Intel Corporation

Telefonaktiebolaget Lm Ericsson (publ)

Nokia Corporation

Nokia Siemens Networks Oy

Axiado Corporation

Hmd Global Oy

Alexander Bachmutsky

Francesc Guim Bernat

Raghu R Kondapalli

Kshitij Arun Doshi

Ned M Smith

Karthik Kumar

Suraj Prabhakaran

Nageen Himayat

Srikathyayani Srikanteswara

S M Iftekharul Alam

Yi Zhang

Satish Chandra Jha

John Joseph Browne

Vadim Sukhomlinov

Patrick G Kutch

Vesh Raj Sharma Banjade

Rajesh Poornachandran

Kapil Sood

Christian Maciocco

Andrew J Herdrich

Mats Gustav Agerstam

Maruti Gupta Hyde

Marcos Emanuel Carranza

Dario Sabella

Tarun Viswanathan

David M Durham

Ravi L Sahita

Chi Fai Ho

Mohan J Kumar

Rita H Wouhaybi

Matthew James Adiletta

Marcin Spoczynski

Tsung-Yuan Charles Tai

Ren Wang

Patrick L Connor

Baiju V Patel

Thomas Willhalm

Ravishankar Iyer

Michael Lemay

Sara S Baghsorkhi

Jr-Shian Tsai

Timothy Verrall

Susanne M Balle

Scott P Dubal

Samita Chakrabarti

Trevor Cooper

Jaime Sanz

Antonino Albarran

Mingqiu Sun

Ian M Steiner

Ravikumar Balakrishnan

Jeffrey D Chamberlain

Eric Dahlen

Dimitrios Ziakas

Nilesh K Jain

Shunliang Zhang

Yipeng Wang

Mohammad R Haghighat

Mingwei Zhang

Amin Firoozshahian

Nagabhushan Chitlur

Wei Hua Zhou

James Robert Hearn

Hao Feng

Duane E Galbi

James A Coleman

Achim Von Brandt

Yeluri Raghuram

Zhongyan Lu

Sunil K Cheruvu

Dmitry Babokin

Sundar Nadathur

Krishna Bhuyan

Anil Rao

Leeor Peled

Srinivas Kadaba

Andrzej Koscinski

Ravi Bail Bhat

Amar Srivastava

Rita D Gupta

Teck Joo Goh

Andrzej Kuriata

Areg Melik-Adamyan

Harshad S Sane

Yifan Yuan

Weihua Zhou

Anup Mohan

Michael Prinke

Niall Mcdonnell

Henry Tzeng

Nicolae Octavian Popovici

Himansu Sahu

Steven Briscoe

Wenyong Huang

Gopi Sirineni

Damjan Damic

Shun Liang Zhang

Ranghu Kondapalli

Partick Connor

System and techniques for infrastructure managed workload distribution are described herein. An infrastructure processing unit (IPU) receives a workload that includes a workload definition. The workload definition includes stages of the workload and a performance expectation. The IPU provides the workload, for execution, to a processing unit of a compute node to which the IPU belongs. The IPU monitors execution of the workload to determine that a stage of the workload is performing outside of the performance expectation from the workload definition. In response, the IPU modifies the execution of the workload.

Infrastructure managed workload distribution

Examples described herein relate to a network interface device that comprises circuitry, when operational, to select a platform to execute a function and based on load of the platform, selectively cause the function to execute on one or more other platforms to attempt to achieve or finish before the time-to-completion. In some examples, the circuitry is to detect progress of function execution to determine whether completion of execution of the function is predicted to not finish within the time-to-completion and cause the function to execute on one or more other platforms based on completion of execution of the function predicted to not finish within the time-to-completion. In some examples, the circuitry is to select the one or more other platforms to execute the function based on one or more of: processor computing utilization, available memory capacity, available cache capacity, network availability, or malfunction of a processor, memory, and/or cache.

Network interface device management of service execution failover

In one embodiment, a node of a data centric network (DCN) may receive a first service request interest packet from another node of the DCN, the first service request interest packet indicating a set of functions to be performed on source data to implement a service. The node may determine that it can perform a particular function of the set of functions, and determine, based on a backlog information corresponding to the particular function, whether to commit to performing the particular function or to forward the service request interest packet to another node. The node may make the determination further based on service delivery information indicating, for each face of the node, a service delivery distance for implementing the set of functions.

Queuing control for distributed compute network orchestration

Methods, apparatus, and software for remote storage of hardware microservices hosted on other processing units (XPUs) and SOC-XPU Platforms. The apparatus may be a platform including a System on Chip (SOC) and an XPU, such as a Field Programmable Gate Array (FPGA). Software, via execution on the SOC, enables the platform to pre-provision storage space on a remote storage node and assign the storage space to the platform, wherein the pre-provisioned storage space includes one or more container images to be implemented as one or more hardware (HW) microservice front-ends. The XPU/FPGA is configured to implement one or more accelerator functions used to accelerate HW microservice backend operations that are offloaded from the one or more HW microservice front-ends. The platform is also configured to pre-provision a remote storage volume containing worker node components and access and persistently store worker node components.

Remote storage for hardware microservices hosted on XPUs and SOC-XPU platforms

Methods, apparatus, systems, and articles of manufacture are disclosed to increase resiliency in self-healing mechanisms. At least one non-transitory machine-readable medium comprises instructions that, when executed, cause at least one processor to at least partition computational resources of a first host into a primary partition and a shadow partition, the primary partition to communicate with a second host, apply a fix for the primary partition, determine if the primary partition can communicate with the second host during the application of the fix, cause, in response to the determination that the primary partition cannot communicate with the second host during the application of the fix, the shadow partition to communicate with the second host; and transfer communication with the second host from the shadow partition to the primary partition, the transfer in response to a determination that the application of the fix is complete.

