公开(公告)号：US20240012769A1

公开(公告)日：2024-01-11

申请号：US18370621

申请日：2023-09-20

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Manish DAVE ,  Vered BAR BRACHA ,  Bradley A. BURRES ,  Uzair QURESHI ,  Joseph GRECCO ,  Paul KAPPLER ,  Dirk F. BLEVINS ,  Mukesh Gangadhar BHAVANI VENKATESAN ,  Hariharan M ,  Marek PIOTROWSKI ,  Dhanya PILLAI ,  John MANGAN ,  Mandar CHINCHOLKAR ,  Eoin WALSH ,  Sumit MOHAN ,  Ned SMITH ,  Tushar Sudhakar GOHAD

IPC: G06F13/16 ,  G06F11/20

CPC classification number: G06F13/1668 ,  G06F11/2017 ,  G06F2201/80

Abstract: Examples described herein relate to a network interface device. In some examples, the network interface device includes a network interface, a direct memory access (DMA) circuitry, a host interface, memory, one or more processors, and circuitry to: based on a configuration of operation specifying a standalone operation, cause the network interface device to operate in standalone to execute one or more applications and based on a configuration of operation specifying a companion operation, cause the network interface device to operate in companion to provide at least one host system with access to one or more hardware resources accessible by the network interface device.

公开(公告)号：US20240012459A1

公开(公告)日：2024-01-11

申请号：US18371949

申请日：2023-09-22

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Karthik KUMAR ,  John J. BROWNE ,  Chris MACNAMARA ,  Patrick CONNOR

IPC: G06F1/26

CPC classification number: G06F1/266

Abstract: Examples described herein relate to receiving a configuration, wherein the configuration is to specify a first level of renewable energy utilized by one or more devices based on telemetry, wherein the telemetry comprises a level of renewable energy supplied to the one or more devices. Based on a second level of available supplied renewable energy, a portion of the first level of available supplied renewable energy can be allocated to one or more devices to perform the process. Based on a third level of available supplied renewable energy, increase renewable energy allocated to the one or more devices, to perform the process, to above the first level.

公开(公告)号：US20230273821A1

公开(公告)日：2023-08-31

申请号：US18136262

申请日：2023-04-18

Applicant: Intel Corporation

Inventor： Amruta MISRA ,  Francesc GUIM BERNAT ,  Kshitij A. DOSHI ,  Marcos E. CARRANZA ,  John J. BROWNE ,  Arun HODIGERE

IPC: G06F9/48 ,  G06F11/34

CPC classification number: G06F9/4893 ,  G06F11/3433

Abstract: A method is described. The method includes dispatching jobs across electronic hardware components. The electronic hardware components are to process the jobs. The electronic hardware components are coupled to respective cooling systems. The respective cooling systems are each capable of cooling according to different cooling mechanisms. The different cooling mechanisms have different performance and cost operating realms. The dispatching of the jobs includes assigning the jobs to specific ones of the electronic hardware components to keep the cooling systems operating in one or more of the realms having lower performance and cost than another one of the realms.

公开(公告)号：US20230208781A1

公开(公告)日：2023-06-29

申请号：US18073106

申请日：2022-12-01

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Antonino ALBARRAN ,  Jaime SANZ ,  Raghu R. KONDAPALLI ,  Alexander BACHMUTSKY

IPC: H04L47/783 ,  H04L47/70 ,  H04L47/762 ,  H04L41/5019 ,  H04L41/5009

CPC classification number: H04L47/783 ,  H04L47/821 ,  H04L47/762 ,  H04L41/5019 ,  H04L41/5009 ,  H04L43/0876

Abstract: Technologies for dynamic allocation of network communication resources includes a resource manager server to allocate a set of network communication resources to a compute device through an expansion bus switch that is coupled to the compute device and to the network communication resources. The resource manager server obtains telemetry data indicative of a present utilization of the allocated set of network communication resources and determines whether the present utilization satisfies a predefined utilization threshold. Additionally, the resource manager server adjusts, through the expansion bus switch and in response to a determination that the present utilization does not satisfy the predefined utilization threshold, an amount of network communication resources in the set to the compute device.

