Microsoft Technology Licensing, LLC

Other

Sanjeev Mehrotra

Wei-Ge Chen

Kazuhito Koishida

Albert S Wang

Jin Li

Philip Andrew Chou

Paramvir Bahl

Chao He

Bozidar Radunovic

Xenofon Foukas

Thomas W Holcomb

Sudipta Sengupta

Costin Hagiu

Serge Smirnov

Yongguang Zhang

Alexander Mohr

Wei-ge Chen

Weidong Zhao

Tong L Wynn

Kishore Arvind Kotteri

Bharath Siravara

Anuj Kalia

Jayashree Sadagopan

Hui Gao

Chih-Lung Lin

Henrique Sarmento Malvar

Timothy Mark Moore

Nadim Y Abdo

Ran Kalach

Navin Chaddha

Cheng Huang

Tin Qian

Andrew Kadatch

Paul Adrian Oltean

Hua Chen

Hao Chen

Nelamangal Krishnaswamy Srinivas

Rajneesh Mahajan

Jiannan Zheng

Stacey Spears

Chuang Gu

William Chen

Abhishek Udupa

Keith W Ross

Chao Zhang

Yu Yan

Chun-Wei Chan

Benjamin Meister

John Bregar

Jay Thaler

Sayandeep Sen

Felix Livni

Manish Jain

Sourabh Jain

Radhika Jandhyala

Andy Precious

Ying-zong Huang

Di Xie

Tanner M Hodgeson

Anurekh Saxena

Abhinav Shrivastava

Vaibhav Pradeep Bhosale

Described are examples for monitoring performance metrics of one or more workloads in a cloud-computing environment and reallocating compute resources based on the monitoring. Reallocating compute resources can include migrating workloads among nodes or other resources in the cloud-computing environment, reallocating hardware accelerator resources, adjusting transmit power for virtual radio access network (vRAN) workloads, and/or the like.

Techniques for adaptively allocating resources in a cloud-computing environment

Described are examples for providing a standby workload to replace an active workload, including initializing a container for the standby workload that includes an entry point that points to a binary to be executed by the container, modifying the entry point of the container to execute a script that monitors a communication channel for an instruction for executing the standby workload, and instructing the standby workload to execute at least one of the binary or a different binary to replace the active workload.

Techniques for deploying workloads in a cloud-computing environment

A method for utilizing computing resources in a vRAN is described. A predicted resource load is determined for data traffic processing of wireless communication channels served by the vRAN using a trained neural network model. The data traffic processing comprises at least one of PHY data processing or MAC processing for a 5G RAN. Computing resources are allocated for the data traffic processing based on the predicted resource load. Wireless parameter limits are determined for the wireless communication channels that constrain utilization of the allocated computing resources using the trained neural network model, including setting one or more of a maximum number of radio resource units per timeslot or a maximum MCS index for the wireless parameter limits. The data traffic processing is performed using the wireless parameter limits to reduce load spikes that cause a violation of real-time deadlines for the data traffic processing.

Wireless parameter limits for predicted vRAN resource loads

Described are examples for providing fine-grained real-time pre-emption of codelets based on a runtime threshold. A controller inserts checkpoints into extended Berkeley packet filter (eBPF) bytecode of a third-party codelet prior to verification of the third-party codelet. A device executes the codelet at a hook point of an application. The inserted checkpoints determine a runtime of the codelet. The device terminates the codelet in response to the runtime exceeding a threshold. The application can be a virtualized radio access network (vRAN) network function and the codelet can control the vRAN function or export network metrics. The application may be executed in a container management system that modifies a container for the application to mount code including a function associated with the hook point of the application to the container; detect an annotation for the container that identifies the codelet; and symbolically links the codelet to the hook point.

Fine-grained real-time pre-emption of codelets based on runtime threshold

Described are examples for receiving, from one or more second virtual radio access network (vRAN) workloads operating one or more second cells, an indication of a measurement of at least a first signal transmitted by a first vRAN workload operating a first cell, computing, based on measurements of at least the first signal as received from the one or more second vRAN workloads, a boundary of the first cell, and adjusting, based on the boundary of the first cell, a transmit parameter of the first vRAN workload for transmitting signals in the first cell.

Techniques for adaptively determining cell boundary in wireless communications

A cloud-connected baseboard management controller (BMC) enables remote management of all management layers of edge-based host machines from the cloud without imposition of costs associated with firewalls and private data connections. A remote management agent incorporated into the BMC enables creation of a remote management-enabled bare-metal server paradigm in which remote management from the cloud is supported at the lowest hardware levels which provides for cost-effective utilization of network resources down to even a single isolated node.

Cloud-connected baseboard management controller

Described are examples for deploying workloads in a cloud-computing environment. In an aspect, based on a desired number of workloads of a process to be executed in a cloud-computing environment and based on one or more failure probabilities, an actual number of workloads of the process to execute in the cloud-computing environment to provide a level of service can be determined and deployed. In another aspect, a standby workload can be executed as a second instance of the process without at least a portion of the separate configuration used by the multiple workloads, and based on detecting termination of one of multiple workloads, the standby workload can be configured to execute based on the separate configuration of the separate instance of the process corresponding to the one of the multiple workloads.

Techniques for deploying workloads on nodes in a cloud-computing environment

Described are examples for overriding a library used by a workload in a cloud-computing environment including initializing a container for a workload that includes an entry point that points to a binary to be executed by the container, causing the workload to load, based on initializing the container, an override library into the container before executing the binary, where the override library includes an override function having a function signature of a function provided by the library, and instructing the workload to execute the binary in the container, where the binary calls the function using the function signature causing the override function in the override library to be called in place of the function.

Techniques for overriding libraries for workloads in a cloud-computing environment

Technologies are described for performing equation-based rate control using delay. For example, an observed network data rate and a network delay can be obtained for a network communication. A target network data rate can be calculated using the observed network data rate and the network delay. The target network data rate is calculated using an equation-based approach. For example, the equation-based rate control can set the target network data rate to a value that is directly proportional to the observed network data rate and inversely related to the network delay. The target network data rate is used to set the bitrate for the network communication.

Equation-based rate control using network delay for variable bitrate scenarios

Technologies are described for performing hybrid rate control that switches between a delay-based mode and a passive loss-based mode for a flow of network traffic. The switching can be performed based on the presence of loss-based TCP network flows. For example, rate control can be performed for a flow of network traffic in a delay-based mode. When the presence of a loss-based TCP network flow is detected, the flow of network traffic can be switched from the delay-based mode to a passive loss-based mode and rate control can be performed in the passive loss-based mode. When the loss-based TCP flow is no longer detected, the flow of network traffic can be switched back to the delay-based mode.

Delay based congestion control protocol co-existing with TCP

An audio decoder provides a combination of decoding components including components implementing base band decoding, spectral peak decoding, frequency extension decoding and channel extension decoding techniques. The audio decoder decodes a compressed bitstream structured by a bitstream syntax scheme to permit the various decoding components to extract the appropriate parameters for their respective decoding technique.

Bitstream syntax for multi-process audio decoding

Growing community of inventors

Kirkland, WA, United States of America

Sanjeev Mehrotra