English
Related papers

Related papers: SnipSnap: A Joint Compression Format and Dataflow …

200 papers

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…

Despite the remarkable success of Large Language Models (LLMs), the massive size poses significant deployment challenges, particularly on resource-constrained hardware. While existing LLM compression methods focus on quantization, pruning…

Artificial Intelligence · Computer Science 2023-10-12 Song Guo , Jiahang Xu , Li Lyna Zhang , Mao Yang

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…

Computation and Language · Computer Science 2023-10-16 Eldar Kurtic , Denis Kuznedelev , Elias Frantar , Michael Goin , Dan Alistarh

Learned sparse retrieval (LSR) is a family of first-stage retrieval methods that are trained to generate sparse lexical representations of queries and documents for use with an inverted index. Many LSR methods have been recently introduced,…

Information Retrieval · Computer Science 2023-03-28 Thong Nguyen , Sean MacAvaney , Andrew Yates

Sparse representation-based classifiers have shown outstanding accuracy and robustness in image classification tasks even with the presence of intense noise and occlusion. However, it has been discovered that the performance degrades…

Computer Vision and Pattern Recognition · Computer Science 2015-12-22 Xiaoxia Sun , Nasser M. Nasrabadi , Trac D. Tran

The employment of high-performance servers and GPU accelerators for training deep neural network models have greatly accelerated recent advances in deep learning (DL). DL frameworks, such as TensorFlow, MXNet, and Caffe2, have emerged to…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-06-11 Soojeong Kim , Gyeong-In Yu , Hojin Park , Sungwoo Cho , Eunji Jeong , Hyeonmin Ha , Sanha Lee , Joo Seong Jeong , Byung-Gon Chun

Deep Learning (DL) has achieved unprecedented success in various application domains. Meanwhile, model pruning has emerged as a viable solution to reduce the footprint of DL models in mobile applications, without compromising their…

Hardware Architecture · Computer Science 2024-01-17 Christodoulos Peltekis , Vasileios Titopoulos , Chrysostomos Nicopoulos , Giorgos Dimitrakopoulos

DNN accelerators, significantly advanced by model compression and specialized dataflow techniques, have marked considerable progress. However, the frequent access of high-precision partial sums (PSUMs) leads to excessive memory demands in…

Hardware Architecture · Computer Science 2025-05-08 Yonghao Tan , Pingcheng Dong , Yongkun Wu , Yu Liu , Xuejiao Liu , Peng Luo , Shih-Yang Liu , Xijie Huang , Dong Zhang , Luhong Liang , Kwang-Ting Cheng

Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers from substantial quality degradation due to strong…

Machine Learning · Computer Science 2026-05-08 Liu Hanzuo , Chaofan Lin , Weixuan Sun , Yulong Wang , Key , Rayying , Mingyu Gao

Modern machine learning accelerators are designed to efficiently execute deep neural networks (DNNs) by optimizing data movement, memory hierarchy, and compute throughput. However, emerging DNN models such as large language models, state…

Hardware Architecture · Computer Science 2025-09-03 Shubham Negi , Manik Singhal , Aayush Ankit , Sudeep Bhoja , Kaushik Roy

We propose the Sparse Abstract Machine (SAM), an abstract machine model for targeting sparse tensor algebra to reconfigurable and fixed-function spatial dataflow accelerators. SAM defines a streaming dataflow abstraction with sparse…

Hardware Architecture · Computer Science 2023-03-27 Olivia Hsu , Maxwell Strange , Ritvik Sharma , Jaeyeon Won , Kunle Olukotun , Joel Emer , Mark Horowitz , Fredrik Kjolstad

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

Hardware Architecture · Computer Science 2025-07-15 Chun-Ting Chen , HanGyeol Mun , Jian Meng , Mohamed S. Abdelfattah , Jae-sun Seo

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances on a wide range of tasks. Its outstanding performance is guaranteed by the long-term memory ability which matches the sequential data perfectly and the gating…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Compressed indexing enables powerful queries over massive and repetitive textual datasets using space proportional to the compressed input. While theoretical advances have led to highly efficient index structures, their practical…

Data Structures and Algorithms · Computer Science 2025-10-24 Ankith Reddy Adudodla , Dominik Kempa

Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed…

Machine Learning · Computer Science 2025-11-18 Vladimír Macko , Vladimír Boža

The exponential growth in Large Language Model (LLM) deployment has intensified the need for efficient model compression techniques to reduce computational and memory costs. While pruning and quantization have shown promise, their combined…

Computation and Language · Computer Science 2025-05-13 Stanislas Laborde , Martin Cousseau , Antoun Yaacoub , Lionel Prevost

Sparse coding is a class of unsupervised methods for learning a sparse representation of the input data in the form of a linear combination of a dictionary and a sparse code. This learning framework has led to state-of-the-art results in…

Machine Learning · Computer Science 2021-09-01 Ye Xue , Vincent Lau , Songfu Cai

Lossy compression is one of the most efficient solutions to reduce storage overhead and improve I/O performance for HPC applications. However, existing parallel I/O libraries cannot fully utilize lossy compression to accelerate parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-06-30 Sian Jin , Dingwen Tao , Houjun Tang , Sheng Di , Suren Byna , Zarija Lukic , Franck Cappello

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