1,184 papers · page 3 of 60
Temporal Graph Networks (TGNs) are widely used to model evolving relationships in dynamic graphs. However, existing inference systems enforce a step-wise paradigm: processing each temporal graph sequentially with a memory update followed by aggregation. We break this dependency b…
Distributed deep learning (DL) training faces instability from GPU/node failures of multi-GPU clusters, necessitating robust fault recovery from model checkpoints. However, we find that existing works only considers node failures but fails to handle partial GPU unavailability, an…
Augmentation makes search trees tremendously more versatile, allowing them to support efficient aggregation queries, order-statistic queries, and range queries in addition to insertion, deletion, and lookup. In this paper, we present the first lock-free augmented balanced search …
Diffusion models have become the dominant approach for generative tasks in images, videos, and other domains. However, diverse data properties in generation requests, which are critical for efficient serving, remain underexploited. To address this issue, we propose a diffusion mo…
The attention mechanism is central to modern deep learning, particularly in large language models (LLMs), but suffers from quadratic computational complexity. To accelerate attention computation on GPUs, fused attention techniques (e.g., FlashAttention) consolidate the matrix mul…
Krylov subspace methods are widely used in scientific computing to solve large sparse linear systems and eigenvalue problems. Their performance bottleneck is often dominated by high-order matrix-power kernels (MPK), especially in polynomial preconditioners that must scale to mill…
Sparse matrix-vector multiplication (SpMV) is a fundamental operation in scientific computing, machine learning, and graph analytics, demanding efficient execution on modern hardware. Recent advances in hardware accelerators, such as Tensor Cores, have significantly improved the …
As transformer sequence lengths grow, existing pipeline parallelisms incur suboptimal performance due to the quadratic attention computation and the substantial memory overhead. To relieve these challenges, we propose HelixPipe, a novel pipeline parallelism for long sequence tran…
This paper proposes FastAlign, a faster, cheaper, and practical end-to-end solution for sequence alignment using commercial CPUs. It introduces two key innovations: a multi-stage seeding algorithm that improves search performance while maintaining low memory consumption, and an i…
Mixed precision quantization has been adopted to accelerate large language models (LLMs) serving by leveraging high-throughput low-precision compute units in GPUs while preserving outliers in higher precision to maintain model accuracy. However, existing methods focus on mitigati…
Space-partitioning indexes are widely used for managing multi-dimensional data, but their throughput is often memory-bottlenecked. Processing-in-memory (PIM), an emerging architectural paradigm, mitigates memory bottlenecks by embedding processing cores directly within memory mod…
Scientific images play a crucial role in many experimental sciences; however, the large volumes of data generated present significant challenges. Effective image compression must be fast, achieve high compression ratios, and preserve critical domain-specific features. Existing co…
The carbon and water footprint of large-scale computing systems poses serious environmental sustainability risks. In this study, we discover that, unfortunately, carbon and water sustainability are at odds with each other - and, optimizing one alone hurts the other. Toward that g…
MCS lock and its variants provide scalability on many-core architectures, using lists of lock requests to reduce access contention on the mutex data. Most recent variants have adopted a two-stage design, allowing requests to be allocated from stack memory rather than heap. Howeve…
Cloud service providers heavily colocate high-priority, latency sensitive (LS), and low-priority, best-effort (BE) DNN inference services on the same GPU to improve resource utilization in data centers. Among the critical shared GPU resources, there has been very limited analysis…
Graph reordering is an effective technique for improving the access locality of graph processing. However, existing methods often overlook the data access locality among concurrently activated vertices (a.k.a. frontiers). These vertices, while lacking direct connections or shared…
In this work, we present theoretically and practically efficient implementations of Big Atomics, i.e., k-word linearizable registers that support the load, store, and compare-and-swap (CAS) operations. While modern hardware supports k = 1 and sometimes k = 2 (e.g., double-width c…
K-means is a popular clustering algorithm with significant applications in numerous scientific and engineering areas. One drawback of K-means is its inability to identify non-linearly separable clusters, which may lead to inaccurate solutions in certain cases. Kernel K-means is a…
Speculative data-parallel algorithms for language recognition have been widely experimented for various types of finitestate automata (FA), deterministic (DFA) and nondeterministic (NFA), often derived fromregular expressions (RE). Such an algorithm cuts the input string into chu…
Graph Pattern Mining (GPM) has made significant progress in recent years, supporting a range of big data applications. However, GPM applications are memory-intensive as they require a tremendous amount of edge checking, which involves enumerating all possible vertex pairs and che…