International Business Machines Corporation

Microsoft Technology Licensing, LLC

Northrop Grumman Systems Corporation

Brian Lee Koehler

Adam James Muff

Eric Oliver Mejdrich

Quentin P Herr

Brian Thomas Vanderpool

Kenneth S Reneris

Timothy Hume Heil

Miguel Comparan

Alfredo Aldereguia

Alexander Louis Braun

Mark Gary Kupferschmidt

Janet Lynn Schneider

Grace Ann Richter

Haitao O Dai

Alfred Thomas Watson, Iii

Brent Francis Hilgart

Corey Arthur Kegerreis

Alison Ii

One example includes an isochronous receiver system. The system includes a pulse receiver configured to receive an input data signal from a transmission line and to convert the input data signal to a pulse signal. The system also includes a converter system comprising a phase converter system. The phase converter system includes a plurality of pulse converters associated with a respective plurality of sampling windows across a period of an AC clock signal. At least two of the sampling windows overlap at any given phase of the AC clock signal, such that the converter system is configured to generate an output pulse signal that is phase-aligned with at least one of a plurality of sampling phases of the AC clock signal based on associating the pulse signal with at least two of the sampling windows.

Superconducting isochronous receiver system

Superconducting circuit with virtual timing elements and related methods are described. A method includes specifying a superconducting circuit portion including a timing path comprising: (1) at least one logic gate to be implemented using Josephson junctions, (2) a first virtual timing element for defining a synchronization point along the timing path, and (3) a second virtual timing element for adding latency to the timing path. The method further includes synthesizing the superconducting circuit portion, where the synthesizing comprises treating the first virtual timing element as a first flip-flop and the second virtual timing element as a second flip-flop, where the first flip-flop is treated as being fixed in relation to the at least one logic gate along the timing path, but the second flip-flop is treated as being movable in relation to the at least one logic gate along the timing path.

Superconducting circuit with virtual timing elements and related methods

A method and apparatus for executing instructions in a processor are provided. In one embodiment of the invention, the method includes receiving a plurality of instructions. The plurality of instructions includes first instructions in a first thread and second instructions in a second thread. The method further includes forming a common issue group including an instruction of a first instruction type and an instruction of a second instruction type. The method also includes issuing the common issue group to a first execution unit and a second execution unit. The instruction of the first instruction type is issued to the first execution unit and the instruction of the second instruction type is issued to the second execution unit.

Method and apparatus for executing instructions

A computer processor that includes a plurality of execution pipelines, each execution pipeline including a configuration of one or more execution units of the processor, each execution pipeline characterized by an execution pipeline type, each execution pipeline type determined according to the types of computer program instructions executed in each execution pipeline; a plurality of hardware threads of execution, each hardware thread including computer program instructions characterized by instruction types, each hardware thread including sequences of instructions of a same instruction type, the sequences interspersed with instructions of other types; and an instruction dispatcher capable of dispatching instructions preferentially during a predefined preference period from a preferred hardware thread to a particular execution pipeline in dependence upon whether the preferred hardware thread presents a sequence of instructions, ready for execution from the preferred hardware thread, of a type for execution in the particular execution pipeline.

Preferential dispatching of computer program instructions

A circuit and method for using hardware to calculate a first derivative of the number of performance events that occur in a microprocessor during a predetermined period of time. This first derivative indicates a frequency of such performance events, which can be used as either a predictor of future problems or needs, or may be used to invoke a corrective action.

Derivative performance counter mechanism

A data receiver circuit in a receiving chip provides the capability to characterize an interface, which includes one or more inter-chip communication lines, between a transmitting chip and the receiving chip by transmitting the data across a primary data path and a secondary data path, latching the data in the secondary data path using a clock signal that is skewed relative to a clock signal used to latch the primary data path, comparing the data latched from the primary and secondary data paths, and recording errors. Because the primary data path is not impacted by the test cycle, the test cycle may be run while data associated with applications running on the system are transmitted across the inter-chip communication lines.

Method and apparatus for testing, characterizing and monitoring a chip interface using a second data path

Growing community of inventors

Rochester, MN, United States of America

Brian Lee Koehler