Kini, US
Adityashankar Kini, San Carlos, CA US
Patent application number | Description | Published |
---|---|---|
20100241654 | VIRTUALIZED DATA STORAGE SYSTEM OPTIMIZATIONS - Virtual storage arrays consolidate branch data storage at data centers connected via wide area networks. Virtual storage arrays appear to storage clients as local data storage; however, virtual storage arrays actually store data at the data center. Virtual storage arrays overcome bandwidth and latency limitations of the wide area network by predicting and prefetching storage blocks, which are then cached at the branch location. Virtual storage arrays leverage an understanding of the semantics and structure of high-level data structures associated with storage blocks to predict which storage blocks are likely to be requested by a storage client. Virtual storage arrays may use proximity-based, heuristic-based, and access time-based prefetching to predict high-level data structure entities that are likely to be accessed by the storage client. Virtual storage arrays then identify and prefetch storage blocks corresponding with the predicted high-level data structure entities. | 09-23-2010 |
20130086264 | Optimized Prefetching of Compound Data - Access to compound data over a wide-area network is optimized by analyzing metadata within compound data to identify internal and external data streams to be prefetched. Upon receiving or intercepting a network packet including an access request for a data resource, metadata in this data resource is analyzed to identify associated data streams and their storage locations within and/or outside of the data resource. Data streams may be proactively or reactively prefetched. Proactive prefetching identifies and retrieves data streams or portions thereof likely to be accessed by a client based on attributes associated with the data resource. Reactive prefetching identifies portions of data streams associated with received access requests and retrieves additional portions of these data streams. Prefetched data streams or portions thereof are stored in a data storage on the same local network or near to the local network including the client. | 04-04-2013 |
Amar G. Kini, Lake Mary, FL US
Patent application number | Description | Published |
---|---|---|
20150162726 | COMPACT MEDIUM VOLTAGE AIR INSULATED SWITCHGEAR USING REAR MOUNTED CURRENT TRANSFORMERS AND BUSHINGS OF DIFFERENT LENGTH - A switchgear includes a housing having a wall separating a circuit breaker compartment from a bus/cable compartment. A plurality of bushings is provided. Each bushing has first and second portions. Each bushing extends through the wall so that the first portion is disposed in the circuit breaker compartment and the second portion is disposed in the bus/cable compartment. Each second portion has an extension. At least one current transformer is mounted on the extension of the second portion of each bushing. The extensions are constructed and arranged so that a phase to phase distance is 180 mm or less. Such a configuration also decreased the overall size of the switchgear. | 06-11-2015 |
20150229109 | MEDIUM VOLTAGE SWITCHGEAR CONSTRUCTION USING SYMMETRIC SHEET METAL PARTS AND PANELS TO BUILD COMPARTMENT ASSEMBLIES AND SUBASSEMBLIES - Side panels for a compartment of a switchgear include a first panel structure and a second panel structure that is identical to the first panel structure. Each panel structure has a body with symmetric surface features in the body. Certain of the surface features are offset from a plane of symmetry of the body. The first panel structure is constructed and arranged to define a left side of the compartment and the second panel structure, upon proper orientation, is constructed and arranged to define an opposing, right side of the compartment. | 08-13-2015 |
20150229111 | METHOD AND STRUCTURE FOR FASTENING AND ELECTRICALLY ISOLATING BUSBARS INSULATED WITH HEAT-SHRINK MATERIAL - Isolation structure is provided for electrically isolating a busbar mounted to a post insulator by a fastener via a busbar mounting hole. The busbar has insulating material covering the busbar except for surfaces defining the mounting hole. The isolation structure includes an electrically insulating sleeve constructed and arranged to be disposed around a portion of a periphery of the fastener and to be received in the busbar mounting hole. At least first and second electrically insulating washers each have a bore that receives the insulating sleeve. The insulating washers are constructed and arranged to engage with the surfaces defining the mounting hole on opposing sides of the busbar so as to sandwich the busbar between the first and second insulating washers. | 08-13-2015 |
