Accelerator

Spiking Vision Transformers (SViTs) have emerged as alternative low-power ViT models, but their large sizes hinder their deployments on resource-constrained embedded AI systems. To address this, state-of-the-art works proposed quantization techniques to compress SViT models, but their manual, human-guided approach needs a huge design time and power/energy consumption to find the appropriate quantization setting for each given network, making this approach not scalable for quantizing multiple networks. Toward this, we propose AQ4SViT, a novel automated quantization framework for SViTs that can provide quick quantization settings with good trade-offs between accuracy and memory. To achieve this, AQ4SViT employs the following key ideas: quantization search strategy that evaluates the quantization setting candidates while considering the accuracy constraint; and search gating policy that quickly evaluates and selects promising quantization candidates by leveraging membrane potential drift as a performance proxy. In the search gating policy, AQSViT employs two search algorithm variants to provide trade-off options: Greedy search, which performs fast but may lead to local optima; and Beam search, which performs slower but has better performance in finding global optima selection due to a wider search space. Experimental results show that AQ4SViT-Greedy quickly finds the appropriate quantization settings, achieving up to 6.6x faster search time and up to 82.5% memory saving compared to the state-of-the-art; while AQ4SViT-Beam further reduces the memory footprint by up to 90% compared to the state-of-the-art, but with 4.5x longer search time; all these results are obtained while maintaining high accuracy within 1.5% from the original/non-quantized models on the ImageNet dataset. These results highlight that AQ4SViT framework offers advancements toward SViT deployments on embedded AI systems.

State estimation is the closed-loop core of every real-time tracking system, from radar surveillance and counter-UAV defense to autonomous driving and robotics. These deployments run on edge platforms, where defense systems mount on vehicles and drones, and civilian pipelines live on cars and handheld devices. Here, every additional watt of compute erodes mission duration or operational range. Two hard constraints follow: each new measurement must be fused before the next control cycle, and the total compute must fit within a strict battery and thermal power envelope. The Linear and Extended Kalman Filters (LKF, EKF) are dominant estimators on these systems, but today they execute almost exclusively on CPUs, which serialize multi-object tracking (MOT) updates, or on custom FPGA/ASIC accelerators that lengthen design cycles. Contemporary AI-PC SoCs, like the Intel Core Ultra Series 1 and 2, integrate a low-power, data-parallel Neural Processing Unit (NPU). We therefore ask whether the Kalman filter can be mapped onto this existing matrix engine to meet real-time and low-power budgets simultaneously, avoiding a dedicated accelerator and keeping the CPU and GPU free for primary workloads. We present KATANA, an NPU-aware optimization framework delivering the first end-to-end mapping of the LKF and EKF onto a commercial NPU, alongside a cross-platform characterization on shipping AI-PC silicon. KATANA applies three algebraic graph rewrites: subtract-to-add reformulation via a precomputed negative-projection matrix H_neg, static-shape tensor fusion, and block-diagonal batched parallelization, ensuring 100% of operations execute on the DPU matrix engine. On the Series 2, the optimized batched EKF reaches 223.35 FPS at 13.43 W active power, and the LKF reaches 408.73 FPS at 14.05 W, delivering up to a 97.9% reduction in dynamic energy versus the CPU implementation.

Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for edge AI, making them attractive for hardware acceleration. However, deploying dense SNNs on FPGAs is constrained by limited on-chip memory for synaptic weight storage. To address this bottleneck, we propose VQ4SNN, a hardware-aware architecture that reduces memory requirements through Vector Quantization (VQ)-based weight sharing. To the best of our knowledge, this is the first application of VQ to pipelined spatial-dataflow SNN accelerators on FPGAs. VQ4SNN replaces conventional weight storage with a two-level memory organization consisting of compact pointers and a shared codebook of quantized weight vectors. The proposed design integrates FPGA-aware memory mapping with analytical VQ parameter selection, enabling efficient deployment on such accelerators while preserving inference accuracy. The experimental results show a reduction of 52-61% in the total number of BRAMs compared to the state-of-the-art uncompressed FPGA SNNs without increasing overall logic utilization.

Accurate power estimation is important for understanding and optimizing CPU power behavior, yet practical workflows often rely on simulation-derived information or post-silicon analysis. In this work, we present BigPower, a hierarchical source-level surrogate model for fine-grained module-level power estimation during CPU design. BigPower leverages large language model-based representations together with architectural hierarchy, module connectivity, configuration parameters, and workload context to estimate module-level power consumption directly from source-level design information, without requiring additional simulation during inference. Experimental results in the open-source XiangShan processor family demonstrate practical fine-grained power estimation across diverse configurations and workloads, offering an efficient alternative to conventional simulation-based workflows.

Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense networks when trained from suitable initializations, its iterative pruning procedure requires multiple complete training cycles. This work evaluates progressive magnitude-based pruning as a single-cycle alternative. The method gradually increases sparsity during training using a linear schedule and updates pruning masks based on active weight magnitudes. We conduct systematic experiments on CIFAR-10 and MNIST across ResNet, VGG-style, and LeNet architectures, comparing the proposed method with representative iterative and initialization-based pruning baselines, including LTH, SNIP, and GraSP. On CIFAR-10, the method achieves 95.12% accuracy on ResNet-18 at 72.9% sparsity, compared with 90.5% reported for LTH. At extreme sparsity, it achieves 93.13% accuracy on a VGG-like architecture at 97% sparsity, compared with approximately 92.0% for SNIP, and 93.44% accuracy on VGG-19 at 97.97% sparsity, compared with 92.19% for GraSP at 98% sparsity. A sparsity-accuracy analysis on ResNet-18 further shows that accuracy remains within 0.1 percentage points of the dense baseline across 70--85% sparsity. These results indicate that progressive magnitude-based pruning provides an effective single-cycle approach for neural network sparsification under the evaluated settings.

This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regular workloads; LLM serving is different, spanning a Python host and a CUDA device, handling requests whose cost varies by orders of magnitude, and relying on rapidly evolving software stacks. We run a 216-hour campaign across six co-located deployments under identical stress conditions, monitor host, device, and client metrics in parallel, and apply a statistical pipeline that accounts for autocorrelation and multiple testing. Our results reveal statistically significant memory aging in all deployments, with leak rates strongly dependent on the serving runtime and deployment configuration. Beyond these findings, we provide a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

Point-based differentiable rendering underpins modern 3D reconstruction, novel-view synthesis, and learning-based graphics pipelines, but developing new rendering methods often requires extensive low-level implementation, hardware-specific kernels, and manually written backward passes. This limits rapid prototyping, reproducibility, exploration, and deployment, especially across diverse hardware platforms. This paper presents XPR, an extensible cross-platform framework for point-based differentiable rendering. XPR introduces a high-level programming interface that separates method-specific logic from the shared rendering pipeline, allowing users to implement new methods in a few lines of code. Its pipeline decomposes rendering into modular, statically shaped parallel operations that can be lowered by a cross-platform compiler to GPUs, TPUs, CPUs, and other ML accelerators. We demonstrate implementations of 3DGS, 3DGUT, and LinPrim, with only a few 100s lines of Python code, each of which can be compiled to a range of hardware platforms with the XLA compiler. These results show that XPR enables fast experimentation and portable execution for emerging point-based differentiable rendering systems.

Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that involves architectural parameters, data flow strategies, and memory hierarchies, making the process very time consuming. While existing methodologies such as SECDA enable rapid hardware-software co-design through SystemC simulation and FPGA execution, identifying efficient accelerator configurations remains a largely manual process requiring extensive domain knowledge. SECDA-DSE is a framework that integrates Large Language Models (LLMs) into the SECDA ecosystem to guide design space exploration (DSE) of FPGA-based accelerators. It combines a structured DSE Explorer for generating candidate architectures with an LLM Stack that performs reasoning-guided exploration using retrieval-augmented generation and chain-of-thought prompting, coupled with a feedback loop for iterative and reinforced refinement. Building on our previous work introducing SECDA-DSE, this paper extends its evaluation by generating three accelerator designs, including element-wise vector multiplication, 2D convolution, and matrix transpose, and performing end-to-end execution on FPGA hardware. The results show that SECDA-DSE can generate SECDA-compliant accelerator designs that are successfully synthesized and executed on FPGA hardware. Furthermore, the generated designs capture kernel-specific trade-offs between compute parallelism and data movement, highlighting the potential of LLM-guided exploration to adapt architectural configurations across diverse workloads while reducing exploration time and the need for extensive human expertise.

