We develop the foundations for confirming monotonicity of a multi-term reciprocal function approximation. We introduce the concept of operand recoding to improve the accuracy of multipartite approximation. The results are applied to provide a proposed four-partite reciprocal implementation with total table size ∼27 Kbytes, that yields an IEEE standard, single precision sized format (24 bit) reciprocal instruction, that is a one-ulp monotonic reciprocal
This paper presents a new scheme for the hardware evaluation of functions in fixed-point format, for...
(eng) Table-based methods are frequently used to implement functions. We examine some methods introd...
The implementation of correctly rounded elementary functions needs high intermediate accuracy before...
This paper presents the design and implementation of a reciprocal unit, in which the initial approxi...
AbstractReciprocal and root reciprocal functions at “half” and IEEE single precision formats are spe...
International audienceA recently proposed complex valued division algorithm designed for efficient h...
This paper deals with the computation of reciprocals, square roots, inverse square roots, and some e...
Quotients, reciprocals, square roots and square root reciprocals all have the property that infinite...
The computation of the reciprocal of a numerical value is an important ingredient of many algorithms...
The reciprocal and square root reciprocal operations are important in several applications such as c...
6th International Conference on Electrical and Electronics Engineering, ELECO 2009 --5 November 2009...
By taking reciprocity of the error network into account, full and accurate calibration of a 16-term ...
International audienceA unified view of most previous table-lookup-and-addition methods (bipartite t...
International audienceThis paper presents a simple hardware architecture for computing the seed valu...
Implementations of the reciprocal, square root and reciprocal square root often share a common struc...
This paper presents a new scheme for the hardware evaluation of functions in fixed-point format, for...
(eng) Table-based methods are frequently used to implement functions. We examine some methods introd...
The implementation of correctly rounded elementary functions needs high intermediate accuracy before...
This paper presents the design and implementation of a reciprocal unit, in which the initial approxi...
AbstractReciprocal and root reciprocal functions at “half” and IEEE single precision formats are spe...
International audienceA recently proposed complex valued division algorithm designed for efficient h...
This paper deals with the computation of reciprocals, square roots, inverse square roots, and some e...
Quotients, reciprocals, square roots and square root reciprocals all have the property that infinite...
The computation of the reciprocal of a numerical value is an important ingredient of many algorithms...
The reciprocal and square root reciprocal operations are important in several applications such as c...
6th International Conference on Electrical and Electronics Engineering, ELECO 2009 --5 November 2009...
By taking reciprocity of the error network into account, full and accurate calibration of a 16-term ...
International audienceA unified view of most previous table-lookup-and-addition methods (bipartite t...
International audienceThis paper presents a simple hardware architecture for computing the seed valu...
Implementations of the reciprocal, square root and reciprocal square root often share a common struc...
This paper presents a new scheme for the hardware evaluation of functions in fixed-point format, for...
(eng) Table-based methods are frequently used to implement functions. We examine some methods introd...
The implementation of correctly rounded elementary functions needs high intermediate accuracy before...