公开(公告)号：US12124939B1

公开(公告)日：2024-10-22

申请号：US17199221

申请日：2021-03-11

申请人： Perceive Corporation

发明人： Justin Tantiongloc ,  Brian Thomas ,  Steven L. Teig

IPC分类号： G06N3/048 ,  G06F9/48 ,  G06F9/50 ,  G06F18/21 ,  G06N3/063

CPC分类号： G06N3/048 ,  G06F9/4881 ,  G06F9/5016 ,  G06F18/2163 ,  G06N3/063 ,  G06F2209/5017 ,  G06F2209/506

摘要： Some embodiments provide a method for generating neural network program instructions for a neural network inference circuit to execute a neural network. The neural network inference circuit includes a particular amount of available memory. The method receives a specification of the neural network including multiple layers. The method determines (i) a required amount of weight memory for the neural network and (ii) required amounts of activation memory for each of a set of layers of the neural network. When the required amount of weight memory and the required amount of activation memory for at least one layer is greater than the particular amount of available memory, the method generates the program instructions for the neural network inference circuit to execute a first set of the layers of the neural network multiple times for different blocks of input data and execute a second set of the layers in a single pass.

公开(公告)号：US12033000B2

公开(公告)日：2024-07-09

申请号：US17201635

申请日：2021-03-15

申请人： Intel Corporation

发明人： Shao-Wen Yang

IPC分类号： G06F9/50 ,  G06F9/48 ,  H04L41/0806 ,  H04L41/0896 ,  H04L41/12

CPC分类号： G06F9/5038 ,  G06F9/4881 ,  G06F9/505 ,  G06F9/5072 ,  H04L41/0806 ,  H04L41/0896 ,  H04L41/12 ,  G06F2209/5017 ,  G06F2209/506

摘要： In one embodiment, an apparatus comprises a communication interface to communicate over a network, and a processor. The processor is to: receive a workload provisioning request from a user, wherein the workload provisioning request comprises information associated with a workload, a network topology, and a plurality of potential hardware choices for deploying the workload over the network topology; receive hardware performance information for the plurality of potential hardware choices from one or more hardware providers; generate a task dependency graph associated with the workload; generate a device connectivity graph associated with the network topology; select, based on the task dependency graph and the device connectivity graph, one or more hardware choices from the plurality of potential hardware choices; and provision a plurality of resources for deploying the workload over the network topology, wherein the plurality of resources are provisioned based on the one or more hardware choices.

公开(公告)号：US11934884B2

公开(公告)日：2024-03-19

申请号：US18161249

申请日：2023-01-30

申请人： ILLUMINA, INC.

发明人： David Kimmel ,  Eunho Noh ,  Paul Smith

IPC分类号： G06F9/46 ,  G06F9/50 ,  G06T1/00 ,  G16B50/30

CPC分类号： G06F9/5066 ,  G06F9/5033 ,  G06T1/0007 ,  G16B50/30 ,  G06F2209/5017

摘要： Coordinated application processing includes obtaining a plurality of images and distributing them to processing engines to perform image processing. The plurality of images cover an image area, with different sub-areas, in which a biological sample to be sequenced is present. The image processing proceeds across multiple cycles to process a respective set of images, of the plurality of images, of each sub-area of the different sub-areas, and therefore of the respective area, of the flow cell, to which that sub-area correlates. The distributing the plurality of images includes, for each sub-area of the different sub-areas, distributing, across the multiple cycles of the image processing, the images of the respective set of images of that sub-area to a respective processing engine, of a plurality of processing engines, associated with, and selected for, processing images of that sub-area.