Robot Operating System 2 (ROS 2), the de facto standard middleware framework for robots, runs each robot as a graph of nodes communicating over the Data Distribution Service (DDS), a publish/subscribe substrate. Observing this inter-node communication in real time is essential to robot development, yet it has a price. A tool can receive data only by joining the DDS domain as a subscriber that discovery has matched to the publisher, so observing folds the tool into the system it measures and perturbs it. We define this protocol-inherent perturbation as the observer's probe effect. It inflates the discovery plane, adds deserialization cost on the observer, makes the loss it reports diverge from what the subscriber actually received, and near saturation displaces the subscriber's messages. The only escape, capturing all wire traffic passively, discards ROS 2 message semantics and scales with total traffic, not what is observed. We present ros2probe, a non-intrusive observation framework that removes the probe effect. It reconstructs the full ROS 2 communication state from the domain's discovery packets at no bandwidth cost, then drives an in-kernel filter restricted to the topics the user asks for, lifting only those packets at minimal cost and observing what the real subscriber receives. Its interfaces and recordings match the standard ROS 2 tools. Across three hardware platforms (laptop, Jetson, and Raspberry Pi), two DDS implementations, and seven robot-operation workloads, ros2probe holds the discovery graph within 0.5% of an unobserved system, whereas domain-joining tools inflate discovery up to 2.6$\times$ and drop 38.5% of the subscriber's messages at saturation while ros2probe drops none. It reports loss with a recall of 1.0, cuts observer CPU and memory by up to 7$\times$ and 28$\times$, and stays practical on the embedded robots where existing tools overload the system.

Spiking Neural Networks (SNNs) provide a naturally temporal machine-learning framework. Their neurons maintain an internal state and propagate information through discrete spikes, enabling low-latency temporal inference. Although SNNs are often associated with asynchronous neuromorphic processors, many scientific real-time inference systems rely on conventional synchronous field-programmable gate arrays (FPGAs) and high-level synthesis (HLS) workflows. In this paper we present an extension of hls4ml that enables clock-driven deployment of SNNs trained in pytorch onto FPGA firmware. We demonstrate the workflow using a dense quantised SNN trained on the Heidelberg Spiking Digits dataset where it achieves inference latencies of approximately $34μ$s. We validate the generated design through software reference comparisons, HLS C simulation, HLS synthesis, export, and Vivado synthesis reports. This work opens up the hls4ml toolkit to neuromorphic computing, allowing streamlined optimisation, synthesis, and deployment of SNN models for real-time inference.

Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks (SnnTorch, Lava, Norse, and others) each with its own model format. The Neuromorphic Intermediate Representation (NIR) addresses this fragmentation by providing a common, framework-independent format for exchanging trained SNN models. NIR solves the exchange problem, but it stops there. It provides a description of a network, not a path to running one. Each backend is still left to implement deployment on its own, with no shared, transformable compiler representation in between. This paper presents snn-mlir, an outof-tree MLIR dialect for SNNs together with a NIR-MLIR-C compilation bridge. The dialect provides a small set of typepolymorphic operations that work identically on floating-point (f32/f64) and quantized data, so a single intermediate representation serves both simulation and hardware-oriented deployment. A Python front end reads any NIR file and emits dialect IR, automatically inserting rescaling operations to keep quantization scales consistent across layers. A reference lowering pass converts the dialect to standard linalg and arith operations, from which the toolchain produces self-contained, dependency free C11 code that compiles and runs on any C-capable CPU or embedded target. We evaluate numerical fidelity against reference outputs, portability across CPU targets, and the cost of quantization. The current scope is feedforward, fully-connected networks with a CPU backend. snn-mlir is released as open source under the Apache-2.0 license with LLVM-exception and it is already available on Github.

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computing improves hardware efficiency by exploiting the error resilience of neural network workloads; however, most approximate CNN accelerators do not jointly consider secure, privacy-aware edge deployment. This paper presents SPARX, a Secure and Privacy-Aware Approximate CNN Acceleration framework integrated within a heterogeneous RV32IMC RISC-V System-on-Chip (SoC). SPARX combines a custom RISC-V instruction extension, an approximate logarithmic CNN acceleration unit, a lightweight differential-noise-based privacy engine, and a challenge-response authentication mechanism. To guide arithmetic selection, an approximation-aware decision framework is introduced that uses the Approximation Severity Index (ASI), Approximation Efficiency (AE), Quality of Approximation (QoA), Approximation Figure-of-Merit (AFOM), and Hardware Acceleration Efficiency (HAE). Evaluation across 11 state-of-the-art approximate MAC architectures identifies the Iterative Logarithmic Multiplier (ILM) as the most suitable design, achieving 51.7% area reduction, 81.5% power reduction, and 2.13x throughput improvement compared with an accurate radix-4 Booth MAC, while only reducing ResNet-20/CIFAR-10 accuracy by 2.82 percentage points. FPGA implementation on a Xilinx VC707 platform achieves 58.4 GOPS/W energy efficiency at 250 MHz, while 28-nm CMOS physical implementation validates ASIC feasibility

Heterogeneous DNN accelerators improve soft real-time multi-DNN execution by mapping each layer to its preferred accelerator to reduce latency. However, under skewed workloads, large layer-latency differences across accelerators limit scheduling flexibility and increase deadline misses. To address this challenge, we introduce layer variants, customized layer implementations that reduce latency gaps on non-preferred accelerators. We then present Terastal, a soft real-time framework for layer-variant design and scheduling on heterogeneous DNN accelerators. Terastal combines offline heterogeneity-aware virtual budget assignment and layer-variant design, and online scheduling to jointly optimize accelerator mapping and variant selection under timing and accuracy constraints. Experimental results show that Terastal reduces deadline miss rate per model by 40.58%, 30.53%, and 36.27% compared with FCFS, EDF, and DREAM, respectively, while incurring only 2.24% average normalized accuracy loss across models with variants.

We study parallel Continuous Local Search (CLS) as a solution approach for Boolean satisfiability problems with symmetric pseudo-Boolean (PB) constraints. Here, the $n$-variable PB-satisfiability problem is relaxed to a continuous optimisation problem with a differentiable objective function on an $n$-dimensional hypercube. For satisfiable instances, the global minimisers of this optimisation problem correspond to satisfying assignments of the SAT problem at hand. We present several novel findings via empirical experiments: (i) redundant constraints can inhibit rather than accelerate convergence; (ii) CLS shows promise as a sub-solver in hybridised settings, quickly completing partial assignments; and (iii) local search rapidly converges to a stable distribution of solution quality (i.e., degree of satisfaction), due to saddle-dense objectives where additional solver steps yield diminishing returns. Our findings inform practical uses of CLS for SAT on modern accelerator hardware.

We present Accelerated Fourier SAT (AFSAT), a GPU-accelerated solver for pseudo-Boolean satisfiability based on continuous local search (CLS). AFSAT realises the proof-of-concept approach, FastFourierSAT, into a fully-engineered solver supporting any heterogeneous mixture of symmetric constraint types and lengths within a single problem instance. Using the JAX compiler, AFSAT leverages pure function composition, automatic vectorisation, automatic differentiation, and just-in-time (JIT) compilation to perform massively parallel CLS across batches of candidate assignments. We demonstrate substantially improved numerical stability, runtime performance, and memory efficiency over the proof-of-concept. We achieve this by way of identifying and addressing various limitations that arise from memory latency and floating-point representation, as well as leveraging automatic parallelisation and compact representations. The inherent representational and stability limitations of floating point are partially addressed by a tailored discrete Fourier transform implementation. We achieve near-linear throughput when scaling to multiple accelerators via JAX array sharding.