Methods and apparatus to increase resiliency in self-healing mechanisms

Systems and techniques for cross-layer automated fault tracking and anomaly detection are described herein. Anomaly data may be obtained from a plurality of layers of a network. Elements of the anomaly data may be identified that correspond to a data flow of an application executing on the network. An artificial intelligence model may be trained using the elements of the anomaly data to generate an impact score for the application. The impact score may be generated for the application by evaluating current network metrics using the artificial intelligence model. An operational component of the network may be modified based on the impact score.

Cross-layer automated fault tracking and anomaly detection

System and techniques for geographic routing are described herein. A node receives a data packet that includes map data, a sequence of geographic areas to a requestor, and a target geographic area. The node may then determine that it is within the target geographic area and start a transmit timer based on a next-hop geographic area. Here, the next-hop geographic area is determined from the sequence of geographic areas in the data packet. The node may then counts how many other nodes from the geographic area sent data packets while the transmit timer is running. When the transmit timer expires, the node may transmit a modified data packet when the number of data packets is less than a predefined threshold. Here, the modified data packet is the data packet updated to include local map data and the next-hop geographic area.

Geographic routing

System and techniques for storage node recruitment in an information centric network (ICN) are described herein. An ICN node receives a storage interest packet that includes an indication differentiating the storage interest from other ICN interests. The ICN node forwards the storage interest packet and receives a storage data packet in response. Here, the storage data packet includes an indication that the storage data packet is not to be cached along with node information for a node that created the storage data packet. The ICN node may then transmit the storage data packet in accordance with a pending interest table (PIT) entry corresponding to the storage interest packet.

Storage node recruitment in an information centric network

A multi-tenant dynamic secure data region in which encryption keys can be shared by services running in nodes reduces the need for decrypting data as encrypted data is transferred between nodes in the data center. Instead of using a key per process/service, that is created by a memory controller when the service is instantiated (for example, MKTME), a software stack can specify that a set of processes or compute entities (for example, bit-streams) share a private key that is created and provided by the data center.

Multi-tenant isolated data regions for collaborative platform architectures

In one embodiment, an apparatus includes an interface to couple a plurality of devices of a system, the interface to enable communication according to a Compute Express Link (CXL) protocol, and a power management circuit coupled to the interface. The power management circuit may: receive, from a first device of the plurality of devices, a request according to the CXL protocol for updated power credits; identify at least one other device of the plurality of devices to provide at least some of the updated power credits; and communicate with the first device and the at least one other device to enable the first device to increase power consumption according to the at least some of the updated power credits. Other embodiments are described and claimed.

System, apparatus and methods for power communications according to a CXL power protocol

Described are methods, systems, and media for detecting malicious activity in a network by performing operations comprising: feeding network packets from the network into a header crypto engine; sending the network packets from the header crypto engine to a work scheduler; divaricating the network packets using the work scheduler based on flow data and header data of the network packets to at least one of a firewall and a neural network processor; generating output data comprising: a first output data from the firewall according to rules of the firewall; a second output data from the neural network processor based on behavioral analysis performed by the neural network processor, wherein the second output data is used to update the rules in the firewall; and aggregating the output data from the firewall and the neural network processor to detect malicious activity in the network.

Systems and methods using network artificial intelligence to manage control plane security in real-time

Methods and apparatus for software-defined coherent caching of pooled memory. The pooled memory is implemented in an environment having a disaggregated architecture where compute resources such as compute platforms are connected to disaggregated memory via a network or fabric. Software-defined caching policies are implemented in hardware in a processor SoC or discrete device such as a Network Interface Controller (NIC) by programming logic in an FPGA or accelerator on the SoC or discrete device. The programmed logic is configured to implement software-defined caching policies in hardware for effecting disaggregated memory (DM) caching in an associated DM cache of at least a portion of an address space allocated for the software application in the disaggregated memory. In connection with DM cache operations, such as cache lines evicted from a CPU, logic implemented in hardware determines whether a cache line in a DM cache is to be evicted and implements the software-defined caching policy for the DM cache including associated memory coherency operations.

Software-defined coherent caching of pooled memory

Examples described herein relate to an apparatus that includes a memory and at least one processor where the at least one processor is to receive configuration to gather performance data for a function from one or more platforms and during execution of the function, collect performance data for the function and store the performance data after termination of execution of the function. Some examples include an interface coupled to the at least one processor and the interface is to receive one or more of: an identifier of a function, resources to be tracked as part of function execution, list of devices to be tracked as part of function execution, type of monitoring of function execution, or meta-data to identify when the function is complete. Performance data can be accessed to determine performance of multiple executions of the short-lived function.

Performance monitoring for short-lived functions

Technologies for collecting metrics associated with a processing resource (e.g., central processing unit (CPU) resources, accelerator device resources, and the like) over a time window are disclosed. According to an embodiment presented herein, a network device receives, in an edge network, a request to provide one or more metrics associated with a processing resource, the request specifying a window indicative of a time period to capture the one or more metrics. The network device obtains the one or more metrics from the processing resource for the specified window and provides the obtained one or more metrics in response to the request.

Technologies for capturing processing resource metrics as a function of time

An apparatus comprising a network interface controller comprising a queue for messages for a thread executing on a host computing system, wherein the queue is dedicated to the thread; and circuitry to send a notification to the host computing system to resume execution of the thread when a monitoring rule for the queue has been triggered.

Advanced queue monitoring system

Growing community of inventors

Sunnyvale, CA, United States of America

Alexander Bachmutsky