公开(公告)号：US20180349421A1

公开(公告)日：2018-12-06

申请号：US15935231

申请日：2018-03-26

申请人： Nuix Pty Ltd

发明人： David Sitsky ,  Matthew Westwood Hill ,  Robin Power ,  Eddie Sheehy ,  Stephen Stewart

IPC分类号： G06F17/30 ,  G06F9/50

CPC分类号： G06F17/30312 ,  G06F9/505 ,  G06F17/30613 ,  G06F2209/5017

摘要： The invention relates to electronic indexing, and more particularly, to the indexing, in a cloud, data held in a cloud. Systems and methods of the invention index data by accessing the data in place in the cloud and breaking a job into work items and sending the work items to multiple cloud processes that can each determine whether to index data associated with the work item or to create a new work item and have a different cloud process index the data. Each cloud process is proximal to an item that it indexes. This gives the system scale as well as an internal load-balancing.

公开(公告)号：US20180293096A2

公开(公告)日：2018-10-11

申请号：US15852480

申请日：2017-12-22

申请人： Swarm Technology LLC

发明人： Alfonso Iniguez

IPC分类号： G06F9/48 ,  G06F9/54 ,  G06F9/50

CPC分类号： G06F9/4843 ,  G06F9/5044 ,  G06F9/54 ,  G06F9/544 ,  G06F2209/5017

摘要： A parallel processing architecture includes a CPU, a task pool populated by the CPU, and a plurality of autonomous co-processing cells each having an agent configured to proactively interrogate the task pool to retrieve tasks appropriate for a particular co-processor. Each co-processor communicates with the task pool through a switching fabric, which facilitates connections for data transfer and arbitration between all system resources. Each co-processor notifies the task pool when a task or task thread is completed, whereupon the task pool notifies the CPU.

公开(公告)号：US20180246755A1

公开(公告)日：2018-08-30

申请号：US15963060

申请日：2018-04-25

申请人： SAP SE

发明人： Anastasia Ailamaki ,  Tobias Scheuer ,  Iraklis Psaroudakis ,  Norman May

IPC分类号： G06F9/46 ,  G06F17/27 ,  G06F9/48 ,  G06F9/50 ,  G06F17/30

CPC分类号： G06F9/466 ,  G06F9/4843 ,  G06F9/5038 ,  G06F9/505 ,  G06F9/5066 ,  G06F16/24532 ,  G06F16/24542 ,  G06F17/2705 ,  G06F2209/5017 ,  G06F2209/5018 ,  G06F2209/504 ,  Y02D10/22

摘要： Systems and method for a task scheduler with dynamic adjustment of concurrency levels and task granularity are disclosed for improved execution of highly concurrent analytical and transactional systems. The task scheduler can avoid both over commitment and underutilization of computing resources by monitoring and controlling the number of active worker threads. The number of active worker threads can be adapted to avoid underutilization of computing resources by giving the OS control of additional worker threads processing blocked application tasks. The task scheduler can dynamically determine a number of parallel operations for a particular task based on the number of available threads. The number of available worker threads can be determined based on the average availability of worker threads in the recent history of the application. Based on the number of available worker threads, the partitionable operation can be partitioned into a number of sub operations and executed in parallel.

公开(公告)号：US10013398B2

公开(公告)日：2018-07-03

申请号：US15584657

申请日：2017-05-02

申请人： A9.com, Inc.

发明人： Matthew W. Amacker

IPC分类号： G06F15/173 ,  G06F17/22 ,  G06F17/27 ,  G06F17/30 ,  G06F9/50 ,  H04L29/08 ,  H04L29/06 ,  G06F9/46

CPC分类号： G06F17/2241 ,  G06F9/465 ,  G06F9/50 ,  G06F9/5027 ,  G06F9/5072 ,  G06F16/24554 ,  G06F17/2705 ,  G06F2209/5017 ,  H04L67/02 ,  H04L67/10 ,  H04L67/42

摘要： A reusable distributed computing framework may be established in which contributors of computing resources may participate by using a web browser to visit a web page that incorporates a distributed computing participation component. A distributed computing job provider may submit distributed computing jobs to a web-based distributed computing service. A distributed computing job may include browser-executable code in accordance with a particular distributed computing programmatic interface and data to be processed by the browser-executable code. The web-based distributed computing service may assign independently processable portions of the job data to browsers visiting a donor page for processing with the job code. Results returned by the donor browsers may be indexed and made available in real-time, as may a status of the distributed computing job such as with respect to processing the job data.

