Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Low latency, high bandwidth data communications between compute nodes in a parallel computer

Patent ·
OSTI ID:1086680
Methods, systems, and products are disclosed for data transfers between nodes in a parallel computer that include: receiving, by an origin DMA on an origin node, a buffer identifier for a buffer containing data for transfer to a target node; sending, by the origin DMA to the target node, a RTS message; transferring, by the origin DMA, a data portion to the target node using a memory FIFO operation that specifies one end of the buffer from which to begin transferring the data; receiving, by the origin DMA, an acknowledgement of the RTS message from the target node; and transferring, by the origin DMA in response to receiving the acknowledgement, any remaining data portion to the target node using a direct put operation that specifies the other end of the buffer from which to begin transferring the data, including initiating the direct put operation without invoking an origin processing core.
Research Organization:
International Business Machines Corporation (Armonk, NY)
Sponsoring Organization:
USDOE
Assignee:
International Business Machines Corporation (Armonk, NY)
Patent Number(s):
8,478,834
Application Number:
11/776,718
OSTI ID:
1086680
Country of Publication:
United States
Language:
English

References (4)

The impact of MPI queue usage on message latency conference January 2004
An analysis of NIC resource usage for offloading MPI conference January 2004
The Blue Gene/L Supercomputer: A Hardware and Software Story journal May 2007
A Hardware Acceleration Unit for MPI Queue Processing conference January 2005

Similar Records

Related Subjects