Search

MEGA is a recent transformer-based architecture, which utilizes a linear recurrent operator whose parallel computation, based on the FFT, scales as $O(LlogL)$, with $L$ being the sequence length. We build upon their approach by replacing the linear recurrence with a special temporal convolutional network which permits larger receptive field size with shallower networks, and reduces the computational complexity to $O(L)$. The resulting model is called TCNCA, a Temporal Convolutional Network with Chunked Attention. We evaluate TCNCA on EnWik8 language modeling, long-range-arena (LRA) sequence classification, as well as a synthetic reasoning benchmark associative recall. On EnWik8, TCNCA outperforms MEGA, reaching a lower loss with $1.37\times$/$1.24\times$ faster forward/backward pass during training. The dilated convolutions used in TCNCA are consistently and significantly faster operations than the FFT-based parallelized recurrence in GPUs, making them a scalable candidate for handling very large sequence lengths: they are up to $7.07\times$/$2.86\times$ faster in the forward/backward pass for sequences up to 131k. Further on LRA, TCNCA achieves, on average, $1.28\times$ speed-up during inference with similar accuracy to what MEGA achieves. On associative recall, we find that even a simplified version of TCNCA, without excessive multiplicative and additive interactions, remains superior or competitive to MEGA on a range of sequence lengths and vocabulary sizes.

With the advent of deep learning, progressively larger neural networks have been designed to solve complex tasks. We take advantage of these capacity-rich models to lower the cost of inference by exploiting computation in superposition. To reduce the computational burden per input, we propose Multiple-Input-Multiple-Output Neural Networks (MIMONets) capable of handling many inputs at once. MIMONets augment various deep neural network architectures with variable binding mechanisms to represent an arbitrary number of inputs in a compositional data structure via fixed-width distributed representations. Accordingly, MIMONets adapt nonlinear neural transformations to process the data structure holistically, leading to a speedup nearly proportional to the number of superposed input items in the data structure. After processing in superposition, an unbinding mechanism recovers each transformed input of interest. MIMONets also provide a dynamic trade-off between accuracy and throughput by an instantaneous on-demand switching between a set of accuracy-throughput operating points, yet within a single set of fixed parameters. We apply the concept of MIMONets to both CNN and Transformer architectures resulting in MIMOConv and MIMOFormer, respectively. Empirical evaluations show that MIMOConv achieves about 2-4 x speedup at an accuracy delta within [+0.68, -3.18]% compared to WideResNet CNNs on CIFAR10 and CIFAR100. Similarly, MIMOFormer can handle 2-4 inputs at once while maintaining a high average accuracy within a [-1.07, -3.43]% delta on the long range arena benchmark. Finally, we provide mathematical bounds on the interference between superposition channels in MIMOFormer. Our code is available at https://github.com/IBM/multiple-input-multiple-output-nets., Comment: accepted in NeurIPS 2023

Sparse matrix vector multiplication (SpMV) is central to numerous data-intensive applications, but requires streaming indirect memory accesses that severely degrade both processing and memory throughput in state-of-the-art architectures. Near-memory hardware units, decoupling indirect streams from processing elements, partially alleviate the bottleneck, but rely on low DRAM access granularity, which is highly inefficient for modern DRAM standards like HBM and LPDDR. To fully address the end-to-end challenge, we propose a low-overhead data coalescer combined with a near-memory indirect streaming unit for AXI-Pack, an extension to the widespread AXI4 protocol packing narrow irregular stream elements onto wide memory buses. Our combined solution leverages the memory-level parallelism and coalescence of streaming indirect accesses in irregular applications like SpMV to maximize the performance and bandwidth efficiency attained on wide memory interfaces. Our solution delivers an average speedup of 8x in effective indirect access, often reaching the full memory bandwidth. As a result, we achieve an average end-to-end speedup on SpMV of 3x. Moreover, our approach demonstrates remarkable on-chip efficiency, requiring merely 27kB of on-chip storage and a very compact implementation area of 0.2-0.3mm^2 in a 12nm node., Comment: 6 pages, 6 figures. Submitted to DATE 2024

The increasing demand for heterogeneous functionality in the automotive industry and the evolution of chip manufacturing processes have led to the transition from federated to integrated critical real-time embedded systems (CRTESs). This leads to higher integration challenges of conventional timing predictability techniques due to access contention on shared resources, which can be resolved by providing system-level observability and controllability in hardware. We focus on the interconnect as a shared resource and propose AXI-REALM, a lightweight, modular, and technology-independent real-time extension to industry-standard AXI4 interconnects, available open-source. AXI-REALM uses a credit-based mechanism to distribute and control the bandwidth in a multi-subordinate system on periodic time windows, proactively prevents denial of service from malicious actors in the system, and tracks each manager's access and interference statistics for optimal budget and period selection. We provide detailed performance and implementation cost assessment in a 12nm node and an end-to-end functional case study implementing AXI-REALM into an open-source Linux-capable RISC-V SoC. In a system with a general-purpose core and a hardware accelerator's DMA engine causing interference on the interconnect, AXI-REALM achieves fair bandwidth distribution among managers, allowing the core to recover 68.2 % of its performance compared to the case without contention. Moreover, near-ideal performance (above 95 %) can be achieved by distributing the available bandwidth in favor of the core, improving the worst-case memory access latency from 264 to below eight cycles. Our approach minimizes buffering compared to other solutions and introduces only 2.45 % area overhead compared to the original SoC., Comment: 6 pages, 6 figures, accepted as a regular paper at DATE24

A key challenge for ultra-low-power (ULP) devices is handling peripheral linking, where the main central processing unit (CPU) periodically mediates the interaction among multiple peripherals following wake-up events. Current solutions address this problem by either integrating event interconnects that route single-wire event lines among peripherals or by general-purpose I/O processors, with a strong trade-off between the latency, efficiency of the former, and the flexibility of the latter. In this paper, we present an open-source, peripheral-agnostic, lightweight, and flexible Peripheral Event Linking System (PELS) that combines dedicated event routing with a tiny I/O processor. With the proposed approach, the power consumption of a linking event is reduced by 2.5 times compared to a baseline relying on the main core for the event-linking process, at a low area of just 7 kGE in its minimal configuration, when integrated into a ULP RISC-V IoT processor., Comment: 6 pages, accepted at DATE24 conference, camera-ready version

From classical HPC to deep learning, MatMul is at the heart of today's computing. The recent Maddness method approximates MatMul without the need for multiplication by using a hash-based version of product quantization (PQ) indexing into a look-up table (LUT). Stella Nera is the first Maddness accelerator and it achieves 15x higher area efficiency (GMAC/s/mm^2) and more than 25x higher energy efficiency (TMAC/s/W) than direct MatMul accelerators implemented in the same technology. The hash function is a decision tree, which allows for an efficient hardware implementation as the multiply-accumulate operations are replaced by decision tree passes and LUT lookups. The entire Maddness MatMul can be broken down into parts that allow an effective implementation with small computing units and memories, allowing it to reach extreme efficiency while remaining generically applicable for MatMul tasks. In a commercial 14nm technology and scaled to 3nm, we achieve an energy efficiency of 161 TOp/s/W@0.55V with a Top-1 accuracy on CIFAR-10 of more than 92.5% using ResNet9., Comment: 6 pages, 7 figures, preprint under review

