A number of issues related to floating point accuracy and compliance are a frequent source of confusion on both CPUs and GPUs. The purpose of this white paper is to discuss the most common issuesâ€¦ (More)

17th IEEE Symposium on Computer Arithmetic (ARITHâ€¦

2005

We introduce an inheritance property and related table lookup structures applicable to simplified evaluation of the modular operations "multiplicative inverse", "discrete log", and "exponentialâ€¦ (More)

Introduction and background: The basic integer arithmetic operations of addition=subtraction, multiplication and division are implemented typically in hardware using k bits of precision with kâ€¦ (More)

Introduction and summary: Hardware capabilities for integer arithmetic generally include addition, multiplication, and division with precision k typically chosen as 16, 32 or 64. Multiplication andâ€¦ (More)

We describe the hardware implementation of a novel algorithm for computing the discrete logarithm modulo 2/sup k/. The circuit has a total latency of less than k table-lookup-determined shift-and-addâ€¦ (More)

IEEE 17th International Conference on Applicationâ€¦

2006

We describe several integer function properties which in combination allow direct lookup tables to be reduced in size and structure to simpler lookup trees. Our principal result is a novel tableâ€¦ (More)

We describe a high radix integer division algorithm where the divisor is prescaled and the quotient is postscaled without modifying the dividend to obtain an identity with the quotient differing fromâ€¦ (More)

Many function approximation procedures can obtain enhanced accur acyby an eÃ†cient table lookup of a pr oduct z=f(x)g(y). Both x and y are represented by indices of i leading bits (typically 7 < i <â€¦ (More)