Intel Corporation

Hewlett-Packard Development Company, L.p.

Hewlett-Packard Company

Paul Robert Thayer

Sanjay Kumar

Glenn T Colon-Bonet

Circuitry for reducing propagation delays in calculation of a value for use in a floating point multiply-accumulate operation. In the circuitry, a carry-save adder receives values of three input operands from three latches. A carry-lookahead adder receives the outputs from the carry-save adder and implements an XOR operation on a most-significant bit along with its own logic operation to produce the value for the floating point multiply-accumulate operation. Modification of the carry-lookahead adder to perform the XOR operation results in elimination of an entire stage of logic.

Faster shift value calculation using modified carry-lookahead adder

Circuitry for reducing propagation delays in calculation of a value for use in a floating point multiply-accumulate operation. In the circuitry, a carry-save adder receives values of three input operands from three latches. A carry-lookahead adder receives the outputs from the carry-save adder and implements an XOR operation on a most-significant bit along with its own logic operation to produce a value for the floating point multiply-accumulate operation. Modification of the carry-lookahead adder to perform the XOR operation results in elimination of an entire stage of logic.

A Multiply Accumulate unit, which may be an FMAC for IEEE 754 format numbers, finds A*B&plusmn;C faster if the multiplier is allowed to assume that it's A and B inputs are always positive, so that it never has to provide a complemented output, and if the C input for the accumulation with the product is also assumed to be positive. The sign magnitude notation of the IEEE 754 format is temporarily exchanged for a positive two's complement notation of the assumed positive values. Notice is taken of the actual signs, and when there is a difference to be formed, either because of addition between numbers having opposite signs, or because of a subtraction between numbers having the same sign, one of the numbers need to be negated (complemented) prior to the addition of C and the product AB. That number can always be C, provided that correct compensatory negation is available after the addition. Such negations of C are accomplished by performing a one's complement followed by a carry-in to the subsequent adder. Each of the complemented and the non-complemented C values are readily available. Their production and the selection of one or the other are operations that overlap the execution of the multiply, and are done in a way that does not increase the path delay through the shifter. The accumulated result will typically need to be normalized, after which it may need a final complement operation to adjust its sign, in accordance with the original signs and whether the accumulation was addition or subtraction. The result may be converted back to the IEEE 754 format in due course.

Growing community of inventors

Fort Collins, CO, United States of America

Paul Robert Thayer