Processors using the open RISC-V ISA are finding increasing adoption in the embedded world. Many embedded use cases have real-time constraints and require flexible, predictable, and fast reactive handling of incoming events. However, RISC- V processors are still lagging in this area compared to more mature proprietary architectures, such as ARM Cortex-M and TriCore, which have been tuned for years. The default interrupt controller standardized by RISC-V, the Core Local Interruptor (CLINT), lacks configurability in prioritization and preemption of interrupts. The RISC-V Core Local Interrupt Controller (CLIC) specification addresses this concern by enabling pre-emptible, low-latency vectored interrupts while also envisioning optional extensions to improve interrupt latency. In this work, we implement a CLIC for the CV32E40P, an industrially supported open-source 32-bit MCU-class RISC-V core, and enhance it with fastirq: a custom extension that provides interrupt latency as low as 6 cycles. We call CV32RT our enhanced core. To the best of our knowledge, CV32RT is the first fully open-source RV32 core with competitive interrupt-handling features compared to the Arm Cortex-M series and TriCore. The proposed extensions are also demonstrated to improve task context switching in real-time operating systems., Comment: 12 pages, submitted to IEEE Transactions on VLSI Systems (TVLSI)

Vector processing is highly effective in boosting processor performance and efficiency for data-parallel workloads. In this paper, we present Ara2, the first fully open-source vector processor to support the RISC-V V 1.0 frozen ISA. We evaluate Ara2's performance on a diverse set of data-parallel kernels for various problem sizes and vector-unit configurations, achieving an average functional-unit utilization of 95% on the most computationally intensive kernels. We pinpoint performance boosters and bottlenecks, including the scalar core, memories, and vector architecture, providing insights into the main vector architecture's performance drivers. Leveraging the openness of the design, we implement Ara2 in a 22nm technology, characterize its PPA metrics on various configurations (2-16 lanes), and analyze its microarchitecture and implementation bottlenecks. Ara2 achieves a state-of-the-art energy efficiency of 37.8 DP-GFLOPS/W (0.8V) and 1.35GHz of clock frequency (critical path: ~40 FO4 gates). Finally, we explore the performance and energy-efficiency trade-offs of multi-core vector processors: we find that multiple vector cores help overcome the scalar core issue-rate bound that limits short-vector performance. For example, a cluster of eight 2-lane Ara2 (16 FPUs) achieves more than 3x better performance than a 16-lane single-core Ara2 (16 FPUs) when executing a 32x32x32 matrix multiplication, with 1.5x improved energy efficiency., Comment: To be published in: IEEE Transactions on Computers

Chiplet architectures are a promising paradigm to overcome the scaling challenges of monolithic chips. Chiplets offer heterogeneity, modularity, and cost-effectiveness. The design space of chiplet architectures is huge as there are many degrees of freedom such as the number, size and placement of chiplets, the topology of the inter-chiplet interconnect and many more. Existing tools for cost and performance prediction are often too slow to explore this design space. We present RapidChiplet, a fast, open-source toolchain to predict latency and throughput of the inter-chiplet interconnect, as well as a chip's manufacturing cost and thermal stability.

Event-based cameras, also called silicon retinas, potentially revolutionize computer vision by detecting and reporting significant changes in intensity asynchronous events, offering extended dynamic range, low latency, and low power consumption, enabling a wide range of applications from autonomous driving to longtime surveillance. As an emerging technology, there is a notable scarcity of publicly available datasets for event-based systems that also feature frame-based cameras, in order to exploit the benefits of both technologies. This work quantitatively evaluates a multi-modal camera setup for fusing high-resolution DVS data with RGB image data by static camera alignment. The proposed setup, which is intended for semi-automatic DVS data labeling, combines two recently released Prophesee EVK4 DVS cameras and one global shutter XIMEA MQ022CG-CM RGB camera. After alignment, state-of-the-art object detection or segmentation networks label the image data by mapping boundary boxes or labeled pixels directly to the aligned events. To facilitate this process, various time-based synchronization methods for DVS data are analyzed, and calibration accuracy, camera alignment, and lens impact are evaluated. Experimental results demonstrate the benefits of the proposed system: the best synchronization method yields an image calibration error of less than 0.90px and a pixel cross-correlation deviation of1.6px, while a lens with 8mm focal length enables detection of objects with size 30cm at a distance of 350m against homogeneous background.

Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.

Nano-sized unmanned aerial vehicles (UAVs) are well-fit for indoor applications and for close proximity to humans. To enable autonomy, the nano-UAV must be able to self-localize in its operating environment. This is a particularly-challenging task due to the limited sensing and compute resources on board. This work presents an online and onboard approach for localization in floor plans annotated with semantic information. Unlike sensor-based maps, floor plans are readily-available, and do not increase the cost and time of deployment. To overcome the difficulty of localizing in sparse maps, the proposed approach fuses geometric information from miniaturized time-of-flight sensors and semantic cues. The semantic information is extracted from images by deploying a state-of-the-art object detection model on a high-performance multi-core microcontroller onboard the drone, consuming only 2.5mJ per frame and executing in 38ms. In our evaluation, we globally localize in a real-world office environment, achieving 90% success rate. We also release an open-source implementation of our work., Comment: Accepted for ICRA 2024, 7 pages

The rapid proliferation of computing domains relying on Internet of Things (IoT) devices has created a pressing need for efficient and accurate deep-learning (DL) models that can run on low-power devices. However, traditional DL models tend to be too complex and computationally intensive for typical IoT end-nodes. To address this challenge, Neural Architecture Search (NAS) has emerged as a popular design automation technique for co-optimizing the accuracy and complexity of deep neural networks. Nevertheless, existing NAS techniques require many iterations to produce a network that adheres to specific hardware constraints, such as the maximum memory available on the hardware or the maximum latency allowed by the target application. In this work, we propose a novel approach to incorporate multiple constraints into so-called Differentiable NAS optimization methods, which allows the generation, in a single shot, of a model that respects user-defined constraints on both memory and latency in a time comparable to a single standard training. The proposed approach is evaluated on five IoT-relevant benchmarks, including the MLPerf Tiny suite and Tiny ImageNet, demonstrating that, with a single search, it is possible to reduce memory and latency by 87.4% and 54.2%, respectively (as defined by our targets), while ensuring non-inferior accuracy on state-of-the-art hand-tuned deep neural networks for TinyML., Comment: Accepted for publication at the IEEE Transactions on Emerging Topics in Computing

