Leveraging the bfloat16 Artificial Intelligence Datatype For Higher-Precision Computations

J. Dongarra, C. Moler, and J. Wilkinson, “Improving the accuracy of computed eigenvalues and eigenvectors,” 1983, sIAM J. Numer. Anal. Vol. 20, No. 1

1983

Earlier work this paper cites.

J. Dongarra, J. D. Croz, S. Hammarling, and I. Duff, “A set of level 3 basic linear algebra subprograms,” 1990

1990

Earlier work this paper cites.

E. Anderson, Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. D. Croz, A. Greenbaum, S. Hammarling, A. McKenney, and D. Sorenson, LAPACK User’s Guide . Philadelphia, PA: SIAM Publications, 1992

1992

Earlier work this paper cites.

Barrett and B. et al, Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods . SIAM Publications, 1993

1993

Earlier work this paper cites.

D. H. B. Yozo Hida, Xiaoye S Li, “Library for double-double and quad-double arithmetic,” 2007

2007

Cited alongside, same era.

I. Yamazaki et al. , “Mixed-precision cholesky qr factorization and its case studies on multicore cpu with multiple gpus,” 2015, sIAM J. Sci. Comput., Volume 37, Issue 3, C307–C330

2015

Cited alongside, same era.

P. Micikevicius, S. Narang, J. Alben, G. F. Diamos, E. Elsen, D. García, B. Ginsburg, M. Houston, O. Kuchaiev, G. Venkatesh, and H. Wu, “Mixed precision training,” CoRR , vol. abs/1710.03740, 2017

Original

2017

Cited alongside, same era.

E. Carson and N. Higham, “A new analysis of iterative refinement and its application to accurate solution of ill-conditioned sparse linear systems,” 2017, sIAM J. SCI. COMPUT. Vol. 39, No. 6, pp. A2834–A2856

2017

Cited alongside, same era.

Intel Math Kernel Library. Reference Manual . Santa Clara, USA: Intel Corporation, iSBN 630813-054US

Cited in the paper.

A. Alvermann et al. , “Benefits from using mixed precision computations in the elpa-aeo and essex-ii eigensolver projects.”

Cited in the paper.

“Tensorflow development summit,” March 30 2018

2018

Later among the works it cites.

BFLOAT16 – Hardware Numerics Definition . Santa Clara, USA: Intel Corporation, 2018

2018

Later among the works it cites.

X. Cheng, A. Sorna, E. D’Azevedo, K. Wong, and S. Tomov, “Accelerating 2d fft: Exploit gpu tensor cores through mixed-precision,” 2018

2018

Later among the works it cites.

A. Haidar, S. Tomov, J. Dongarra, and N. J. Higham, “Harnessing gpu tensor cores for fast fp16 arithmetic to speed up mixed-precision iterative refinement solvers,” 2018

2018

Later among the works it cites.