公开(公告)号：US09904576B2

公开(公告)日：2018-02-27

申请号：US15475828

申请日：2017-03-31

申请人： Lawrence J. Dickson

发明人： Lawrence J. Dickson

IPC分类号： G06F9/46 ,  G06F9/48

CPC分类号： G06F9/485 ,  G06F9/4881 ,  G06F9/5038 ,  G06F2209/483 ,  G06F2209/5017 ,  G06F2209/5021

摘要： A task scheduling method is disclosed, where each processor core is programmed with a short list of priorities, each associated with a minimum response time. The minimum response times for adjacent priorities are different by at least one order of magnitude. Each process is assigned a priority based on how its expected response time compares with the minimum response times of the priorities. Lower priorities may be assigned a timeslice period that is a fraction of the minimum response time. Also disclosed is a task division method of dividing a complex task into multiple tasks is; one of the tasks is an input gathering authority task having a higher priority, and it provides inputs to the other tasks which have a lower priority. A method that permits orderly shutdown or scaling back of task activities in case of resource emergencies is also described.

公开(公告)号：US20180039507A1

公开(公告)日：2018-02-08

申请号：US15684514

申请日：2017-08-23

申请人： INTIGUA, INC.

发明人： Tomer LEVY ,  Shimon Hason

IPC分类号： G06F9/455 ,  G06F9/50

CPC分类号： G06F9/45558 ,  G06F9/5027 ,  G06F2009/45595 ,  G06F2209/5017 ,  G06F2209/509

摘要： A system and method for operating an agent. A policy may be generated based on an analysis of a code segment of an agent, analysis of the execution and/or installation of an agent. An interaction with the agent may be intercepted. The interaction may be analyzed according to the policy. A machine for performing an operation related to the interaction may be selected. A proxy on the selected machine may perform the operation and return a result to the agent. In some embodiments, a request to perform a task may be intercepted. A first portion of the task may be performed by an agent and a second portion of the task may be performed by a proxy.

公开(公告)号：US09848044B2

公开(公告)日：2017-12-19

申请号：US14287499

申请日：2014-05-27

申请人： CLEVERSAFE, INC.

发明人： Wesley Leggette ,  Andrew Baptist ,  Greg Dhuse ,  Jason K. Resch ,  Gary W. Grube

IPC分类号： G06F9/46 ,  H04L29/08 ,  G06F3/06 ,  G06F11/07 ,  G06F11/14 ,  G06F11/10 ,  G06F9/48 ,  G06F17/30 ,  G06F9/50

CPC分类号： H04L67/1097 ,  G06F3/0604 ,  G06F3/0614 ,  G06F3/0619 ,  G06F3/0646 ,  G06F3/065 ,  G06F3/0668 ,  G06F3/067 ,  G06F3/0683 ,  G06F3/0689 ,  G06F9/4881 ,  G06F9/5066 ,  G06F11/07 ,  G06F11/1076 ,  G06F11/1092 ,  G06F11/1448 ,  G06F11/1458 ,  G06F17/30067 ,  G06F2003/0697 ,  G06F2209/5017 ,  G06F2211/1028

摘要： A method includes receiving a task for execution by a plurality of distributed storage and task execution units A priority level is determined for the task. A plurality of coordinated partial task requests are generated and sent to the plurality of distributed storage and task execution units, wherein the plurality coordinated partial task requests indicate a plurality of coordinated partial tasks and the priority level. A plurality of partial task results are received in response to performance of the plurality of coordinated partial tasks by the plurality of distributed storage and task execution units. A task result for the task is generated based on the plurality of partial task results.