One of the key challenges when operating microcontrollers in harsh environments such as space is radiation-induced Single Event Upsets (SEUs), which can lead to errors in computation. Common countermeasures rely on proprietary radiation-hardened technologies, low density technologies, or extensive replication, leading to high costs and low performance and efficiency. To combat this, we present Trikarenos, a fault-tolerant 32-bit RISC-V microcontroller SoC in an advanced TSMC 28nm technology. Trikarenos alleviates the replication cost by employing a configurable triple-core lockstep configuration, allowing three Ibex cores to execute applications reliably, operating on ECC-protected memory. If reliability is not needed for a given application, the cores can operate independently in parallel for higher performance and efficiency. Trikarenos consumes 15.7mW at 250MHz executing a fault-tolerant matrix-matrix multiplication, a 21.5x efficiency gain over state-of-the-art, and performance is increased by 2.96x when reliability is not needed for processing, with a 2.36x increase in energy efficiency., Comment: 4 pages, 4 figures, accepted by IEEE International Conference on Electronics Circuits and Systems (ICECS) 2023

Ultrasound is a key technology in healthcare, and it is being explored for non-invasive, wearable, continuous monitoring of vital signs. However, its widespread adoption in this scenario is still hindered by the size, complexity, and power consumption of current devices. Moreover, such an application demands adaptability to human anatomy, which is hard to achieve with current transducer technology. This paper presents a novel ultrasound system prototype based on a fully printed, lead-free, and flexible polymer ultrasound transducer, whose bending radius promises good adaptability to the human anatomy. Our application scenario focuses on continuous blood flow monitoring. We implemented a hardware envelope filter to efficiently transpose high-frequency ultrasound signals to a lower-frequency spectrum. This reduces computational and power demands with little to no degradation in the task proposed for this work. We validated our method on a setup that mimics human blood flow by using a flow phantom and a peristaltic pump simulating 3 different heartbeat rhythms: 60, 90 and 120 beats per minute. Our ultrasound setup reconstructs peristaltic pump frequencies with errors of less than 0.05 Hz (3 bpm) from the set pump frequency, both for the raw echo and the enveloped echo. The analog pre-processing showed a promising reduction of signal bandwidth of more than 6x: pulse-echo signals of transducers excited at 12.5 MHz were reduced to about 2 MHz. Thus, allowing consumer MCUs to acquire and elaborate signals within mW-power range in an inexpensive fashion., Comment: 5 pages, 2 tables, 3 figures, Accepted at IEEE BioCAS 2023

In ski jumping, low repetition rates of jumps limit the effectiveness of training. Thus, increasing learning rate within every single jump is key to success. A critical element of athlete training is motor learning, which has been shown to be accelerated by feedback methods. In particular, a fine-grained control of the center of gravity in the in-run is essential. This is because the actual takeoff occurs within a blink of an eye ($\sim$300ms), thus any unbalanced body posture during the in-run will affect flight. This paper presents a smart, compact, and energy-efficient wireless sensor system for real-time performance analysis and biofeedback during ski jumping. The system operates by gauging foot pressures at three distinct points on the insoles of the ski boot at 100Hz. Foot pressure data can either be directly sent to coaches to improve their feedback, or fed into a ML model to give athletes instantaneous in-action feedback using a vibration motor in the ski boot. In the biofeedback scenario, foot pressures act as input variables for an optimized XGBoost model. We achieve a high predictive accuracy of 92.7% for center of mass predictions (dorsal shift, neutral stand, ventral shift). Subsequently, we parallelized and fine-tuned our XGBoost model for a RISC-V based low power parallel processor (GAP9), based on the PULP architecture. We demonstrate real-time detection and feedback (0.0109ms/inference) using our on-chip deployment. The proposed smart system is unobtrusive with a slim form factor (13mm baseboard, 3.2mm antenna) and a lightweight build (26g). Power consumption analysis reveals that the system's energy-efficient design enables sustained operation over multiple days (up to 300 hours) without requiring recharge., Comment: 5 pages, 2 tables, 4 figure, Accepted at IEEE BioCAS 2023

Perceiving and mapping the surroundings are essential for enabling autonomous navigation in any robotic platform. The algorithm class that enables accurate mapping while correcting the odometry errors present in most robotics systems is Simultaneous Localization and Mapping (SLAM). Today, fully onboard mapping is only achievable on robotic platforms that can host high-wattage processors, mainly due to the significant computational load and memory demands required for executing SLAM algorithms. For this reason, pocket-size hardware-constrained robots offload the execution of SLAM to external infrastructures. To address the challenge of enabling SLAM algorithms on resource-constrained processors, this paper proposes NanoSLAM, a lightweight and optimized end-to-end SLAM approach specifically designed to operate on centimeter-size robots at a power budget of only 87.9 mW. We demonstrate the mapping capabilities in real-world scenarios and deploy NanoSLAM on a nano-drone weighing 44 g and equipped with a novel commercial RISC-V low-power parallel processor called GAP9. The algorithm is designed to leverage the parallel capabilities of the RISC-V processing cores and enables mapping of a general environment with an accuracy of 4.5 cm and an end-to-end execution time of less than 250 ms., Comment: 23 pages

The ever-increasing computational and storage requirements of modern applications and the slowdown of technology scaling pose major challenges to designing and implementing efficient computer architectures. In this paper, we leverage the architectural balance principle to alleviate the bandwidth bottleneck at the L1 data memory boundary of a tightly-coupled cluster of processing elements (PEs). We thus explore coupling each PE with an L0 memory, namely a private register file implemented as Standard Cell Memory (SCM). Architecturally, the SCM is the Vector Register File (VRF) of Spatz, a compact 64-bit floating-point-capable vector processor based on RISC-V's Vector Extension Zve64d. Unlike typical vector processors, whose VRF are hundreds of KiB large, we prove that Spatz can achieve peak energy efficiency with a VRF of only 2 KiB. An implementation of the Spatz-based cluster in GlobalFoundries' 12LPP process with eight double-precision Floating Point Units (FPUs) achieves an FPU utilization just 3.4% lower than the ideal upper bound on a double-precision, floating-point matrix multiplication. The cluster reaches 7.7 FMA/cycle, corresponding to 15.7 GFLOPS-DP and 95.7 GFLOPS-DP/W at 1 GHz and nominal operating conditions (TT, 0.80V, 25^oC) with more than 55% of the power spent on the FPUs. Furthermore, the optimally-balanced Spatz-based cluster reaches a 95.0% FPU utilization (7.6 FMA/cycle), 15.2 GFLOPS-DP, and 99.3 GFLOPS-DP/W (61% of the power spent in the FPU) on a 2D workload with a 7x7 kernel, resulting in an outstanding area/energy efficiency of 171 GFLOPS-DP/W/mm^2. At equi-area, our computing cluster built upon compact vector processors reaches a 30% higher energy efficiency than a cluster with the same FPU count built upon scalar cores specialized for stream-based floating-point computation., Comment: 14 pages

Brain-machine interfaces (BMIs) have emerged as a transformative force in assistive technologies, empowering individuals with motor impairments by enabling device control and facilitating functional recovery. However, the persistent challenge of inter-session variability poses a significant hurdle, requiring time-consuming calibration at every new use. Compounding this issue, the low comfort level of current devices further restricts their usage. To address these challenges, we propose a comprehensive solution that combines a tiny CNN-based Transfer Learning (TL) approach with a comfortable, wearable EEG headband. The novel wearable EEG device features soft dry electrodes placed on the headband and is capable of on-board processing. We acquire multiple sessions of motor-movement EEG data and achieve up to 96% inter-session accuracy using TL, greatly reducing the calibration time and improving usability. By executing the inference on the edge every 100ms, the system is estimated to achieve 30h of battery life. The comfortable BMI setup with tiny CNN and TL paves the way to future on-device continual learning, essential for tackling inter-session variability and improving usability.

