Intel Corporation

Other

Rahul Khanna

Susanne M Balle

Francesc Guim Bernat

Sujoy Sen

Mrittika Ganguli

Vincent J Zimmer

Evan Custodio

Slawomir Putyrski

Henry M Mitchel

Nishi Ahuja

Joe Grecco

Greeshma Pisharody

Christopher R Carlson

Karthik Kumar

Mahesh S Natu

Murugasamy K Nachimuthu

Yufu Li

Minh T Le

Paul H Dormitzer

Ananth S Narayan

Andrew J Herdrich

Mallik Bulusu

Jaideep Moses

James W Edwards

Abdul M Bailey

Kevin Yufu Li

Xiaohua Cai

Di Tang

Muthuvel M I

Kshitij Arun Doshi

Mohan J Kumar

Telesphor Kamgaing

Robert Charles Swanson

Eugene Gorbatov

Sarathy Jayakumar

Ulf Hanebutte

Howard S David

Narayan Ranganathan

Jian Tang

Thanunathan Rangarajan

Anil S Keshavamurthy

Kerry Vander Kamp

James Tang

Mahesh S Naru

Abishai Daniel

Piyush Gupta

Michael A Rothman

James W Tschanz

Yu Meng Li

Arvind A Kumar

Robert F Kwasnick

Dean A Mulla

Kai Cheng

Andrew J Fish

James W Alexander

Kirk D Brannock

Daniel Rivas Barragan

Rafael De La Guardia Gonzalez

Bruce Querbach

Thijs Metsch

Ali Taha

Robin A Steinbrecher

Keith Robert Pflederer

Christopher Connor

Marcin Spoczynski

Jay Joseph Nejedlo

Kushal Datta

Annie Ibrahim Rana

Vikram A Saletore

Krishna Kant

Meenakshi Arunachalam

Jason Liu

Vishal Verma

Deepthi Karkada

Xiaohu Zhou

Leonard Feehan

Richard Marian Thomaiyar

Christian Le

Fernando A Lopez

William Zand

Zhijie Sheng

Gordon McFadden

Koo Heng Daniel Aw

Wenson Lin

William Cai

Sharon Ruane

Vamsi Sripathi

Xin Kang

Diyong Fu

Minh Tung Duy Le

Ulf R Hanebutte

Yu Fu Li

Technologies for dividing work across one or more accelerator devices include a compute device. The compute device is to determine a configuration of each of multiple accelerator devices of the compute device, receive a job to be accelerated from a requester device remote from the compute device, and divide the job into multiple tasks for a parallelization of the multiple tasks among the one or more accelerator devices, as a function of a job analysis of the job and the configuration of each accelerator device. The compute engine is further to schedule the tasks to the one or more accelerator devices based on the job analysis and execute the tasks on the one or more accelerator devices for the parallelization of the multiple tasks to obtain an output of the job.

Technologies for dividing work across accelerator devices

Technologies for offloading acceleration task scheduling operations to accelerator sleds include a compute device to receive a request from a compute sled to accelerate the execution of a job, which includes a set of tasks. The compute device is also to analyze the request to generate metadata indicative of the tasks within the job, a type of acceleration associated with each task, and a data dependency between the tasks.

Technologies for offloading acceleration task scheduling operations to accelerator sleds

Technologies for dynamically managing resources in disaggregated accelerators include an accelerator. The accelerator includes acceleration circuitry with multiple logic portions, each capable of executing a different workload. Additionally, the accelerator includes communication circuitry to receive a workload to be executed by a logic portion of the accelerator and a dynamic resource allocation logic unit to identify a resource utilization threshold associated with one or more shared resources of the accelerator to be used by a logic portion in the execution of the workload, limit, as a function of the resource utilization threshold, the utilization of the one or more shared resources by the logic portion as the logic portion executes the workload, and subsequently adjust the resource utilization threshold as the workload is executed. Other embodiments are also described and claimed.

