Search for: All records

Graph convolutional networks (GCNs) are fundamental in various scientific applications, ranging from biomedical protein-protein interactions (PPI) to large-scale recommendation systems. An essential component for modeling graph structures in GCNs is sparse general matrix-matrix multiplication (SpGEMM). As the size of graph data continues to scale up, SpGEMMs are often conducted in an out-of-core fashion due to limited GPU memory space in resource-constrained systems. Albeit recent efforts that aim to alleviate the memory constraints of out-of-core SpGEMM through either GPU feature caching, hybrid CPU-GPU memory layout, or performing the computation in sparse format, current systems suffer from both high I/O latency and GPU under-utilization issues. In this paper, we first identify the problems of existing systems, where sparse format data alignment and memory allocation are the main performance bottlenecks, and propose AIRES, a novel algorithm-system co-design solution to accelerate out-of-core SpGEMM computation for GCNs. Specifically, from the algorithm angle, AIRES proposes to alleviate the data alignment issues on the block level for matrices in sparse formats and develops a tiling algorithm to facilitate row block-wise alignment. On the system level, AIRES employs a three-phase dynamic scheduling that features a dual-way data transfer strategy utilizing a tiered memory system: integrating GPU memory, GPU Direct Storage (GDS), and host memory to reduce I/O latency and improve throughput. Evaluations show that AIRES significantly outperforms the state-of-the-art methods, achieving up to 1.8× lower latency in real-world graph processing benchmarks. 

Abstract This paper presents NURBS-OT (non-uniform rational B-splines—optimal transport), a new approach in the field of computer graphics and computer-aided design (CAD)/computer-aided manufacturing (CAM) for modeling complex free-form designs like aerodynamic and hydrodynamic structures, traditionally shaped by parametric curves such as Bézier, B-spline, and NURBS. Unlike prior models that used generative adversarial networks (GANs) involving large and complex parameter sets, our approach leverages a much lighter (0.37M versus 5.05M of BézierGAN), theoretically robust method by blending optimal transport with NURBS. This integration facilitates a more efficient generation of curvilinear designs. The efficacy of NURBS-OT has been validated through extensive testing on the University of Illinois Urbana-Champaign (UIUC) airfoil and superformula datasets, where it showed enhanced performance on various metrics. This demonstrates its ability to produce precise, realistic, and esthetically coherent designs, marking a significant advancement by merging classical geometrical techniques with modern deep learning. 

Abstract The cost‐effective and scalable synthesis and patterning of soft nanomaterial composites with improved electrical conductivity and mechanical stretchability remains challenging in wearable devices. This work reports a scalable, low‐cost fabrication approach to directly create and pattern crumpled porous graphene/NiS₂nanocomposites with high mechanical stretchability and electrical conductivity through laser irradiation combined with electrodeposition and a pre‐strain strategy. With modulated mechanical stretchability and electrical conductivity, the crumpled graphene/NiS₂nanocomposite can be readily patterned into target geometries for application in a standalone stretchable sensing platform. By leveraging the electrical energy harvested from the kinetic motion from wearable triboelectric nanogenerator (TENG) and stored in micro‐supercapacitor arrays (MSCAs) to drive biophysical sensors, the system is demonstrated to monitor human motions, body temperature, and toxic gas in the exposed environment. The material selections, design strategies, and fabrication approaches from this study provide functional nanomaterial composites with tunable properties for future high‐performance bio‐integrated electronics. 

Abstract Isogeometric analysis (IGA) is a computational technique that integrates computer-aided design (CAD) with finite element analysis (FEA) by employing the same basis functions for both geometry representation and solution approximation. While IGA offers numerous advantages, such as improved accuracy and efficiency, it also presents several challenges related to geometric modeling. Some of these challenges include accurately representing complex geometries with NURBS (Non-Uniform Rational B-Splines) or other basis functions used in IGA and generating high-quality meshes that conform to the complex geometry represented by NURBS curves/surfaces. This paper introduces an analytical framework to provide a more efficient and theoretically grounded method for generating curvilinear configurations and its analytical solution in IGA, bridging the gap between generated data and its physical representations. This innovative approach is distinguished by integrating the NURBS parameterization in curve generation and providing a corresponding framework to achieve a broader and more accurate explanation of meshes and properties, especially constructing new coordinates and calculating the physical displacements under these conditions. Our model enables the analytical understanding of complex curves from the UIUC airfoil and superformula datasets, demonstrating a deeper dive into simulations. This study signifies a pivotal juncture wherein machine-learning-based complex geometrical formulations are synergistically combined with actual isogeometric analysis.