Spiking neural networks (SNNs) have the potential to emerge as the third generation of neural networks and have attracted increasing attention across a wide range of applications. However, the large number of synaptic connections in SNNs leads to intensive weight-update computation by on-chip learning algorithms during training, resulting in substantial hardware resource utilization and energy consumption. Among existing SNN learning algorithms, spike-timing-dependent plasticity (STDP) is one of the most extensively studied and widely adopted, serving as a fundamental learning component in SNNs. To address the hardware and energy overheads associated with SNN training, this paper presents intrinsic-timing power-of-two STDP (ITP-STDP) and its corresponding prototype learning engine hardware architecture. The proposed design is evaluated through a dedicated mean-field synaptic drift model for dynamical analysis and further validated across SNN networks of different scales and datasets. It is further implemented on both ASIC and FPGA platforms and compared with state-of-the-art approaches, including the original STDP and more complex STDP variants. The results demonstrate superior energy efficiency, higher operating speed, and substantially lower hardware resource utilization, as the proposed design eliminates most of the computational overhead of STDP through both algorithmic and hardware-level optimizations. On the FPGA platform, the proposed design improves energy efficiency by 4.5$\times$ to 219.8$\times$ over the compared designs. On the ASIC platform, the proposed design achieves a 4.8$\times$ to 22.01$\times$ speedup while consuming only 1.2% to 3.3% of the area required by prior works.

Noisy intermediate-scale quantum (NISQ) processors are entering an early fault-tolerance regime where full quantum error correction carries prohibitive resource costs, yet lightweight error detection can meaningfully improve algorithmic success rates. Existing compilation and error-detection toolchains treat these concerns in isolation, with no principled way to balance detection overhead against success probability under latency constraints. We present an integrated hardware-aware compilation and data-driven quantum error-detection (QED) framework that jointly optimises qubit mapping, SWAP insertion, and syndrome-schedule placement via a noise-weighted cost function and a learned multi-objective scheduler. Simulation experiments on an HPC cluster using GPU-accelerated density-matrix simulation (NVIDIA cuQuantum SDK) across VQE, phase-estimation, and Grover benchmarks, three noise profiles, and circuit sizes of 6-20 qubits (depths 10-160), show that joint co-design raises algorithmic success probability by up to 68 percent (95 percent CI: 60 percent to 76 percent) over SABRE on an 8-qubit VQE instance with post-selection.

This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy that enhances data locality. RMSNorm is fused with matrix multiplication in self-attention and in the FFN, enabling back-to-back execution of memory-bound and compute-bound operators in on-chip SRAM to significantly reduce DRAM reads/writes of intermediate results and scheduling overhead. To support multi-core parallelism, a NoC-based multicast mechanism is leveraged in which row/column master nodes efficiently distribute inputs and weights across the core mesh, alleviating DRAM bandwidth contention. Experiments on the Wormhole platform with Qwen2.5-0.5B, Qwen3-0.6B, and Qwen3-4B show up to 37.44% latency reduction for attention and 15.89% for MLP, with up to 7.91% reduction per decoder layer, while Pearson Correlation Coefficient (PCC) remains above 98.75%, confirming significant end-to-end efficiency gains under numerical consistency.

Hearing aids impose strict latency and power constraints that current DNN-based speech enhancement systems struggle to meet on embedded hardware. We characterize this gap by deploying both speech separation and denoising using the lightweight SuDoRM-RF++ architecture on the AMD-Xilinx Kria KV260, evaluated at FP32 and 16-bit fixed-point precision for each task. Across these configurations, first-sample latency tracks with on-chip parameter caching rather than arithmetic throughput, identifying data movement as the primary bottleneck. Precision reduction halves the model memory footprint without compromising objective speech quality. The fixed-point denoising accelerator achieves a first-sample latency of 9.7ms, meeting the 10ms clinical threshold, while speech separation reaches 16.0~ms. These measurements establish concrete resource requirements for embedded DNN-based speech enhancement and quantify the remaining gap to hearing aid deployment.

The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-of-the-art works compress SViT models through unstructured pruning, which needs specialized hardware accelerators for their specific sparsity patterns to maximize efficiency gains. Moreover, their manual approach requires a huge design time to find an appropriate pruning setting for each network, thus making this approach not scalable. To address this limitation, we propose PrimeSVT, a novel framework that performs automated memory-aware structured pruning on pre-trained SViT models, thereby maximizing their efficiency gains during inference amenable to widely-used computing architectures. To achieve this, PrimeSVT first sorts the SViT layers based on their sizes (i.e., number of parameters), identifies the targeted pruning layers based on their robustness under different pruning rates, then leverages this order for compressing the model layer-by-layer sequentially from the largest one to the smallest one (i.e., so-called prioritized compression policy), while considering the user-defined constraints (i.e., acceptable accuracy and memory saving). In each layer, PrimeSVT employs channel-wise filter pruning based on their L2-norm values to structurally remove the non-significant weights. Experimental results show that PrimeSVT saves 26.68% memory through automated single-shot pruning, while preserving accuracy within 3% (70.3% without fine-tuning and 72.9% with fine-tuning) from the original unpruned SViT model (73.3%), thus meeting the accuracy and memory constraints. These show that our PrimeSVT framework enables design automation for SViTs and their embedded implementation.

Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However, their large sizes limit their deployments for resource-constrained embedded platforms, underscoring the needs of model compression. One of prominent compression techniques is pruning, and the state-of-the-art works employ unstructured pruning techniques to compress SViT models. Such techniques require specialized hardware architectures tailored for the sparsity patterns to maximize their efficiency benefits, making this approach not scalable. To address this, we propose PSViT, a novel methodology to perform structured pruning on SViT models, hence making it possible to efficiently accelerate their inference using the existing and widely-used computing architectures. To do this, PSViT employs several key steps: uniform channel-wise filter pruning to structurally eliminate the non-significant weights, sensitivity analysis to evaluate the impact of channel-wise pruning of individual layer on accuracy and network size, as well as fine-grained channel-wise pruning based on the sensitivity analysis and the given network architecture. Experimental results show that PSViT effectively obtains 22.4% memory saving through single-shot pruning, while maintaining high accuracy within 3% (70.3% without fine-tuning and 72.8% with fine-tuning) from the original non-pruned SViT model (73.3%) on the ImageNet-1K. These results also show that the PSViT methodology advances the effort in enabling efficient SViT deployments on resource-constrained applications.

Binary spike activations allow a language-model runtime to read only active weight columns and replace multiplications by weight sums. We implement this execution strategy in C++ for an 874M-parameter spike-gated language model. Sparse projections use column-major INT8 weights, integer accumulation, and one scale application per output channel; dense projections retain row-major access and FP32 activations. In a single-thread comparison using an early checkpoint, INT8 achieves 23.31 tokens/s versus 9.82 for FP32, while reducing weight storage from 3355.2 to 1087.4 MiB. A variant using INT4 on dense projections saves a further 17.4% of storage but reduces decode throughput by 46.6%. On an AMD Ryzen 7 5800X, the final INT8 checkpoint achieves 22.63 tokens/s on one thread and 47.90 on four threads; 512-token prefill reaches 94.68 tokens/s on eight threads. A separate ARM output-head case study records higher trimmed decode-window energy metrics for two candidate-verification configurations. The results characterize how activation-specific layouts and quantized kernels support CPU deployment of a spike-gated language model.

