Results 121 to 130 of about 322 (162)

Floating-Point Arithmetic

2019
You already know about integer arithmetic; now we will introduce some floating-point computations. There is nothing difficult here; a floating-point value has a decimal point in it and zero or more decimals. We have two kinds of floating-point numbers: single precision and double precision.
openaire   +1 more source

A Cordic-based Floating-point Arithmetic Unit

1992 Proceedings of the IEEE Custom Integrated Circuits Conference, 1992
A floating-point arithmetic unit based on the CORDIC algorithm is described. It computes a wide range of arithmetic, trigonometric, and hyperbolic functions and achieves a normalized peak performancle off 220 MFLOPs. The unit is implemented in 1.6pm double-metal CMOS technology and packaged in a 280 pin PGA.
Rix, Bernold, Timmermann, Dirk, Hahn, Helmut, Hosticka, Bedrich   +3 more
openaire   +1 more source

A floating-point residue arithmetic unit

Journal of the Franklin Institute, 1981
Abstract A floating-point arithmetic unit (FPAU), based on the residue number system, is reported which can perform addition, subtraction and multiplication. As a result, several classic problems associated with RNS based digital filters such as: overflow detection, sign detection and non-integer filter coefficients are overcome by virtue of ...
Fred J. Taylor, Chao H. Huang
openaire   +1 more source

Floating Point Arithmetic Circuits

1979
Floating-point arithmetic in hardware still belongs to the more or less expensive extras of many types of computers. The algorism of floating point computation requires more circuits than the ordinary integer arithmetic circuits. A number of these circuits will be discussed in later sections of this chapter.
openaire   +1 more source

Is Floating-Point. Arithmetic Still Adequate?

1988
For complicated numerical problems, the error analysis has to be performed by the computer. Several methods for automated error analysis are known. Floating-point arithmetic has to be augmented and programming languages for scientific computation have to be provided (PASCAL-SC and FORTRAN-SC) for that purpose.
openaire   +1 more source

Quantization errors in floating-point arithmetic

IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978
In this paper, the quantization of the mantissa in a normalized floating-point number is investigated. A necessary and sufficient condition is given for the mantissa to have a reciprocal probability density. A model to represent a floating-point quantizer with the mantissa having a reciprocal density is developed.
Sripad, Anekal B., Snyder, Donald L.
openaire   +1 more source

Required scientific floating point arithmetic

1978 IEEE 4th Symposium onomputer Arithmetic (ARITH), 1978
Previous papers in computer arithmetic have shown that correct rounded floating point with good arithmetic properties can be attained using guard digits and careful algorithms on the floating point fractions. This paper combines that body of knowledge with proposed exponent forms that are closed with respect to inversion and detection and recovery of ...
openaire   +1 more source

Unum: Adaptive Floating-Point Arithmetic

2016 Euromicro Conference on Digital System Design (DSD), 2016
Usually, arithmetic units represent numeric data-types employing fixed-length representations. For instance, hardware representations of real numbers usually employ fixed-length formats defined by the IEEE Standard 754 (32-bit single-precision, 64-bit double-precision, , floating-point numbers).
openaire   +1 more source

Axiomatizations of floating point arithmetics

1985 IEEE 7th Symposium on Computer Arithmetic (ARITH), 1985
We present a universal scheme for axiomatizing floating point ariththmetic. The schema can be used to axiomatize any floating point arithmetic. It consists of a labeled graph with vertices describing some arithmetical properties and edges containing appropriate axioms. The language of floating point arithmetic is developed gradually in this scheme. The
openaire   +1 more source

Floating-point recurring rational arithmetic system

1983 IEEE 6th Symposium on Computer Arithmetic (ARITH), 1983
Major computer arithmetic systems are based on the concept of realizing only terminate rationals in positional notation. This paper proposes a new arithmetic scheme of indicating periodicity in the radix representation of a mantissa to realize recurring rationals as well as terminate rationals.
openaire   +1 more source