公开(公告)号：US20200285523A1

公开(公告)日：2020-09-10

申请号：US16878861

申请日：2020-05-20

申请人： Francesc Guim Bernat ,  Kshitij Arun Doshi ,  Bassam N. Coury ,  Suraj Prabhakran ,  Timothy Verrall

发明人： Francesc Guim Bernat ,  Kshitij Arun Doshi ,  Bassam N. Coury ,  Suraj Prabhakran ,  Timothy Verrall

IPC分类号： G06F9/50 ,  G06F9/48

摘要： Systems and methods may be used to determine where to run a service based on workload-based conditions or system-level conditions. An example method may include determining whether power available to a resource of a compute device satisfies a target power, for example to satisfy a target performance for a workload. When the power available is insufficient, an additional resource may be provided, for example on a remote device from the compute device. The additional resource may be used as a replacement for the resource of the compute device or to augment the resource of the compute device.

公开(公告)号：US20230133020A1

公开(公告)日：2023-05-04

申请号：US18090653

申请日：2022-12-29

申请人： Deboleena Minz Sakalley ,  Kshitij Arun Doshi ,  Francesc Guim Bernat

发明人： Deboleena Minz Sakalley ,  Kshitij Arun Doshi ,  Francesc Guim Bernat

IPC分类号： G06F9/50 ,  G06F9/48

摘要： Various approaches for deploying and controlling distributed accelerated compute operations with the use of infrastructure processing units (IPUs) and similar networked processing units are disclosed. A system for orchestrating acceleration functions in a network compute mesh is configured to access a flowgraph, the flowgraph including data producer-consumer relationships between a plurality of tasks in a workload; identify available artifacts and resources to execute the artifacts to complete each of the plurality of tasks, wherein an artifact is an instance of a function to perform a task of the plurality of tasks; determine a configuration assigning artifacts and resources to each of the plurality of tasks in the flowgraph; and schedule, based on the configuration, the plurality of tasks to execute using the assigned artifacts and resources.

公开(公告)号：US20220222337A1

公开(公告)日：2022-07-14

申请号：US17711768

申请日：2022-04-01

申请人： Kshitij Arun Doshi ,  Francesc Guim Bernat

发明人： Kshitij Arun Doshi ,  Francesc Guim Bernat

IPC分类号： G06F21/53

摘要： The present disclosure describes a micro-enclave (μenclave) framework including μenclave operations, which are library functions that split off from normal code execution. The μenclaves contain a mix of stateful and stateless operations, including such steps as reading or writing various hardware registers or resource counters in operating system, timer setup, deferring preemption events by a small value within a threshold set by the operating system, and the like. The operations in a μenclave, even though performed at a user level privilege, are compiled by a separate compilation sequence and installed unforgeably as static and unforgeable procedure collections that do not yield control to an operating system scheduler.

公开(公告)号：US20220222077A1

公开(公告)日：2022-07-14

申请号：US17709824

申请日：2022-03-31

申请人： Kshitij Arun Doshi ,  Francesc Guim Bernat

发明人： Kshitij Arun Doshi ,  Francesc Guim Bernat

IPC分类号： G06F9/30 ,  G06K7/00

摘要： System and techniques for tag checking procedure calls include specifying a value for a color in a program-counter relative (PC-relative) call instruction from a call site to a call target. A pointer is provided to steer the PC-relative call instruction to the call target based on the color. A function call is generated to the call target based on the pointer. Other systems, methods and apparatuses are also described.

公开(公告)号：US20220124005A1

公开(公告)日：2022-04-21

申请号：US17561254

申请日：2021-12-23

申请人： Kshitij Arun Doshi ,  John J. Browne ,  Marcos E. Carranza ,  Francesc Guim Bernat ,  Mats Gustav Agerstam ,  Adrian Hoban ,  Thijs Metsch

发明人： Kshitij Arun Doshi ,  John J. Browne ,  Marcos E. Carranza ,  Francesc Guim Bernat ,  Mats Gustav Agerstam ,  Adrian Hoban ,  Thijs Metsch

IPC分类号： H04L41/5003 ,  H04L41/5019 ,  G06F9/50

摘要： Various systems and methods for reactive intent-driven end-to-end (E2E) orchestration are described herein. An orchestrator system, includes a processor; and memory to store instructions, which when executed by the processor, cause the system to: receive, at the orchestrator system, an intent-based service level agreement (SLA) for execution of a series of tasks on a plurality of compute nodes; calculate, based on the intent-based SLA, intermediate latency thresholds corresponding to each task of the series of tasks; calculate slack estimates based on the latency thresholds and real-time telemetry of the plurality of compute nodes or real-time telemetry of connections between the plurality of compute nodes; monitor execution of the series of tasks on the plurality of compute nodes; and perform a corrective action in response to determining that the execution of the series of tasks is predicted to exceed one of the intermediate latency thresholds

公开(公告)号：US20230136612A1

公开(公告)日：2023-05-04

申请号：US18090749

申请日：2022-12-29

申请人： Kshitij Arun Doshi ,  Francesc Guim Bernat

发明人： Kshitij Arun Doshi ,  Francesc Guim Bernat

IPC分类号： G06F9/48 ,  G06F9/54

摘要： Various approaches for managing distributed compute operations for workload execution of concurrent tasks, including with the use of infrastructure processing units (IPUs) and similar networked processing units, are disclosed. An example method may include: identifying multiple tasks of a computing workload, for a workload that provides processing dependencies among the tasks, and that uses concurrent execution with one or more of the tasks; monitoring an execution time for each of the tasks, relative to an execution time threshold for each of the tasks; identifying the execution time of a particular task as exceeding an execution time threshold for the particular task; determining a remediation based on the particular task and the identified execution time, with the remediation including use of other compute resources in the distributed computing environment for the workload; and applying the remediation to increase speed of execution of the workload.

