Abstract: Two related extended precision operand formats provide for efficient multiply/accumulate operations in a SIMD data processing system. Each format utilizes a group of “b” bit elements in a vector register. Each of the elements provides “m” bits of precision, with b>m. The remaining b−m bits in each element accumulate overflows and carries across multiple additions and subtractions. Existing SIMD multiply-sum instructions can be used to efficiently take input operands from the first format and produce output results in the second extended precision format when b2=2b1 and m2=2m1.

Abstract: A programmable function block comprises a core logic circuit having a first argument input group consisting of first through fourth argument input terminals, a second argument input group consisting of first through fourth argument input terminals, first through third configuration input terminals, a core logic carry output terminal, a core logic carry generation output terminal, a core logic carry propagation output terminal, a ripple-core logic carry input terminal, and a sum output terminal. Connected to interconnection wires and the first and the second argument input groups, an input block includes eighth input selection units for selecting, as eight input selected signals, eight ones of signals on the interconnection wires, a fixed logic value of “1”, and a fixed logic value of “0”. Connected to the first through the third configuration input terminals, respectively, first through third memory circuits stores, as first through third stored logic values, a logic value of one bit.

Abstract: A circuiting method is disclosed for adding operands of multiple size. This circuit and method employ an n bit adder having n first and second inputs. A first m bit operand is inputted into the m least significant first inputs of the adder, where n is greater than m. A second m bit operand is inputted into the m least significant circuit inputs of the adder. A first (n-m) bit operand is inputted into the (n-m) most significant first inputs of the adder. Each bit of the first (n-m) bit operand represents logical 0. A second (n-m) bit operand is inputted into the most significant (n-m) second inputs of the adder. Each bit of the second (n-m) bit operand represents a logical 1. The first and second m bit operands, the first and second (n-m) bit operands and a carry in bit provided to a carry input node of the adder, are all inputted in parallel. In response, the adder generates n carry bits and n bit output operand.

Abstract: A circuit for generating partial products for variable width multiplication operations is provided. According to an embodiment of the present invention, the circuit includes a plurality of partial product selector groups, each partial product selector group includes a plurality of partial product selector circuits. Each partial product selector circuit receives a portion of a multiplicand as an input and outputs a partial product. The circuit also includes a plurality of Booth encoders. At least one of the Booth encoders is coupled to each partial product selector group. Each Booth encoder receives as an input a portion of a wide multiplier and outputs a Booth encoded value to at least a portion of a partial product selector group. The circuit further includes an override circuit coupled to one or more of the partial product selector circuits.

Abstract: A data processing apparatus including a multiplier unit forming a product from L bits of each two data buses of N bits each N is greater than L. The multiplier forms a N bit output having a first portion which is the L most significant bits of the of product and a second portion which is M other bits not including the L least significant bits of the product, where N is the sum of M and L. In the preferred embodiment the M other bits are derived from other bits of the two input data busses, such as the M other bits of the first input data bus.

Abstract: An adder unit for a microprocessor, being capable, in response to a first control signal, of adding two full word data values, stored in a first storage location and in a second storage location, respectively, and being capable, in response to a second control signal, of adding in parallel four half word data values, a first half word data value and a second half word data value being stored in the first storage location at the low half and the high half thereof, respectively, and a third half word data value and a fourth half word data value being stored in the second storage location at the low half and the high half thereof, respectively. The adder unit includes a first half word adder, arranged so as to add the first half word and the third half word to provide a first sum output of the adder unit, and a first carry out signal. The adder unit also includes a second half word adder arranged so as to add the second half word and the fourth half word, with a carry-in of 0 to provide a second sum output.