Shared-Memory Cluster in 12nm FinFET with Systolic Execution Support for Efficient B5G/6G AI-Enhanced O-RAN

    by Yichao Zhang, Marco Bertuletti, Sergio Mazzola, Samuel Riedel, Luca Benini

    We present HeartStream, a 64-RV-core shared-L1-memory cluster (410 GFLOP/s peak performance and 204.8 GBps L1 bandwidth) for energy-efficient AI-enhanced O-RAN. The cores and cluster architecture are customized for baseband processing, supporting complex (16-bit real&imaginary) instructions: multiply&accumulate, division&square-root, SIMD instructions, and hardware-managed systolic queues, improving up to 1.89x the energy efficiency of key baseband kernels. At 800MHz@0.8V, HeartStream delivers up to 243GFLOP/s on complex-valued wireless workloads. Furthermore, the cores also support efficient AI processing on received data at up to 72 GOP/s. HeartStream is fully compatible with base station power and processing latency limits: it achieves leading-edge software-defined PUSCH efficiency (49.6GFLOP/s/W) and consumes just 0.68W (645MHz@0.65V), within the 4 ms end-to-end constraint for B5G/6G uplink.

  • TeraPool: A Physical Design Aware, 1024 RISC-V Cores Shared-L1-Memory Scaled-Up Cluster Design With High Bandwidth Main Memory Link

    by Yichao Zhang, Marco Bertuletti, Chi Zhang, Samuel Riedel, Diyou Shen, Bowen Wang, Alessandro Vanelli-Coralli, Luca Benini

    Shared L1-memory clusters of streamlined instruction processors (processing elements - PEs) are commonly used as building blocks in modern, massively parallel computing architectures (e.g. GP-GPUs). Scaling out these architectures by increasing the number of clusters incurs computational and power overhead, caused by the requirement to split and merge large data structures in chunks and move chunks across memory hierarchies via the high-latency global interconnect. Scaling up the cluster reduces buffering, copy, and synchronization overheads. However, the complexity of a fully connected cores-to-L1-memory crossbar grows quadratically with PE-count, posing a major physical implementation challenge. We present TeraPool, a physically implementable, >1000 floating-point-capable RISC-V PEs scaled-up cluster design, sharing a Multi-MegaByte >4000-banked L1 memory via a low latency hierarchical interconnect (1-7/9/11 cycles, depending on target frequency). Implemented in 12nm FinFET technology, TeraPool achieves near-gigahertz frequencies (910MHz) typical, 0.80V/25 °C. The energy-efficient hierarchical PE-to-L1-memory interconnect consumes only 9-13.5 pJ for memory bank accesses, just 0.74-1.1× the cost of a FP32 FMA. A high bandwidth main memory link is designed to manage data transfers in/out of the shared L1, sustaining transfers at the full bandwidth of an HBM2E main memory. At 910MHz, the cluster delivers up to 1.89 single precision TFLOP/s peak performance and up to 200GFLOP/s/W energy efficiency (at a high IPC/PE of 0.8 on average) in benchmark kernels, demonstrating the feasibility of scaling a shared-L1 cluster to a thousand PEs, four times the PE count of the largest clusters reported in literature.


  • Open Access

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

    by Marco Bertuletti, Yichao Zhang, Alessandro Vanelli-Coralli, Luca Benini

    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 °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.

  • Open Access

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

    by Marco Bertuletti, Yichao Zhang, Mahdi Abdollahpour, Samuel Riedel, Alessandro Vanelli-Coralli

    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.

  • Open Access

    TeraNoC: A Multi-Channel 32-bit Fine-Grained, Hybrid Mesh-Crossbar NoC for Efficient Scale-up of 1000+ Core Shared-L1-Memory Clusters

    by Yichao Zhang, Zexin Fu, Tim Fischer, Yinrong Li, Marco Bertuletti, Luca Benini