公开(公告)号：US20220360646A1

公开(公告)日：2022-11-10

申请号：US17873618

申请日：2022-07-26

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Kshitij A. DOSHI ,  Ned SMITH ,  Satish C. JHA ,  Vesh Raj SHARMA BANJADE ,  S M Iftekharul ALAM

IPC: H04L67/60 ,  H04L49/20 ,  H04L67/10

Abstract: Switching architectures to manage mutex primitives used to control access to objects or data blocks that are being processed by two or more microservices in a data center are provided.

公开(公告)号：US20220329450A1

公开(公告)日：2022-10-13

申请号：US17852174

申请日：2022-06-28

Applicant: Intel Corporation

Inventor： Harald SERVAT ,  Amruta MISRA ,  Mikko BYCKLING ,  Francesc GUIM BERNAT ,  Jaime ARTEAGA MOLINA ,  Karthik KUMAR

IPC: H04L12/12 ,  H04L67/1097 ,  G06F13/42 ,  G06F13/28

Abstract: Examples described herein relate to a network interface device that includes circuitry to perform switching and perform a received command in one or more packets while at least one of the at least one compute device is in a reduced power state, wherein the command is associated with operation of the at least one of the at least one compute device that is in a reduced power state. In some examples, the network interface device is able to control power available to at least one compute device.

公开(公告)号：US20220317692A1

公开(公告)日：2022-10-06

申请号：US17847236

申请日：2022-06-23

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Marcos E. CARRANZA ,  Akhilesh THYAGATURU ,  Rony FERZLI ,  Teemu KAERKKAEINEN

IPC: G05D1/02 ,  B25J9/16

Abstract: A computation offloading device includes a plurality of communication nodes, each configured to wirelessly send and receive data; a processor, configured to instruct a computation node of a plurality of computation nodes to process a data payload received from a robot at a first communication node of the plurality of communication nodes; select one or more second communication nodes of the plurality of communication nodes, different from the first communication node, based on a predicted location of the robot; and instruct the one or more second communication nodes to send a result of the processed data payload to the robot at the predicted location.

公开(公告)号：US20220206849A1

公开(公告)日：2022-06-30

申请号：US17700313

申请日：2022-03-21

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Karthik KUMAR ,  Alexander BACHMUTSKY

IPC: G06F9/48 ,  G06F9/50 ,  H04L67/51

Abstract: Methods and apparatus for hardware support for low latency microservice deployments in switches. A switch is communicatively coupled via a network or fabric to a plurality of platforms configured to implement one or more microservices. The microservices are used to perform a distributed workload, job, or task as defined by a corresponding graph representation of the microservices including vertices (also referred to as nodes) associated with microservices and edges defining communication between microservices. The graph representation also defines dependencies between microservices. The switch is configured to schedule execution of the graph of microservices on the plurality of platforms, including generating an initial schedule that is dynamically revised during runtime in consideration of performance telemetry data for the microservices received from the platforms and network/fabric utilization monitored onboard the switch. The switch also may include memory in which graph representations, microservice tables, and node-to-microservice maps are stored.

公开(公告)号：US20220138025A1

公开(公告)日：2022-05-05

申请号：US17471927

申请日：2021-09-10

Applicant: Intel Corporation

Inventor： Evan Custodio ,  Susanne M. Balle ,  Francesc GUIM BERNAT ,  Slawomir Putyrski ,  Joe Grecco ,  Henry Mitchel

IPC: G06F9/54 ,  G02B6/44 ,  G06F15/78

Abstract: Technologies for providing efficient reprovisioning in an accelerator device include an accelerator sled. The accelerator sled includes a memory and an accelerator device coupled to the memory. The accelerator device is to configure itself with a first bit stream to establish a first kernel, execute the first kernel to produce output data, write the output data to the memory, configure itself with a second bit stream to establish a second kernel, and execute the second kernel with the output data in the memory used as input data to the second kernel. Other embodiments are also described and claimed.

公开(公告)号：US20220004873A1

公开(公告)日：2022-01-06

申请号：US17479858

申请日：2021-09-20

Applicant: Intel Corporation

Inventor： Francesc GUIM BERNAT ,  Suraj PRABHAKARAN ,  Kshitij A. DOSHI ,  Da-Ming CHIANG

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/063

Abstract: Examples include techniques to manage training or trained models for deep learning applications. Examples include routing commands to configure a training model to be implemented by a training module or configure a trained model to be implemented by an inference module. The commands routed via out-of-band (OOB) link while training data for the training models or input data for the trained models are routed via inband links.