English
Related papers

Related papers: FusionStitching: Boosting Execution Efficiency of …

200 papers

Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing…

Machine Learning · Computer Science 2025-01-08 Yifei He , Yuzheng Hu , Yong Lin , Tong Zhang , Han Zhao

Many emerging use cases of data mining and machine learning operate on large datasets with data from heterogeneous sources, specifically with both sparse and dense components. For example, dense deep neural network embedding vectors are…

Machine Learning · Computer Science 2019-03-22 Xiang Wu , Ruiqi Guo , David Simcha , Dave Dopson , Sanjiv Kumar

State of art DL models are growing in size and complexity, with many modern models also increasing in heterogeneity of behavior. GPUs are still the dominant platform for DL applications, relying on a bulk-synchronous execution model which…

Hardware Architecture · Computer Science 2025-02-26 Michael Davies , Neal Crago , Karthikeyan Sankaralingam , Stephen W. Keckler

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…

Cryptography and Security · Computer Science 2025-12-01 Wenbo Song , Xinxin Fan , Quanliang Jing , Shaoye Luo , Wenqi Wei , Chi Lin , Yunfeng Lu , Ling Liu

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…

Machine Learning · Computer Science 2025-03-14 Shilong Wang , Jianchun Liu , Hongli Xu , Jiaming Yan , Xianjun Gao

A number of computations exist, especially in area of error-control coding and matrix computations, whose underlying data flow graphs are based on finite projective-geometry(PG) based balanced bipartite graphs. Many of these applications…

Discrete Mathematics · Computer Science 2013-11-05 Swadesh Choudhary , Hrishikesh Sharma , Sachin Patkar

The training of large-scale Mixture of Experts (MoE) models faces a critical memory bottleneck due to severe load imbalance caused by dynamic token routing. This imbalance leads to memory overflow on GPUs with limited capacity, constraining…

In order to satisfy their ever increasing capacity and compute requirements, machine learning models are distributed across multiple nodes using numerous parallelism strategies. As a result, collective communications are often on the…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-24 Kishore Punniyamurthy , Khaled Hamidouche , Bradford M. Beckmann

Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping…

Machine Learning · Computer Science 2026-01-30 Xiao Zhang , Yaoyao Ding , Bolin Sun , Yang Hu , Tatiana Shpeisman , Gennady Pekhimenko

Connected components and spanning forest are fundamental graph algorithms due to their use in many important applications, such as graph clustering and image segmentation. GPUs are an ideal platform for graph algorithms due to their high…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-08-28 Changwan Hong , Laxman Dhulipala , Julian Shun

In this paper we develop the first fine-grained rounding error analysis of finite element (FE) cell kernels and assembly. The theory includes mixed-precision implementations and accounts for hardware-acceleration via matrix multiplication…

Numerical Analysis · Mathematics 2024-10-17 M. Croci , G. N. Wells

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…

Hardware Architecture · Computer Science 2025-11-26 Jinsong Zhang , Minghe Li , Jiayi Tian , Jinming Lu , Zheng Zhang

We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective…

Machine Learning · Computer Science 2019-01-10 Tianqi Chen , Lianmin Zheng , Eddie Yan , Ziheng Jiang , Thierry Moreau , Luis Ceze , Carlos Guestrin , Arvind Krishnamurthy

In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…

Hardware Architecture · Computer Science 2026-04-29 Zihao Xuan , Jia Chen , Yewen Li , Wei Xuan , Hegan Chen , Xiao Huo , Fengbin Tu

Batching has a fundamental influence on the efficiency of deep neural network (DNN) execution. However, for dynamic DNNs, efficient batching is particularly challenging as the dataflow graph varies per input instance. As a result,…

Machine Learning · Computer Science 2023-02-09 Siyuan Chen , Pratik Fegade , Tianqi Chen , Phillip B. Gibbons , Todd C. Mowry

This paper presents a workflow for synthesizing near-optimal FPGA implementations for structured-mesh based stencil applications for explicit solvers. It leverages key characteristics of the application class, its computation-communication…

Hardware Architecture · Computer Science 2021-01-08 Kamalavasan Kamalakkannan , Gihan R. Mudalige , Istvan Z. Reguly , Suhaib A. Fahmy

Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the…

For the last thirty years, several Dynamic Memory Managers (DMMs) have been proposed. Such DMMs include first fit, best fit, segregated fit and buddy systems. Since the performance, memory usage and energy consumption of each DMM differs,…

Neural and Evolutionary Computing · Computer Science 2024-07-16 José L. Risco-Martín , David Atienza , J. Manuel Colmenar , Oscar Garnica

Fusion and inference from multiple and massive disparate data sources - the requirement for our most challenging data analysis problems and the goal of our most ambitious statistical pattern recognition methodologies - -has many and varied…

Methodology · Statistics 2011-12-26 Carey E. Priebe , David J. Marchette , Zhiliang Ma , Sancar Adali

Multi-fidelity modeling and calibration are data fusion tasks that ubiquitously arise in engineering design. In this paper, we introduce a novel approach based on latent-map Gaussian processes (LMGPs) that enables efficient and accurate…

Machine Learning · Statistics 2022-01-17 Nicholas Oune , Jonathan Tammer Eweis-Labolle , Ramin Bostanabad