Results 241 to 250 of about 4,958,187 (282)

Floating point micropipeline performance

Journal of Systems Architecture, 1998
Abstract Recent superscalar computer chips implement complex pipelines using independent integer and floating-point units (FPUs). Floating-point performance is critical for many engineering and scientific applications and good floating-point performance requires hardware resources that occupy a major portion of the chip area.
Shlomo Weiss, A. Goldstein
openaire   +1 more source

Floating-point behavioral synthesis

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2001
Traditionally, the data processed by a synthesized digital design is fixed (occasionally variable) width integer, and the functional units available are concomitantly simple ladders, subtractors, multipliers, multiplexers, and so on). The aims of paper work are two-fold: 1) to provide a library of high-level floating-point functions (trigonometric ...
Zaher Abdulkarim Baidas, Andrew D. Brown, Alan Christopher Williams   +2 more
openaire   +1 more source

Decimal Floating-Point Multiplication

IEEE Transactions on Computers, 2009
Decimal multiplication is important in many commercial applications including financial analysis, banking, tax calculation, currency conversion, insurance, and accounting. This paper presents the design of two decimal floating-point multipliers: one whose partial product accumulation strategy employs decimal carry-save addition and one that employs ...
Mark A. Erle, Brian J. Hickmann, Michael J. Schulte   +2 more
openaire   +2 more sources

The NS32081 Floating-point Unit

IEEE Micro, 1986
This chip's designers kept the hardware relatively simple and yet obtained high, IEEE-standard, floating-point performance.
Moshe Oavrielov, Lev Epstein
openaire   +2 more sources

On Accurate Floating-Point Summation

Communications of the ACM, 1971
cumulation of floating-point sums is considered on a computer which performs t -digit base β floating-point addition with exponents in the range — m to M .
exaly   +3 more sources

Accurate floating-point summation

Communications of the ACM, 1970
This paper describes an alternate method for summing a set of floating-point numbers. Comparison of the error bound for this method with that of the standard summation method shows that it is considerably less sensitive to propagation of round-off error.
openaire   +1 more source

Multiprecision floating point addition

Proceedings of the 2000 international symposium on Symbolic and algebraic computation, 2000
An efficient algorithm is presented that returns the exactly rounded sum of two multiprecision floating point numbers. Depending on the input signs and exponents the algorithm distinguishes five cases. In each case, the method minimizes the number of computer words that are subject to de-normalization, addition or subtraction, and normalization.
George E. Collins, Werner Krandick
openaire   +1 more source

Floating‐point number LISP

Software: Practice and Experience, 1991
AbstractA floating‐point‐number‐oriented LISP has been developed. Though it performs type checking on every numeric operation, it runs as fast as Fortran for simple differential‐equation problems. This paper describes the implementation, provides some measurements of its efficiency, and discusses the feasibility of this type of implementation.
openaire   +2 more sources

Multiplications of floating point expansions

Proceedings 14th IEEE Symposium on Computer Arithmetic (Cat. No.99CB36336), 2003
In modern computers, the floating point unit is the part of the processor delivering the highest computing power and getting most attention from the design team. Performance of any multiple precision application will be dramatically enhanced by adequate use of floating point expansions.
openaire   +2 more sources

Floating point error analysis

Preprints of papers presented at the 14th national meeting of the Association for Computing Machinery on - ACM '59, 1959
In many floating point calculations it is important to arrange the sequence of calculations such that significant digits are not deleted by intermediate rounding of the numbers. The danger that gross errors may be introduced is always present in floating point calculations, since the number of digits carried in each number is restricted in normal ...
openaire   +1 more source