Surface electromyography (sEMG) is a well-established approach to monitor muscular activity on wearable and resource-constrained devices. However, when measuring deeper muscles, its low signal-to-noise ratio (SNR), high signal attenuation, and crosstalk degrade sensing performance. Ultrasound (US) complements sEMG effectively with its higher SNR at high penetration depths. In fact, combining US and sEMG improves the accuracy of muscle dynamic assessment, compared to using only one modality. However, the power envelope of US hardware is considerably higher than that of sEMG, thus inflating energy consumption and reducing the battery life. This work proposes a wearable solution that integrates both modalities and utilizes an EMG-driven wake-up approach to achieve ultra-low power consumption as needed for wearable long-term monitoring. We integrate two wearable state-of-the-art (SoA) US and ExG biosignal acquisition devices to acquire time-synchronized measurements of the short head of the biceps. To minimize power consumption, the US probe is kept in a sleep state when there is no muscle activity. sEMG data are processed on the probe (filtering, envelope extraction and thresholding) to identify muscle activity and generate a trigger to wake-up the US counterpart. The US acquisition starts before muscle fascicles displacement thanks to a triggering time faster than the electromechanical delay (30-100 ms) between the neuromuscular junction stimulation and the muscle contraction. Assuming a muscle contraction of 200 ms at a contraction rate of 1 Hz, the proposed approach enables more than 59% energy saving (with a full-system average power consumption of 12.2 mW) as compared to operating both sEMG and US continuously., Comment: 4 pages, 5 figures, 1 table, 2023 IEEE International Ultrasonics Symposium

The use of Unmanned Aerial Vehicles (UAVs) is rapidly increasing in applications ranging from surveillance and first-aid missions to industrial automation involving cooperation with other machines or humans. To maximize area coverage and reduce mission latency, swarms of collaborating drones have become a significant research direction. However, this approach requires open challenges in positioning, mapping, and communications to be addressed. This work describes a distributed mapping system based on a swarm of nano-UAVs, characterized by a limited payload of 35 g and tightly constrained on-board sensing and computing capabilities. Each nano-UAV is equipped with four 64-pixel depth sensors that measure the relative distance to obstacles in four directions. The proposed system merges the information from the swarm and generates a coherent grid map without relying on any external infrastructure. The data fusion is performed using the iterative closest point algorithm and a graph-based simultaneous localization and mapping algorithm, running entirely on-board the UAV's low-power ARM Cortex-M microcontroller with just 192 kB of SRAM memory. Field results gathered in three different mazes from a swarm of up to 4 nano-UAVs prove a mapping accuracy of 12 cm and demonstrate that the mapping time is inversely proportional to the number of agents. The proposed framework scales linearly in terms of communication bandwidth and on-board computational complexity, supporting communication between up to 20 nano-UAVs and mapping of areas up to 180 m2 with the chosen configuration requiring only 50 kB of memory.

Multi-tenancy is essential for unleashing SmartNIC's potential in datacenters. Our systematic analysis in this work shows that existing on-path SmartNICs have resource multiplexing limitations. For example, existing solutions lack multi-tenancy capabilities such as performance isolation and QoS provisioning for compute and IO resources. Compared to standard NIC data paths with a well-defined set of offloaded functions, unpredictable execution times of SmartNIC kernels make conventional approaches for multi-tenancy and QoS insufficient. We fill this gap with OSMOSIS, a SmartNICs resource manager co-design. OSMOSIS extends existing OS mechanisms to enable dynamic hardware resource multiplexing of the on-path packet processing data plane. We integrate OSMOSIS within an open-source RISC-V-based 400Gbit/s SmartNIC. Our performance results demonstrate that OSMOSIS fully supports multi-tenancy and enables broader adoption of SmartNICs in datacenters with low overhead., Comment: 12 pages, 14 figures, 103 references

High Performance and Energy Efficiency are critical requirements for Internet of Things (IoT) end-nodes. Exploiting tightly-coupled clusters of programmable processors (CMPs) has recently emerged as a suitable solution to address this challenge. One of the main bottlenecks limiting the performance and energy efficiency of these systems is the instruction cache architecture due to its criticality in terms of timing (i.e., maximum operating frequency), bandwidth, and power. We propose a hierarchical instruction cache tailored to ultra-low-power tightly-coupled processor clusters where a relatively large cache (L1.5) is shared by L1 private caches through a two-cycle latency interconnect. To address the performance loss caused by the L1 capacity misses, we introduce a next-line prefetcher with cache probe filtering (CPF) from L1 to L1.5. We optimize the core instruction fetch (IF) stage by removing the critical core-to-L1 combinational path. We present a detailed comparison of instruction cache architectures' performance and energy efficiency for parallel ultra-low-power (ULP) clusters. Focusing on the implementation, our two-level instruction cache provides better scalability than existing shared caches, delivering up to 20\% higher operating frequency. On average, the proposed two-level cache improves maximum performance by up to 17\% compared to the state-of-the-art while delivering similar energy efficiency for most relevant applications., Comment: 14 pages

Epilepsy is a prevalent neurological disorder that affects millions of individuals globally, and continuous monitoring coupled with automated seizure detection appears as a necessity for effective patient treatment. To enable long-term care in daily-life conditions, comfortable and smart wearable devices with long battery life are required, which in turn set the demand for resource-constrained and energy-efficient computing solutions. In this context, the development of machine learning algorithms for seizure detection faces the challenge of heavily imbalanced datasets. This paper introduces EpiDeNet, a new lightweight seizure detection network, and Sensitivity-Specificity Weighted Cross-Entropy (SSWCE), a new loss function that incorporates sensitivity and specificity, to address the challenge of heavily unbalanced datasets. The proposed EpiDeNet-SSWCE approach demonstrates the successful detection of 91.16% and 92.00% seizure events on two different datasets (CHB-MIT and PEDESITE, respectively), with only four EEG channels. A three-window majority voting-based smoothing scheme combined with the SSWCE loss achieves 3x reduction of false positives to 1.18 FP/h. EpiDeNet is well suited for implementation on low-power embedded platforms, and we evaluate its performance on two ARM Cortex-based platforms (M4F/M7) and two parallel ultra-low power (PULP) systems (GAP8, GAP9). The most efficient implementation (GAP9) achieves an energy efficiency of 40 GMAC/s/W, with an energy consumption per inference of only 0.051 mJ at high performance (726.46 MMAC/s), outperforming the best ARM Cortex-based solutions by approximately 160x in energy efficiency. The EpiDeNet-SSWCE method demonstrates effective and accurate seizure detection performance on heavily imbalanced datasets, while being suited for implementation on energy-constrained platforms., Comment: 5 pages, 4 tables, 1 figure, Accepted at BioCAS 2023

