International Business Machines Corporation

Stmicroelectronics Gmbh

Akil Khamisi Sutton

Michael Sperling

Pawel Owczarczyk

Erik English

Marc Henri Coq

Luis Angel Bathen

Cedric D Cook

Lawrence Alfred Clevenger

Carl John Radens

John H Zhang

Sami Rosenblatt

Terry Allen Spooner

Ali Y Duale

Nicole A Saulnier

Yiheng Xu

Eric Kevin Butler

Peter A Smith

John Greg Massey

Chandrasekara Kothandaraman

Edward C McCain

Kennedy K Cheruiyot

Sandra C Thompson

Yufei Wu

William Edward Ansley

Richard Stephan Wise

Glen Arthur Wiedemeier

Richard Stephen Wise

Sekou Lionel Remy

Uma Srinivasan

Otis Smart

Myneeka Holloway

Egduard Ramon Jauregui

Lauren Quigley

Lisander Lopez

A process to train a machine learning model to predict fault location in a system includes generating a data set for training the machine learning model. The generating includes injecting, at a selected location of the system, a test fault into a simulation of the system using a workload, and recording a respective error syndrome generated by the simulation. Further, the generating includes repeating the injecting, at other selected location(s) of the system, of other test fault(s) into the simulation of the system, and the recording of respective, generated error syndromes. In addition, the process includes training, using the data set, the machine learning model, and providing the trained machine learning model for use in debugging the system, where the debugging includes predicting, using the trained machine learning model, a fault location within the system based on an error syndrome generated by the system due to the fault.

Machine learning model training to assist in system debug

Embodiments include thermally coupled aware device placement in the schematic design stage of the development of an integrated circuit. Aspects of the invention include obtaining a schematic design of a macro, the schematic design including a plurality of devices disposed within the macro. Aspects also include determining an initial temperature for each of the plurality of devices, where the initial temperature due to self-heating. Aspects further include determining, iteratively for each of the plurality of devices, an uplift temperature, where the uplift temperature for a first device of the plurality of devices is determined based on the initial temperature of each of the other plurality of devices and a distance between the first device and each of the other plurality of devices as encoded in the schematic design. Aspects also include modifying the schematic design of the macro based on a determination that the uplift temperature of at least one of the plurality of devices is above a threshold value.

Thermally coupled aware device placement

Embodiments are for using adaptive fill techniques to avoid electromigration, thereby resulting in electromigration signoff. A wire segment failing to meet an electromigration current limit is determined on an integrated circuit (IC). Fill shapes are connected adjacent to the wire segment to cause the wire segment to meet the electromigration current limit. The fill shapes are non-functional shapes on the IC.

Adaptive fill techniques for avoiding electromigration

A computer-implemented method for validating ownership of a digital asset is disclosed. The computer-implemented method includes transmitting a public key for encrypting a digital asset to an owner of the digital asset responsive to receiving a request for the public key. The computer-implemented method further includes receiving from the owner of the digital asset, an encrypted digital asset and a first liveness hash, wherein the digital asset is encrypted using the public key, and the first liveness hash is generated based, at least in part, on the digital asset in an unencrypted form and a first nonce. The computer-implemented method further includes determining whether the first liveness hash is valid. The computer-implemented method further includes generating in response to determining that the first liveness hash is valid, a digital asset record, wherein the digital asset record includes the encrypted digital asset and the first liveness hash.

Method to validate ownership and authentication of a digital asset

Computer-implemented methods selecting a cloud computing system for deployment of a workload are provided. Aspects include obtaining an input function that characterizes the workload and obtaining a plurality of performance models, wherein each of the plurality of performance models corresponds to one of a plurality of cloud computing systems including the cloud computing system. Aspects also include applying the input function into each of the plurality of performance models, calculating one or more of a gain, a phase shift, and a stability margin for each of the plurality of performance models, and selecting the cloud computing system from the plurality of cloud computing systems based at least in part on the one or more of the gain, the phase shift, and the stability margin.

Benchmarking and prediction of cloud system performance

Techniques are disclosed, using one or more computers. for bidding on digital advertising space associated with media content on a digital platform. Popularity is determined of a plurality of electronic communication and associated clips on a digital platform. A clip is detected which meets a threshold for approaching an activity level of user activity indicating the popularity of the clip. The clip meeting the threshold is labeled as a non-fungible token (NFT) indicating available digital advertising space associated with the clip. In response to the labeling of the clip, monetary bidding is received, based on the NFT by entities buying digital advertising space for digital advertising content associated with the NFT.