20150244156 | INTEGRATED COMPACT BUSHING STRUCTURE COMBINING THE FUNCTIONALITY OF PRIMARY CONTACT WITH A CURRENT TRANSFORMER PRIMARY CONDUCTOR AND A POST INSULATOR - A bushing structure for a switchgear includes a mounting portion constructed and arranged to mount the bushing structure. A barrel portion extends from the mounting portion and is coaxial there-with. The barrel portion includes a plurality of undulations in a peripheral surface thereof to increase creepage distance. A primary contact is disposed within and extends a length of the barrel portion. The primary contact has a first end constructed and arranged to be contacted by a movable contact of the switchgear and a second end constructed and arranged to be connected with a busbar. | 08-27-2015 |
Ameet Kini, Herndon, VA US
Patent application number | Description | Published |
---|---|---|
20140095428 | SYSTEMS AND METHODS FOR APPLYING AN ANALYTICAL MODEL TO PERFORMANCE ANALYSIS - Aspects of the present disclosure describe systems and methods for providing active session history data to users for use in database performance analysis. In various aspects, active session history data obtained from monitoring a database and/or database system over a period of time may be segmented into multiple dimensions. The segmented data may be subsequently provide and/or displayed on one or more interfaces, such as a graphical user interface, to users. The interface may visualize the dimensional ASH data in a variety of ways, such as through icons, graphs, charts, histograms, temporal delineations, treemaps, etc. | 04-03-2014 |
20140095453 | REAL-TIME AUTOMATIC DATABASE DIAGNOSTIC MONITOR - A method for obtaining data items from an unresponsive database host. The method includes receiving an indication that the database host is unresponsive, receiving, from a management server via a diagnostic connection, a first request for a first organized data item, and sending a first query, using a first interface, to a memory for the first organized data item. The method further includes receiving, from the management server via a normal connection, a second request for a second organized data item, retrieving, from memory on the database host, a first data item in response to the first query, converting the first data item into the first organized data item, and sending the first organized data item to the management server, wherein the first organized data item is analyzed to determine a source causing the database host to be unresponsive. | 04-03-2014 |
Ameet M. Kini, Sterling, VA US
Patent application number | Description | Published |
---|---|---|
20090144276 | COMPUTERIZED DATA MINING SYSTEM AND PROGRAM PRODUCT - Under the present invention, a data exploration system, a customized model system and an existing model system are provided. The data exploration system analyzes user data to identify statistical information such as data distribution, data relationships, data outliners and invalid or missing data values. The customized model center iteratively generates customized data mining models in parallel based on permutations of the user data, user-provided business parameters and/or a set of model generation algorithms. The existing model system provides users with a library of existing data mining models, assembled based on the business parameters, from which they can choose one or more. In any event, any customized or existing data mining models selected can be run against the user data in parallel. | 06-04-2009 |
Ananth Kini, Philadelphia, PA US
Patent application number | Description | Published |
---|---|---|
20130194931 | SYSTEMS AND/OR METHODS FOR PROVIDING EPDCCH IN A MULTIPLE CARRIER BASED AND/OR QUASI-COLLATED NETWORK - ePDCCH may be provided. For example, a WTRU may receive a configuration for monitoring an ePDCCH resource. Based on the configuration, the WTRU may be configured to monitor and may monitor the ePDCCH resource on a particular subframe. Additionally, a WTRU may derive an aggregation level for a subframe associated with an aggregation level number N | 08-01-2013 |
Ananth Kini, East Norriton, PA US
Patent application number | Description | Published |
---|---|---|
20160029239 | METHOD AND APPARATUS FOR CONTROLLING UPLINK TRANSMISSION POWER BASED ON ACCUMULATED TRANSMIT POWER CONTROL COMMANDS AND CORRESPONDING UPLINK SUBFRAME SETS - A method and apparatus are described for controlling uplink (UL) transmission power. A wireless transmit/receive unit (WTRU) may receive a configuration of UL subframe sets and maintain a plurality of transmit power control (TPC) command accumulator values that correspond to respective ones of the UL subframe sets. The WTRU may receive a TPC command in a subframe n of a downlink (DL) transmission, determine a subframe n+k of a UL transmission that the received TPC command corresponds to, determine which of the UL subframe sets the UL transmission subframe n+k belongs to, and adjust a TPC command accumulator value that corresponds to the determined UL subframe set to determine power of the UL transmission when transmitting in the UL transmission subframe, where n is an integer, and k is an integer greater than zero. | 01-28-2016 |