Emerging deep neural network (DNN) applications require high-performance multi-core hardware acceleration with large data bursts. Classical network-on-chips (NoCs) use serial packet-based protocols suffering from significant protocol translation overheads towards the endpoints. This paper proposes PATRONoC, an open-source fully AXI-compliant NoC fabric to better address the specific needs of multi-core DNN computing platforms. Evaluation of PATRONoC in a 2D-mesh topology shows 34% higher area efficiency compared to a state-of-the-art classical NoC at 1 GHz. PATRONoC's throughput outperforms a baseline NoC by 2-8X on uniform random traffic and provides a high aggregated throughput of up to 350 GiB/s on synthetic and DNN workload traffic., Comment: Accepted and presented at 60th DAC

Relative localization is a crucial functional block of any robotic swarm. We address it in a fleet of nano-drones characterized by a 10 cm-scale form factor, which makes them highly versatile but also strictly limited in their onboard power envelope. State-of-the-Art solutions leverage Ultra-WideBand (UWB) technology, allowing distance range measurements between peer nano-drones and a stationary infrastructure of multiple UWB anchors. Therefore, we propose an UWB-based infrastructure-free nano-drones swarm, where part of the fleet acts as dynamic anchors, i.e., anchor-drones (ADs), capable of automatic deployment and landing. By varying the Ads' position constraint, we develop three alternative solutions with different trade-offs between flexibility and localization accuracy. In-field results, with four flying mission-drones (MDs), show a localization root mean square error (RMSE) spanning from 15.3 cm to 27.8 cm, at most. Scaling the number of MDs from 4 to 8, the RMSE marginally increases, i.e., less than 10 cm at most. The power consumption of the MDs' UWB module amounts to 342 mW. Ultimately, compared to a fixed-infrastructure commercial solution, our infrastructure-free system can be deployed anywhere and rapidly by taking 5.7 s to self-localize 4 ADs with a localization RMSE of up to 12.3% in the most challenging case with 8 MDs.

Synchronization is likely the most critical performance killer in shared-memory parallel programs. With the rise of multi-core and many-core processors, the relative impact on performance and energy overhead of synchronization is bound to grow. This paper focuses on barrier synchronization for TeraPool, a cluster of 1024 RISC-V processors with non-uniform memory access to a tightly coupled 4MB shared L1 data memory. We compare the synchronization strategies available in other multi-core and many-core clusters to identify the optimal native barrier kernel for TeraPool. We benchmark a set of optimized barrier implementations and evaluate their performance in the framework of the widespread fork-join Open-MP style programming model. We test parallel kernels from the signal-processing and telecommunications domain, achieving less than 10% synchronization overhead over the total runtime for problems that fit TeraPool's L1 memory. By fine-tuning our tree barriers, we achieve 1.6x speed-up with respect to a naive central counter barrier and just 6.2% overhead on a typical 5G application, including a challenging multistage synchronization kernel. To our knowledge, this is the first work where shared-memory barriers are used for the synchronization of a thousand processing elements tightly coupled to shared data memory., Comment: 15 pages, 7 figures

This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20% more efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference., Comment: * The first three authors contributed equally to this research

The complexity of automotive systems is increasing quickly due to the integration of novel functionalities such as assisted or autonomous driving. However, increasing complexity poses considerable challenges to the automotive supply chain since the continuous addition of new hardware and network cabling is not considered tenable. The availability of modern heterogeneous multi-processor chips represents a unique opportunity to reduce vehicle costs by integrating multiple functionalities into fewer Electronic Control Units (ECUs). In addition, the recent improvements in open-hardware technology allow to further reduce costs by avoiding lock-in solutions. This paper presents a mixed-criticality multi-OS architecture for automotive ECUs based on open hardware and open-source technologies. Safety-critical functionalities are executed by an AUTOSAR OS running on a RISC-V processor, while the Linux OS executes more advanced functionalities on a multi-core ARM CPU. Besides presenting the implemented stack and the communication infrastructure, this paper provides a quantitative gap analysis between an HW/SW optimized version of the RISC-V processor and a COTS Arm Cortex-R in terms of real-time features, confirming that RISC-V is a valuable candidate for running AUTOSAR Classic stacks of next-generation automotive MCUs., Comment: 8 pages, 2023 12th Mediterranean Conference on Embedded Computing (MECO)

Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and audio processing. However, the efficient hardware acceleration of transformer models poses new challenges due to their high arithmetic intensities, large memory requirements, and complex dataflow dependencies. In this work, we propose ITA, a novel accelerator architecture for transformers and related models that targets efficient inference on embedded systems by exploiting 8-bit quantization and an innovative softmax implementation that operates exclusively on integer values. By computing on-the-fly in streaming mode, our softmax implementation minimizes data movement and energy consumption. ITA achieves competitive energy efficiency with respect to state-of-the-art transformer accelerators with 16.9 TOPS/W, while outperforming them in area efficiency with 5.93 TOPS/mm$^2$ in 22 nm fully-depleted silicon-on-insulator technology at 0.8 V., Comment: Accepted for publication at the 2023 ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED)

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved with homogeneous-bit-width quantization. To navigate the intractable search space of mixed-precision configurations for a given network, this paper proposes a hybrid search methodology. It consists of a hardware-agnostic differentiable search algorithm followed by a hardware-aware heuristic optimization to find mixed-precision configurations latency-optimized for a specific hardware target. We evaluate our algorithm on MobileNetV1 and MobileNetV2 and deploy the resulting networks on a family of multi-core RISC-V microcontroller platforms with different hardware characteristics. We achieve up to 28.6% reduction of end-to-end latency compared to an 8-bit model at a negligible accuracy drop from a full-precision baseline on the 1000-class ImageNet dataset. We demonstrate speedups relative to an 8-bit baseline, even on systems with no hardware support for sub-byte arithmetic at negligible accuracy drop. Furthermore, we show the superiority of our approach with respect to differentiable search targeting reduced binary operation counts as a proxy for latency., Comment: Accepted for publication at the 2023 IEEE International Conference of Artificial Intelligence Circuits and Systems (AICAS '23)

Wearable biosignal processing applications are driving significant progress toward miniaturized, energy-efficient Internet-of-Things solutions for both clinical and consumer applications. However, scaling toward high-density multi-channel front-ends is only feasible by performing data processing and machine Learning (ML) near-sensor through energy-efficient edge processing. To tackle these challenges, we introduce BioGAP, a novel, compact, modular, and lightweight (6g) medical-grade biosignal acquisition and processing platform powered by GAP9, a ten-core ultra-low-power SoC designed for efficient multi-precision (from FP to aggressively quantized integer) processing, as required for advanced ML and DSP. BioGAPs form factor is 16x21x14 mm$^3$ and comprises two stacked PCBs: a baseboard integrating the GAP9 SoC, a wireless Bluetooth Low Energy (BLE) capable SoC, a power management circuit, and an accelerometer; and a shield including an analog front-end (AFE) for ExG acquisition. Finally, the system also includes a flexibly placeable photoplethysmogram (PPG) PCB with a size of 9x7x3 mm$^3$ and a rechargeable battery ($\phi$ 12x5 mm$^2$). We demonstrate BioGAP on a Steady State Visually Evoked Potential (SSVEP)-based Brain-Computer Interface (BCI) application. We achieve 3.6 uJ/sample in streaming and 2.2 uJ/sample in onboard processing mode, thanks to an efficiency on the FFT computation task of 16.7 Mflops/s/mW with wireless bandwidth reduction of 97%, within a power budget of just 18.2 mW allowing for an operation time of 15 h., Comment: 7 pages, 9 figures, 1 table, accepted for IEEE COINS 2023

