Abstract: Methods and composition are provided for deriving cement and/or supplementary cementitious materials, such as pozzolans, from one or more non-limestone materials, such as one or more non-limestone rocks and/or minerals. The non-limestone materials, e.g., non-limestone rocks and/or minerals, are processed in a manner that a desired product, e.g., cement and/or supplementary cementitious material, is produced.

Abstract: Methods and apparatus for software-controlled active-backup mode of link aggregation for RDMA and virtual functions. A Network Interface Controller (NIC) includes hardware implementing first and second physical functions (PFs) including transmit and receive resources to support data transfers via first and second ports. A bonding group is created with the first and second PFs. The first PF as an active PF and used for primary data transfers while implementing the second PF as a backup PF. On a link or port failure of the active PF, the bonding group is reconfigured to employ transmit and receive resources of the backup PF such that those resources are shared with the active PF. Data transfers are then performed using the shared resources of the active PF and the backup PF. Embodiments may support RDMA data transfers using PF bonding and the solution may be implemented in virtualized environments including virtual machines (VMs) in a manner transparent to the VMs.

Abstract: Methods and composition are provided for deriving cement and/or supplementary cementitious materials, such as pozzolans, from one or more non-limestone materials, such as one or more non-limestone rocks and/or minerals. The non-limestone materials, e.g., non-limestone rocks and/or minerals, are processed in a manner that a desired product, e.g., cement and/or supplementary cementitious material, is produced.

Abstract: Techniques for maintaining service continuity in a 5G NR network in communication with a MEC system and an edge application (EDGEAPP) system are disclosed. A notification message originating from a service management function (SMF) of a core network (CN) is decoded at a network exposure function (NEF) of the CN. The notification message includes a UE IP address change of a UE. A private IP address of the UE is determined based on the UE IP address change. A query with the private IP address is encoded for transmission to a NAT server. A response from the NAT server is decoded. The response includes a public IP address and a UE ID of the UE. The public IP address corresponds to the private IP address. A tuple including the UE ID, the public IP address, and the private IP address is generated at the NEF.

Abstract: Examples described herein relate to a switch comprising circuitry configured to for packet communications associated with a collective operation to train machine learning (ML) models: utilize a reliable transport protocol for communications from at least one worker node of the collective operation to a switch, wherein the utilize a reliable transport protocol for communications from at least one worker node of the collective operation to the switch comprises store packet receipt state for per-packet communications from the at least one worker node of the collective operation to the switch and utilize a non-reliable transport protocol by the switch to a device that is to perform aggregation of results, wherein the reliable transport protocol comprises a different protocol than that of the non-reliable transport protocol.

Abstract: Methods and composition are provided for deriving cement and/or supplementary cementitious materials, such as pozzolans, from one or more non-limestone materials, such as one or more non-limestone rocks and/or minerals. The non-limestone materials, e.g., non-limestone rocks and/or minerals, are processed in a manner that a desired product, e.g., cement and/or supplementary cementitious material, is produced.

Abstract: Automatic server configuration by a switch may include determining, by a firmware interface application of the switch, a configuration pattern for a plurality of servers; generating, by a network caching application of the switch, a network cache; receiving, based on the configuration pattern, a solution stack; storing the solution stack in the network cache; and providing, from the network cache, the solution stack to the plurality of servers.

Abstract: Methods and apparatus for software-controlled active-backup mode of link aggregation for RDMA and virtual functions. A Network Interface Controller (NIC) includes hardware implementing first and second physical functions (PFs) including transmit and receive resources to support data transfers via first and second ports. A bonding group is created with the first and second PFs. The first PF as an active PF and used for primary data transfers while implementing the second PF as a backup PF. On a link or port failure of the active PF, the bonding group is reconfigured to employ transmit and receive resources of the backup PF such that those resources are shared with the active PF. Data transfers are then performed using the shared resources of the active PF and the backup PF. Embodiments may support RDMA data transfers using PF bonding and the solution may be implemented in virtualized environments including virtual machines (VMs) in a manner transparent to the VMs.

Abstract: Automatic server configuration by a switch may include determining, by a firmware interface application of the switch, a configuration pattern for a plurality of servers; generating, by a network caching application of the switch, a network cache; receiving, based on the configuration pattern, a solution stack; storing the solution stack in the network cache; and providing, from the network cache, the solution stack to the plurality of servers.

Abstract: There are provided a transparent performance enhancing proxy, a method for operating a transparent performance enhancing proxy between a source device and a destination device, and corresponding computer program product. The method includes preserving, without translation, packet header information of a header for a packet received from the source device to be forwarded to the destination device. The method further includes during a transmission control protocol connection setup phase for the packet, preserving transmission control protocol connection semantics. The method also includes during a transmission control protocol data transfer phase for the packet, running a transmission control protocol by masquerading as the source device to the destination device and masquerading as the destination device to the source device to transmit the packet to the destination device with the preserved packet header information.

Abstract: There are provided a transparent performance enhancing proxy, a method for operating a transparent performance enhancing proxy between a source device and a destination device, and corresponding computer program product. The method includes preserving, without translation, packet header information of a header for a packet received from the source device to be forwarded to the destination device. The method further includes during a transmission control protocol connection setup phase for the packet, preserving transmission control protocol connection semantics. The method also includes during a transmission control protocol data transfer phase for the packet, running a transmission control protocol by masquerading as the source device to the destination device and masquerading as the destination device to the source device to transmit the packet to the destination device with the preserved packet header information.