Electronic marketplace for digital advertising space

A node in a blockchain network may send an operation for geometrically fractionalizing an non-fungible token (NFT) into geometric shards to a blockchain network. The geometric fractionalization associates each geometric shard with a specific part of the NFT. The node may also record, on distributed ledger of the blockchain network, the fractionalization of the NFT and the association between each geometric shard with the specific part of the NFT.

Creating non-fungible token shards

A processor may identify that a computing device is below a power threshold. The processor may generate a charge request. The charge request may include metrics associated with a requested power exchange. The processor may send the charge request to a decentralized exchange. The decentralized exchange may include the computing device and at least two other devices. The processor may receive respective charging proposals from the at least two other devices. The processor may select one of the respective charging proposals.

Decentralized green-energy ecosystem

Aspects of the invention include forming a semiconductor device. Gates are formed in a first direction over fins, the gates including gate material, the fins being formed in a second direction. Fin interconnects are formed in the first direction over the fins. A dielectric material is formed on the fins, and capacitor interconnects are formed over portions of the dielectric material in the first direction over the fins.

FEOL interconnect used as capacitance over fins instead of gates

Aspects of the invention include a first voltage sensitive circuit including first transistors, the first transistors being coupled together so as to be operatively coupled to a first current source. A second voltage sensitive circuit includes second transistors, the second transistors being coupled together so as to be operatively coupled to a second current source, the first voltage sensitive circuit being coupled to the second voltage sensitive circuit to form a delay chain, the first and second current sources being responsive to changes in voltage of a power supply according to a voltage reference. A voltage sensitive current reference module is coupled to the first and second current sources and configured to supply the voltage reference to the first and second current sources, the voltage sensitive current reference module being responsive to changes in the voltage of the power supply.

Voltage sensitive current circuit

Aspects of the invention include a circuit having a power supply sensitive delay circuit, a variable delay circuit coupled to the power supply sensitive delay circuit, a delay line coupled to the variable delay circuit, and a logic circuit coupled to the delay line.

Droop detection using power supply sensitive delay

Aspects include monitoring for occurrences of selected events at a computer system, the monitoring by a processor that is coupled to the computer system. A list of event records for each of the selected events is built by the processor. The building of event records includes generating an event record for each occurrence of an event detected by the monitoring. The lists of event records for the selected events are merged into a merged list of event records that are in chronological order. A machine report for the computer system that includes the merged list of event records is stored.

Self-reporting and self-upgrading of enterprise systems

Aspects of the invention relate to an apparatus having a transmission gate coupled to a delay element and including a first transistor and a second transistor. A first node is coupled to a first gate of the first transistor, a first current source, and a first resistive element, an opposite end of the first resistive element being coupled to a ground potential. A second node is coupled to a second gate of the second transistor, a second current source, and a second resistive element, an opposite end of the second resistive element being coupled to a power supply.

Voltage starved passgate with IR drop

A management system monitors a set of objects of a user by wirelessly communicating with one or more location components associated with the objects, and each object of the set has a respective location component. The monitoring includes ascertaining by the management system, based at least in part on data obtained via wireless communication with the location component(s), a spatial centroid of the set and a spatial separation of an object in the set from the spatial centroid, and correlating the ascertained spatial centroid to a context classification of multiple context classifications. The management system further determines whether a difference between the ascertained spatial separation and the average spatial separation of the location component(s) for the correlated context classification exceeds an acceptable spatial separation tolerance. Based on the difference exceeding the acceptable tolerance, the management system provides an electronic alert to the user.

Set-based object management system

Aspects of the invention include a circuit including a power circuit having an amplifier, a resistor, a current source, and a first node, one end of the resistor being configured to couple to a power supply, the first node being coupled to an opposite end of the resistor, a first input terminal of the amplifier, and the current source. A voltage sensitive circuit includes a logic gate coupled to both a second input terminal of the amplifier and an output terminal of the amplifier at a second node.

Growing community of inventors

Dutchess County, NY, United States of America

Akil Khamisi Sutton