Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2604.24800

Opto-Atomic Spatio-Temporal Holographic Correlators for High-Speed 3D CNNs

Xi Shen·Bowen Qi·Tabassom Hamidfar·Selim M. Shahriar
View original source ↗Read source document ↗Export metadata ↓

Abstract

Three-dimensional convolutional neural networks (3D CNNs) have demonstrated remarkable performance in video recognition tasks by processing both spatial and temporal features. However, the cubic scaling of computational complexity poses significant time and energy efficiency challenges for conventional silicon-based hardware. To address this, we propose a hybrid optoelectronic architecture that delegates the computationally intensive 3D convolutional layer to an opto-atomic Spatio-temporal Holographic Correlator (STHC). This system stores temporal information as atomic coherence in an array of inhomogeneously broadened cold Rubidium-85 atoms and combines a traditional 2D spatial correlator to perform correlation in both space and time simultaneously. Our results on a four-class human action dataset demonstrate a classification accuracy of 59.72% using parallel large-scale kernels (30X40 pixels spatially, 8 frames temporally), with potential operating speeds projected up to 125,000 frames per second. This approach offers a pathway to massively accelerated video classification through a hybrid architecture.

Explore related subjects

cs.AReess.IV

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xi Shen, Bowen Qi, Tabassom Hamidfar, Selim M. Shahriar. 2026-04-27. Opto-Atomic Spatio-Temporal Holographic Correlators for High-Speed 3D CNNs. https://arxiv.org/abs/2604.24800

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning

Design verification remains one of the most resource-intensive stages of hardware development, often consuming up to 70% of the total design effort. While recent work has explored using Large Language Models (LLMs) to automate testbench generation, most existing approaches focus narrowly on functional correctness, overlooking the critical aspect of coverage quality. To bridge this gap, we present CovR, an agentic framework for automated testbench generation that combines self-reflection loops with simulation-based feedback to maximize coverage. Using this pipeline, we construct a large-scale dataset of 16,514 natural specification RTL reasoning testbench tuples with a strong teacher model, enabling coverage-aware supervision. Building on this, we propose a reinforcement learning (RL) framework tailored for coverage-driven testbench generation, leveraging tool-derived rewards from simulation and coverage feedback to optimize a student model. Experimental results show that the CovR finetuned model achieves 93.81% cov@10 on VerilogEval and RTLLM V2.0, and 87.76% cov@10 on CVDP, outperforming state-of-the-art approaches by 7.97% and 3.59%, respectively. Furthermore, deploying the finetuned model back into the agentic refinement pipeline further improves cov@10 to 94.27% on VerilogEval and RTLLM V2.0 and 91.39% on CVDP. Moreover, when integrated as a plug-in stimulus engine for full verification workflows, CovR improves coverage by 18.95% and mutation detection score by 1.19%, while revealing 4.46% undetected failures, highlighting the importance of optimizing for coverage in LLM-based hardware verification.

cs.AR↗
arXiv2026

TEMPO: A Tag-Based Framework for Efficient Memory Ordering

Weak-memory processors rely on ordering instruc- tions for correctness, yet conventional implementations often en- force them more conservatively than the memory model requires. This over-enforcement manifests as drain-induced retirement stalls at ordering instructions and conservative squash/replay of speculative loads, suppressing legal executions and reducing throughput. We present TEMPO, a tag-based framework for precise microarchitectural implementation of ordering instructions. TEMPO assigns lightweight ordering tags to instructions and decomposes enforcement across retirement-time predicates and completion-time store ordering, allowing the core to enforce required ordering without conservative retirement serialization. TEMPO eliminates unnecessary retirement serialization at ordering instructions and speculative-load squash/replay. In our evaluation, TEMPO reduces geometric-mean normalized exe- cution cycles by 7.9% on native four-thread workloads and improves geometric-mean IPC by 15.9% on an instrumented SPEC2017 dynamic binary translation (DBT) proxy for cross- ISA execution (e.g., x86-on-Arm), while adding only 262 bytes per core.

cs.AR↗
arXiv2026

Quality over Quantity: Diversity-Aware Data Selection for Efficient Verilog Code Generation

Large Language Models (LLMs) have shown remarkable potential in Verilog code generation, yet existing datasets contain con siderable noise and redundancy. Prior data selection methods address only isolated quality aspects, neglect the global diversity of the training set, and cannot capture Verilog-specific structural semantics. To bridge this gap, we propose VeriSelector, the first data selection framework for Verilog code generation that jointly optimizes quality and diversity. We formulate the selec tion problem as a constrained bi-objective subset selection problem and solve it via a three-stage approximation. For quality, a multi-granularity pipeline first verifies functional correctness through testbench simulation and then filters misaligned samples via Instruction-Following Difficulty (IFD) scoring. For diversity, 109-dimensional Verilog-specific structural features (AST, CFG, and Netlist) are fused with textual embeddings for clustering-based diversity modeling. A proportional adaptive sampling strat egy then allocates per-cluster quotas guided by IFD ranks, with a provable distribution preservation guarantee. Experiments on three LLMs and three benchmarks show that VeriSelector outperforms full-dataset training and state-of-the-art baselines us ing only 20%-25% of the data, achieving Performance Retention Rates above 118% and reducing training time by over 80%. Notably, VeriSelector improves average Pass@1 by 18.49%-29.43% over full-dataset training and by 1.36%-7.95% over the best-performing baseline across all evaluated models.

cs.AR↗