Production inference increasingly targets a heterogeneous mix of accelerators. Agentic pipelines interleave reasoning, tool calls, and multi-agent coordination, each with distinct compute and memory profiles. For optimal efficiency, each stage should run on the accelerator best suited to it. This creates a systems challenge: each pipeline now requires high-performance kernels across a growing set of hardware backends and programming models. Writing these kernels by hand is time-consuming, demands deep low-level expertise, and does not scale as kernel complexity grows. Recently, Large Language Models (LLMs) have been leveraged for automatic kernel generation, but challenges in low-level code generation and cross-backend generalization persist. We present KForge, a cross-platform framework built around an iterative refinement loop driven by two collaborating LLM-based agents: a generation agent that produces and progressively refines kernels using compilation and correctness feedback, and a performance-analysis agent that interprets profiling data, from programmatic APIs to GUI-based tools, and emits recommendations that steer the next round of synthesis. The loop alternates between functional passes, which drive a candidate to correctness, and optimization passes, which close the performance gap to hand-tuned baselines. We evaluate KForge on two backends with very different baseline reference availability. On NVIDIA B200, KForge achieves a 2.12$\%$ improvement in end-to-end throughput compared to TensorRT-LLM on the gpt-oss-20b inference speed benchmark. On Intel Arc B580, KForge generates Triton kernels achieving a 5.13$\times$ geometric mean speedup over the faster of PyTorch eager and torch.compile on 37 GEMM + tail-ops workloads from KernelBench Level 2, primarily via operator fusion and mixed-precision execution.

This paper demonstrates the effectiveness of machine learning-driven optimization for designing application-specific GaN tri-gate FinFETs in vertical power delivery systems. Conventional TCAD-based approaches are computationally intensive and insufficient for navigating the high-dimensional, nonlinear design space of advanced GaN devices. To address this, a physics-informed active learning framework is used to intelligently guide simulations, accelerating convergence while preserving accuracy. This ML-guided approach enables the discovery of optimal configurations by efficiently exploring key structural parameters -- most notably the GaN-to-AlGaN thickness ratio -- a long-standing focus of debate in device design. By systematically exploring key structural parameters, two optimized devices with aggressively scaled gate-to-drain lengths are identified. Single-fin, multi-channel simulations show that deviceD2, with a thinner GaN channel relative to the AlGaN barrier, achieves higher drive current. However, in a 300-fin configuration, deviceD1 outperforms deviceD2 by delivering 3.3,A at 0.49ohm on-resistance -- approximately 2$\times$ better -- despite slightly higher parasitics. Both devices operate in a normally-off mode. Based on an application-specific figure of merit, deviceD1 achieves 5,pC$\cdot$ohm, demonstrating 2$\times$ greater switching efficiency than deviceD2, while both designs outperform industrial benchmarks from different performance standpoints.

Spiking neural networks (SNNs) provide event-driven and low-power computation inspired by biological neural systems, but current implementations rely on von Neumann graphics processing units (GPUs) and central processing units (CPUs) platforms, where memory and computation bottlenecks limit energy efficiency. To address this challenge, this paper proposes an analog memristor-based spiking neural network (SNN) accelerator that integrates in-memory synaptic computation with analog integrate-and-fire (IF) neurons, eliminating multi-transistor CMOS synapse circuits and enabling asynchronous event-driven operation at the 45nm technology node. Additionally, a digital SNN accelerator is designed and optimized at the 5 nm technology node for comparison. The proposed architecture is evaluated using a predator-prey tracking task that emulates pursuit behavior. In this task, the analog SNN accelerator's inference closely matches the ideal software inference with a mean squared error (MSE) of 0.004. HSPICE simulation results show that the proposed analog SNN accelerator achieves 12.7 times lower energy consumption and 1.26 times lower delay compared to the digital baseline, demonstrating the potential of memristor-based neuromorphic circuits for energy-efficient real-time edge intelligence.

Event-based vision sensors offer asynchronous, high-temporal-resolution measurements that are attractive for low-latency robotic perception, but many event-based motion estimation methods are computationally intensive and difficult to map to FPGA hardware. We present a streaming velocity estimator that discretizes asynchronous events into fixed-duration time bins, constructs a 1-bit spatial occupancy grid, and evaluates multiple velocity hypotheses in parallel using only fixed-width integer logic - shift registers, counters, comparators, and small LUT-mapped multiplies - with no dividers and no DSP blocks. It requires no frame reconstruction, no floating-point arithmetic, and no iterative optimization. The method deliberately trades dense sub-pixel optical flow for a sparse, quantized velocity estimate at each active pixel, suited to low-latency tasks such as reactive obstacle avoidance on size-, weight-, and power-constrained platforms. On noisy synthetic data with known ground-truth velocities, the method recovers both magnitude and direction, with magnitude estimates being most challenged when objects of different velocities intersect. On a real event-camera sequence, directional accuracy reaches 99.5% across all four evaluated motion segments, with performance remaining robust across occupancy densities in the 10-40% range. We characterize the algorithm's density-dependent behavior, present a parameter sensitivity analysis, show that the proposed datapath requires less than 2 kB of storage, and implement a single-axis prototype on a low-cost Xilinx Artix-7.

Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains. As a result, state-of-the-art energy-aware Federated Learning (FL) frameworks typically rely on simplified approximate power models to estimate computation energy, rather than the more accurate analytical CMOS-based model. To bridge this gap, we propose a reproducible CPU power estimation methodology combined with a rail-to-cluster mapping technique to retrieve cluster-level supply voltage. We evaluate our approach on two commodity Android devices and show that the analytical model predicts CPU power with errors below 10%, whereas the approximate model incurs errors of up to 959%. Using AnycostFL, a state-of-the-art energy-aware FL framework, we show that the analytical model achieves the same 80% model accuracy while consuming 1.4x less energy than the approximate model. These results highlight that approximate models can severely misestimate computation energy and lead to suboptimal decisions. This work facilitates the use of analytical CPU power models on heterogeneous multi-cluster ARM-based mobile SoCs without additional hardware support or external power measurement tools.

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing mixed-precision methods typically operate at coarse layer- or channel-level granularity. These methods often rely on heuristic or search-based bit-allocation strategies, which may overlook fine-grained variability at the neuron level. We propose Neuron-Level Mixed-Precision QAT (NMP-QAT), where each neuron independently learns its own discrete precision during training. Starting from low-bit precision, NMP-QAT expands bit-width only when training signals demand it, via differentiable surrogates and straight-through estimators, while preserving a fully discrete inference graph. This adaptability extends to both weights and activations, reducing memory movement. Evaluated on telecom and non-telecom datasets across MLP and tabular foundation model architectures, NMP-QAT achieves superior compression-accuracy trade-offs over mixed-precision QAT baselines, making it well-suited for Green AI deployments at the network edge.

In a landscape of high-performance distributed ML systems, JAX has emerged as a framework of choice. However, JAX's modular design philosophy leaves it without a standardized checkpointing solution. In this paper, we introduce Orbax, a modular, JAX-native checkpointing library that abstracts the complexities of distributed accelerator systems while also providing flexibility for user-friendly checkpoint manipulations throughout the ML model lifecycle. We demonstrate performance exceeding comparable PyTorch competitors by up to 3.5$\times$ for saving and 2$\times$ for loading. The library is available at https://github.com/google/orbax.

Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A key temporal property of SNNs, elastic inference, allows outputs to emerge progressively, enabling responses to salient inputs much earlier than full evaluation. However, existing SNN-specific accelerators cannot capitalize on this property. Layer-by-layer designs emit outputs only after all layers are complete, while time-step-by-time-step designs rely on coarse-grained, layer-wise pipelines that require synchronizing all spines/tokens within a layer. This barrier prevents results from being forwarded immediately, delaying the earliest possible response and forfeiting the benefits of elastic inference. To address these challenges, we propose ELSA, a near-SRAM dataflow architecture that realizes true elastic inference through a fine-grained spine/token-wise pipeline and hardware optimizations tailored to SNNs. ELSA forwards each spine/token immediately upon production, forming a continuous streaming pipeline that substantially reduces the latency to the first response. To enhance this lightweight execution, ELSA introduces a bundled address event representation protocol to lower communication traffic of network-on-chip (NoC), and leverages mini-batch spiking Gustavson-product to cut memory access and exploit inherent sparsity. Combined with mapping and scheduling optimizations, ELSA achieves efficient, event-driven computation without compromising accuracy. Experiments show that SNNs can outperform quantized artificial neural networks (QANNs) while maintaining on-par accuracy. For a 4-bit ResNet-50, ELSA achieves 3.4$\times$ speedup and 13.6$\times$ higher energy efficiency over the SOTA QANN accelerator (ANT), and 2.9$\times$ speedup and 22.1$\times$ energy efficiency gains over the SOTA SNN accelerator (PAICORE).

Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is merely a trivial linear scaling. Kuramoto orientation diffusion replaces this trivial drift with locally coupled phase interactions, improving sampling efficiency but introducing a new hardware bottleneck: a center-dependent nonlinear 5 x 5 stencil evaluated at every reverse step. This kernel maps poorly to conventional CNN accelerators and matrix-oriented engines. We present SA-Kura, to our knowledge the first digital systolic-array accelerator dedicated to locally coupled Kuramoto drift. By reformulating pair-wise sinusoidal coupling into neighbor accumulation independent of the center phase followed by a single center-dependent multiply-subtract combination, SA-Kura eliminates in-PE transcendental units and enables regular systolic execution with register-level reuse. SA-Kura was implemented in synthesizable RTL, integrated into a lightweight RISC-V-based SoC, prototyped on FPGA, and evaluated through 45 nm CMOS synthesis and power analysis. For the drift kernel only, compared with software execution of the same kernel on the processor core in the same SoC platform, SA-Kura reduces latency and energy by 193x and 69.4x, respectively. Compared with a standalone Jetson Orin Nano CUDA implementation of the same kernel, it is 6.57x faster and achieves approximately 46.0x lower energy per pixel.

A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is specific to in-context learning (ICL) teachers: they leak labels when scoring their own training set, so the soft targets collapse to near-one-hot vectors with no inter-class structure left to distill. Stratified out-of-fold (OOF) teacher labeling prevents this. Across 153 classification datasets drawn from TALENT, OpenML-CC18, TabZilla, and TabArena, distilling TabICLv2 into XGBoost gives 0.882 macro-mean AUC (96.5% of teacher AUC) at 1.9 ms on CPU, a 38x to 860x speedup across teacher-student pairs with a statistically significant edge over a tuned CatBoost baseline (Wilcoxon p = 0.0008; 51% win rate). Four further findings: teacher rank transfers exactly to student rank; gains concentrate on low-dimensional data (< 21 features: +0.011 over CatBoost vs. >21 features: +0.001); multi-teacher averaging helps MLP students (+0.006, p = 0.003) but adds less than 0.001 for tree students; and on high-dimensional tasks where the teacher itself trails CatBoost, distillation makes things worse rather than better. The full pipeline is open-sourced as part of the TabTune library.

Hardware aging poses a significant challenge for integrated circuits (ICs), leading to performance degradation and eventual failure. In this work, we focus on the aging of arithmetic multipliers, which are a cornerstone of modern computing systems including in CPUs, GPUs, and FPGAs, as well as AI accelerators like systolic arrays. In particular, AI workloads, which rely predominantly on multiplications, can accelerate Negative Bias Temperature Instability (NBTI) effects in multipliers. This paper presents a novel aging mitigation technique that leverages the signinvariance property of multiplication. By selectively applying 2s complement transformations to inputs, the method redistributes stress across transistors, reducing the effects of NBTI aging. The proposed method is also integrated into systolic arrays, a common AI accelerator, to demonstrate its efficiency in a high-throughput AI accelerator. Experimental evaluations using Cadence tools show better lifetime compared to natural aging (with no mitigation) baseline, while introducing negligible area and delay overheads.

Deploying adaptive intelligence at the edge remains challenging due to the high computational and energy cost of training neural models. Spiking Neural Networks (SNNs) offer a promising alternative, but enabling on-device learning requires hardware-algorithm co-design. This paper presents SPIKER-LL, an FPGA-based SNN accelerator that extends the open-source Spiker+ inference architecture with efficient support for the STSF local learning rule. Through targeted microarchitectural extensions, SPIKER-LL performs inference and online learning with minimal overhead. Across MNIST, F-MNIST, and DIGITS, it achieves up to 93% accuracy, sub-millisecond latency, and less than 0.1 mJ per inference, while remaining DSP-free and highly scalable for edge-FPGA deployments.

Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow because autoregressive decoding repeatedly invokes the target model and incurs costly I/O. We observe that speculative decoding is a natural fit for this setting: a small draft model can remain in DRAM, while a larger flash-resident target model verifies multiple candidate tokens per invocation. However, existing methods assume server-class accelerators and fail to account for prolonged I/O latency, limited computation parallelism, and irregular speculation execution. We present Lever, an end-to-end system for efficient flash-backed LLM inference on smartphones. Lever jointly optimizes the three stages of speculative decoding under mobile constraints. For drafting, it builds token trees using an I/O- and compute-aware gain-cost objective. For verification, it prunes low-value branches through early-exit prediction to reduce target-model computation. For execution, it maps speculation efficiently across mobile CPU-NPU hardware to improve utilization. Comprehensive evaluations show that Lever reduces inference latency by an average of 2.93x over baseline flash-offloaded inference and 1.50x over conventional speculative decoding, narrowing the latency gap between flash-backed and memory-resident LLM inference.

Demand for AI accelerators is rapidly increasing rack power density, with projections approaching 1MW per deployment by 2027. This poses a major challenge for datacenter power delivery designers. As power densities increase, a datacenter designed for a different target density may strand power, i.e., may be unable to use all the power that its delivery hierarchy has provisioned. Designs must remain efficient over long datacenter lifetimes and multiple hardware generations. Power utilization is particularly important as grid power capacity is a scarce resource in the AI era. Designing an efficient power delivery hierarchy for the long run is difficult because rack placement feasibility, workload impact, and cost depend jointly on electrical topology, deployment granularity, placement policy, power oversubscription, and workload mix. Moreover, each of these factors evolve over time, have inter-dependencies across multiple resource dimensions, and generally do not lend themselves to closed-form analysis. To address this challenge, we develop a framework for evaluating datacenter power delivery designs using throughput, power, and cost metrics over realistic arrival, oversubscription, and decommissioning sequences. The framework combines projection models for GPU, compute, and storage deployments with operational factors grounded in production data from Microsoft Azure. Our results show that multi-resource stranding materially changes deployable capacity, effective capital expenditure, and delivered performance, and quantify how rising density from rack- and pod-scale AI systems shapes these outcomes. For AI datacenter design, the relevant planning objective is not installed megawatts, but deployable capacity over time.

Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture Codesign Package (SNAC-Pack), an open-source AutoML framework for hardware-aware neural architecture codesign and end-to-end FPGA deployment. SNAC-Pack runs a multi-objective global search with Optuna and NSGA-II, loading trials to a shared SQLite store that enables parallel workers across compute nodes. A hardware surrogate model outputs per-trial resource and latency estimates, avoiding the synthesis cost that would otherwise dominate the search loop. A local search stage then applies quantization-aware training (QAT) together with iterative magnitude pruning in a combined compression loop, after which the final model is synthesized to FPGA firmware via the hls4ml Python library. A YAML configuration and an optional agentic frontend let users run the pipeline on new datasets without modifying the framework. We demonstrate SNAC-Pack on jet classification at the Large Hadron Collider and superconducting qubit readout, discovering compact architectures that match or exceed strong baselines on the task metric while reducing FPGA resource utilization and, in the qubit readout case, reducing the design space exploration process from months of manual fine-tuning to hours of automated search.

Industrial Water Treatment Systems (IWTS) are safety critical cyber-physical infrastructures and due to increased connectivity, these systems are exposed to cyber threats that can manipulate process behaviour without creating obvious devices outliers. In particular, logic-layer deception anomalies can preserve numerically plausible measurements while breaking expected cause-and-effect relationships in the control process. These attacks are difficult to detect using threshold-based monitoring or require heavy server-oriented anomaly detection models. This paper explores the potential of Tiny Deep Learning (TinyDL) to provide lightweight on-device logic-level anomaly detection for resource constrained Programmable Logic Controllers (PLCs). We propose a novel framework, TinyDL-based incremental LSTM (Ti-iLSTM) which optimises the memory and space foot print of Long Short-Term Memory (LSTM), to detect logic-layer inconsistencies in Programmable Logic Controller (PLC) based Industrial Water Treatment Systems (IWTS). Experiments on the publicly available SWaT dataset show that the optimised model achieves high detection performance (F1-score=0.983 and ROC-AUC=0.998). A deployment-style validation on the WADI dataset confirms that the proposed light-weight framework remains applicable beyond a single dataset. The research demonstrates that combining logic-aware supervision with Tiny Deep Learning (TinyDL) sequence learning creates an efficient and accurate anomaly detection suitable for resource constrained Programmable Logic Controllers (PLCs) in industrial environments.

