Abstract: Methods, systems and products are provided for relevant alert delivery with event and alert suppression including identifying by the event analyzer in dependence upon the event arrival rules one or more alerts; closing, by the event analyzer in dependence upon the events pool operation rules, the events pool; determining, by the events analyzer in dependence upon the event suppression rules, whether to suppress one or more events in the closed events pool; identifying by the event analyzer in dependence upon the events pool closure rules and any unsuppressed events assigned to the events pool, one or more additional alerts; assigning by the alert analyzer the identified alerts to an alerts pool; determining by the alert analyzer in dependence upon alert analysis rules and the alerts in the alert pool whether to suppress any alerts; and transmitting the unsuppressed alerts to one or more components of the distributed processing system.

Abstract: Data processing in a hybrid computing environment that includes a host computer and an accelerator, the host and the accelerator adapted to one another for data communications by a system level message passing module and a plurality data communications fabrics of at least two different fabric types, the data processing including: monitoring data communications performance for a plurality of data communications modes; receiving, from an application program on the host computer, a request to transmit data according to a data communications mode from the host computer to the accelerator; determining, in dependence upon the monitored performance, whether to transmit the data according to the requested data communications mode; and if the data is not to be transmitted according to the requested data communications mode: selecting, in dependence upon the monitored performance, another data communications mode for transmitting the data and transmitting the data according to the selected data communications mode.

Abstract: A method, apparatus, and program product checkpoint an application in a parallel computing system of the type that includes a plurality of hybrid nodes. Each hybrid node includes a host element and a plurality of accelerator elements. Each host element may include at least one multithreaded processor, and each accelerator element may include at least one multi-element processor. In a first hybrid node from among the plurality of hybrid nodes, checkpointing the application includes executing at least a portion of the application in the host element and at least one accelerator element and, in response to receiving a command to checkpoint the application, checkpointing the host element separately from the at least one accelerator element.

Abstract: Optimizing collective operations including receiving an instruction to perform a collective operation type; selecting an optimized collective operation for the collective operation type; performing the selected optimized collective operation; determining whether a resource needed by the one or more nodes to perform the collective operation is not available; if a resource needed by the one or more nodes to perform the collective operation is not available: notifying the other nodes that the resource is not available; selecting a next optimized collective operation; and performing the next optimized collective operation.

Abstract: A hybrid computing environment in which the host computer allocates, in the shadow memory area of the host computer, a memory region for a packet to be written to the shared memory of an accelerator; writes packet data to the accelerator's shared memory in a memory region corresponding to the allocated memory region; inserts, in a next available element of the accelerator's descriptor array, a descriptor identifying the written packet data; increments the copy of the head pointer of the accelerator's descriptor array maintained on the host computer; and updates a copy of the head pointer of the accelerator's descriptor array maintained on the accelerator with the incremented copy.

Abstract: In a distributed computing system including a nodes organized for collective operations: initiating, by a root node through an active message to all other nodes, a collective operation, the active message including an instruction to each node to store operating parameter data in each node's send buffer; and, responsive to the active message: storing, by each node, the node's operating parameter data in the node's send buffer and returning, by the node, the operating parameter data as a result of the collective operation.

Abstract: Sending, by a node requesting information regarding a resource to one or more nodes in a distributed computing system, an active message to perform a collective operation; contributing, by each node not having a resource, a value of zero to the collective operation; contributing, by a node having the resource, the node's rank; storing the result of the collective operation in a buffer of the requesting node; and identifying, in dependence upon the result of the collective operation, the rank of the node having the resource.

Abstract: Controlling access to a resource in a distributed computing system that includes nodes having a status field, a next field, a source data buffer, and that are characterized by a unique node identifier, where controlling access includes receiving a request for access to the resource implemented as an active message that includes the requesting node's unique node identifier, the value stored in the requesting node's source data buffer, and an instruction to perform a reduction operation with the value stored in the requesting node's source data buffer and the value stored in the receiving node's source data buffer; returning the requesting node's unique node identifier as a result of the reduction operation; and updating the status and next fields to identify the requesting node as a next node to have sole access to the resource.

Abstract: Creating, by a parent master process of a parent communicator, a child communicator, including configuring the child communicator with a child master process, wherein a communicator includes a collection of one or more processes executing on compute nodes of a distributed computing system; determining, by the parent master process, whether a unique identifier is available to assign to the child communicator; if a unique identifier is available to assign to the child communicator, assigning, by the parent master process, the available unique identifier to the child communicator; and if a unique identifier is not available to assign to the child communicator: retrieving, by the parent master process, an available unique identifier from a master process of another communicator in a tree of communicators and assigning the retrieved unique identifier to the child communicator.

Abstract: Methods, apparatus, and products for broadcasting data in a hybrid computing environment that includes a host computer, a number of accelerators, the host computer and the accelerators adapted to one another for data communications by a system level message passing module, the host computer having local memory shared remotely with the accelerators, the accelerators having local memory for the accelerators shared remotely with the host computer, where broadcasting data according to embodiments of the present invention includes: writing, by the host computer remotely to the shared local memory for the accelerators, the data to be broadcast; reading, by each of the accelerators from the shared local memory for the accelerators, the data; and notifying the host computer, by the accelerators, that the accelerators have read the data.

Abstract: Terminating an accelerator application program in a hybrid computing environment that includes a host computer having a host computer architecture and an accelerator having an accelerator architecture, where the host computer and the accelerator are adapted to one another for data communications by a system level message passing module (‘SLMPM’), and terminating an accelerator application program in a hybrid computing environment includes receiving, by the SLMPM from a host application executing on the host computer, a request to terminate an accelerator application program executing on the accelerator; terminating, by the SLMPM, execution of the accelerator application program; returning, by the SLMPM to the host application, a signal indicating that execution of the accelerator application program was terminated; and performing, by the SLMPM, a cleanup of the execution environment associated with the terminated accelerator application program.