The emerging trend of deploying complex algorithms, such as Deep Neural Networks (DNNs), increasingly poses strict memory and energy efficiency requirements on Internet-of-Things (IoT) end-nodes. Mixed-precision quantization has been proposed as a technique to minimize a DNN's memory footprint and maximize its execution efficiency, with negligible end-to-end precision degradation. In this work, we present a novel hardware and software stack for energy-efficient inference of mixed-precision Quantized Neural Networks (QNNs). We introduce Flex-V, a processor based on the RISC-V Instruction Set Architecture (ISA) that features fused Mac&Load mixed-precision dot product instructions; to avoid the exponential growth of the encoding space due to mixed-precision variants, we encode formats into the Control-Status Registers (CSRs). Flex-V core is integrated into a tightly-coupled cluster of eight processors; in addition, we provide a full framework for the end-to-end deployment of DNNs including a compiler, optimized libraries, and a memory-aware deployment flow. Our results show up to 91.5 MAC/cycle and 3.26 TOPS/W on the cluster, implemented in a commercial 22nm FDX technology, with up to 8.5x speed-up, and an area overhead of only 5.6% with respect to the baseline. To demonstrate the capabilities of the architecture, we benchmark it with end-to-end real-life QNNs, improving performance by 2x - 2.5x with respect to existing solutions using fully flexible programmable processors.

Recent trends in deep learning (DL) imposed hardware accelerators as the most viable solution for several classes of high-performance computing (HPC) applications such as image classification, computer vision, and speech recognition. This survey summarizes and classifies the most recent advances in designing DL accelerators suitable to reach the performance requirements of HPC applications. In particular, it highlights the most advanced approaches to support deep learning accelerations including not only GPU and TPU-based accelerators but also design-specific hardware accelerators such as FPGA-based and ASIC-based accelerators, Neural Processing Units, open hardware RISC-V-based accelerators and co-processors. The survey also describes accelerators based on emerging memory technologies and computing paradigms, such as 3D-stacked Processor-In-Memory, non-volatile memories (mainly, Resistive RAM and Phase Change Memories) to implement in-memory computing, Neuromorphic Processing Units, and accelerators based on Multi-Chip Modules. Among emerging technologies, we also include some insights into quantum-based accelerators and photonics. To conclude, the survey classifies the most influential architectures and technologies proposed in the last years, with the purpose of offering the reader a comprehensive perspective in the rapidly evolving field of deep learning., Comment: Preprint version of our manuscript submitted to the journal @ ACM CSUR (58 pages including Appendix) on June 22nd, 2023. Major revision submitted on July 12th, 2024

High-Performance Computing (HPC) processors are nowadays integrated Cyber-Physical Systems demanding complex and high-bandwidth closed-loop power and thermal control strategies. To efficiently satisfy real-time multi-input multi-output (MIMO) optimal power requirements, high-end processors integrate an on-die power controller system (PCS). While traditional PCSs are based on a simple microcontroller (MCU)-class core, more scalable and flexible PCS architectures are required to support advanced MIMO control algorithms for managing the ever-increasing number of cores, power states, and process, voltage, and temperature variability. This paper presents ControlPULP, an open-source, HW/SW RISC-V parallel PCS platform consisting of a single-core MCU with fast interrupt handling coupled with a scalable multi-core programmable cluster accelerator and a specialized DMA engine for the parallel acceleration of real-time power management policies. ControlPULP relies on FreeRTOS to schedule a reactive power control firmware (PCF) application layer. We demonstrate ControlPULP in a power management use-case targeting a next-generation 72-core HPC processor. We first show that the multi-core cluster accelerates the PCF, achieving 4.9x speedup compared to single-core execution, enabling more advanced power management algorithms within the control hyper-period at a shallow area overhead, about 0.1% the area of a modern HPC CPU die. We then assess the PCS and PCF by designing an FPGA-based, closed-loop emulation framework that leverages the heterogeneous SoCs paradigm, achieving DVFS tracking with a mean deviation within 3% the plant's thermal design power (TDP) against a software-equivalent model-in-the-loop approach. Finally, we show that the proposed PCF compares favorably with an industry-grade control algorithm under computational-intensive workloads., Comment: 33 pages, 11 figures

Modern smartwatches often include photoplethysmographic (PPG) sensors to measure heartbeats or blood pressure through complex algorithms that fuse PPG data with other signals. In this work, we propose a collaborative inference approach that uses both a smartwatch and a connected smartphone to maximize the performance of heart rate (HR) tracking while also maximizing the smartwatch's battery life. In particular, we first analyze the trade-offs between running on-device HR tracking or offloading the work to the mobile. Then, thanks to an additional step to evaluate the difficulty of the upcoming HR prediction, we demonstrate that we can smartly manage the workload between smartwatch and smartphone, maintaining a low mean absolute error (MAE) while reducing energy consumption. We benchmark our approach on a custom smartwatch prototype, including the STM32WB55 MCU and Bluetooth Low-Energy (BLE) communication, and a Raspberry Pi3 as a proxy for the smartphone. With our Collaborative Heart Rate Inference System (CHRIS), we obtain a set of Pareto-optimal configurations demonstrating the same MAE as State-of-Art (SoA) algorithms while consuming less energy. For instance, we can achieve approximately the same MAE of TimePPG-Small (5.54 BPM MAE vs. 5.60 BPM MAE) while reducing the energy by 2.03x, with a configuration that offloads 80\% of the predictions to the phone. Furthermore, accepting a performance degradation to 7.16 BPM of MAE, we can achieve an energy consumption of 179 uJ per prediction, 3.03x less than running TimePPG-Small on the smartwatch, and 1.82x less than streaming all the input data to the phone., Comment: Published at 2023 Design, Automation \& Test in Europe Conference \& Exhibition (DATE)

The need to execute Deep Neural Networks (DNNs) at low latency and low power at the edge has spurred the development of new heterogeneous Systems-on-Chips (SoCs) encapsulating a diverse set of hardware accelerators. How to optimally map a DNN onto such multi-accelerator systems is an open problem. We propose ODiMO, a hardware-aware tool that performs a fine-grain mapping across different accelerators on-chip, splitting individual layers and executing them in parallel, to reduce inference energy consumption or latency, while taking into account each accelerator's quantization precision to maintain accuracy. Pareto-optimal networks in the accuracy vs. energy or latency space are pursued for three popular dataset/DNN pairs, and deployed on the DIANA heterogeneous ultra-low power edge AI SoC. We show that ODiMO reduces energy/latency by up to 33%/31% with limited accuracy drop (-0.53%/-0.32%) compared to manual heuristic mappings., Comment: Accepted at 2023 ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED)

Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications. This paper tackles this challenge by introducing a novel reduced precision optimization technique for ODL primitives on MCU-class devices, leveraging the State-of-Art advancements in RISC-V RV32 architectures with support for vectorized 16-bit floating-point (FP16) Single-Instruction Multiple-Data (SIMD) operations. Our approach for the Forward and Backward steps of the Back-Propagation training algorithm is composed of specialized shape transform operators and Matrix Multiplication (MM) kernels, accelerated with parallelization and loop unrolling. When evaluated on a single training step of a 2D Convolution layer, the SIMD-optimized FP16 primitives result up to 1.72$\times$ faster than the FP32 baseline on a RISC-V-based 8+1-core MCU. An average computing efficiency of 3.11 Multiply and Accumulate operations per clock cycle (MAC/clk) and 0.81 MAC/clk is measured for the end-to-end training tasks of a ResNet8 and a DS-CNN for Image Classification and Keyword Spotting, respectively -- requiring 17.1 ms and 6.4 ms on the target platform to compute a training step on a single sample. Overall, our approach results more than two orders of magnitude faster than existing ODL software frameworks for single-core MCUs and outperforms by 1.6 $\times$ previous FP32 parallel implementations on a Continual Learning setup., Comment: Pre-print version submitted to Elsevier's Future Generation Computer Systems journal. For the associated open-source release, see https://github.com/pulp-platform/pulp-trainlib

The interest in dynamic vision sensor (DVS)-powered unmanned aerial vehicles (UAV) is raising, especially due to the microsecond-level reaction time of the bio-inspired event sensor, which increases robustness and reduces latency of the perception tasks compared to a RGB camera. This work presents ColibriUAV, a UAV platform with both frame-based and event-based cameras interfaces for efficient perception and near-sensor processing. The proposed platform is designed around Kraken, a novel low-power RISC-V System on Chip with two hardware accelerators targeting spiking neural networks and deep ternary neural networks.Kraken is capable of efficiently processing both event data from a DVS camera and frame data from an RGB camera. A key feature of Kraken is its integrated, dedicated interface with a DVS camera. This paper benchmarks the end-to-end latency and power efficiency of the neuromorphic and event-based UAV subsystem, demonstrating state-of-the-art event data with a throughput of 7200 frames of events per second and a power consumption of 10.7 \si{\milli\watt}, which is over 6.6 times faster and a hundred times less power-consuming than the widely-used data reading approach through the USB interface. The overall sensing and processing power consumption is below 50 mW, achieving latency in the milliseconds range, making the platform suitable for low-latency autonomous nano-drones as well.

Optical Flow (OF) is the movement pattern of pixels or edges that is caused in a visual scene by the relative motion between an agent and a scene. OF is used in a wide range of computer vision algorithms and robotics applications. While the calculation of OF is a resource-demanding task in terms of computational load and memory footprint, it needs to be executed at low latency, especially in robotics applications. Therefore, OF estimation is today performed on powerful CPUs or GPUs to satisfy the stringent requirements in terms of execution speed for control and actuation. On-sensor hardware acceleration is a promising approach to enable low latency OF calculations and fast execution even on resource-constrained devices such as nano drones and AR/VR glasses and headsets. This paper analyzes the achievable accuracy, frame rate, and power consumption when using a novel optical flow sensor consisting of a global shutter camera with an Application Specific Integrated Circuit (ASIC) for optical flow computation. The paper characterizes the optical flow sensor in high frame-rate, low-latency settings, with a frame rate of up to 88 fps at the full resolution of 1124 by 1364 pixels and up to 240 fps at a reduced camera resolution of 280 by 336, for both classical camera images and optical flow data., Comment: Accepted by IWASI 2023

Optical flow estimation is crucial for autonomous navigation and localization of unmanned aerial vehicles (UAV). On micro and nano UAVs, real-time calculation of the optical flow is run on low power and resource-constrained microcontroller units (MCUs). Thus, lightweight algorithms for optical flow have been proposed targeting real-time execution on traditional single-core MCUs. This paper introduces an efficient parallelization strategy for optical flow computation targeting new-generation multicore low power RISC-V based microcontroller units. Our approach enables higher frame rates at lower clock speeds. It has been implemented and evaluated on the eight-core cluster of a commercial octa-core MCU (GAP8) reaching a parallelization speedup factor of 7.21 allowing for a frame rate of 500 frames per second when running on a 50 MHz clock frequency. The proposed parallel algorithm significantly boosts the camera frame rate on micro unmanned aerial vehicles, which enables higher flight speeds: the maximum flight speed can be doubled, while using less than a third of the clock frequency of previous single-core implementations., Comment: Accepted by ISCAS 2022

Meeting the staggering bandwidth requirements of today's applications challenges the traditional narrow and serialized NoCs, which hit hard bounds on the maximum operating frequency. This paper proposes FlooNoC, an open-source, low-latency, fully AXI4-compatible NoC with wide physical channels for latency-tolerant high-bandwidth non-blocking transactions and decoupled latency-critical short messages. We demonstrate the feasibility of wide channels by integrating a 5x5 router and links within a 9-core compute cluster in 12 nm FinFet technology. Our NoC achieves a bandwidth of 629Gbps per link while running at only 1.23 GHz (at 0.19 pJ/B/hop), with just 10% area overhead post layout.

Emerging Artificial Intelligence-enabled Internet-of-Things (AI-IoT) System-on-a-Chip (SoC) for augmented reality, personalized healthcare, and nano-robotics need to run many diverse tasks within a power envelope of a few tens of mW over a wide range of operating conditions: compute-intensive but strongly quantized Deep Neural Network (DNN) inference, as well as signal processing and control requiring high-precision floating-point. We present Marsellus, an all-digital heterogeneous SoC for AI-IoT end-nodes fabricated in GlobalFoundries 22nm FDX that combines 1) a general-purpose cluster of 16 RISC-V Digital Signal Processing (DSP) cores attuned for the execution of a diverse range of workloads exploiting 4-bit and 2-bit arithmetic extensions (XpulpNN), combined with fused MAC&LOAD operations and floating-point support; 2) a 2-8bit Reconfigurable Binary Engine (RBE) to accelerate 3x3 and 1x1 (pointwise) convolutions in DNNs; 3) a set of On-Chip Monitoring (OCM) blocks connected to an Adaptive Body Biasing (ABB) generator and a hardware control loop, enabling on-the-fly adaptation of transistor threshold voltages. Marsellus achieves up to 180 Gop/s or 3.32 Top/s/W on 2-bit precision arithmetic in software, and up to 637 Gop/s or 12.4 Top/s/W on hardware-accelerated DNN layers., Comment: Post-print accepted by IEEE Journal of Solid-State Circuits

Emerging applications in the IoT domain require ultra-low-power and high-performance end-nodes to deal with complex near-sensor-data analytics. Domains such as audio, radar, and Structural Health Monitoring require many computations to be performed in the frequency domain rather than in the time domain. We present ECHOES, a System-On-a-Chip (SoC) composed of a RISC-V core enhanced with fixed and floating-point digital signal processing (DSP) extensions and a Fast-Fourier Transform (FFT) hardware accelerator targeting emerging frequency-domain application. The proposed SoC features an autonomous I/O engine supporting a wide set of peripherals, including Ultra-Low-Power radars, MEMS, and digital microphones over I2S protocol with full-duplex Time Division Multiplexing DSP mode, making ECHOES the first open-source SoC which offers this functionality enabling simultaneous communication with up to 16 I/Os devices. ECHOES, fabricated with 65nm CMOS technology, reaches a peak performance of 0.16 GFLOPS and a peak energy efficiency of 9.68 GFLOPS/W on a wide range of floating and fixed-point general-purpose DSP kernels. The FFT accelerator achieves performance up to 10.16 GOPS with an efficiency of 199.8 GOPS/W, improving performance and efficiency by up to 41.1x and 11.2x, respectively, over its software implementation of this critical task for frequency domain processing.

