Technologies for providing streamlined provisioning of accelerated functions in a disaggregated architecture include a compute sled. The compute sled includes a network interface controller and circuitry to determine whether to accelerate a function of a workload executed by the compute sled, and send, to a memory sled and in response to a determination to accelerate the function, a data set on which the function is to operate. The circuitry is also to receive, from the memory sled, a service identifier indicative of a memory location independent handle for data associated with the function, send, to a compute device, a request to schedule acceleration of the function on the data set, receive a notification of completion of the acceleration of the function, and obtain, in response to receipt of the notification and using the service identifier, a resultant data set from the memory sled. The resultant data set was produced by an accelerator device during acceleration of the function on the data set. Other embodiments are also described and claimed.

Technologies for providing streamlined provisioning of accelerated functions in a disaggregated architecture include a compute sled. The compute sled includes a network interface controller and circuitry to determine whether to accelerate a function of a workload executed by the compute sled, and send, to a memory sled and in response to a determination to accelerate the function, a data set on which the function is to operate. The circuitry is also to receive, from the memory sled, a service identifier indicative of a memory location independent handle for data associated with the function, send, to a compute device, a request to schedule acceleration of the function on the data set, receive a notification of completion of the acceleration of the function, and obtain, in response to receipt of the notification and using the service identifier, a resultant data set from the memory sled. The resultant data set was produced by an accelerator device during acceleration of the function on the data set. Other embodiments are also described and claimed.

Datalink frames or networking packets contain protocol information in the header and optionally in the trailer of a frame or a packet. We are proposing a method in which part of or all of the protocol information corresponding to a frame or a packet is transmitted separately in another datalink frame. The “Separately Transmitted Protocol Information” is referred to as STPI. The STPI contains enough protocol information to identify the next hop node or port. STPI can be used avoid network congestion and improve link efficiency. Preferably, there will be one datalink frame or network packet corresponding to each STPI, containing the data and the rest of the protocol information and this frame/packet is referred to as DFoNP. The creation of STPI and DFoNP is done by the originator of the frame or packet such as an operating system.

Datalink frames or networking packets contain protocol information in the header and optionally in the trailer of a frame or a packet. We are proposing a method in which part of or all of the protocol information corresponding to a frame or a packet is transmitted separately in another datalink frame. The “Separately Transmitted Protocol Information” is referred to as STPI. The STPI contains enough protocol information to identify the next hop node or port. STPI can be used avoid network congestion and improve link efficiency. Preferably, there will be one datalink frame or network packet corresponding to each STPI, containing the data and the rest of the protocol information and this frame/packet is referred to as DFoNP. The creation of STPI and DFoNP is done by the originator of the frame or packet such as an operating system.

A method is described that comprises collecting communication data travelling among a plurality of computing nodes in a networked environment. The method includes using the communication data to create a plurality of connectivity records, wherein each connectivity record comprises a communication between a source computing node and a destination computing node of the plurality of computing nodes. The method includes associating the communication with an application context and protocol. The method includes processing the plurality of connectivity records to eliminate connectivity records that meet at least one criteria, wherein the plurality of connectivity records includes associated application contexts and protocols, wherein a first portion of the plurality of connectivity records comprises the eliminated connectivity records, wherein a second portion of the plurality of connectivity records comprises the remainder of the connectivity records. The method includes building a graph using the second portion of the connectivity records.

A method is described that comprises collecting communication data travelling among a plurality of computing nodes in a networked environment. The method includes using the communication data to create a plurality of connectivity records, wherein each connectivity record comprises a communication between a source computing node and a destination computing node of the plurality of computing nodes. The method includes associating the communication with an application context and protocol. The method includes processing the plurality of connectivity records to eliminate connectivity records that meet at least one criteria, wherein the plurality of connectivity records includes associated application contexts and protocols, wherein a first portion of the plurality of connectivity records comprises the eliminated connectivity records, wherein a second portion of the plurality of connectivity records comprises the remainder of the connectivity records. The method includes building a graph using the second portion of the connectivity records.

If the sequence of a traffic of a first communication link from a communication apparatus to another communication apparatus includes a traffic of a second communication link from that another communication apparatus to a communication apparatus, latency is reduced, thereby saving processing time. If, after data is transmitted from a communication apparatus to another communication apparatus by the upper layer, a data receive response signal is required from that another communication apparatus to the communication apparatus, a predetermined frame including transmission grant information for that another communication apparatus to transmit the receive response signal and data is generated in the communication apparatus. The communication apparatus transmits this generated frame to that another communication apparatus. That is, data and transmission grant information are transmitted from the communication apparatus to that another communication apparatus as a predetermined frame.

If the sequence of a traffic of a first communication link from a communication apparatus to another communication apparatus includes a traffic of a second communication link from that another communication apparatus to a communication apparatus, latency is reduced, thereby saving processing time. If, after data is transmitted from a communication apparatus to another communication apparatus by the upper layer, a data receive response signal is required from that another communication apparatus to the communication apparatus, a predetermined frame including transmission grant information for that another communication apparatus to transmit the receive response signal and data is generated in the communication apparatus. The communication apparatus transmits this generated frame to that another communication apparatus. That is, data and transmission grant information are transmitted from the communication apparatus to that another communication apparatus as a predetermined frame.

Data is received at a buffer used by a protocol processing stack which protocol processes the received data. The received data is made available to, for example, an application, before the protocol processing of the data is complete. If the protocol processing is successful, the data made available to the application is committed.

Data is received at a buffer used by a protocol processing stack which protocol processes the received data. The received data is made available to, for example, an application, before the protocol processing of the data is complete. If the protocol processing is successful, the data made available to the application is committed.