Ananth P. Kini, Washington, IL US
Patent application number | Description | Published |
---|---|---|
20140214235 | MACHINE CONTROL SYSTEM HAVING AUTONOMOUS EDGE DUMPING - A control system is disclosed for use with a plurality of machines operating at a worksite. The control system may have a plurality of communicating devices, and a plurality of onboard controllers, each mountable to the plurality of machines. The control system may also have an offboard controller in communication with the plurality of onboard controllers via the plurality of communicating devices. The offboard controller may be configured to selectively assign each of a plurality of sequentially arranged dump targets for use by each of the plurality of machines based on an order in which the plurality of machines arrive at a dump location. The offboard controller may be further configured to make a determination that lanes extending to two dump targets of the plurality of sequentially arranged dump targets overlap, and selectively skip assignment of one of the two dump targets based on the determination. | 07-31-2014 |
20140214236 | MACHINE CONTROL SYSTEM HAVING AUTONOMOUS EDGE DUMPING - A control system is disclosed for use with a machine at a worksite. The control system may have an offboard controller. The offboard controller may be configured to receive information regarding a berm at the worksite, determine starting and ending points spaced apart along an edge of the berm based on the information, and determine a maximum orthogonal distance from a virtual line extending between the starting and ending points to the edge of the berm. The offboard controller may be further configured to selectively validate the starting and ending points based on the maximum orthogonal distance, and to designate a center of the virtual line between validated starting and ending points as a dump target. | 07-31-2014 |
20140214237 | MACHINE CONTROL SYSTEM HAVING AUTONOMOUS EDGE DUMPING - A control system is disclosed for use with a machine. The control system may have a communicating device, a locating device configured to generate a first signal indicative of a location of the machine, a sensor configured to generate a second signal indicative of contact of the machine with a berm, and an onboard controller. The control system may also have an offboard controller configured to generate a first set of coordinates of a dump target, and to assign the first set of coordinates to the onboard controller for use in controlling the machine. The offboard controller may also be configured to detect contact of the machine with the berm based on the second signal during reverse travel toward the dump target, and to generate a second set of coordinates of the dump target to correspond with a location of the machine at a time of contact detection. | 07-31-2014 |
Ganesh D. Kini, Bristow, VA US
Patent application number | Description | Published |
---|---|---|
20100173870 | Phosphonate Compounds - The present invention relates to phosphonate compounds, compositions containing them, processes for obtaining them, and their use for treating a variety of medical disorders, e.g., osteoporosis and other disorders of bone metabolism, cancer, viral infections, and the like. | 07-08-2010 |
20120058975 | Phosphonate Compounds - The present invention relates to phosphonate compounds, compositions containing them, processes for obtaining them, and their use for treating a variety of medical disorders, e.g., osteoporosis and other disorders of bone metabolism, cancer, viral infections, and the like. | 03-08-2012 |
20130045950 | Phosphonate Compounds - The present invention relates to phosphonate compounds, compositions containing them, processes for obtaining them, and their use for treating a variety of medical disorders, e.g., osteoporosis and other disorders of bone metabolism, cancer, viral infections, and the like. | 02-21-2013 |
Gautam Kini, Houston, TX US
Patent application number | Description | Published |
---|---|---|
20150050741 | TRANSPORTERS OF OIL SENSORS FOR DOWNHOLE HYDROCARBON DETECTION - Various embodiments of the present disclosure pertain to nanocomposites for detecting hydrocarbons in a geological structure. In some embodiments, the nanocomposites include: a core particle; a polymer associated with the core particle; a sulfur-based moiety associated with the polymer; and a releasable probe molecule associated with the core particle, where the releasable probe molecule is releasable from the core particle upon exposure to hydrocarbons. Additional embodiments of the present disclosure pertain to methods of detecting hydrocarbons in a geological structure by utilizing the nanocomposites of the present disclosure. | 02-19-2015 |
