Robert S. Blackmore

EFFICIENT PIPELINING OF RDMA FOR COMMUNICATIONS

User level message broadcast mechanism in distributed computing environment

Interrupt handling using simultaneous multi-threading

Facilitating intra-node data transfer in collective communications, and methods therefor

Guaranteeing delivery of multi-packet GSM messages

Mechanism to provide software guaranteed reliability for GSM operations

Mechanisms to order global shared memory operations

Generating and issuing global shared memory operations via a send FIFO

Mechanism to prevent illegal access to task address space by unauthorized tasks

Notification to task of completion of GSM operations by initiator node

Notification by task of completion of GSM operations at target node

Mechanism to perform debugging of global shared memory (GSM) operations

Termination of in-flight asynchronous memory move

Completion of asynchronous memory move in the presence of a barrier operation

Asynchronous memory move across physical nodes with dual-sided communication

Launching multiple concurrent memory moves via a fully asynchronoous memory mover

Handling of address conflicts during asynchronous memory move operations

Mechanisms for communicating with an asynchronous memory mover to perform AMM operations

Reporting of partially performed memory move

Performing an asynchronous memory move (AMM) via execution of AMM store instruction within the instruction set architecture

Fully asynchronous memory mover

Host fabric interface (HFI) to perform global shared memory (GSM) operations

Specialized memory move barrier operations

Method for enabling direct prefetching of data during asychronous memory move operation

Cache management during asynchronous memory move operations

Issuing global shared memory operations via direct cache injection to a host fabric interface

Mechanism to provide reliability through packet drop detection

Allocating a global shared memory

Reserving a global address space

System and program product to recover from node failure/recovery incidents in distributed systems in which notification does not occur

Method to recover from node failure/recovery incidents in distributed systems in which notification does not occur

Interrupt handling using simultaneous multi-threading

Memory sharing in a distributed data processing system using modified address space to create extended address space for copying data

Mechanisms for efficient message passing with copy avoidance in a distributed system using advanced network devices

Method and system for efficiently transferring a self-defined non-contiguous message in a one-sided communication model

Facilitating intra-node data transfer in collective communications

Remote direct memory access with striping over an unreliable datagram transport

Interface method, system, and program product for facilitating layering of a data communications protocol over an active message layer protocol

Lazy deregistration of user virtual machine to adapter protocol virtual offsets

RDMA server (OSI) global TCE tables

Early interrupt notification in RDMA and in DMA operations

Half RDMA and half FIFO operations

Failover mechanisms in RDMA operations

Sharing lock mechanism between protocol layers