Abstract: Reducing remote reads of memory in a hybrid computing environment by maintaining remote memory values locally, the hybrid computing environment including a host computer and a plurality of accelerators, the host computer and the accelerators each having local memory shared remotely with the other, including writing to the shared memory of the host computer packets of data representing changes in accelerator memory values, incrementing, in local memory and in remote shared memory on the host computer, a counter value representing the total number of packets written to the host computer, reading by the host computer from the shared memory in the host computer the written data packets, moving the read data to application memory, and incrementing, in both local memory and in remote shared memory on the accelerator, a counter value representing the total number of packets read by the host computer.

Abstract: A method, apparatus, and program product checkpoint an application in a parallel computing system of the type that includes a plurality of hybrid nodes. Each hybrid node includes a host element and a plurality of accelerator elements. Each host element may include at least one multithreaded processor, and each accelerator element may include at least one multi-element processor. In a first hybrid node from among the plurality of hybrid nodes, checkpointing the application includes executing at least a portion of the application in the host element, configuring and executing at least one computation kernel in at least one accelerator element, and, in response to receiving a command to checkpoint the application, checkpointing the host element separately from the at least one accelerator element upon which the at least one computation kernel is executing.

Abstract: Methods, apparatus, and products for broadcasting data in a hybrid computing environment that includes a host computer, a number of accelerators, the host computer and the accelerators adapted to one another for data communications by a system level message passing module, the host computer having local memory shared remotely with the accelerators, the accelerators having local memory for the accelerators shared remotely with the host computer, where broadcasting data according to embodiments of the present invention includes: writing, by the host computer remotely to the shared local memory for the accelerators, the data to be broadcast; reading, by each of the accelerators from the shared local memory for the accelerators, the data; and notifying the host computer, by the accelerators, that the accelerators have read the data.

Abstract: Software development for a hybrid computing environment that includes a host computer and an accelerator, the host computer and the accelerator adapted to one another for data communications by a system level message passing module and by two or more data communications fabrics of at least two different fabric types where software development includes creating, by a programmer, a computer program for execution in the hybrid computing environment, the computer program including directives for generation of computer program code that moves contents of memory among host computers and accelerators in the hybrid computing environment; generating, by a code generator application, source code in accordance with the directives; analyzing, by the code generator application, operation of the generated code for data movement and utilization of moved data; and regenerating, by the code generator application, the source code in accordance with the directives and further in accordance with results of the analysis.

Abstract: Data processing in a hybrid computing environment that includes a host computer, a plurality of accelerators, the host computer and the accelerators adapted to one another for data communications by a system level message passing module, the host computer having local memory shared remotely with the accelerators, the accelerators having local memory for the plurality of accelerators shared remotely with the host computer, where data processing according to embodiments of the present invention includes performing, by the plurality of accelerators, a local reduction operation with the local shared memory for the accelerators; writing remotely, by one of the plurality of accelerators to the shared memory local to the host computer, a result of the local reduction operation; and reading, by the host computer from shared memory local to the host computer, the result of the local reduction operation.

Abstract: A hybrid node of a High Performance Computing (HPC) cluster uses accelerator nodes for checkpointing to increase overall efficiency of the multi-node computing system. The host node or processor node reads/writes checkpoint data to the accelerators. After offloading the checkpoint data to the accelerators, the host processor can continue processing while the accelerators communicate the checkpoint data with the host or wait for the next checkpoint. The accelerators may also perform dynamic compression and decompression of the checkpoint data to reduce the checkpoint size and reduce network loading. The accelerators may also communicate with other node accelerators to compare checkpoint data to reduce the amount of checkpoint data stored to the host.

Abstract: Efficient application checkpointing uses checkpointing characteristics of a job to determine how to schedule jobs for execution on a multi-node computer system. A checkpoint profile in the job description includes information on the expected frequency and duration of a check point cycle for the application. The checkpoint profile may be based on a user/administrator input as well as historical information. The job scheduler will attempt to group applications (jobs) that have the same checkpoint profile, on the same nodes or group of nodes. Additionally, the job scheduler may control when new jobs start based on when the next checkpoint cycle(s) are expected. The checkpoint monitor will monitor the checkpoint cycles, updating the checkpoint profiles of running jobs. The checkpoint monitor will also keep track of an overall system checkpoint profile to determine the available checkpointing capacity before scheduling jobs on the cluster.

Abstract: A method, apparatus, and program product checkpoint an application in a parallel computing system of the type that includes a plurality of hybrid nodes. Each hybrid node includes a host element and a plurality of accelerator elements. Each host element may include at least one multithreaded processor, and each accelerator element may include at least one multi-element processor. In a first hybrid node from among the plurality of hybrid nodes, checkpointing the application includes executing at least a portion of the application in the host element and at least one accelerator element and, in response to receiving a command to checkpoint the application, checkpointing the host element separately from the at least one accelerator element.

Abstract: A method, apparatus, and program product checkpoint an application in a parallel computing system of the type that includes a plurality of hybrid nodes. Each hybrid node includes a host element and a plurality of accelerator elements. Each host element may include at least one multithreaded processor, and each accelerator element may include at least one multi-element processor. In a first hybrid node from among the plurality of hybrid nodes, checkpointing the application includes executing at least a portion of the application in the host element, configuring and executing at least one computation kernel in at least one accelerator element, and, in response to receiving a command to checkpoint the application, checkpointing the host element separately from the at least one accelerator element upon which the at least one computation kernel is executing.