US 12,170,625 B2
Buffer allocation for parallel processing of data by message passing interface (MPI)
Todd Rimmer, Exton, PA (US); Sayantan Sur, Portland, OR (US); and Michael William Heinz, Phoenixville, PA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Jul. 30, 2020, as Appl. No. 16/944,072.
Prior Publication US 2020/0358721 A1, Nov. 12, 2020
Int. Cl. H04L 12/54 (2022.01); G06F 15/173 (2006.01); H04L 49/90 (2022.01); H04L 49/9047 (2022.01)
CPC H04L 49/9047 (2013.01) [G06F 15/17331 (2013.01); H04L 49/9068 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a network interface device, an allocation of a first group of one or more buffers to store data to be processed by a Message Passing Interface (MPI);
based on a received packet including a command that causes the network interface device to select a buffer for the received packet and store the received packet in the selected buffer, the network interface device storing a portion of the received packet in a buffer of the first group of the one or more buffers to be processed by the MPI;
receiving, at the network interface device, an allocation of a second group of one or more buffers to store data to be processed by the MPI; and
based on a second received packet including an indicator that indicates to store the second received packet in a buffer based on a tag and source associated with the second received packet, the network interface device storing a portion of the second received packet in a buffer of the second group of one or more buffers, wherein the buffer of the second group of one or more buffers corresponds to the tag and source associated with the second received packet.