Gautam Chandrakanth Kini, Houston, TX US
Patent application number | Description | Published |
---|---|---|
20110220839 | CONVERTING NANOPARTICLES IN OIL TO AQUEOUS SUSPENSIONS - An improved process for converting an oil suspension of nanoparticles (NPs) into a water suspension of NPs, wherein water and surfactant plus salt is used instead of merely water and surfactant, leading to greatly improved NP aqueous suspensions. | 09-15-2011 |
20160097003 | SYSTEMS AND PROCESSES FOR SEPARATING EMULSIFIED WATER FROM A FLUID STREAM - Low-water content organic phases can be difficult to achieve at high fluxes when water is present in an emulsified form, such as in a water-in-oil emulsion. Processes for de-emulsifying a fluid stream containing emulsified water, such as water-in-crude oil emulsions, include introduction of the fluid stream into a vessel that defines a coalescence zone. The vessel is configured to provide for simultaneous application of a centrifugal force and an electric field to the fluid stream within the coalescence zone. The simultaneous application of the centrifugal force and the electric field to the fluid stream provides for the coalescence of a portion of the emulsified water into a bulk aqueous phase. Continuous phases of the organic component and the bulk aqueous phase form in the coalescence zone and are separately removed from the vessel. The bulk aqueous phase is removed from the underside of the vessel. | 04-07-2016 |
20160097004 | PROCESSES FOR DESALTING CRUDE OIL UNDER DYNAMIC FLOW CONDITIONS - Presented is a process for desalting crude oil. The process includes mixing a partially dehydrated crude oil, comprising less than 10 vol. % water and at least one water-extractable contaminant, with an aqueous wash fluid. A water-in-oil emulsion is formed. The water-in-oil emulsion is introduced into a first coalescence zone defined by a first vessel. The first vessel is configured to apply an electric field to the emulsion. The water-in-oil emulsion is broken within the first coalescence zone in the presence of the electric field under dynamic flow conditions to form a partially desalted crude oil and a non-emulsified aqueous salt solution. The partially desalted crude oil and the non-emulsified aqueous salt solution are then separated from one another under the dynamic flow conditions to yield a separated, partially desalted crude oil comprising less than 1 vol. % water. | 04-07-2016 |
Gautan Chandrakanth Kini, Houston, TX US
Patent application number | Description | Published |
---|---|---|
20160097005 | SYSTEMS AND PROCESSES FOR SEPARATING EMULSIFIED WATER FROM A FLUID STREAM - Decreasing the water content of an organic phase can often be desirable, but low water levels can be difficult to achieve at high fluxes when the water is present in an emulsified form, such as in a water-in-oil emulsion. Processes for de-emulsifying a fluid stream containing emulsified water, such as water-in-crude oil emulsions, include introduction of the fluid stream into a vessel that defines a coalescence zone. The vessel is configured to provide for simultaneous application of a centrifugal force and an electric field to the fluid stream within the coalescence zone. The simultaneous application of the centrifugal force and the electric field to the fluid stream provides for the coalescence of a portion of the emulsified water into a bulk aqueous phase. A biphasic mixture comprising continuous phases of the organic component and the bulk aqueous phase is formed within the coalescence zone and subsequently removed from the vessel. | 04-07-2016 |
Naveen Kini, San Jose, CA US
Patent application number | Description | Published |
---|---|---|
20120281377 | VIAS FOR MITIGATING PAD DELAMINATION - A signal carrier medium is disclosed including support vias for maintaining laminated portions of the signal carrier medium together. The signal carrier medium includes metal portions such as a contact pad. The metal portions may have one or more adjacent support vias for dissipating stresses which build in the metal portions. | 11-08-2012 |
20120305305 | ELECTRONIC COMPONENT INCLUDING MICRO BALLS - A system of micro balls is disclosed for coupling an electronic component to a printed circuit board. The micro balls have a small diameter, and each contact pad may include an array of two or more micro balls. An example of a micro ball may include a polymer core, surrounded by a copper layer, which is in turn surrounded by a layer of solder. | 12-06-2012 |