Accelerating applications through the design of hardware accelerators can significantly enhance system performance and energy efficiency. Despite advances, such as high-level synthesis (HLS), designing accelerators for complex applications still remains highly labor-intensive, demanding considerable expertise in understanding workloads to be accelerated, hardware design, micro-architecture, and EDA tool usage, posing challenges for application domain experts. Therefore, most accelerator solutions are limited to applications with a regular predictable dataflow. Advances in AI have enabled agents that perform autonomous planning, reasoning, execution and reflection, leading to unprecedented potential for automation through agentic AI. We present A3D, an Agentic AI flow for end-to-end Automation of hardware Accelerator Design. A3D automates workload analysis, performance bottleneck identification, code refactoring for HLS compatibility and micro-architecture generation. A3D also generates diverse accelerator designs by automatically exploring the speed-area tradeoff space. Recent efforts have explored the use of AI for specific tasks such as design space exploration in HLS, leaving several tasks to still be performed manually. A3D addresses the challenges in applying modern LLMs to accelerator design by judiciously partitioning tasks among specialist agents, orchestrating process loops with specialist and verifier agents, utilizing pre-existing and custom tools, and employing agentic RAG for codebase and proprietary EDA tool documentation exploration. Our implementation of A3D, using commercial components like Claude Sonnet 4.5 and the Catapult HLS tool, demonstrates its effectiveness by generating accelerator designs with no human intervention from complex scientific applications like LAMMPS (molecular dynamics simulation) and QMCPACK (quantum chemistry).

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer normalization. Recent methods attempt to bypass this by replacing normalization layers with hardware-friendly scalar approximations. However, these homogeneous replacements do not optimally fit to all layers' behaviour and rely on expensive model retraining. In this work, we propose a highly efficient, hardware-aware framework that utilizes genetic programming (GP) to evolve heterogeneous, layer-specific scalar functions directly from pre-trained weights. Coupled with a novel post-training re-alignment strategy, our approach eliminates the need to retrain models from scratch entirely. Our evolved expressions accurately approximate the target normalization behaviours, capturing $91.6\%$ of the variance ($R^2$) compared to only $70.2\%$ for homogeneous baselines, allowing our modified architecture to recover $84.25\%$ Top-1 ImageNet-1K accuracy in only 20 epochs. By preserving this performance while eliminating the global reduction bottleneck, our approach establishes a highly favourable trade-off between arithmetic complexity and off-chip memory traffic, removing a primary barrier to the efficient deployment of ViTs on edge accelerators.

The growing popularity of Spiking Neural Networks (SNNs) and their applications has led to a significant fast-paced increase of neuromorphic architectures capable of mimicking the spike-based data processing typical of biological neurons. The efficient power consumption and parallel computing capabilities of the SNNs lead researchers towards the development of digital accelerators, which exploit such features to bring fast and low-power computation on edge devices. The spread of digital neuromorphic hardware however is slowed down by the prohibitive costs that the silicon tape out of circuits brings, that's why targeting Field Programmable Gate Arrays (FPGAs) could represent a viable alternative, offering a flexible and cost-effective platform for implementing digital neuromorphic systems and helping the spread of open-source hardware designs. In this work we present an heterogeneous System-on-Chip (SoC) where the operations of ReckOn, a Recurrent SNN accelerator, are managed through the integration with traditional processors. These include the RISC-V-based, open-source microcontroller X-HEEP and the ARM processor featured in Zynq Ultrascale systems. We validate our design by reproducing the classification results through the implementation on FPGA of the taped-out version of ReckOn in order to check the equivalence of the accuracy and the characteristics in terms of physical implementation. In a second set of experiments, we evaluate the online learning capability of the solution in classifying a subset of the Braille digit dataset recently used to compare neuromorphic frameworks and platforms.

Quantum error correction (QEC) is essential for enabling quantum advantages, with decoding as a central algorithmic primitive. Owing to its importance and intrinsic difficulty, substantial effort has been made to QEC decoder design, among which neural decoders have recently emerged as a promising data-driven paradigm. Despite this progress, practical deployment remains hindered by a fundamental accuracy-latency tradeoff, often on the microsecond timescale. To address this challenge, here we revisit neural decoders for surface-code decoding under explicit accuracy-latency constraints, considering code distances up to d=9 (161 physical qubits). We unify and redesign representative neural decoders into five architectural paradigms and develop an end-to-end compression pipeline to evaluate their deployability and performance on FPGA hardware. Through systematic experiments, we reveal several previously underexplored insights: (i) near-term decoding performance is driven more by data scale than architectural complexity; (ii) appropriate inductive bias is essential for achieving high decoding accuracy; and (iii) INT4 quantization is a prerequisite for meeting microsecond-scale latency requirements on FPGAs. Together, these findings provide concrete guidance toward scalable and real-time neural QEC decoding.

Spiking Neural Networks (SNNs) can reduce energy consumption compared to conventional Artificial Neural Networks (ANNs) when spiking activity is sparse and the neuron model is hardware-friendly. However, biologically faithful models are often too costly to implement on FPGAs, whereas very simple models (e.g., IR/LIF) sacrifice part of the neuronal dynamics. In this work, we present an FPGA accelerator for an SNN using Spiking Recurrent Cell (SRC) neurons, providing a trade-off between biological plausibility and hardware cost. We propose a set of mathematical simplifications that remove costly unary operators (\textit{tanh}, \textit{exp}) and avoid floating-point arithmetic through scaling and piecewise-defined approximations. The complete network is implemented in VHDL and validated using spiking traces derived from the MNIST dataset. The weight matrices computed off-line are stored directly in LUT-registers without any adaptation. This demonstrates the robustness of SRC cells. Experiments were conducted on an Artix-7 XC7A200T clocked at 100 MHz. The reference implementation achieves 96.31% accuracy with a 220-image spiking trace and a processing time of 1.7424 ms per digit. We then investigate accuracy/energy trade-offs by reducing the spiking trace length and quantizing synaptic weights down to 4 bits, achieving 93.32% accuracy at 0.55 mJ per digit (55 images, 5-bit weights) and 92.89% at 0.45 mJ (44 images, 4-bit weights). These results show that SRC-based SNNs can deliver competitive performance with reduced energy consumption, while preserving richer neuronal dynamics than standard LIF/IR models.

Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render deployment on embedded platforms challenging. As detectors move towards higher granularity, the number of inputs per inference increase and FPGA-only solutions face resource bottlenecks. This work presents an end-to-end demonstrator for the real-time deployment of a dynamic Graph Neural Network for the Belle II electromagnetic calorimeter hardware trigger on the AMD Versal VCK190, leveraging both FPGA fabric and AI Engine tiles. We develop a Python-based semi-automated design flow covering operator fusion, partitioning, mapping, spatial parallelization, and kernel-level optimization. Our design achieves a throughput of 2.94 million events per second at an end-to-end latency of 7.15 microseconds. Compared to the FPGA-only baseline, this represents a 53% throughput improvement while reducing DSP utilization from 99% to 19% at 29% AI Engine tile utilization. To validate the deployment, an interactive visualization pipeline enables real-time monitoring of inference results on the physical demonstrator.

