Abstract: A processor having a first and second storage having a first and second packed data, respectively. Each packed data includes a first, second, third, and fourth data element. A multiply-add circuit is coupled to the first and second storage areas. The multiply-add circuit includes a first, second, third, and fourth multiplier, wherein each of the multipliers receives a corresponding set of said data elements. The multiply-add circuit further includes a first adder coupled to the first and second multipliers, and second adder coupled to the third and fourth multipliers. A third storage area is coupled to the adders. The third storage area includes a first and second field for saving output of the first and second adders, respectively, as first and second data elements of a third packed data.

Abstract: A method of reducing microprocessor peak power by scheduling execution of instructions to multiple execution units. In the prior art, parallel processing of instructions by high-power execution units caused the microprocessor peak power to increase. The method of the present invention attempts to reduce microprocessor peak power by ensuring that two high-power execution units are not executing simultaneously. While a first instruction is being executed by a first execution unit, a first signal is asserted. A second instruction is prevented from being dispatched to a second execution unit while the first signal is asserted. Thus, the second execution unit remains in an idle state while the first execution unit is executing the first instruction.

Abstract: A technique for increasing the number of physical segment registers by renaming logical segment registers into a larger register space. The remapping of the segment registers allows for instructions accessing the segment registers to be executed non-serially. The renaming of segment registers is achieved by assigning a shadow register to a segment register name. Thus, a pair of registers are physically available for a specified logical register in an instruction set to be renamed. Two bits, designated as the PSEG and SPEC bits, are used to control the remapping.

Abstract: A processor having a circuit for performing a packed addition and/or packed subtraction operation. The decoder accesses the registers addressed by SRC1 and SRC2. These registers provide a first packed data and a second packed data to the circuit. Packed data consists of a number of fixed length data elements. The data elements can be eight bits, sixteen bits or thirty-two bits in length. The circuit performs the operation on the first data element from the first packed data and the first data element from second packed data, producing a first result data element. The circuit performs this operation on the next data element from the first packed data and the next data element from the second packed data, producing a next result data element. This continues for all the data elements in the first and second packed data. The result data elements constitute a result packed data that is stored in the destination register.

Abstract: A microprocessor that handles invalid opcodes via an event-signaling micro-operation is disclosed. The microprocessor comprises a decoder that decodes macroinstructions, including an opcode, into a single microprocessor cycle micro-operation. The decoder detects invalid opcodes and replaces the invalid opcodes with an event-signaling micro-operation that triggers an invalid opcode assist. The invalid opcode assist triggers an invalid opcode exception handler that processes the invalid opcode.

Abstract: A processor having a circuit for performing a packed addition and/or packed subtraction operation. The decoder accesses the registers addressed by SRC1 and SRC2. These registers provide a first packed data and a second packed data to the circuit. Packed data consists of a number of fixed length data elements. The data elements can be eight bits, sixteen bits or thirty-two bits in length. The circuit performs the operation on the first data element from the first packed data and the first data element from second packed data, producing a first result data element. The circuit performs this operation on the next data element from the first packed data and the next data element from the second packed data, producing a next result data element. This continues for all the data elements in the first and second packed data. The result data elements constitute a result packed data that is stored in the destination register.