Broadcom Corporation

Intel Corporation

Broadcom Israel Research, Ltd.

Avago Technologies International Sales Pte. Limited

Uri Elzur

Scott Sterling McDaniel

Frankie Fan

Steven B Lindsay

Patricia Ann Thaler

Hemal Vinodchandra Shah

Kan Frankie Fan

Eliezer Aloni

Mohan V Kalkunte

Shekhar Ambe

Shiri Kadambi

Daniel Talayco

Sandeep Kumar Relan

Martin Lund

Allan Christie

Mark Leonard Buer

Kobby Carmona

Dan G Wartski

Jeyhan Karaoguz

James D Bennett

Matthew James Fischer

Scott R Powell

Caitlin Bestler

Rafi Shalom

Joseph John Tardo

Predrag Kostic

Klaus Friedrich

Baiju V Patel

Yongbum Kim

Shay Mizrachi

Zheng Qi

Raj S Yavatkar

Yuval Bachrach

Amit Oren

Uri Tal

Bora Akyol

Dov Hirshfeld

Steve J Lindsay

Merav Sicron

Kan (Frankie) Fan

Charles Tai

Ford Tamer

Scott S Mcdaniel

Examples described herein relate to a first graphics processing unit (GPU) comprising at least one integrated network interface controller (NIC), wherein a data plane of the at least one integrated NIC is configured by a particular entity. In some examples, the data plane of the at least one integrated NIC is configured by the particular entity as a control plane but the first GPU and a central processing unit (CPU) are prevented from configuring the data plane of the at least one integrated NIC.

Graphics processing unit with network interfaces

Embodiments of the present disclosure may relate to an apparatus for infrastructure management with an interface to receive a plurality of telemetry signals from first one or more infrastructure components of an infrastructure; and a policy controlled semi-autonomous (PCSA) infrastructure evaluator coupled with the interface, where the PCSA infrastructure evaluator includes a machine-learning (ML) model of service level metric (SLM) deviation by second one or more application or infrastructure components of the infrastructure and the PCSA infrastructure evaluator is to: determine a deviation from a SLM of third one or more infrastructure components based at least in part the ML model and one or more of the plurality of telemetry signals; and send a message, based at least in part on the deviation from the SLM. Other embodiments may be described and/or claimed.

Policy controlled semi-autonomous infrastructure management

Disclosed are mechanisms to support integrating network semantics into communications between processor cores operating on the same server hardware. A network communications unit is implemented in a coherent domain with the processor cores. The network communications unit may be implemented on the CPU package, in one or more of the processor cores, and/or coupled via the coherent fabric. The processor cores and/or associated virtual entities communicate by transmitting packet headers via the network communications unit. When communicating locally compressed headers may be employed. The headers may omit specified fields and employ simplified addressing schemes for increased communication speed. When communicating locally, data can be moved between memory locations and/or pointers can be communicated to reduce bandwidth needed to transfer data. The network communications unit may maintain/access a local policy table containing rules governing communications between entities and enforce such rules accordingly.

Network semantics integrated into central processing unit (CPU) chipset

Technologies for zero-copy inter-virtual-machine communication include a computing device with extended page table support. A sender virtual machine stores data in a shared memory block and enables access to protected code without generating a virtual machine exit, for example by executing a specialized processor instruction. From the protected code, the sender virtual machine sets a permission in an extended page table associated with the shared memory block and notifies a receiver virtual machine. When the permission is set, the sender virtual machine is prohibited from writing or executing the contents of the shared memory block. The receiver virtual machine reads data from the shared memory block and then enables access to protected code without generating a virtual machine exit. From the protected code, the receiver virtual machine clears the permission and notifies the sender virtual machine that reading is complete. Other embodiments are described and claimed.

Technologies for zero-copy inter-virtual-machine data movement

An embodiment may include forwarding, at least in part, received traffic, based at least in part upon programming provided, at least in part, by at least one controller. The programming may be based at least in part upon at least one policy. The forwarding may be in accordance with various parameters, criteria, usage models, processing considerations, etc. Many modifications are possible.

Traffic forwarding for processing in network environment

Aspects of a method and system for traffic engineering in an IPSec secured network are provided. In this regard, a node in a network may be authenticated as a trusted third party and that trusted third party may be enabled to acquire security information shared between or among a plurality of network entities. In this manner, the trusted third party may parse, access and operate on IPSec encrypted traffic communicated between or among the plurality of network entities. Shared security information may comprise one or more session keys utilized for encrypting and/or decrypting the IPSec secured traffic. The node may parse IPSec traffic and identify a flow associated with the IPsec traffic. In this manner, the node may generate and/or communicate statistics pertaining to said IPSec secured traffic based on the flow with which the traffic is associated.

