Titlebook: Application-Specific Arithmetic; Computing Just Right Florent de Dinechin,Martin Kumm Book 2024 The Editor(s) (if applicable) and The Autho

jungle

chastise

Florent de Dinechin,Martin KummPresents a unique focus on application-specific computer arithmetic.Helps developers gain a deep understanding of the arithmetic in their projects, and tailor it to their application.Illustrates conce

否认

http://image.papertrans.cn/a/image/159207.jpg

ANIM

Lecture Notes in Networks and SystemsComputer arithmetic is the art of representing and processing numbers in a machine. It has its roots in the abacus of ancient times and in the mechanical calculator built by Schickhard, Pascal, Leibniz, and others during the Renaissance. It has also been at the core of electronic computers since the dawn of this technology in the 1940s.

reaching

考博

Ajith Abraham,Paramartha Dutta,Soumi DuttaField programmable gate arrays (FPGAs) are a natural target for application-specific arithmetic, and many of the techniques developed in this book were motivated by FPGA applications. This chapter gives a brief overview of FPGA architectural features relevant to application-specific arithmetic.

Bumptious

Deepshikha Thakur,Vineet Shyam,Varsha SinghThis chapter is dedicated to the Euclidean division by an integer constant. Of particular interest are small constants such as 3, 5, etc., for which several specific techniques can be used.

Foam-Cells

Horst Chmiel,Valko Mavrov,Armin FähnrichA squarer is another useful specialization of multiplication in the case when the two inputs are identical. It is useful in all sorts of coarser components such as Euclidean norms or polynomials. Besides, operators for . for . > 2 can also be built efficiently out of squares and multiplications.

finale

Mirat D. Gurol,Shu-Sung Lin,Nilesh BhatThis chapter studies the possible optimizations that arise in the specialization or fusion of floating-point operators. It builds upon the specialized fixed operators of previous chapters and focuses on exponent management and rounding issues specific to floating point.

FLINT