Abstract: A router is provided that includes a plurality of lanes to receive inbound data from a plurality of different input ports. The router may further include a shared crossbar channel coupled to each of the lanes and to a plurality of output ports, the crossbar channel to receive inbound data from the plurality of lanes and to provide outbound data to the plurality of output ports. Each lane may include a local lane arbiter, a global lane arbiter and a port arbiter associated with each port.

Abstract: A router is provided that includes a plurality of lanes to receive inbound data from a plurality of different input ports. The router may further include a shared crossbar channel coupled to each of the lanes and to a plurality of output ports, the crossbar channel to receive inbound data from the plurality of lanes and to provide outbound data to the plurality of output ports. Each lane may include a local lane arbiter, a global lane arbiter and a port arbiter associated with each port.

Abstract: A method for automatically mapping state elements between a first circuit and a second circuit is described. The method proceeds by comparing, in a structural phase, structural features of state elements in the first circuit to structural features of state elements in the second circuit for equivalence. Mappings between state elements of the first circuit and the second circuit are determined based on the comparison of structural features. “Don't care” input conditions are then accounted for prior to determination of functional features. During an inversion detection phase, the polarity of the mappings found in the prior structural phase are determined. A functional phase follows in which the functionality of state elements in the first circuit are compared to the functionality of state elements in the second circuit for equivalence using a three-valued random simulation and further mappings are determined based upon the functional comparison.

Abstract: A floating point adder circuit includes an exponent path and a mantissa path. The exponent path includes a comparator to compare two three-bit exponents. The two exponents are each incremented, and a resultant exponent is chosen from one of the two original exponents or one of the incremented exponents. The mantissa path includes an adder to add mantissas, and an adder bypass path to select one of the mantissas in lieu of performing an addition. The mantissa path also includes constant shifters that conditionally shift the mantissas right by thirty-two bit positions.

Abstract: A multiply-accumulate circuit includes a compressor tree to generate a product with a binary exponent and a mantissa in carry-save format. The product is converted into a number having a three bit exponent and a fifty-seven bit mantissa in carry-save format for accumulation. An adder circuit accumulates the converted products in carry-save format. The adder operates on floating point number representations having exponents with a least significant bit weight of thirty-two, and exponent comparisons within the adder exponent path are limited in size. The adder circuit includes intermediate registers to provide multi-threaded capability. Products interleaved in time are accumulated into separate sums simultaneously.

Abstract: A floating point adder circuit includes an exponent path and a mantissa path. The exponent path includes a comparator to compare two three-bit exponents. The two exponents are each incremented, and a resultant exponent is chosen from one of the two original exponents or one of the incremented exponents. The mantissa path includes an adder to add mantissas, and an adder bypass path to select one of the mantissas in lieu of performing an addition. The mantissa path also includes constant shifters that conditionally shift the mantissas right by thirty-two bit positions.

Abstract: One aspect of the invention is a coverage metric to identify that part of a state space which is covered by properties verified by model checking. In each property, a signal is identified (or a proposition on several signals) as the observed signal in that property. The coverage metric measures the coverage of a set of properties with respect to the observed signal. The coverage metric identifies the reachable states in which the value of the observed signal determines the validity of the verified properties. Then a model checking algorithm can be used to check the correctness condition on the observed signal in these “covered” states to prove or disprove the property.

Abstract: A method for automatically mapping state elements between a first circuit and a second circuit is described. The method proceeds by comparing, in a structural phase, structural features of state elements in the first circuit to structural features of state elements in the second circuit for equivalence. Mappings between state elements of the first circuit and the second circuit are determined based on the comparison of structural features. “Don't care” input conditions are then accounted for prior to determination of functional features. During an inversion detection phase, the polarity of the mappings found in the prior structural phase are determined. A functional phase follows in which the functionality of state elements in the first circuit are compared to the functionality of state elements in the second circuit for equivalence using a three-valued random simulation and further mappings are determined based upon the functional comparison.