Abstract: A method of recovering from loading invalid data into a register within a pipelined processor. The method comprises the steps of (A) setting a register status for the register to an invalid state in response to loading invalid data into the register and (B) stalling the processor in response to an instruction requiring data buffered by the register and the register status being in the invalid state.

Abstract: An iterative mantissa calculator calculates a quotient mantissa for a divide mode or a result mantissa for a square-root mode. The calculator includes at least first and second summing devices. In the divide mode, each summing device calculates a respective estimated partial remainder W[j+1] for the next iteration, j+1, as 2*W[j]?Sj+1*D, where W[j] is the estimated partial remainder for the current iteration calculated during the prior iteration, Sj+1 is the quotient bit estimated for the next iteration, and D is the respective divisor bit. The estimated quotient bit for the next iteration is selected based on the calculated partial remainder. In the square-root mode, the first summing device calculates 2W[j]?2S[j]Sj+1, where W[j] is the estimated partial remainder and Sj+1 is the estimated result generated during the current iteration, j.

Abstract: A circuit that may comprise a data-cache memory and a data-path circuit. The data-cache memory may be configured to (i) store a cache input data item among a plurality of associative sets and (ii) present a plurality of cache output data items. The data-path circuit may be configured to (i) independently shift each of the plurality of cache output data items and (ii) multiplex the plurality of shifted cache output data items to present an output data item.

Abstract: A circuit that may comprise a data-cache memory and a data-path circuit. The data-cache memory may be configured to (i) store a cache input data item among a plurality of associative sets and (ii) present a plurality of cache output data items. The data-path circuit may be configured to (i) independently shift each of the plurality of cache output data items and (ii) multiplex the plurality of shifted cache output data items to present an output data item.