Naveen Kini, Fremont, CA US
Patent application number | Description | Published |
---|---|---|
20080206904 | METHOD OF MAKING PCB CIRCUIT MODIFICATION FROM MULTIPLE TO INDIVIDUAL CHIP ENABLE SIGNALS - A semiconductor package is disclosed having a single CE signal during electrical test and a plurality of CE signals during normal operation thereafter. After electrical testing of the memory die during fabrication, the electrical traces carrying the single CE signal from the memory test pad matrix to each of the memory die may be severed. Severing the electrical traces from the memory test pad matrix electrically isolates the multiple electrical traces between the controller die and memory die, and allows separate and individual CE signals between the controller die and memory die during normal usage of the memory die. | 08-28-2008 |
20080208384 | PCB CIRCUIT MODIFICATION FROM MULTIPLE TO INDIVIDUAL CHIP ENABLE SIGNALS - A semiconductor package is disclosed having a single CE signal during electrical test and a plurality of CE signals during normal operation thereafter. After electrical testing of the memory die during fabrication, the electrical traces carrying the single CE signal from the memory test pad matrix to each of the memory die may be severed. Severing the electrical traces from the memory test pad matrix electrically isolates the multiple electrical traces between the controller die and memory die, and allows separate and individual CE signals between the controller die and memory die during normal usage of the memory die. | 08-28-2008 |
20100309707 | PCB CIRCUIT MODIFICATION FROM MULTIPLE TO INDIVIDUAL CHIP ENABLE SIGNALS - A semiconductor package is disclosed having a single CE signal during electrical test and a plurality of CE signals during normal operation thereafter. After electrical testing of the memory die during fabrication, the electrical traces carrying the single CE signal from the memory test pad matrix to each of the memory die may be severed. Severing the electrical traces from the memory test pad matrix electrically isolates the multiple electrical traces between the controller die and memory die, and allows separate and individual CE signals between the controller die and memory die during normal usage of the memory die. | 12-09-2010 |
Prashanth Kini, San Mateo, CA US
Patent application number | Description | Published |
---|---|---|
20120072780 | Continuous System Health Indicator For Managing Computer System Alerts - A method is provided for detecting when users are being adversely impacted by poor system performance. A system health indicator is determined that is based on the amount of work that is blocked waiting for each of a set of an external events and combined with a heuristic that is based on the number of users waiting for the work to complete. The system health indicator is compared to a threshold such that an alert is generated when the system health indicator crosses the threshold. However, the system health indicator is designed so that an alert is only generated when a significant user base is or will in the near future experience a problem with the system. Furthermore, the system health indicator is designed to vary smoothly to maintain its suitability for the application of predictive technology. | 03-22-2012 |
20120072781 | PREDICTIVE INCIDENT MANAGEMENT - An incident predictor system is described herein for predicting impactful incidents in which server computer system operations fail or perform poorly. According to one embodiment of the invention, the incident prediction system trains a generalized linear model (GLM) to predict when a system health indicator will reach a level that represents an incident for the server system. | 03-22-2012 |
Rajesh R. Kini, Austin, TX US
Patent application number | Description | Published |
---|---|---|
20100027360 | INTEGRATED CIRCUIT HAVING AN ARRAY SUPPLY VOLTAGE CONTROL CIRCUIT - An integrated circuit comprises a plurality of memory cells and an array supply voltage control circuit. The plurality of memory cells are organized in rows and columns. A row comprises a word line and all of the memory cells coupled to the word line. A column comprises a bit line pair and all of the memory cells coupled to the bit line pair. The array supply voltage control circuit is coupled to the plurality of memory cells. The array supply voltage control circuit is for receiving a power supply voltage and for providing a reduced power supply voltage to memory cells of a selected column during a write operation in response to a voltage differential on the bit line pair of the selected column. | 02-04-2010 |
Sriram Kini, Sunnyvale, CA US
Patent application number | Description | Published |
---|---|---|
