Frequency scaling for per-core accelerator assignments

    公开(公告)号:US12248783B2

    公开(公告)日:2025-03-11

    申请号:US18369082

    申请日:2023-09-15

    Abstract: Methods for frequency scaling for per-core accelerator assignments and associated apparatus. A processor includes a CPU (central processing unit) having multiple cores that can be selectively configured to support frequency scaling and instruction extensions. Under this approach, some cores can be configured to support a selective set of AVX instructions (such as AVX3/5G-ISA instructions) and/or AMX instructions, while other cores are configured to not support these AVX/AMX instructions. In one aspect, the selective AVX/AMX instructions are implemented in one or more ISA extension units that are separate from the main processor core (or otherwise comprises a separate block of circuitry in a processor core) that can be selectively enabled or disabled. This enables cores having the separate unit(s) disabled to consume less power and/or operate at higher frequencies, while supporting the selective AVX/AMX instructions using other cores. These capabilities enhance performance and provides flexibility to handle a variety of applications requiring use of advanced AVX/AMX instructions to support accelerated workloads.

    Compression engine with configurable search depths and window sizes

    公开(公告)号:US12021550B2

    公开(公告)日:2024-06-25

    申请号:US17119892

    申请日:2020-12-11

    CPC classification number: H03M7/3086 G06F16/2255 H03M7/40

    Abstract: Examples described herein relate to an encoder circuitry to apply one of multiple lossless data compression schemes on input data. In some examples, to compress input data, the encoder circuitry is to utilize a search window size and number of searches based on an applied compression scheme. In some examples, content of a memory is reconfigured to store data corresponding to a search window size of the applied compression scheme. In some examples, an applicable hash function is configured based on the applied compression scheme. In some examples, a number of searches are made for a byte position. In some examples, the encoder circuitry includes a hash table look-up and a bank decoder. In some examples, the hash table look-up is to generate a hash index to identify an address of an entry in the search window. In some examples, the bank decoder is to select a bank based on the hash index.

    FINGERPRINT-BASED vRAN CELL INTEGRITY MONITORING

    公开(公告)号:US20240098514A1

    公开(公告)日:2024-03-21

    申请号:US18514418

    申请日:2023-11-20

    CPC classification number: H04W16/18 H04L5/0048 H04W40/22

    Abstract: Various approaches for the deployment and coordination of network operation processing, compute processing, and communications for 5G networks, including with the use of fingerprint-based vRAN cell integrity monitoring, are discussed. In an example, analyzing a state of a 5G network includes: obtaining initial fingerprint reference data of a network state between a virtualized radio access network (vRAN) node and at least one fingerprint reference unit (FRU) device wirelessly connected to the vRAN node; comparing the initial fingerprint reference data to subsequent fingerprint data of the network state between the vRAN node (e.g., operating as vRAN gNB, or as an IAB Donor or IAB Node) and the at least one FRU device to detect a changed network condition; and performing an action at the vRAN node to modify or disable a component of the 5G network, in response to detection of the changed network condition.

    Multi-cast long range low power access point

    公开(公告)号:US10225851B2

    公开(公告)日:2019-03-05

    申请号:US15487670

    申请日:2017-04-14

    Abstract: System and techniques for a multi-class Long Range Lower Power (LRLP) access point (AP) multifactor intelligent agent control are described herein. A station (STA) association at the AP is received. Here, the association includes Class Identifier (ID) information. The Class ID information encompasses a set of communication parameters. A schedule of LRLP and non-LRLP STAs with associations at the AP is maintained. A transceiver chain is modified based on the schedule and the set of communication parameters to complete a communication with the STA.

    Networked peer device round-robin security controller

    公开(公告)号:US10200410B2

    公开(公告)日:2019-02-05

    申请号:US15282564

    申请日:2016-09-30

    Abstract: A round-robin network security system implemented by a number of peer devices included in a plurality of networked peer devices. The round-robin security system permits the rotation of the system security controller among at least a portion of the peer devices. Each of the peer devices uses a defined trust assessment ruleset to determine whether the system security controller is trusted/trustworthy. An untrusted system security controller peer device is replaced by another of the peer devices selected by the peer devices. The current system security controller peer device transfers system threat information and security risk information collected from the peer devices to the new system security controller elected by the peer devices.

    TECHNOLOGIES FOR INDEPENDENT SERVICE LEVEL AGREEMENT MONITORING

    公开(公告)号:US20170250892A1

    公开(公告)日:2017-08-31

    申请号:US15056570

    申请日:2016-02-29

    CPC classification number: G06F21/44 G06F21/552 H04L41/5009 H04L41/5019

    Abstract: Technologies for monitoring service level agreement (SLA) performance in an end-to-end SLA monitoring architecture include a network functions virtualization (NFV) SLA controller configured to manage SLA agents initialized in various network processing components of the end-to-end SLA monitoring architecture. To do so, the NFV SLA controller is configured to provide instruction to the SLA agents indicating which types of telemetry data to monitor and receive the requested telemetry data, as securely collected and securely packaged by the SLA agents. The NFV SLA controller is further configured to securely analyze the received telemetry data to determine one or more performance metrics and compare performance benchmarks against the performance metrics to generate an SLA report that includes the results of the comparison. Other embodiments are described and claimed.

Patent Agency Ranking