As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as optimizing latency and throughput. Existing approaches either treat latency as an energy proxy or rely on data-hungry black-box surrogates. Both fail under varying parallelism strategies: latency and energy optima diverge in over 20% of configurations we tested, and black-box surrogates require hundreds of profiling samples to generalize across model families and hardware. We present EnergyLens, which uses symbolic regression as a structure-discovery tool over profiling data to derive a single twelve-parameter closed-form energy model expressed in terms of system properties such as degree of parallelism, batch size, and sequence length. Unlike black-box surrogates, EnergyLens decouples tensor and pipeline parallelism contributions and separates prefill from decode energy, making its predictions physically interpretable and actionable. Fitted from as few as 50 profiling measurements, EnergyLens achieves 88.2% Top-1 configuration selection accuracy across many evaluation scenarios compared to 60.9% for the closest prior analytical baseline, matches the predictive accuracy of ensemble ML methods with 10x fewer profiling samples, and extrapolates reliably to unseen batch sizes and hardware platforms without structural modification, making it a practical, interpretable tool for energy-optimal LLM deployment.

LLM-based agents deliver state-of-the-art performance across tasks but incur high end-to-end latency on edge devices. We introduce Agent-X, a software-only, accuracy-preserving framework that accelerates both the prefill and decode stages of on-device agent workloads. Agent-X's two key components rewrite prompts to leverage prefix caching tailored to agent-specific input-token patterns and enable LLM-free speculative decoding for fast token generation with minimal overhead. On representative agentic workloads, Agent-X achieves a 1.61x end-to-end speedup in real systems with no accuracy loss and can be seamlessly integrated into existing on-device AI agents. To the best of our knowledge, ours is the first to systematically characterize and eliminate latency bottlenecks in on-device agents.

This paper presents a hardware architecture that implements the Contrast Maximization (CM) algorithm in Field-Programmable Gate Array (FPGA) resources for event-based vision systems. CM estimates motion parameters by maximizing the contrast of an Image of Warped Events (IWE) reconstructed from asynchronous event streams. Event-based vision sensors generate sparse data with high temporal resolution and low spatial redundancy, which makes them well suited for hardware processing. The deterministic, massively parallel structure of the FPGA is leveraged to design a deeply pipelined architecture capable of high-throughput, energy-efficient processing suitable for real-time embedded applications. This paper details the hardware modules responsible for event warping, contrast computation, and iterative optimization, discusses key implementation decisions, and presents the hardware-aware optimization method used in the design. Experimental results demonstrate a substantial speed and efficiency improvement over CPU- and GPU-based implementations, with motion parameter estimation executing over 200 times faster. To the best of our knowledge, this is the first hardware architecture enabling acceleration of CM algorithm computations. Its performance is evaluated in terms of processing speed, energy efficiency, and hardware resource utilization. The proposed design is validated using an event-based object tracking application. The results confirm that the architecture provides a solid foundation for real-time motion estimation in high-speed, low-power embedded systems.

With the rapid growth of mobile robotics and embedded intelligence, there is an increasing demand for efficient on-device data processing on edge platforms. A promising research direction is the use of neuromorphic sensors inspired by human sensory systems, which generate sparse, event-based data encoding changes in the environment. In this work, we present the first end-to-end FPGA implementation of a keyword spotting system that integrates a Neuromorphic Auditory Sensor (NAS) and a graph neural network (GNN) on a single FPGA device, enabling real-time processing of raw audio data. The proposed architecture eliminates conventional signal preprocessing and operates directly on event-based audio streams. Leveraging a compute-near-memory network architecture, the system achieves efficient inference with low latency and low power consumption. Experimental results demonstrate an accuracy of 87.43% after quantization on the Google Speech Commands v2 dataset processed through the neuromorphic sensor, with end-to-end latency below 35 us and average power consumption of 1.12 W. The processed datasets, software models, and hardware modules are available at https://github.com/vision-agh/NAS-GNN-KWS.

Hardware-aware training (HAT) is widely used to improve the robustness of neural networks on non-ideal AI accelerators, such as analog in-memory computing (IMC) systems. However, not all hardware-induced distortions are equally compensable by training. This paper presents a diagnostic framework that models hardware non-idealities as structured perturbations of the forward operator and evaluates their compatibility with gradient-based optimization. We analyze six representative perturbation classes--read noise, variability, drift, stuck-at faults, IR-drop, and ADC discretization--and identify three key diagnostics: gradient expectation consistency, bounded gradient variance, and non-degenerate sensitivity. Our results show a clear separation between perturbations that can be compensated by HAT and those that consistently break optimization. This provides practical guidance for hardware-software co-design, clarifying which non-idealities can be addressed at the training level and which require circuit-, architecture-, or calibration-level mitigation. This study should be interpreted as a controlled empirical analysis under vanilla forward-perturbation HAT, rather than as a universal theory of hardware-aware training.

Graph-based accelerators have been widely adopted in symbolic data processing applications such as genomics, cybersecurity, and artificial intelligence. However, these systems often suffer from excessive memory usage and inefficiencies stemming from redundant graph structures. We present AutoSlim, a machine learning-based framework that leverages data-driven methods to prune automata graphs for hardware accelerators. Using features extracted from prior graph executions and a Random Forest classifier, AutoSlim identifies and removes low-impact nodes and edges. When applied to a Non-deterministic Finite Automata overlay architecture (NAPOLY+), AutoSlim reduces FPGA resource usage by up to 40%, with corresponding improvements in throughput and power efficiency. The framework includes a verification step to ensure functional equivalence after pruning and suggests promising directions for both hardware optimization and security.

Neural Networks (NNs) have been widely adopted due to their outstanding efficacy and adaptability across computer vision and deep learning applications. The optimization of NNs is necessary to enable their deployment on energy constrained embedded devices, where the limited available energy poses a significant challenge for efficient inference. This paper presents a runtime reconfigurable multiplier architecture integrated into the RISC-V core, targeting energy efficient neural network inference and edge AI applications. The proposed multiplier supports adaptability for exact and approximate computation with multiple configurable accuracy levels via a dedicated mulscr, enabling fine-grained energy accuracy control within a standard processor pipeline. The proposed design achieves 44%-52% and 62%-68% power reduction in exact and approximate modes respectively, while maintaining the computational performance of 1.89 DMIPS/MHz. Evaluations on error-tolerant workloads including 2d convolution and matrix multiplication demonstrate up to 63% reduction in energy consumption, with the proposed design achieving 1.21 pJ/instruction for matrix multiplication, confirming its effectiveness for energy-constrained edge AI deployments.

JPEG decode is routine ML infrastructure, but Python decoder choices are often justified by single-process, single-thread microbenchmarks. We audit this evaluation assumption with thirteen Python-accessible JPEG decode paths on five matched 16 vCPU Google Cloud CPUs: Intel Emerald Rapids, AMD Zen 4, AMD Zen 5, ARM Neoverse V2, and ARM Neoverse N1. ImageNet validation is the workload, not a new dataset contribution: each run decodes the full 50,000-image split from memory and reports single-thread throughput for all decoders, PyTorch \texttt{DataLoader} throughput for eligible decoders at worker counts $\{0,2,4,8\}$, and decoder skip behavior. The evaluation protocol changes the supported conclusion. On Neoverse V2, \texttt{imageio} is ninth in single-thread throughput yet lands in the top DataLoader tier with \texttt{torchvision}; on Zen 4, \texttt{torchvision} rises from seventh single-thread to the top measured DataLoader tier; on Neoverse N1, \texttt{imagecodecs} is the single-thread leader but fifth at peak DataLoader throughput. We also find that worker-count conclusions differ between Zen 4 and Zen 5, TensorFlow has a large single-thread ARM penalty, and strict native JPEG decoders/wrappers reject the same rare ImageNet JPEG. For PyTorch DataLoader workloads, \texttt{torchvision} and \texttt{simplejpeg} form the strongest measured zero-skip tier: \texttt{torchvision} has the highest mean normalized throughput, while \texttt{simplejpeg} has the highest minimum. OpenCV remains a robust general-purpose fallback above 90% of the platform-local winner on every tested CPU. We release raw JSON, generated tables/figures, and an executable local/cloud benchmark framework.

