Advanced Micro Devices Corporation

Other

Texas Instruments Corporation

University of Texas System

Carl E Lemonds

Eric C Quinnell

Earl E Swartzlander, Jr

Alan Gatherer

Michael J Schulte

Jay E Fleischman

Dimitri Tan

David M Russinoff

A method, performed by a processor, of determining a square root using a single processor cycle per iteration is described. The method includes, in a single cycle: obtaining, from a stored lookup table, a quotient digit and a square of the quotient digit; retrieving a current solution; and determining a new solution using the current solution and the quotient digit. Circuitry configured to perform the method is described.

Method and circuitry for square root determination

A bridge fused multiply-adder is disclosed. The fused multiply-adder is for the single instruction execution of (A&#xd7;B)+C. The bridge fused multiply-add unit adds this functionality to existing floating-point co-processor units by including a fused multiply-add hardware 'bridge' between an existing floating-point adder and a floating-point multiplier unit. This fused multiply-add functionality is added to existing two-operand architecture designs without degrading the performance or parallel pipe execution of floating-point adder and floating-point multiplier instructions.

Bridge fused multiply-adder circuit

A three-path floating-point fused multiply-adder is disclosed. The fused multiply-adder is for the single instruction execution of (A&#xd7;B)+C. The three-path fused multiply-adder is based on a dual-path adder and reduces latency significantly by operating on case data in parallel and by reducing component bit size. The fused multiply-adder is a common serial fused multiply-adder that reuses floating-point adder (FPA) and floating-point multiplier (FPM) hardware, allowing single adds, single multiplies, and fused multiply-adds to execute at maximum speed.

Three-path fused multiply-adder circuit

A division method includes determining a precision indicator for the division operation that indicates whether the quotient should be a single precision, double precision, or extended precision floating-point number. The division is performed at a rectangular multiplier using the Goldschmidt or Newton-Raphson algorithm. Each algorithm calculates one or more intermediate values in order to determine the quotient. For example, the Goldschmidt algorithm calculates a complement of a product of the dividend and an estimate of the reciprocal of the divisor. The quotient is determined based on a portion of one or more of these intermediate values. Because only a portion of the intermediate value is used, the division can be performed efficiently at the rectangular multiplier, and therefore the quotient can be determined more quickly and still achieve the desired level of precision.

Division with rectangular multiplier supporting multiple precisions and operand types

A multiplier ( ) is disclosed that includes an encoder ( ), a hierarchy of compressors ( and ), a bit detector ( ) and a switch ( ). The encoder ( ) is operable to receive a first and second encoder input. The compressors ( and ) are coupled to the encoder ( ). The compressors ( and ) are operable to receive a first number of inputs and to generate a second number of outputs, with the second number being less than the first number. The bit detector ( ) is operable to monitor the first encoder input to determine whether the first encoder input is in a reduced precision range ( ). The bit detector ( ) is also operable to deactivate a subset of the compressors ( and ) when the bit detector ( ) determines that the first encoder input is in the reduced precision range ( ). The switch ( ) is coupled to a specified one of the compressors ( ). The switch ( ) is operable to redirect the path of one of the outputs for the specified compressor ( ) such that the subset of the compressors ( and ) is removed from the path when the bit detector ( ) determines that the first encoder input is in the reduced precision range ( ).

Growing community of inventors

Austin, TX, United States of America

Carl E Lemonds