Abstract: In one embodiment, a method includes detecting that a processor is attempting to boot a server using a network boot option over a first network. The method also includes receiving a network address, using the processor, from an integrated management module (IMM) connected to the processor via a local connection without using a dynamic host configuration protocol (DHCP) server on the first network. In another embodiment, a computer program product includes a computer readable program medium. The computer readable program medium includes program instructions configured to cause a processor in an IMM to intercept a network boot option initiated by a server over a first network and acquire a network address for the server without using a DHCP in the first network. The IMM is connected to the server via a local connection. Other methods, systems, and computer program products are described according to more embodiments.

Abstract: There are provided a transparent performance enhancing proxy, a method for operating a transparent performance enhancing proxy between a source device and a destination device, and corresponding computer program product. The method includes preserving, without translation, packet header information of a header for a packet received from the source device to be forwarded to the destination device. The method further includes during a transmission control protocol connection setup phase for the packet, preserving transmission control protocol connection semantics. The method also includes during a transmission control protocol data transfer phase for the packet, running a transmission control protocol by masquerading as the source device to the destination device and masquerading as the destination device to the source device to transmit the packet to the destination device with the preserved packet header information.

Abstract: A virtual switch connected to at least one virtual machine of multiple virtual machines communicatively connected through an overlay network, receives a data packet, each of the virtual machines configured within a separate one of multiple virtual groups in the overlay network, the data packet comprising a packet header comprising at least one address. The virtual switch receives a virtual group identifier for the at least one address from at least one address resolution service returning the virtual group identifier and a resolved address for the at least one address, in response to an address resolution request for the at least one address. The virtual switch sends the data packet through the virtual switch to the resolved address only if the virtual group identifier is allowed according to a filtering policy applied by the virtual switch for a particular virtual group identified by the virtual group identifier.

Abstract: Methods may provide peak load processing on a computer system. A method may include receiving at a remote computer system a request from a local computer system, coupled to the remote computer system by a network, to replicate at the remote computer system a local instance of an application executing on the local computer system that is subject to user requests received at the local computer system. The method may further include replicating on the remote computer system a remote instance of the application and redirecting user requests from the local computer system to the remote computer system. The method may further include executing on the remote computer system the remote instance of the application, including processing with the remote instance of the application user requests redirected from the local computer system to the remote instance of the application.

Abstract: Systems and computer program products may provide peak load processing on a computer system. A first computer system may include a processor and a memory storage device operatively coupled to the processor. The memory storage device may store instructions that are executed by the processor to receive from a second computer system coupled to the first computer system by a network, a request to replicate at the first computer system a first instance of an application executing on the second computer system, replicate on the first computer system the first instance of the application and execute the first instance of the application on the first computer system, including processing user requests related to the application received from the second computer system.

Abstract: In one embodiment, a method includes detecting that a processor is attempting to boot a server using a network boot option over a first network. The method also includes receiving a network address, using the processor, from an integrated management module (IMM) connected to the processor via a local connection without using a dynamic host configuration protocol (DHCP) server on the first network. In another embodiment, a computer program product includes a computer readable program medium. The computer readable program medium includes program instructions configured to cause a processor in an IMM to intercept a network boot option initiated by a server over a first network and acquire a network address for the server without using a DHCP in the first network. The IMM is connected to the server via a local connection. Other methods, systems, and computer program products are described according to more embodiments.

Abstract: A system, method and computer program product for implementing network connection failover during application service interruption. While the application is quiesced, a network socket that terminates a network connection to a network peer is maintained on behalf of the application. The socket's network connection state information is sustained by providing acknowledgements of incoming network traffic to the network peer that prevent the peer from terminating the connection. Upon restart, the application is brought up with a blocked socket. The state of the blocked socket is conformed to a current network connection state of the original socket and the blocked socket is unblocked.

Abstract: There are provided a transparent performance enhancing proxy, a method for operating a transparent performance enhancing proxy between a source device and a destination device, and corresponding computer program product. The method includes preserving, without translation, packet header information of a header for a packet received from the source device to be forwarded to the destination device. The method further includes during a transmission control protocol connection setup phase for the packet, preserving transmission control protocol connection semantics. The method also includes during a transmission control protocol data transfer phase for the packet, running a transmission control protocol by masquerading as the source device to the destination device and masquerading as the destination device to the source device to transmit the packet to the destination device with the preserved packet header information.

Abstract: There are provided a transparent performance enhancing proxy, a method for operating a transparent performance enhancing proxy between a source device and a destination device, and corresponding computer program product. The method includes preserving, without translation, packet header information of a header for a packet received from the source device to be forwarded to the destination device. The method further includes during a transmission control protocol connection setup phase for the packet, preserving transmission control protocol connection semantics. The method also includes during a transmission control protocol data transfer phase for the packet, running a transmission control protocol by masquerading as the source device to the destination device and masquerading as the destination device to the source device to transmit the packet to the destination device with the preserved packet header information.