Patent
Low latency floating-point divider
Reads0
Chats0
TLDR
In this article, an improved method and apparatus for performing floating-point division is described, in which fractional operands are pre-scaled and an estimate of a reciprocal of the prescaled fractional divisor is obtained from a lookup table using a portion of the bits of the prior bits.Abstract:
An improved method and apparatus for performing floating-point division is disclosed. In a particular embodiment, fractional operands are pre-scaled and an estimate of a reciprocal of the pre-scaled fractional divisor is obtained from a lookup table using a portion of the bits of the pre-scaled fractional divisor. This value is used to scale the fractional operands and a multiply-add operation is used based on principles of series expansion to compute a final result with an acceptable degree of accuracy.read more
References
More filters
Patent
Scheme for computing Montgomery division and Montgomery inverse realizing fast implementation
TL;DR: In this paper, a scheme for performing high speed Montgomery division within the Montgomery space was proposed, where the Montgomery inverse X =A -1 ·2 2n mod N for a positive integer N, a positive A which is relatively prime with respect to N and satisfying 0≦A
Patent
Method and apparatus for performining floating point division
TL;DR: In this article, a floating-point division (FPD) method was proposed for producing a quotient having a mantissa of n bits. But this method is not suitable for the problem of estimating the exact magnitude of the quotient.
Patent
Method and system for performing floating-point division using selected approximation values
TL;DR: In this paper, a method and system for floating-point division of a dividend by a divisor within a floating point unit having multiply and add functions is presented, which uses an approximation based on a linear approximation stored within a first table.
Patent
Processing unit having decimal floating-point divider using Newton-Raphson iteration
TL;DR: In this paper, a decimal floating-point divider is described that implements efficient hardware-based techniques for performing decimal floating point division using an accurate piecewise linear approximation to obtain an initial estimate of a divisor's reciprocal.
Patent
Method and apparatus for obtaining the quotient of two numbers within one clock cycle
TL;DR: In this article, a divider circuit for producing a quotient result within one cycle time is presented, which utilizes combinational circuitry for performing a division operation by computing a scaled reciprocal of the denominator, and multiplying the scaled output by a similarly scaled numerator.