Weitek Corporation

Larry Hu

Frederick Abbott Ware

Jnyaneshwar P Prabhu

S M Quek

George K Chu

Mark Birman

John McLeod

Ting Chuk

In an apparatus and method for computing inverses and square roots, a highly accurate initial approximation is computed using a second order polynomial equation, the coefficients of which are stored in a ROM. The most significant bits of an operand are used to address a ROM to select coefficients, providing different coefficients for different operand ranges. The remaining lesser significant operand bits are used in the computation; the coefficient values already account for the bits used to address them. The result is in single precision accuracy. For double precision, the polynomial results are used as the first approximation for a Newton-Raphson iteration. The multiplier has a split array mode to speed up the calculation of the polynomial, whereby two lesser precision values can be computed at once. The size of the coefficients is tailored to produce the proper precision result for each of the elements of Ax.sup.2 +Bx+C. Separate values for the coefficients A, B, and C must be stored for the 1/x approximation and for the 1/.sqroot.x approximation. Also to speed up the multiplier, the multiplier can accept one operand in carry/save format, by providing Booth recoder logic which can accept operands in a normal binary or in a carry/save format. Also employed is a rounding technique which provides IEEE exact rounding by an operation that includes only one multiplication.

Apparatus for determining booth recoder input control signals

In an apparatus and method for computing inverses and square roots a highly accurate initial approximation is computed using a second order polynomial equation, the coefficients of which are stored in a ROM. The most significant bits of an operand are used to address a ROM to select coefficients, providing different coefficients for different operand ranges. The remaining lesser significant operand bits are used in the computation; the coefficient values already account for the bits used to address them. The result is in single precision accuracy. For double precision, the polynomial results are used as the first approximation for a Newton-Raphson iteration. The multiplier has a split array mode to speed up the calculation of the polynomial, whereby two lesser precision values can be computed at once. The size of the coefficients is tailored to produce the proper precision result for each of the elements of Ax.sup.2 +Bx+C. Separate values for the coefficients A, B, and C must be stored for the 1/x approximation and for the 1/.sqroot.x approximation. Also to speed up the multiplier, the multiplier can accept one operand in carry/save format, by providing Booth recoder logic which can accept operands in a normal binary or in a carry/save format. Also employed is a rounding technique which provides IEEE exact rounding by an operation that includes only one multiplication.

Apparatus for multiplying operands

A programmable latency (a programmable number of clock cycles) needed for an operation completion. The required latency for a pipe is determined from a formula including the system clock cycle time which the unit will be specified to operate under. The latency is preprogrammed by setting the count of a timer accordingly to provide at least the minimum number of clock cycles necessary to cover the time required to do the computation. Separate timers are independently set for arithmetic logic unit (ALU) operations, multiply operations, logical operations and divide and square root operations.

Variable latency method and apparatus for floating-point coprocessor

Growing community of inventors

Mountain View, CA, United States of America

Larry Hu