English
Related papers

Related papers: Representing numeric data in 32 bits while preserv…

200 papers

Scientific computing applications, such as computational fluid dynamics and climate modeling, typically rely on 64-bit double-precision floating-point operations, which are extremely costly in terms of computation, memory, and energy. While…

Hardware Architecture · Computer Science 2024-09-24 Cong "Callie" Hao

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Machine Learning · Computer Science 2024-07-24 Hiroyuki Tokunaga , Joel Nicholls , Daria Vazhenina , Atsunori Kanemura

Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit…

Machine Learning · Computer Science 2019-05-30 Naveen Mellempudi , Sudarshan Srinivasan , Dipankar Das , Bharat Kaul

The b-posit, or bounded posit, is a variation of the posit format designed for high performance computing (HPC) and AI applications. Unlike traditional floating-point formats (floats), posits use variable-length fields for exponent scaling…

Hardware Architecture · Computer Science 2026-03-03 Aditya Anirudh Jonnalagadda , Rishi Thotli , John L. Gustafson

We introduce a new distance-preserving compact representation of multi-dimensional point-sets. Given $n$ points in a $d$-dimensional space where each coordinate is represented using $B$ bits (i.e., $dB$ bits per point), it produces a…

Data Structures and Algorithms · Computer Science 2017-11-07 Piotr Indyk , Ilya Razenshteyn , Tal Wagner

Recent advances in convolutional neural networks have considered model complexity and hardware efficiency to enable deployment onto embedded systems and mobile devices. For example, it is now well-known that the arithmetic operations of…

Neural and Evolutionary Computing · Computer Science 2016-03-18 Daisuke Miyashita , Edward H. Lee , Boris Murmann

With the increasing complexity of machine learning models, managing computational resources like memory and processing power has become a critical concern. Mixed precision techniques, which leverage different numerical precisions during…

Machine Learning · Computer Science 2026-04-20 Juyoung Yun , Sol Choi , Francois Rameau , Byungkon Kang , Zhoulai Fu

Data compression has been widely applied in many data processing areas. Compression methods use variable-size codes with the shorter codes assigned to symbols or groups of symbols that appear in the data frequently. Fibonacci coding, as a…

Performance · Computer Science 2007-12-19 R. Baca , V. Snasel , J. Platos , M. Kratky , E. El-Qawasmeh

This paper proposes a set of techniques to develop correctly rounded math libraries for 32-bit float and posit types. It enhances our RLibm approach that frames the problem of generating correctly rounded libraries as a linear programming…

Mathematical Software · Computer Science 2021-04-12 Jay P. Lim , Santosh Nagarakatte

Matrix-vector multiplication forms the basis of many iterative solution algorithms and as such is an important algorithm also for hierarchical matrices which are used to represent dense data in an optimized form by applying low-rank…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-30 Ronald Kriemann

Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Shivam Aggarwal , Hans Jakob Damsgaard , Alessandro Pappalardo , Giuseppe Franco , Thomas B. Preußer , Michaela Blott , Tulika Mitra

The study on the expressive power of transformers shows that transformers are permutation equivariant, and they can approximate all permutation-equivariant continuous functions on a compact domain. However, these results are derived under…

Machine Learning · Computer Science 2026-01-26 Sejun Park , Yeachan Park , Geonho Hwang

Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning.…

Transformers, central to the successes in modern Natural Language Processing, often falter on arithmetic tasks despite their vast capabilities --which paradoxically include remarkable coding abilities. We observe that a crucial challenge is…

Computation and Language · Computer Science 2023-11-28 Ruoqi Shen , Sébastien Bubeck , Ronen Eldan , Yin Tat Lee , Yuanzhi Li , Yi Zhang

In recent years, image compression for high-level vision tasks has attracted considerable attention from researchers. Given that object information in images plays a far more crucial role in downstream tasks than background information,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Chengjie Dai , Tiantian Song , Hui Tang , Fangdong Chen , Bowei Yang , Guanghua Song

Given a combinatorial decomposition for a counting problem, we resort to the simple scheme of approximating large numbers by floating-point representations in order to obtain efficient Fully Polynomial Time Approximation Schemes (FPTASes)…

Data Structures and Algorithms · Computer Science 2013-11-19 Romeo Rizzi , Alexandru I. Tomescu

We consider the ubiquitous technique of VByte compression, which represents each integer as a variable length sequence of bytes. The low 7 bits of each byte encode a portion of the integer, and the high bit of each byte is reserved as a…

Information Retrieval · Computer Science 2017-01-17 Jeff Plaisance , Nathan Kurz , Daniel Lemire

The amounts of data that need to be transmitted, processed, and stored by the modern deep neural networks have reached truly enormous volumes in the last few years calling for the invention of new paradigms both in hardware and software…

Machine Learning · Computer Science 2022-11-08 Ilya Soloveychik , Ilya Lyubomirsky , Xin Wang , Sudeep Bhoja

Conventional hardware-friendly quantization methods, such as fixed-point or integer, tend to perform poorly at very low word sizes as their shrinking dynamic ranges cannot adequately capture the wide data distributions commonly seen in…

Machine Learning · Computer Science 2020-02-12 Thierry Tambe , En-Yu Yang , Zishen Wan , Yuntian Deng , Vijay Janapa Reddi , Alexander Rush , David Brooks , Gu-Yeon Wei

Customizing the precision of data can provide attractive trade-offs between accuracy and hardware resources. We propose a novel form of vector computing aimed at arrays of custom-precision floating point data. We represent these vectors in…

Other Computer Science · Computer Science 2016-02-16 Shixiong Xu , David Gregg