Systolic arrays are the dominant compute fabric for neural network inference. Prior work has addressed column-level fault detection efficiently with uniform test patterns, but row-level (PE-level) fault localization within a faulty column remains open without resorting to hardware redundancy. The fundamental obstacle is that uniform test inputs destroy per-row signatures: any test that activates every row equally cannot distinguish which row is the source of an observed deviation. In this paper, we propose a lightweight, purely algorithmic remedy based on coprime test vectors. By assigning pairwise coprime integers as test-input entries, a permanent weight-register fault produces a deviation whose divisibility signature uniquely identifies the faulty row. Under a general bounded error model, a single test pass localizes the faulty row with high probability. This error model covers a broader class of faults than what prior dataflow-aware testing work has primarily emphasized. When one round is insufficient, a second pass using a ratio computation achieves exact localization; for the special case of single-bit errors, odd coprime entries guarantee exact localization in one round. For INT16 arithmetic, a single test pass covers array sizes up to $256{\times}256$ with localization probability above $0.98$, at a test cost under $1\%$ of one inference GEMM tile.

Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats. Intuitively, finer block sizes should yield lower quantization error; however, a paradox recently identified by Fasoli et al. (2026) demonstrates that standard abs-max scaling can actually result in degraded model quality as block sizes shrink. In this work, we investigate the underlying mechanics of this phenomenon. We demonstrate that this degradation is not an inherent limitation of finer granularity, but is primarily driven by how elements in smaller blocks statistically cluster closer to their local block maximum, interacting poorly with the coarse subnormal E4M3 values used as scaling factors. Specifically, we show that i) preventing the scaling factor from underflowing to zero mitigates errors caused by extreme underflow, ii) targeted algorithmic interventions like the 4-over-6 methodology that give more flexibility to the choice of scaling factor resolve the paradox for larger values, and iii) a brute-force search establishes an optimal baseline, confirming that the theoretical Mean Squared Error (MSE) strictly improves with finer block sizes. Ultimately, our findings highlight a critical insight for hardware-software co-design: the block-size paradox is partially an artifact of naive scale selection. While using hierarchical scaling factors or wider formats like UE5M3 interchangeably resolves much of the quality loss, we found the 4-over-6 scale selection heuristic can even further improve quality, especially for very small block sizes. Consequently, maximizing the performance of next-generation ML accelerators will require treating silicon format specifications and software scaling algorithms as tightly coupled design choices.

Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence length complexity by leveraging the Fast Fourier Transform (FFT). However, this theoretical improvement does not always meaningfully land in practice. One critical obstacle is that applying standard FFTs is not amenable to the large-scale training pipeline wherein data is packed from different sources into a single sequence for hardware efficiency. Indeed, standard FFT algorithms are not easily amenable to document packing. Existing workarounds suffer from severe inefficiencies, crippling the practical performance of convolutional architectures. We close this gap with RubiConv, a novel algorithm for performing hardware-efficient, boundary-respecting convolutions on packed sequences. Extensive experiments show that RubiConv achieves significant speedups over both attention and standard FFT-based baselines. This work makes the theoretical efficiency of long convolutional models a practical reality for large-scale, real-world data packing.

Embedding models in natural language processing (NLP) increasingly rely on deep architectures such as BERT, while simpler models such as Word2Vec provide efficient representations but limited interpretability. The Tsetlin Machine (TM) offers an alternative logic-based learning paradigm. Omni TM Autoencoder (Omni TM-AE) applies this paradigm to static embedding by exploiting automaton state distributions within a single clause layer, but its training process remains slow. In this work, we propose FastOmniTMAE, a reformulation of Omni TM-AE that replaces sequential training dependencies with a two-stage parallel process: evaluation and update. Using a Single-Run Multi-Environment Benchmark covering classification, similarity, and clustering, FastOmniTMAE achieves up to 5$\times$ faster training in classification while maintaining comparable embedding quality under both Spearman and Kendall similarity measures. To address the limited efficiency of TM training on conventional GPUs, we further implement FastOmniTMAE as a reusable accelerator on SoC-FPGA platforms. The Multi-Hardware Benchmark shows that FastOmniTMAE achieves similarity scores of 0.669 on a resource-constrained FPGA and 0.696 on an UltraScale+ SoC, demonstrating efficient logic-based embedding training with a small hardware footprint.

This paper presents CARMEN, a runtime-adaptive, CORDIC-accelerated multi-precision vector engine for resource-efficient deep learning inference. The key insight is that CORDIC iteration depth directly governs computational accuracy, enabling dynamic switching between approximate and accurate execution modes without hardware modification. The architecture integrates a low-resource iterative CORDIC-based MAC unit with a time-multiplexed multi-activation function block, supporting flexible 8/16-bit precision and high hardware utilization. ASIC implementation in 28 nm CMOS achieves up to 33% reduction in computation cycles and 21% power savings per MAC stage; a 256-PE configuration delivers 4.83 TOPS/mm2 compute density and 11.67 TOPS/W energy efficiency. FPGA deployment on PynqZ2 validates 154.6 ms latency at 0.43 W for real-time object detection.

Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion personal computers underutilized for AI workloads. Ternary models offer a path forward: their weights are constrained to {-1, 0, +1}, theoretically eliminating the need for floating-point multiplication. However, existing frameworks fail to exploit this structure, treating ternary models as dense floating-point networks. We address this gap with custom SIMD kernels that replace matrix multiplication with simple addition and subtraction operations, targeting the integer dot product instructions available on modern CPUs. Our implementation, Litespark-Inference, is pip-installable and integrates directly with Hugging-Face, achieving 18.15x higher throughput, 7.15x faster time-to-first-token and 6.03x memory reduction compared to standard PyTorch inference on Apple Silicon, with comparable or higher throughput speedups up to 95.81x on Intel and AMD processors.

Power-of-two (PoT) quantization significantly reduces the size of deep neural networks (DNNs) and replaces multiplications with bit-shift operations for inference. Prior work has shown that PoT-quantized DNNs can preserve accuracy for tasks such as image classification; however, their performance on resource-constrained edge devices remains insufficiently understood. While general-purpose edge CPUs and GPUs do not provide optimized backends for bit-shift operations, custom hardware accelerators can better exploit PoT quantization by implementing dedicated shift-based processing elements. However, deploying PoT-quantized models on such accelerators is challenging due to limited support in existing inference frameworks. In addition, the impact of different PoT quantization strategies on hardware design, performance, and energy efficiency during full inference has not been systematically explored. To address these challenges, we propose PoTAcc, an open-source end-to-end pipeline for accelerating and evaluating PoT-quantized DNNs on resource-constrained edge devices. PoTAcc enables seamless preparation and deployment of PoT-quantized models via TensorFlow Lite (TFLite) across heterogeneous platforms, including CPU-only systems and hybrid CPU-FPGA systems with custom accelerators. We design shift-based processing element (shift-PE) accelerators for three PoT quantization methods and implement them on two FPGA platforms. We evaluate accuracy, performance, energy efficiency, and resource utilization across a range of models, including CNNs and Transformer-based architectures. Results show that our CPU-accelerator design achieves up to 3.6x speedup and 78% energy reduction compared to CPU-only execution for PoT-quantized DNNs on PYNQ-Z2 and Kria boards. The code will be publicly released at https://github.com/gicLAB/PoTAcc

Designing field-programmable gate array (FPGA)-based accelerators for modern artificial intelligence workloads requires navigating a large and complex hardware design space encompassing architectural parameters, dataflow strategies, and memory hierarchies, making the process time-consuming and resource-intensive. While the SECDA methodology enables rapid hardware-software co-design of accelerators through SystemC simulation and FPGA execution, identifying optimal accelerator configurations still requires substantial manual effort and domain expertise. This work presents SECDA-DSE, a framework that integrates Large Language Models (LLMs) into the SECDA ecosystem, comprising tools built around SECDA to automate the design space exploration (DSE) of FPGA-based accelerators. SECDA-DSE combines a structured DSE Explorer for generating accelerator configurations with an LLM Stack that performs reasoning-guided exploration using retrieval-augmented generation and chain-of-thought prompting, alongside a feedback loop that enables reinforced fine-tuning for continuous improvement. We demonstrate the feasibility of SECDA-DSE through an initial high-level synthesis based evaluation of a generated accelerator design that meets synthesis timing and resource constraints on an Zynq-7000 FPGA.