Search for: All records

Wafer-scale computing has emerged as an alternative solution to sustain performance scaling in the post-Moore era, driven by recent technology advancements such as chiplet integration. This enables considerable computing and storage capabilities on a single chip, making it capable of accommodating large machine learning models and datasets. Recent efforts have heralded the promise of wafer-scale architectures for deep learning inference and training. However, scaling the training of Graph Neural Networks in wafer-scale architecture remains a challenge and is relatively unexplored due to irregularities in gradient propagation as well as physical constraints from flat on-chip topologies. In this paper, we propose Aster, a topology-aware framework designed to efficiently support GNN training on arbitrary wafer-scale architectures. The proposed framework, as opposed to the current application or topology-specific heuristics, can be generalized to support any network topology and irregular GNN datasets. Specifically, we mathematically formulate commonly-seen network topologies in their geometric representation and prioritize communication efficiency during GNN workload partitioning and mapping. Based on the geometric representation, we propose a quadratic assignment problem solver to efficiently map irregular dataflows to a flat topology with reduced communication distance. The simulation results show that Aster can achieve performance speedup by 2.91x, 1.50 x, 1.84 x, and 1.58 x in Mesh and speedup by 3.84x, 1.56 x, 2.05x, and 1.49 x in Torus on average compared to Mini-cut, ScalaGraph, Chunk-V, and Chunk-E, respectively. 

Abstract Understanding how the 3D structure of the genome influences gene regulation is a growing area of interest, particularly in the context of alternative post-transcriptional regulatory events such as alternative splicing (AS) and alternative polyadenylation (APA). These processes are essential for generating transcript and protein diversity, and they are tightly coordinated with transcription. However, despite their biological importance, the relationship between chromatin interactions and alternative pre-messenger RNA regulation remains poorly understood. This gap largely stems from a lack of computational tools capable of integrating structural genomic data with RNA processing dynamics. Exploring how chromatin interactions and epigenetic landscapes shape these events is essential for uncovering the multilayered regulation of gene expression. To bridge this gap, we present EpGAT, a graph attention network-based model that integrates epigenetic read coverage and chromatin interaction data to predict and quantify AS and APA events. By explicitly modeling the spatial organization of the genome, EpGAT captures the regulatory influence of chromatin looping and long-range genomic interactions on RNA processing. The model’s predictions are validated through rigorous cross-cell line and cross-chromosome evaluations, affirming its generalizability and reliability. Beyond prediction, EpGAT offers interpretability by tracing learned parameters back to genomic features, enabling the identification of active enhancers, mapping promoter–enhancer connectivity, and pinpointing the epigenetic factors most critical to specific RNA processing events. These capabilities make EpGAT a powerful tool for dissecting the complex interplay between genome architecture and transcriptomic regulation. More broadly, it provides a generalizable framework for multiple tasks to study the link between 3D genome organization, epigenetic signals, and RNA processing. 

The success of Graph Neural Networks (GNNs) leverages the homophily principle, where connected nodes share similar features and labels. However, this assumption breaks down in heterophilic graphs, where same-class nodes are often distributed across distant neighborhoods rather than immediate connections. Recent attempts expand the receptive field through multi-hop aggregation schemes that explicitly preserve intermediate representations from each hop distance. While effective at capturing heterophilic patterns, these methods require separate weight matrices per hop and feature concatenation, causing parameters to scale linearly with hop count. This leads to high computational complexity and GPU memory consumption. We propose Gated Multi-hop Message Passing (GAMMA), where nodes assess how relevant the aggregated information is from their k-hop neighbors. This assessment occurs through multiple refinement steps where the node compares each hop’s embedding with its current representation, allowing it to focus on the most informative hops. During the forward pass, GAMMA finds the optimal mix of multi-hop information local to each node using a single feature vector without needing separate representations for each hop, thereby maintaining dimensionality comparable to single hop GNNs. In addition, we propose a weight sharing scheme that leverages a unified transformation for aggregated features from multiple hops so the global heterophilic patterns specific to each hop are learned during training. As such, GAMMA captures both global (per-hop) and local (per-node) heterophily patterns without high computation and memory overhead. Experiments show GAMMA matches or exceeds state-of-the-art heterophilic GNN accuracy, achieving up to 20× faster inference. 

Sparse Matrix Dense Matrix Multiplication (SpMM) is a fundamental computation kernel across various domains, including scientific computing, machine learning, and graph processing. Despite extensive research, existing approaches optimize SpMM using loop transformations and linear algebra principles, which (1) poorly handle unstructured sparsity patterns, (2) rely on empirical methods to explore data reuse opportunities, and (3) enforce rigid coordinate alignment, compromising data locality. In this paper, we demonstrate that these limitations stem from the fundamental matrix representation and traditional dataflows of SpMM (e.g., inner-product, outer-product, and Gustavson). We propose Aquila, a graph transformation framework that reformulates SpMM computations as a graph optimization problem, leveraging graph theory to reinterpret tiling and dataflow. First, on the theoretical side, we introduce vertex decomposition and adaptive depth traversal (ADT) to enable non-contiguous tiling, where nonzero elements from discontinuous rows and columns are clustered by connectivity rather than following matrix dimensionality. This approach quantifies data reuse and improves data locality beyond traditional loop transformations while maintaining output equivalence. Second, on the algorithm side, we develop a pull-after-push (PaP) dataflow that simultaneously enhances the dense matrix data reuse while eliminating synchronization issues in output matrix accumulation. Third, building on our theoretical approach and dataflow, we present a versatile accelerator architecture that handles a variety of SpMM kernels with diverse data sizes and sparsity patterns in a unified architecture. Additionally, we introduce a bidirectional fiber tree (BFT) format to support the proposed graph-oriented dataflow in contrast to traditional column or row-major access. Evaluation across diverse sparse datasets shows Aquila achieves speedups of 4.3 ×, 3.4 ×, 3.7 ×, 2.9 ×, and 2.7 × in execution time and up to 4.8 × improvements in energy efficiency compared to state-of-the-art accelerators. 

Not AvailableThis paper proposes a novel method for automatically inferring message flow specifications from the communication traces of a system-on-chip (SoC) design that captures messages exchanged among the components during a system execution. The inferred message flows characterize the communication and coordination of components in a system design for realizing various system functions, and they are essential for SoC validation and debugging. The proposed method relieves the burden of manual development and maintenance of such specifications on human designers. Our method also uses a new accuracy metric, acceptance ratio, to evaluate the quality of the mined specifications instead of the specification size often used in the previous work, enabling more accurate specifications to be mined. Furthermore, this paper introduces the concept of essential causalities to enhance the accuracy of the message flow mining and accelerate the mining process. The effectiveness of the proposed method is evaluated on both synthetic traces and traces generated from executing several system models in GEM5. In both cases, the proposed method achieves superior accuracies compared to a previous approach. Additionally, this paper includes some practical use cases.