We present an efficient B-spline finite element method (FEM) for cloth simulation. While higher-order FEM has long promised higher accuracy, its adoption in cloth simulators has been limited by its larger computational costs while generating results with similar visual quality. Our contribution is a full algorithmic pipeline that makes cloth simulation using quadratic B-spline surfaces faster than standard linear FEM in practice while consistently improving accuracy and visual fidelity. Using quadratic B-spline basis functions, we obtain a globally C 1 -continuous displacement field that supports consistent discretization of both membrane and bending energies, effectively reducing locking artifacts and mesh dependence common to linear elements. To close the performance gap, we introduce a reduced integration scheme that separately optimizes quadrature rules for membrane and bending energies, an accelerated Hessian assembly procedure tailored to the spline structure, and an optimized linear solver based on partial factorization. Together, these optimizations make high-order, smooth cloth simulation competitive at scale, yielding an average 2× speedup over linear FEM in our tests. Extensive experiments demonstrate improved accuracy, wrinkle detail, and robustness, including contact-rich scenarios, relative to linear FEM and recent higher-order approaches. Our method enables realistic wrinkling dynamics across a wide range of material parameters and supports practical garment animation, providing a new promising spatial discretization for high-quality cloth simulation.

Large Language Models (LLMs) inference have gained popularity over the past two years, driven by their high performance achieved through rapid increases in the number of parameters. The inference process of LLMs consists of two distinct stages: prefill and decode, each with unique computational characteristics. While existing neural network inference platforms, such as Google's TPU, perform well during the prefill stage, they often suffer from poor resource utilization during the decode stage. To address this challenge, we propose the scalable Headtile architecture, specifically designed to improve hardware resource utilization. By analyzing the inference behavior of LLMs, we examine how each layer executes on TPUv3 and introduce the Maarg paradigm in Headtile for inter-layer scheduling and mapping. Experimental results show that Headtile can achieve up to 24 × higher throughput in the decode stage compared to TPUv3. In addition, the Maarg paradigm reduces memory accesses by up to 60 % during the prefill stage.

As the main workload of many scientific and machine learning applications, sparse matrix-matrix multiplication (spGEMM) has become a hot research field. The current spG EMM workloads exhibit sparsity and irregularity, leading to computational inefficiencies on traditional hardware platforms and motivating numerous customized accelerators. These spe-cialized hardware designs typically accelerate only one type of spGEMM dataflow (such as Inner-Product, Outer-Product, or Gustavson), yet the computational efficiency of the same spG EMM kernel can vary significantly under different dataflows. Flexagon is the first spGEMM accelerator to support multiple dataflows, but its MRN (Merger-Reduction Network) design causes a lot of data blocking and load imbalance, which limits its performance. In this work, we propose Sparm, which achieves efficient merging of psums (partial sums) for different dataflows through a specialized indexing unit. Sparm addresses the performance bottlenecks encountered by Flexagon when facing highly sparse matrices. Furthermore, Sparm employs a row/column prefetcher to load the streaming matrices proactively and thus significantly reduces the amount of DRAM access. We conduct simulations using a cycle-accurate simulator on workloads from various application domains, and the results demonstrate that Sparm achieves average performance gains of 2.62× and 1.35× compared to state-of-the-art spGEMM accelerators SIGMA and Flexagon. Meanwhile, Sparm brings only a small amount of additional hardware overhead over Flexagon.

In recent years, MultiModal Large Language Models (MM-LLMs), based on the Contrastive Language-Image Pretraining models (CLIP), have achieved the best results in many fields. CLIP breaks through the gaps between language models and image models, realizes zero-shot image classification, and achieves excellent performance in tasks such as text-to-image generation, image style transformation, and long video generation. However, there are few studies on the fault tolerance of CLIP with soft errors, which hinders the application of multimodal large models in the field of security. Based on the analysis of the fault tolerance of common multimodal large models, we proposes a soft error mitigation framework. According to the experiments in this paper, the framework can effectively detect soft errors and mitigate the errors.