Design, implementation and testing of extended and mixed precision BLAS

Author:

Li Xiaoye S.1,Demmel James W.2,Bailey David H.1,Henry Greg3,Hida Yozo2,Iskandar Jimmy2,Kahan William2,Kang Suh Y.2,Kapur Anil2,Martin Michael C.2,Thompson Brandon J.2,Tung Teresa2,Yoo Daniel J.2

Affiliation:

1. Lawrence Berkeley National Laboratory

2. University of California, Berkeley, CA

3. Intel Corporation, Hillsboro, OR

Abstract

This article describes the design rationale, a C implementation, and conformance testing of a subset of the new Standard for the BLAS (Basic Linear Algebra Subroutines): Extended and Mixed Precision BLAS. Permitting higher internal precision and mixed input/output types and precisions allows us to implement some algorithms that are simpler, more accurate, and sometimes faster than possible without these features. The new BLAS are challenging to implement and test because there are many more subroutines than in the existing Standard, and because we must be able to assess whether a higher precision is used for internal computations than is used for either input or output variables. We have therefore developed an automated process of generating and systematically testing these routines. Our methodology is applicable to languages besides C. In particular, our algorithms used in the testing code will be valuable to all other BLAS implementors. Our extra precision routines achieve excellent performance---close to half of the machine peak Megaflop rate even for the Level 2 BLAS, when the data access is stride one.

Publisher

Association for Computing Machinery (ACM)

Subject

Applied Mathematics,Software

Reference51 articles.

1. Basic Linear Algebra Subprograms (BLAS) Standard. 2000. http://www.netlib.org/utk/papers/blast-forum.html. Basic Linear Algebra Subprograms (BLAS) Standard. 2000. http://www.netlib.org/utk/papers/blast-forum.html.

2. IEEE. 2001. 754 Revision. http://grouper.ieee.org/groups/754/. IEEE. 2001. 754 Revision. http://grouper.ieee.org/groups/754/.

3. Anderson E. Bai Z. Bischof C. Blackford S. Demmel J. Dongarra J. Du Croz J. Greenbaum A. Hammarling S. McKenney A. and Sorensen D. 1999. LAPACK Users' Guide Release 3.0. SIAM Philadelphia. Pa. Anderson E. Bai Z. Bischof C. Blackford S. Demmel J. Dongarra J. Du Croz J. Greenbaum A. Hammarling S. McKenney A. and Sorensen D. 1999. LAPACK Users' Guide Release 3.0. SIAM Philadelphia. Pa.

4. ANSI/IEEE Std. 754-1985. IEEE Standard for Binary Floating Point Arithmetic. ANSI/IEEE Std. 754-1985. IEEE Standard for Binary Floating Point Arithmetic.

5. ANSI/IEEE Std. 854-1987. IEEE Standard for Radix Independent Floating Point Arithmetic. ANSI/IEEE Std. 854-1987. IEEE Standard for Radix Independent Floating Point Arithmetic.

Cited by 126 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Useful applications of correctly-rounded operators of the form ab + cd + e;2024 IEEE 31st Symposium on Computer Arithmetic (ARITH);2024-06-10

2. Sparse Matrix-Vector Multiplication with Reduced-Precision Memory Accessor;2023 IEEE 16th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC);2023-12-18

3. Leveraging Mixed Precision in Exponential Time Integration Methods;2023 IEEE High Performance Extreme Computing Conference (HPEC);2023-09-25

4. LAProof: A Library of Formal Proofs of Accuracy and Correctness for Linear Algebra Programs;2023 IEEE 30th Symposium on Computer Arithmetic (ARITH);2023-09-04

5. Acceleration of iterative refinement for singular value decomposition;Numerical Algorithms;2023-07-19

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3