20160092288 | DETECT PROCESS HEALTH REMOTELY IN A REALTIME FASHION - A system of remote nodes may be divided into sets of partner nodes. One remote node becomes a partner of another remote node. As partners, the nodes agree to monitor each other's health and report anomalies, such as a failure of one of the nodes, to a monitoring server. The nodes do so using a persistent communication link, such as an open socket. Using the described techniques, the monitoring load of a system is distributed in part away from the monitoring server and to the nodes themselves. This may reduce the resources required of the monitoring server. At the same time, since nodes are now being monitored by partner nodes that are likely to be closer than the monitoring server, and/or on account of the monitoring being performed via a persistent communication link, certain failures can be detected in real-time or near real-time. | 03-31-2016 |
Sunil Suresh Kini, Sharon, MA US
Patent application number | Description | Published |
---|---|---|
20140046700 | SYSTEMS AND METHODS OF PROVIDING A MARKETPLACE FOR DISTRIBUTING LEADS - Systems and method of providing a web-based marketplace for distributing leads to a network of agents are provided. A method includes receiving data indicative of user identification and user insurance coverage from a plurality of website users, identifying a subset of the plurality of website users that fail to purchase insurance, generating a database that stores the data received from the subset of website users, and generating a price for purchasing the data received from each of the subset of website users. The price is added to the respective website user's data in the database. The method includes transmitting a portion of the database including the price to a third party, and receiving a request to purchase a first website user's data. | 02-13-2014 |
20140046723 | SYSTEMS AND METHODS OF PROVIDING A MARKETPLACE FOR DISTRIBUTING LEADS - Systems and method of providing a web-based marketplace for distributing leads to a network of agents are provided. A method includes receiving data indicative of user identification and user insurance coverage from a plurality of website users, identifying a subset of the plurality of website users that fail to purchase insurance, generating a database that stores the data received from the subset of website users, and generating a price for purchasing the data received from each of the subset of website users. The price is added to the respective website user's data in the database. The method includes transmitting a portion of the database including the price to a third party, and receiving a request to purchase a first website user's data. | 02-13-2014 |
Vittal Kini, Portland, OR US
Patent application number | Description | Published |
---|---|---|
20090096086 | Cooling system for semiconductor devices - In one embodiment, the present invention includes a socket for a semiconductor package, where the socket has a frame with a segmented design, where socket streets are located between the segments. One or more of the streets may include a conduit to enable thermal transfer during operation of the semiconductor package. Other embodiments are described and claimed. | 04-16-2009 |
Vivek Kini, Santa Clara, CA US
Patent application number | Description | Published |
---|---|---|
20150143347 | SOFTWARE DEVELOPMENT ENVIRONMENT AND METHOD OF COMPILING INTEGRATED SOURCE CODE - A software development environment (SDE) and a method of compiling integrated source code. One embodiment of the SDE includes: (1) a parser configured to partition an integrated source code into a host code partition and a device code partition, the host code partition including a reference to a device variable, (2) a translator configured to: (2a) embed device machine code, compiled based on the device code partition, into a modified host code, (2b) define a pointer in the modified host code configured to be initialized, upon execution of the integrated source code, to a memory address allocated to the device variable, and (2c) replace the reference with a dereference to the pointer, and (3) a host compiler configured to employ a host library to compile the modified host code. | 05-21-2015 |
Vivek Kini, Sunnyvale, CA US
Patent application number | Description | Published |
---|---|---|
