Altera Corporation

Intel Corporation

Google Inc.

Jakob Raymond Jones

David Wolk Mendel

Keith Duwel

Jeffrey Erik Schulz

Dinesh D Patil

Gary Brian Wallichs

Huy X Ngo

Prasanna Padmanabhan

Kevin W Mai

Tim Tri Hoang

Xi Chelsea Chen

Jeffrey Fox

Vishwas Tumkur Vijayendra

Nikolaos Liveris

Yury Markovskiy

Ben Chunben Wang

Chao Ni

A seemingly monolithic interface between separate integrated circuit die may appear to be parallel or asynchronous from the perspective of the separate integrated circuit die. The signals of the seemingly monolithic interface, however, may actually be communicated between the separate die via serial and/or synchronous communication. In one method, a number of signals stored in a first parallel interface on a first integrated circuit die may be sampled. In some cases, at least one of the signals may be sampled more often than another one of the signals. A serial signal may be generated based on sampled signals. The serial signal may be transmitted to a corresponding second parallel interface on the second integrated circuit die.

Seemingly monolithic interface between separate integrated circuit die

An interface bridge to enable communication between a first integrated circuit die and a second integrated circuit die is disclosed. The two integrated circuit die may be connected via chip-to-chip interconnects. The first integrated circuit die may include programmable logic fabric. The second integrated circuit die may support the first integrated circuit die. The first integrated circuit die and the secondary integrated circuit die may communicate with one another via the chip-to-chip interconnects using an interface bridge. The first and second component integrated circuits may include circuitry to implement the interface bridge, which may provide source-synchronous communication using a data receive clock from the second integrated circuit die to the first integrated circuit die.

Interface bridge between integrated circuit die

A data processing device incorporates a plurality of chiplets having working elements such as processing and memory elements. At least one of the working elements is operative to generate messages directed to working elements of the same chiplet or another one of the chiplets. Each message includes a global address. An evaluation circuit determines whether the global address of a message is within a range of global addresses assigned to the chiplet. If so, the message passes to a translation circuit which translates the message to a local address for routing to a working element of the chiplet. If not, the message is dispatched to one or more other chiplets.

Chiplet architecture data processing devices and methods

Systems and methods for reconfiguration of a hardened intellectual property (IP) block in an integrated circuit (IC) device are provided. Reconfiguration of the hardened IP block in the IC device may transition between functions supported by the hardened IP block. A transition may occur as a pre-configured profile is selected to reconfigure the hardened IP block. Further, configuration data associated with each of the pre-configured profiles of the hardened IP block may be generated and storage space to store the configuration data may be created. Additionally, reconfiguration control logic to read and implement the configuration data in hard IP design primitives may also be generated.

Selectable reconfiguration for dynamically reconfigurable IP cores

A computer-implemented method includes receiving a first circuit design for an integrated circuit device, determining when multiple power-drawing events are to occur at substantially the same time via one or more circuitry components of the integrated circuit device, which would have a disruptive effect on a power distribution network of the integrated circuit device, based on the first circuit design, and generating logic that schedules the more than one event so that the more than one event do not occur simultaneously. The logic is included in an event sequencer. The method also includes inserting the event sequencer into the first circuit design during compilation to create a second circuit design and outputting the second circuit design to be implemented on the integrated circuit device.

Reset sequencing for reducing noise on a power distribution network

A method for designing a system on a target device includes generating a timing netlist that reflects timing delays and timing relationships of a base configuration of a block in the system and a target configuration of the block in the system, wherein the base configuration of the block and the target configuration of the block implement different functionalities, and performing synthesis, placement, and routing on the system in response to the timing netlist.

Method and apparatus for performing a single pass compilation for systems with dynamically reconfigurable logic blocks

Methods for designing and developing models for simulating the behavior of clock signals and in particular those generated by phase-locked loop (PLL) circuits are provided. The clock period of a phase-locked loop circuit's variable frequency oscillator signal may be modeled by combining the inverse of the oscillator frequency rounded up to the simulation time scale with the inverse rounded down to the simulation time scale. The variable frequency oscillator signal may further be synchronized with a reference clock signal at a rate determined by the relationship between the reference clock signal and the variable frequency oscillator signal. A parameter may indicate a target range for the deviation between the two signals and a runtime monitor may be used together with the parameter setting to decide whether synchronization is required and make the appropriate adjustments.

Growing community of inventors

San Jose, CA, United States of America

Jakob Raymond Jones