English
Related papers

Related papers: Recovering single precision accuracy from Tensor C…

200 papers

The rapid growth of artificial intelligence (AI) has made low-precision formats such as FP16, FP8, and, most recently, block-scaled FP4 the primary focus of modern GPUs, where Tensor Cores now deliver orders-of-magnitude higher throughput…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Angelika Schwarz , Anton Anders , Cole Brower , Harun Bayraktar , John Gunnels , Kate Clark , RuQing G. Xu , Samuel Rodriguez , Sebastien Cayrols , Paweł Tabaszewski , Victor Podlozhnyuk

Tensor decomposition has been widely used in machine learning and high-volume data analysis. However, large-scale tensor factorization often consumes huge memory and computing cost. Meanwhile, modernized computing hardware such as tensor…

Optimization and Control · Mathematics 2022-09-12 Zi Yang , Junnan Shan , Zheng Zhang

In this paper, we propose a mixed-precision convolution unit architecture which supports different integer and floating point (FP) precisions. The proposed architecture is based on low-bit inner product units and realizes higher precision…

Hardware Architecture · Computer Science 2021-01-29 Hamzah Abdel-Aziz , Ali Shafiee , Jong Hoon Shin , Ardavan Pedram , Joseph H. Hassoun

Sparse general matrix-matrix multiplication (spGEMM) is an essential component in many scientific and data analytics applications. However, the sparsity pattern of the input matrices and the interaction of their patterns make spGEMM…

Mathematical Software · Computer Science 2020-10-01 Orestis Zachariadis , Nitin Satpute , Juan Gómez-Luna , Joaquín Olivares

Time-independent quantum response calculations are performed using Tensor cores. This is achieved by mapping density matrix perturbation theory onto the computational structure of a deep neural network. The main computational cost of each…

Mixed-precision quantization is a popular approach for compressing deep neural networks (DNNs). However, it is challenging to scale the performance efficiently with mixed-precision DNNs given the current FPGA architecture and conventional…

Hardware Architecture · Computer Science 2023-11-07 Yuzong Chen , Jordan Dotzel , Mohamed S. Abdelfattah

Because of the increasing demand for computation in DNN, researchers develope both hardware and software mechanisms to reduce the compute and memory burden. A widely adopted approach is to use mixed precision data types. However, it is hard…

Programming Languages · Computer Science 2021-03-30 Jian Weng , Animesh Jain , Jie Wang , Leyuan Wang , Yida Wang , Tony Nowatzki

Matrix-accelerated stencil computation is a hot research topic, yet its application to three-dimensional (3D) high-order stencils and HPC remains underexplored. With the emergence of matrix units on multicore CPUs, we analyze matrix-based…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-16 Yinuo Wang , Tianqi Mao , Lin Gan , Wubing Wan , Zeyu Song , Jiayu Fu , Lanke He , Wenqiang Wang , Zekun Yin , Wei Xue , Guangwen Yang

Recently, tensor algebra have witnessed significant applications across various domains. Each operator in tensor algebra features different computational workload and precision. However, current general accelerators, such as VPU, GPGPU, and…

Hardware Architecture · Computer Science 2024-05-06 Chenyang Ai , Lechuan Zhao , Zhijie Huang , Cangyuan Li , Xinan Wang , Ying Wang

Modern AI accelerators provide high-throughput low-precision matrix engines, but their support for FP32 GEMM is often limited or inefficient. This work presents SGEMM-cube, a precision-recovery FP32 GEMM approximation on Ascend NPUs using…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-07 Weicheng Xue , Baisong Xu , Kai Yang , Yongxiang Liu , Dengdeng Fan , Pengxiang Xu , Yonghong Tian

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 Xiaoyu Yu , Yuwei Wang , Jie Miao , Ephrem Wu , Heng Zhang , Yu Meng , Bo Zhang , Biao Min , Dewei Chen , Jianlin Gao

Emerging deep learning workloads urgently need fast general matrix multiplication (GEMM). To meet such demand, one of the critical features of machine-learning-specific accelerators such as NVIDIA Tensor Cores, AMD Matrix Cores, and Google…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-11-13 Bo Fang , Xinyi Li , Harvey Dam , Cheng Tan , Siva Kumar Sastry Hari , Timothy Tsai , Ignacio Laguna , Dingwen Tao , Ganesh Gopalakrishnan , Prashant Nair , Kevin Barker , Ang Li

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…

Hardware Architecture · Computer Science 2024-07-12 Mohammed Elbtity , Peyton Chandarana , Ramtin Zand

Recent hardware acceleration advances have enabled powerful specialized accelerators for finite element computations, spiking neural network inference, and sparse tensor operations. However, existing approaches face fundamental limitations:…

Hardware Architecture · Computer Science 2026-01-09 Chuanzhen Wang , Leo Zhang , Eric Liu

Sparse tensors appear in many large-scale applications with multidimensional and sparse data. While multidimensional sparse data often need to be processed on manycore processors, attempts to develop highly-optimized GPU-based…

Mathematical Software · Computer Science 2017-12-18 Bangtian Liu , Chengyao Wen , Anand D. Sarwate , Maryam Mehri Dehnavi

This paper describes the application of the code generated by the CAMPARY software to accelerate the solving of linear systems in the least squares sense on Graphics Processing Units (GPUs), in double double, quad double, and octo double…

Mathematical Software · Computer Science 2022-03-22 Jan Verschelde

Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-17 Jinliang Shi , Shigang Li , Youxuan Xu , Rongtian Fu , Xueying Wang , Tong Wu

General matrix-matrix multiplication (GEMM) is a cornerstone of AI computations, making tensor processing engines (TPEs) increasingly critical in GPUs and domain-specific architectures. Existing architectures primarily optimize dataflow or…

Hardware Architecture · Computer Science 2025-03-11 Qizhe Wu , Huawen Liang , Yuchen Gui , Zhichen Zeng , Zerong He , Linfeng Tao , Xiaotian Wang , Letian Zhao , Zhaoxi Zeng , Wei Yuan , Wei Wu , Xi Jin

This whitepaper proposes the design and adoption of a new generation of Tensor Processing Unit which has the performance of Google's TPU, yet performs operations on wide precision data. The new generation TPU is made possible by…

Hardware Architecture · Computer Science 2017-06-13 Eric B. Olsen

As the demand for AI computation rapidly increases, more hardware is being developed to efficiently perform the low-precision matrix multiplications required by such workloads. However, these operations are generally not directly applicable…

Performance · Computer Science 2025-09-26 Daichi Mukunoki