Method and system for traffic engineering in secured networks

Methods and systems for a plurality of physical layers for network connection may include coupling a MAC to one of a plurality of PHYs. The coupling to a specific PHY may be based on auto-detection of network activity, or network devices, via the PHYs. Also, one of the PHYs may be coupled to the MAC as a power-up default. The PHYs may be coupled to a same network, by, for example, cables. A first cable to a first PHY may couple it to a first network switch and a second cable to a second PHY may couple it to a second network switch. The first network switch may be rated to handle, for example, a greater data rate than the second network switch. The first cable may not be able to be used as a cable for the second PHY, and vice versa.

Method and system for a plurality of physical layers for network connection

In this embodiment, techniques are provided that may permit operations performed by hardware and software to process one or more (e.g., network traffic-related) workloads to be coordinated, at least in part. Such coordination may permit this embodiment to operate in accordance with one or more advantageous usage models, and/or to achieve advantages such as, accelerated network traffic processing, while permitting and/or facilitating a multi-tenant (e.g., software-defined) network environment to be provided, for example, via enforcement of one or more associated policies. Many modifications are possible without departing from this embodiment.

Traffic and/or workload processing

Aspects of a method and system for networking are provided. In this regard, one or more circuits and/or processors in a network adapter of a first network device may determine whether to communicate traffic between virtual machines running on the first network device via a path that resides solely within the first network device, or via a path that comprises a second network device that is external to the first network device. The determination may be based, at least in part, on characteristics of the traffic. The determination may be based, at least in part, on capabilities and/or available resources of the network adapter. The determination may be based, at least in part, on management information exchanged between the one or more circuits and/or processors and one or more of: software running on the first network device, the second network device, and a third network device.

Method and system for virtual machine networking

An embodiment may include policy engine circuitry that may enforce, at least in part, one or more platform resource management policies in a cloud computing environment. The one or more policies may be based, at least in part, upon service arrangements of the cloud computing environment. The one or more policies may establish respective isolated computing environments in the cloud computing environment that may be used by respective users. The enforcement of the one or more policies may result in the respective isolated computing environments being virtually isolated from each other and prevented from interfering with each other in derogation of the one or more policies. The one or more policies may be established, at least in part, via interaction of at least one management process with one or more application program interfaces of the circuitry. Many modifications are possible.

Policy enforcement in computing environment

Systems and methods that network interface in a multiple network environment are provided. In one embodiment, the system includes, for example, a network connector, a processor, a peripheral component interface (PCI) bridge and a unified driver. The processor may be coupled to the network connector and to the PCI bridge. The processor may be adapted, for example, to process a plurality of different types of network traffic. The unified driver may be coupled to the PCI bridge and may be adapted to provide drivers associated with the plurality of different types of network traffic.

System and method for network interfacing in a multiple network environment

A method for establishing a virtual channel between network devices is disclosed. In the case of a local network device establishing a virtual channel with a remote network device, a virtual channel request message is sent from the local network device to the remote network device. A virtual channel acknowledgement message and a remote capability list are received and a virtual channel resume message and a local capability list are sent. The virtual channel is then enabled. In the case of a remote network device establishing a virtual channel with a local network device, a virtual channel request message is received from a local network device by a remote network device. A virtual channel acknowledgement message and a remote capability list are sent and a virtual channel resume message and a local capability list are received. The virtual channel is then enabled.

Multiple logical channels for use in network devices

A local manager in a local networking domain may configure a plurality of logical switches by combining switching functions available in network devices and/or network switches in the local networking domain. The configuration may utilize vertical and/or horizontal combinations of the switching functions. The switching functions may comprise network switch-based switching functions, and/or hypervisor-level switching functions and/or network adapter-level switching functions available in network devices which may be configured as virtualized platforms. The local manager may provide interfacing services to enable exposing configured logical switches. The interfacing services may comprise an internal interface, which may be utilized, via the local manager, to control the switching functions corresponding to logical switches and/or to route messages sent to and/or from the logical switches. The interfacing services may also comprise an external interface, which may be used by external entities, such as remote management entities, to manage and/or interact with configured logical switches.

Method and system for switching in a virtualized platform

Growing community of inventors

Irvine, CA, United States of America

Uri Elzur