Abstract: A program product for processing a request for a state of a resource in a distributed processing environment may in general terms comprise receiving an identification of a resource, and identifying a provider associated with an indicator of states of the resource. The program product may further comprise obtaining the state of the resource. The state may be obtained by observing the state in memory shared with the indicator, or by retrieving the state from memory in which the state is contained, or by requesting and receiving the state from a remote provider, depending upon the particular resource.

Abstract: An adapter card in a computer system includes an application specific integrated circuit (ASIC) and a field programmable gate array (FPGA) coupled to the ASIC. Random data is provided to the ASIC logic function(s) by control of the FPGA, which is configured by a programmable logic device on the card and coupled thereto. The logic function(s) of the ASIC is then exercised with the random data, and the output is compared with expected output by the system to determine if there are any errors. The determination is made based on a signature produced by a multiple input shift register (MISR) within the ASIC, based on the output data from the logic function(s). The FPGA can then be reconfigured for normal adapter card functions.

Abstract: In a distributed computing environment having a plurality of groups of processors, each processor group maintains its own set of ordered messages. A message is sent to a group of processors. In particular, a request to multicast a message is sent to a leader of the group of processors, i.e., a group leader, and the group leader assigns a sequence number to the message to be sent, thereby providing an ordered message. Then, the group leader multicasts the ordered message to the group of processors. When the processors of the group receive the ordered message, each determines whether the message is in proper sequence order. If the message is out of order for a particular processor indicating that a message has been missed, then that particular processor requests the missing message from a processor within the group.

Abstract: System managing membership of a group of processors in a distributed computing environment. Specific actions are identified and performed in order to manage the group membership. A processor requests to join the group of processors and thus, is added to the group. Similarly, processors may request to leave the group or may fail and then are removed from the group. The group of members also receives multicasts initiated from one member of the group to other members of the group. Additionally, each group of processors within a distributed computing environment has a group leader that controls the actions being performed for the group of members.

Abstract: A system for processing a request for a state of a resource in a distributed processing environment may in general terms comprise receiving an identification of a resource, and identifying a provider associated with an indicator of states of the resource. The system may further comprise obtaining the state of the resource. The state may be obtained by observing the state in memory shared with the indicator, or by retrieving the state from memory in which the state is contained, or by requesting and receiving the state from a remote provider, depending upon the particular resource.

Abstract: In a distributed computing environment having a plurality of groups of processors, each processor group maintains its own set of ordered messages. A message is sent to a group of processors. In particular, a request to multicast a message is sent to a leader of the group of processors, i.e., a group leader, and the group leader assigns a sequence number to the message to be sent, thereby providing an ordered message. Then, the group leader multicasts the ordered message to the group of processors. When the processors of the group receive the ordered message, each determines whether the message is in proper sequence order. If the message is out of order for a particular processor indicating that a message has been missed, then that particular processor requests the missing message from a processor within the group.

Abstract: Membership of a group of processors in a distributed computing environment is managed. Specific actions are identified and performed in order to manage the group membership. A processor requests to join the group of processors and thus, is added to the group. Similarly, processors may request to leave the group or may fail and then are removed from the group. The group of members also receives multicasts initiated from one member of the group to other members of the group. Additionally, each group of processors within a distributed computing environment has a group leader that controls the actions being performed for the group of members.

Abstract: Program product for managing membership of a group of processors in a distributed computing environment. Specific actions are identified and performed in order to manage the group membership. A processor requests to join the group of processors and thus, is added to the group. Similarly, processors may request to leave the group or may fail and then are removed from the group. The group of members also receives multicasts initiated from one member of the group to other members of the group. Additionally, each group of processors within a distributed computing environment has a group leader that controls the actions being performed for the group of members.

Abstract: A method for processing a request for a state of a resource in a distributed processing environment may in general terms comprise receiving an identification of a resource, and identifying a provider associated with an indicator of states of the resource. The method may further comprise obtaining the state of the resource. The state may be obtained by observing the state in memory shared with the indicator, or by retrieving the state from memory in which the state is contained, or by requesting and receiving the state from a remote provider, depending upon the particular resource.

Abstract: A method of processing a request for notice of occurrence of an event in a distributed processing environment may in general terms comprise receiving a request for notice of occurrence of an event, the request including an identification of a resource in which the will occur, and identifying a monitor associated with an indicator of states of the resource. The method may further comprise obtaining indication of the event. The state characterizing the event may be received from the client or may be a default value. Indication of the event may be obtained by receiving state values and determining if they indicate the event, or periodically monitoring the indicator for occurrence of the event, or requesting monitoring from a monitor associated with the indicator.

Abstract: A barrier synchronization technique in a distributed computing environment. A group of members, including a plurality of related processes executing on one or more processors of the distributed computing environment, is provided a protocol having a dynamic number of synchronization phases. The protocol is voted on by one or more members of the group to determine how the protocol should proceed for the group of members. The protocol may complete successfully, continue to another synchronization phase or be rejected. The group of members determines how many synchronization phases the protocol is to include.

Abstract: In a distributed computing environment having a plurality of groups of processors, each processor group maintains its own set of ordered messages. A message is sent to a group of processors. In particular, a request to multicast a message is sent to a leader of the group of processors, i.e., a group leader, and the group leader assigns a sequence number to the message to be sent, thereby providing an ordered message. Then, the group leader multicasts the ordered message to the group of processors. When the processors of the group receive the ordered message, each determines whether the message is in proper sequence order. If the message is out of order for a particular processor indicating that a message has been missed, then that particular processor requests the missing message from a processor within the group.

Abstract: In a multi-processor parallel processing computer environment different communication modes are available for performing an information distribution operation (e.g., a broadcast) between processors. The technique comprises automatically selecting an optimal communications mode at operation run-time. The selection decision utilizes hardware parameters of the system (e.g., communication speed between processors) and run-time parameters (e.g., number of nodes to broadcast a message to). The communication mode selection decision seeks to optimize factors such as time required to execute or work space requirements of the distribution operation.

Abstract: A method and system for synchronizing allocation of resources in a parallel processing system. At predefined time intervals, each user application executing in a parallel processing system is given a higher priority such that the system resources are allocated to the user applications instead of the operating system services. This high priority lasts for a predetermined amount of time. When the time has elapsed, each priority value is lowered, thus giving the operating system services an opportunity to execute.

Abstract: A method and system for pipelining the processing of channel command words is provided. The channel is permitted to send commands and data to the control unit for several channel command words associated with a channel program without having to wait for responses from the control unit for prior commands sent. The channel can pipeline several commands to the control unit and the control unit can then process the commands in the order it receives them. The control unit sends responses to the channel for each command it receives acknowledging receipt of the commands.