    A key challenge in on-chip interconnect design is to scale up bandwidth while maintaining low latency and high area efficiency. 2D-meshes scale with low wiring area and congestion overhead; however, their end-to-end latency increases with the number of hops, making them unsuitable for latency-sensitive core-to-L1-memory access. On the other hand, crossbars offer low latency, but their routing complexity grows quadratically with the number of I/Os, requiring large physical routing resources and limiting area-efficient scalability. This two-sided interconnect bottleneck hinders the scale-up of many-core, low-latency, tightly coupled shared-memory clusters, pushing designers toward instantiating many smaller and loosely coupled clusters, at the cost of hardware and software overheads. We present TeraNoC, an open-source, hybrid mesh-crossbar on-chip interconnect that offers both scalability and low latency, while maintaining very low routing overhead. The topology, built on 32bit word-width multi-channel 2D-meshes and crossbars, enables the area-efficient scale-up of shared-memory clusters. A router remapper is designed to balance traffic load across interconnect channels. Using TeraNoC, we build a cluster with 1024 single-stage, single-issue cores that share a 4096-banked L1 memory, implemented in 12nm technology. The low interconnect stalls enable high compute utilization of up to 0.85 IPC in compute-intensive, data-parallel key GenAI kernels. TeraNoC only consumes 7.6\% of the total cluster power in kernels dominated by crossbar accesses, and 22.7\% in kernels with high 2D-mesh traffic. Compared to a hierarchical crossbar-only cluster, TeraNoC reduces die area by 37.8\% and improves area efficiency (GFLOP/s/mm2) by up to 98.7\%, while occupying only 10.9\% of the logic area.

  • Open Access

    A Dynamic Allocation Scheme for Adaptive Shared-Memory Mapping on Kilo-core RV Clusters for Attention-Based Model Deployment

    by Bowen Wang, Marco Bertuletti, Yichao Zhang, Victor J. B. Jung, Luca Benini

    Attention-based models demand flexible hardware to manage diverse kernels with varying arithmetic intensities and memory access patterns. Large clusters with shared L1 memory, a common architectural pattern, struggle to fully utilize their processing elements (PEs) when scaled up due to reduced throughput in the hierarchical PE-to-L1 intra-cluster interconnect. This paper presents Dynamic Allocation Scheme (DAS), a runtime programmable address remapping hardware unit coupled with a unified memory allocator, designed to minimize data access contention of PEs onto the multi-banked L1. We evaluated DAS on an aggressively scaled-up 1024-PE RISC-V cluster with Non-Uniform Memory Access (NUMA) PE-to-L1 interconnect to demonstrate its potential for improving data locality in large parallel machine learning workloads. For a Vision Transformer (ViT)-L/16 model, each encoder layer executes in 5.67 ms, achieving a 1.94x speedup over the fixed word-level interleaved baseline with 0.81 PE utilization. Implemented in 12nm FinFET technology, DAS incurs <0.1 % area overhead.

  • Maestro: A 302 GFLOPS/W and 19.8GFLOPS RISC-V Vector-Tensor Architecture for Wearable Ultrasound Edge Computing

    by Mattia Sinigaglia, Amirhossein Kiamarzi, Marco Bertuletti, Luigi Ghionda, Mattia Orlandi, Riccardo Tedeschi, Aurora Di Giampietro, Yvan Tortorella, Luca Bertaccini, Simone Benatti, et al.

    Most Wearable Ultrasound (WUS) devices lack the computational power to process signals at the edge, instead relying on remote offload, which introduces latency, high power consumption, and privacy concerns. We present Maestro, a RISC-V SoC with unified Vector-Tensor Unit (VTU) and memory-coupled Fast Fourier Transform (FFT) accelerators targeting edge processing for wearable ultrasound devices, fabricated using low-cost TSMC 65nm CMOS technology. The VTU achieves peak 302GFLOPS/W and 19.8GFLOPS at FP16, while the multi-precision 16/32-bit floating-point FFT accelerator delivers peak 60.6GFLOPS/W and 3.6GFLOPS at FP16. We evaluate Maestro on a US-based gesture recognition task, achieving 1.62GFLOPS in signal processing at 26.68GFLOPS/W, and 19.52GFLOPS in Convolutional Neural Network (CNN) workloads at 298.03GFLOPS/W. Compared to a state-of-the-art SoC with a similar mission profile, Maestro achieves a $5\times $ speedup while consuming only 12mW, with an energy consumption of 2.5mJ in a wearable US channel preprocessing and ML-based postprocessing pipeline.


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

    by Marco Bertuletti, Yichao Zhang, Alessandro Vanelli-Coralli, Luca Benini

    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 $\gt$ 20-Gb/s uplink wireless data rate on the fly, in $\lt$ 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}~^{\circ } $ 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.