English
Related papers

Related papers: Tailors: Accelerating Sparse Tensor Algebra by Ove…

200 papers

Latency and energy consumption are key metrics in the performance of deep neural network (DNN) accelerators. A significant factor contributing to latency and energy is data transfers. One method to reduce transfers or data is reusing data…

Hardware Architecture · Computer Science 2024-10-15 Michael Gilbert , Yannan Nellie Wu , Joel S. Emer , Vivienne Sze

In scientific fields such as quantum computing, physics, chemistry, and machine learning, high dimensional data are typically represented using sparse tensors. Tensor contraction is a popular operation on tensors to exploit meaning or alter…

Data Structures and Algorithms · Computer Science 2024-10-15 Andrew Ensinger , Gabriel Kulp , Victor Agostinelli , Dennis Lyakhov , Lizhong Chen

Modern AI workloads rely heavily on optimized computing kernels for both training and inference. These AI kernels follow well-defined data-flow patterns, such as moving tiles between DRAM and SRAM and performing a sequence of computations…

Machine Learning · Computer Science 2025-04-29 Lei Wang , Yu Cheng , Yining Shi , Zhengju Tang , Zhiwen Mo , Wenhao Xie , Lingxiao Ma , Yuqing Xia , Jilong Xue , Fan Yang , Zhi Yang

The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…

Hardware Architecture · Computer Science 2024-01-18 Rebecca Pelke , Jose Cubero-Cascante , Nils Bosbach , Felix Staudigl , Rainer Leupers , Jan Moritz Joseph

Researchers are increasingly incorporating numeric high-order data, i.e., numeric tensors, within their practice. Just like the matrix/vector (MV) paradigm, the development of multi-purpose, but high-performance, sparse data structures and…

Mathematical Software · Computer Science 2018-02-09 Adam P. Harrison , Dileepan Joseph

Recent research has focused on accelerating stencil computations by exploiting emerging hardware like Tensor Cores. To leverage these accelerators, the stencil operation must be transformed to matrix multiplications. However, this…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-27 Qiqi GU , Chenpeng Wu , Heng Shi , Jianguo Yao

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…

Sparse matrix-matrix multiplication (SpGEMM) is a critical operation in numerous fields, including scientific computing, graph analytics, and deep learning. These applications exploit the sparsity of matrices to reduce storage and…

Machine Learning · Computer Science 2024-08-30 Sanjali Yadav , Bahar Asgari

Stencil computations are a key class of applications, widely used in the scientific computing community, and a class that has particularly benefited from performance improvements on architectures with high memory bandwidth. Unfortunately,…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-10-27 Istvan Z Reguly , Gihan R Mudalige , Michael B Giles

Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, leading to…

Machine Learning · Computer Science 2025-04-04 Leonardo Iurada , Marco Ciccone , Tatiana Tommasi

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To…

Machine Learning · Computer Science 2023-06-30 Haihao Shen , Hengyu Meng , Bo Dong , Zhe Wang , Ofir Zafrir , Yi Ding , Yu Luo , Hanwen Chang , Qun Gao , Ziheng Wang , Guy Boudoukh , Moshe Wasserblat

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are…

Neural and Evolutionary Computing · Computer Science 2020-09-24 Dingqing Yang , Amin Ghasemazar , Xiaowei Ren , Maximilian Golub , Guy Lemieux , Mieszko Lis

The matrices used in many computational settings are naturally sparse, holding a small percentage of nonzero elements. Storing such matrices in specialized sparse formats enables algorithms that avoid wasting computation on zeros,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-13 Pratyush Das , Amirhossein Basareh , Adhitha Dias , Artem Pelenitsyn , Kirshanthan Sundararajah , Milind Kulkarni , Ben Delaware

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Hardware Architecture · Computer Science 2025-07-15 Weihong Xu , Haein Choi , Po-kai Hsu , Shimeng Yu , Tajana Rosing

The rapid increases in model parameter sizes introduces new challenges in pre-trained model loading. Currently, machine learning code often deserializes each parameter as a tensor object in host memory before copying it to device memory. We…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-30 Takeshi Yoshimura , Tatsuhiro Chiba , Manish Sethi , Daniel Waddington , Swaminathan Sundararaman

As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero…

We over-approximate reachability sets in string rewriting by languages defined by admissible factors, called tiles. A sparse set of tiles contains only those that are reachable in derivations, and is constructed by completing an automaton.…

Logic in Computer Science · Computer Science 2020-03-04 Alfons Geser , Dieter Hofbauer , Johannes Waldmann

In recent years, the fervent demand for computational power across various domains has prompted hardware manufacturers to introduce specialized computing hardware aimed at enhancing computational capabilities. Particularly, the utilization…

Numerical Analysis · Mathematics 2024-03-12 Hongyaoxing Gu

Offloading compute-intensive kernels to hardware accelerators relies on the large degree of parallelism offered by these platforms. However, the effective bandwidth of the memory interface often causes a bottleneck, hindering the…

Hardware Architecture · Computer Science 2022-02-25 Corentin Ferry , Tomofumi Yuki , Steven Derrien , Sanjay Rajopadhye