公开(公告)号：US20230135645A1

公开(公告)日：2023-05-04

申请号：US18090764

申请日：2022-12-29

申请人： Francesc Guim Bernat ,  Karthik Kumar ,  Kshitij Arun Doshi ,  Marcos E. Carranza

发明人： Francesc Guim Bernat ,  Karthik Kumar ,  Kshitij Arun Doshi ,  Marcos E. Carranza

IPC分类号： G06F9/50

摘要： Various approaches for deploying and controlling distributed compute operations with the use of infrastructure processing units (IPUs) and similar networked processing units are disclosed. A system that includes a networked processing unit may perform workload processing with operations that: receive, from another networked processing unit, workload information for a workload, for a workload having respective tasks to be processed among distributed computing entities; perform an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities; perform an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and identify locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.

公开(公告)号：US20220124009A1

公开(公告)日：2022-04-21

申请号：US17561061

申请日：2021-12-23

申请人： Thijs Metsch ,  Susanne M. Balle ,  Patrick Koeberl ,  Bin Li ,  Mark Yarvis ,  Adrian Hoban ,  Kshitij Arun Doshi ,  Francesc Guim Bernat ,  Cesar Martinez-Spessot ,  Mats Gustav Agerstam ,  Dario Nicolas Oliver ,  Marcos E. Carranza ,  John J. Browne ,  Mikko Ylinen ,  David Cremins

发明人： Thijs Metsch ,  Susanne M. Balle ,  Patrick Koeberl ,  Bin Li ,  Mark Yarvis ,  Adrian Hoban ,  Kshitij Arun Doshi ,  Francesc Guim Bernat ,  Cesar Martinez-Spessot ,  Mats Gustav Agerstam ,  Dario Nicolas Oliver ,  Marcos E. Carranza ,  John J. Browne ,  Mikko Ylinen ,  David Cremins

IPC分类号： H04L41/5054 ,  H04L47/72 ,  H04L43/08 ,  H04L41/5025

摘要： Various systems and methods for implementing intent-based orchestration in heterogenous compute platforms are described herein. An orchestration system is configured to: receive, at the orchestration system, a workload request for a workload, the workload request including an intent-based service level objective (SLO); generate rules for resource allocation based on the workload request; generate a deployment plan using the rules for resource allocation and the intent-based SLO; deploy the workload using the deployment plan; monitor performance of the workload using real-time telemetry; and modify the rules for resource allocation and the deployment plan based on the real-time telemetry.

公开(公告)号：US20220121455A1

公开(公告)日：2022-04-21

申请号：US17561181

申请日：2021-12-23

申请人： Adrian Hoban ,  Thijs Metsch ,  Francesc Guim Bernat ,  John J. Browne ,  Kshitij Arun Doshi ,  Mark Yarvis ,  Bin Li ,  Susanne M. Balle ,  Benjamin Walker ,  David Cremins ,  Mats Gustav Agerstam ,  Marcos E. Carranza ,  MIkko Ylinen ,  Dario Nicolas Oliver ,  John Mangan

发明人： Adrian Hoban ,  Thijs Metsch ,  Francesc Guim Bernat ,  John J. Browne ,  Kshitij Arun Doshi ,  Mark Yarvis ,  Bin Li ,  Susanne M. Balle ,  Benjamin Walker ,  David Cremins ,  Mats Gustav Agerstam ,  Marcos E. Carranza ,  MIkko Ylinen ,  Dario Nicolas Oliver ,  John Mangan

IPC分类号： G06F9/445 ,  G06F9/38 ,  G06N20/00 ,  G06Q10/08

摘要： Various systems and methods for implementing intent-based cluster administration are described herein. An orchestrator system includes: a processor; and memory to store instructions, which when executed by the processor, cause the orchestrator system to: receive, at the orchestrator system, an administrative intent-based service level objective (SLO) for an infrastructure configuration of an infrastructure; map the administrative intent-based SLO to a set of imperative policies; deploy the set of imperative policies to the infrastructure; monitor performance of the infrastructure; detect non-compliance with the set of imperative policies; and modify the administrative intent-based SLO to generate a revised set of imperative policies that cause the performance of the infrastructure to be compliant with the revised set of imperative policies.

公开(公告)号：US20190222518A1

公开(公告)日：2019-07-18

申请号：US16369430

申请日：2019-03-29

申请人： Francesc Guim Bernat ,  Karthik Kumar ,  Ned M. Smith ,  Monica Kenguva ,  Rashmin Patel

发明人： Francesc Guim Bernat ,  Karthik Kumar ,  Ned M. Smith ,  Monica Kenguva ,  Rashmin Patel

IPC分类号： H04L12/803 ,  H04L12/851 ,  H04L12/813 ,  H04L12/927 ,  H04L12/26

CPC分类号： H04L47/125 ,  H04L43/08 ,  H04L47/20 ,  H04L47/2425 ,  H04L47/805

摘要： Technologies for load balancing on a network device in an edge network are disclosed. According to one embodiment, a network device receives, in the edge network, a request to access a function. The request includes one or more performance requirements. The network device identifies, as a function of an evaluation of the performance requirements and on monitored properties of each device associated with the network device, one or more of the devices to service the request. The network device selects one of the identified devices according to a load balancing policy and sends the request to the selected device.