Computing systems have shifted towards highly parallel and heterogeneous architectures to tackle the challenges imposed by limited power budgets. These architectures must be supported by novel power management paradigms addressing the increasing design size, parallelism, and heterogeneity while ensuring high accuracy and low overhead. In this work, we propose a systematic, automated, and architecture-agnostic approach to accurate and lightweight DVFS-aware statistical power modeling of the CPU and GPU sub-systems of a heterogeneous platform, driven by the sub-systems' local performance monitoring counters (PMCs). Counter selection is guided by a generally applicable statistical method that identifies the minimal subsets of counters robustly correlating to power dissipation. Based on the selected counters, we train a set of lightweight, linear models characterizing each sub-system over a range of frequencies. Such models compose a lookup-table-based system-level model that efficiently captures the non-linearity of power consumption, showing desirable responsiveness and decomposability. We validate the system-level model on real hardware by measuring the total energy consumption of an NVIDIA Jetson AGX Xavier platform over a set of benchmarks. The resulting average estimation error is 1.3%, with a maximum of 3.1%. Furthermore, the model shows a maximum evaluation runtime of 500 ns, thus implying a negligible impact on system utilization and applicability to online dynamic power management (DPM).

Data transfers are essential in today's computing systems as latency and complex memory access patterns are increasingly challenging to manage. Direct memory access engines (DMAEs) are critically needed to transfer data independently of the processing elements, hiding latency and achieving high throughput even for complex access patterns to high-latency memory. With the prevalence of heterogeneous systems, DMAEs must operate efficiently in increasingly diverse environments. This work proposes a modular and highly configurable open-source DMAE architecture called intelligent DMA (iDMA), split into three parts that can be composed and customized independently. The front-end implements the control plane binding to the surrounding system. The mid-end accelerates complex data transfer patterns such as multi-dimensional transfers, scattering, or gathering. The back-end interfaces with the on-chip communication fabric (data plane). We assess the efficiency of iDMA in various instantiations: In high-performance systems, we achieve speedups of up to 15.8x with only 1 % additional area compared to a base system without a DMAE. We achieve an area reduction of 10 % while improving ML inference performance by 23 % in ultra-low-energy edge AI systems over an existing DMAE solution. We provide area, timing, latency, and performance characterization to guide its instantiation in various systems., Comment: 14 pages, 14 figures, accepted by an IEEE journal for publication

Sparse linear algebra is crucial in many application domains, but challenging to handle efficiently in both software and hardware, with one- and two-sided operand sparsity handled with distinct approaches. In this work, we enhance an existing memory-streaming RISC-V ISA extension to accelerate both one- and two-sided operand sparsity on widespread sparse tensor formats like compressed sparse row (CSR) and compressed sparse fiber (CSF) by accelerating the underlying operations of streaming indirection, intersection, and union. Our extensions enable single-core speedups over an optimized RISC-V baseline of up to 7.0x, 7.7x, and 9.8x on sparse-dense multiply, sparse-sparse multiply, and sparse-sparse addition, respectively, and peak FPU utilizations of up to 80% on sparse-dense problems. On an eight-core cluster, sparse-dense and sparse-sparse matrix-vector multiply using real-world matrices are up to 4.9x and 5.9x faster and up to 2.9x and 3.0x more energy efficient. We explore further applications for our extensions, such as stencil codes and graph pattern matching. Compared to recent CPU, GPU, and accelerator approaches, our extensions enable higher flexibility on data representation, degree of sparsity, and dataflow at a minimal hardware footprint, adding only 1.8% in area to a compute cluster. A cluster with our extensions running CSR matrix-vector multiplication achieves 9.9x and 1.7x higher peak floating-point utilizations than recent highly optimized sparse data structures and libraries for CPU and GPU, respectively, even when accounting for off-chip main memory (HBM) and on-chip interconnect latency and bandwidth effects., Comment: 15 pages, 8 figures. Accepted for publication in IEEE TPDS

Power and cost constraints in the internet-of-things (IoT) extreme-edge and TinyML domains, coupled with increasing performance requirements, motivate a trend toward heterogeneous architectures. These designs use energy-efficient application-class host processors to coordinate compute-specialized multicore accelerators, amortizing the architectural costs of operating system support and external communication. This brief presents Cheshire, a lightweight and modular 64-bit Linux-capable host platform designed for the seamless plug-in of domain-specific accelerators. It features a unique low-pin-count DRAM interface, a last-level cache configurable as scratchpad memory, and a DMA engine enabling efficient data movement to or from accelerators or DRAM. It also provides numerous optional IO peripherals including UART, SPI, I2C, VGA, and GPIOs. Cheshire's synthesizable RTL description, comprising all of its peripherals and its fully digital DRAM interface, is available free and open-source. We implemented and fabricated Cheshire as a silicon demonstrator called Neo in TSMC's 65nm CMOS technology. At 1.2 V, Neo achieves clock frequencies of up to 325 MHz while not exceeding 300 mW in total power on data-intensive computational workloads. Its RPC DRAM interface consumes only 250 pJ/B and incurs only 3.5 kGE in area for its PHY while attaining a peak transfer rate of 750 MB/s at 200 MHz., Comment: 5 pages, 11 figures, accepted by IEEE Transactions on Circuits and Systems Part II: Express Briefs

To meet the growing need for computational power for DNNs, multiple specialized hardware architectures have been proposed. Each DNN layer should be mapped onto the hardware with the most efficient schedule, however, SotA schedulers struggle to consistently provide optimum schedules in a reasonable time across all DNN-HW combinations. This paper proposes SALSA, a fast dual-engine scheduler to generate optimal execution schedules for both even and uneven mapping. We introduce a new strategy, combining exhaustive search with simulated annealing to address the dynamic nature of the loop ordering design space size across layers. SALSA is extensively benchmarked against two SotA schedulers, LOMA and Timeloop on 5 different DNNs, on average SALSA finds schedules with 11.9% and 7.6% lower energy while speeding up the search by 1.7x and 24x compared to LOMA and Timeloop, respectively., Comment: 5 pages, 6 figures, open-source at https://github.com/ZigZag-Project/zigzag