20140344528 | TECHNIQUES FOR ASSIGNING PRIORITIES TO MEMORY COPIES - One embodiment sets forth a method for guiding the order in which a parallel processing subsystem executes memory copies. A driver creates semaphores for all but the lowest priority included in a plurality of priorities and associates one priority with each copy hardware channel included in the parallel processing subsystem. The driver then aliases prioritized streams to the copy hardware channels based on the priorities. Upon receiving a request to execute a memory copy within one of the streams, the driver inserts commands into the aliased copy hardware channel. These commands use the semaphores to direct the parallel processing subsystem to execute the memory copy based on the priority of the copy hardware channel. Advantageously, by assigning priorities to streams and, subsequently, strategically requesting memory copies within the prioritized streams, an application developer may fine-tune their software application to increase the overall processing efficiency of the software application. | 11-20-2014 |
20140344821 | TECHNIQUES FOR SHARING PRIORITIES BETWEEN STREAMS OF WORK AND DYNAMIC PARALLELISM - One embodiment sets forth a method for assigning priorities to kernels launched by a software application and executed within a stream of work on a parallel processing subsystem that supports dynamic parallelism. First, the software application assigns a maximum nesting depth for dynamic parallelism. The software application then assigns a stream priority to a stream. These assignments cause a driver to map the stream priority to a device priority and, subsequently, associate the device priority with the stream. As part of the mapping, the driver ensures that each device priority is at least the maximum nesting depth higher than the device priorities associated with any lower priority streams. Subsequently, the driver launches any kernel included in the stream with the device priority associated with the stream. Advantageously, by strategically assigning the maximum nesting depth and prioritizing streams, an application developer may increase the overall processing efficiency of the software application. | 11-20-2014 |
20140344822 | TECHNIQUES FOR ASSIGNING PRIORITIES TO STREAMS OF WORK - One embodiment sets forth a method for assigning priorities to kernels launched by a software application and executed within a stream of work on a parallel processing subsystem. First, the software application assigns a desired priority to a stream using a call included in the API. The API receives this call and passes it to a driver. The driver maps the desired priority to an appropriate device priority associated with the parallel processing subsystem. Subsequently, if the software application launches a particular kernel within the stream, then the driver assigns the device priority associated with the stream to the kernel before adding the kernel to the stream for execution on the parallel processing subsystem. Advantageously, by assigning priorities to streams and, subsequently, strategically launching kernels within the prioritized streams, an application developer may fine-tune the software application to increase the overall processing efficiency of the software application. | 11-20-2014 |
20150206272 | SELECTIVELY KILLING TRAPPED MULTI-PROCESS SERVICE CLIENTS SHARING THE SAME HARDWARE CONTEXT - A method for handling parallel processing clients associated with a server in a GPU, the method comprising: receiving a failure indication for at least client running a thread in the GPU; determining threads in the GPU associated with the failing client; exiting threads in the GPU associated with the failing client; and continuing to execute remaining threads in the GPU for other clients running threads in the GPU. | 07-23-2015 |
20150206277 | UNIFIED MEMORY SYSTEMS AND METHODS - The present invention facilitates efficient and effective utilization of unified virtual addresses across multiple components. In one embodiment, the presented new approach or solution uses Operating System (OS) allocation on the central processing unit (CPU) combined with graphics processing unit (GPU) driver mappings to provide a unified virtual address (VA) across both GPU and CPU. The new approach helps ensure that a GPU VA pointer does not collide with a CPU pointer provided by OS CPU allocation (e.g., like one returned by “malloc” C runtime API, etc.). | 07-23-2015 |
Vivekanand Kini, Sunnyvale, CA US
Patent application number | Description | Published |
---|---|---|
20140319342 | Method and System for Adaptively Scanning a Sample During Electron Beam Inspection - A system for adaptive electron beam scanning may include an inspection sub-system configured to scan an electron beam across the surface of a sample. The inspection sub-system may include an electron beam source, a sample stage, a set of electron-optic elements, a detector assembly and a controller communicatively coupled to one or more portions of the inspection sub-system. The controller may assess one or more characteristics of one or more portions of an area of the sample for inspection and, responsive to the assessed one or more characteristics, adjust one or more scan parameters of the inspection sub-system. | 10-30-2014 |