Technologies for dynamically managing resources in disaggregated accelerators

In accordance with some embodiments, a cloud service provider may operate a data center in a way that dynamically reallocates resources across nodes within the data center based on both utilization and service level agreements. In other words, the allocation of resources may be adjusted dynamically based on current conditions. The current conditions in the data center may be a function of the nature of all the current workloads. Instead of simply managing the workloads in a way to increase overall execution efficiency, the data center instead may manage the workload to achieve quality of service requirements for particular workloads according to service level agreements.

Managing data center resources to achieve a quality of service

Methods, apparatus, systems and articles of manufacture are disclosed to optimize a guard band of a hardware resource. An example apparatus includes at least one storage device, and at least one processor to execute instructions to identify a phase of a workload based on an output from a machine-learning model, the phase based on a utilization of one or more hardware resources, and based on the phase, control a guard band of a first hardware resource of the one or more hardware resources.

Methods and apparatus to optimize a guard band of a hardware resource

Technologies for providing accelerated functions as a service in a disaggregated architecture include a compute device that is to receive a request for an accelerated task. The task is associated with a kernel usable by an accelerator sled communicatively coupled to the compute device to execute the task. The compute device is further to determine, in response to the request and with a database indicative of kernels and associated accelerator sleds, an accelerator sled that includes an accelerator device configured with the kernel associated with the request. Additionally, the compute device is to assign the task to the determined accelerator sled for execution. Other embodiments are also described and claimed.

Technologies for providing accelerated functions as a service in a disaggregated architecture

Lost, misplaced, incorrectly delivered, and damaged assets are a common occurrence in shipment or asset tracking. Disclosed are various embodiments concerning a battery-less or intermittent battery use environments in which a node uses internal logic (e.g., circuitry and/or software) that, based at least in part on sensor information and stored information regarding the history of the node, may track events that have occurred to the node. The node may be responsive to events and determine whether exceptions have occurred that require attention. For example, detecting damage might cause the node to update an output to indicate the node and associated material, if any, needs to be rerouted to address the exception.

Self-directing node

Apparatuses and methods for providing change and/or transfer of custody signaling in a wireless sensor network (WSN) are disclosed. An apparatus may include communications circuitry to interact with a cloud server to receive an instruction regarding a change of custody for at least one sensor node within a WSN. The at least one sensor node may be assigned to the apparatus for tracking, and the instruction may identify a second apparatus within the WSN to assume custody of the at least one sensor. The apparatus may further include a control unit coupled to the communications circuitry to signal the second apparatus and the at least one sensor node regarding the transfer of custody, wherein the signaling is over a wireless protocol of the WSN. Other embodiments may be described and/or claimed.

Seamless and reliable chain of custody transfer over low power wireless protocol

Technologies for allocating resources of managed nodes to workloads to balance multiple resource allocation objectives include an orchestrator server to receive resource allocation objective data indicative of multiple resource allocation objectives to be satisfied. The orchestrator server is additionally to determine an initial assignment of a set of workloads among the managed nodes and receive telemetry data from the managed nodes. The orchestrator server is further to determine, as a function of the telemetry data and the resource allocation objective data, an adjustment to the assignment of the workloads to increase an achievement of at least one of the resource allocation objectives without decreasing an achievement of another of the resource allocation objectives, and apply the adjustments to the assignments of the workloads among the managed nodes as the workloads are performed. Other embodiments are also described and claimed.

Technologies for assigning workloads to balance multiple resource allocation objectives

A method for distributing at least one computational process amongst shared resources is proposed. At least two shared resources capable of performing the computational process are determined. According to the method, a workload characteristic for each of the shared resources is predicted. The workload characteristic accounts for at least two subsystems of each shared resource. One of the at least two shared resources is selected based on the predicted workload characteristics.

Method for distributing a computational process, workload distribution device and system for distributing a computational process

Growing community of inventors

Portland, OR, United States of America

Rahul Khanna