Broadcast and Scatter Communication Operation

Abstract

According to one aspect, a computer-implemented method for performing a distributed communication operation includes: a first computing system receiving a request to perform a distributed communication operation; and the first computing system obtaining a tree structure for performing the distributed communication operation, where the first computing system is a root node of the tree structure. The method also includes the first computing system creating a message having header information and a payload for the distributed communication operation; and the first computing system sending portions of the message to each child node of the first computing system, where the portions sent to each child node are unique.

Description

[Technical Field]

[0001] The present invention relates generally to communication networks, and more particularly to computer systems, computer-implemented methods, and computer program products for performing distributed operations such as broadcast and scatter communication operations.

[0002] Broadcasting a message to a set of participants (e.g., processes, machines) across a network is a frequently used pattern in distributed systems. In this pattern, an origin participant (sometimes called the "root") sends the same message to a set of remote participants, often in a tree pattern. Scattering a message can be considered a derivative of the broadcast operation. The origin participant (the "root") often sends a different message to each remote participant, using a tree pattern to improve performance over centralized point-to-point communication patterns.

[0003] Many High-Performance Computing (HPC) and Machine Learning (ML) applications rely on the Message Passing Interface (MPI) standard and similar libraries for point-to-point and collective communication between distributed operations. The MPI standard defines the MPI_Bcast and MPI_Scatter(v) operations for these two widely used collectives. In addition, other collective algorithms, such as MPI_Allgather and MPI_Allreduce, often rely on broadcast and scatter operations to support higher-level algorithms.

[0004] Broadcast and scatter-aggregate algorithms are also beneficial to any distributed system of persistent daemons for information dissemination. HPC schedulers and job launchers frequently use these patterns to update distributed state and launch applications by sending "launch job" messages to all remote systems. Specifically, the latter example of job launching would benefit greatly from efficient broadcast and scatter algorithms, resulting in faster startup times for user applications and improved machine utilization. Overall, improvements to these two collective communication patterns, especially in dynamic networking environments such as the cloud, can bring significant performance benefits to client applications and data center middleware. Summary of the Invention

[0005]

[0006] Embodiments of the present invention are directed to a method for performing a distributed communication operation. According to one aspect, the computer-implemented method includes: a first computing system receiving a request to perform a distributed communication operation; and the first computing system obtaining a tree structure for performing the distributed communication operation, wherein the first computing system is a root node of the tree structure. The method also includes the first computing system creating a message having header information and a payload for the distributed communication operation; and the first computing system sending portions of the message to each child node of the first computing system, wherein the portions sent to each child node are unique.

[0006] Other embodiments of the present invention implement features of the above-described methods in computer systems and computer program products.

[0007] Additional technical features and advantages are realized through the techniques of the present invention. Embodiments and aspects of the present invention are described in detail herein and are considered a part of the claimed subject matter. For a better understanding, reference is made to the detailed description and drawings. [Brief explanation of the drawings]

[0008] The details of the exclusive rights set forth herein are particularly pointed out and distinctly claimed in the claims at the conclusion of this specification. The above and other features and advantages of embodiments of the present invention will become apparent from the following detailed description when read in conjunction with the accompanying drawings.

[0009] [Figure 1] FIG. 1 shows a block diagram of an exemplary computer system for use in conjunction with one or more embodiments of the present invention.

[0010] [Figure 2] FIG. 1 shows a block diagram of a tree structure for use in conjunction with one or more embodiments of the present invention.

[0011] [Figure 3] FIG. 2 is a block diagram illustrating a broadcast operation in accordance with one or more embodiments of the present invention.

[0012] [Figure 4] FIG. 1 is a block diagram illustrating a scattering operation in accordance with one or more embodiments of the present invention.

[0013] [Figure 5] FIG. 1 is a block diagram illustrating a combination of broadcast and scatter operations in accordance with one or more embodiments of the present invention.

[0014] [Figure 6] 1 is a flowchart of a method for initiating a distributed communication operation in accordance with one or more embodiments of the present invention.

[0015] [Figure 7] 1 is a flowchart of a method for performing distributed communication operations in accordance with one or more embodiments of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] As discussed above, broadcast and scatter algorithms are increasingly used by HPC and ML processes. Existing broadcast and scatter algorithms require members to know the tree structure before operations begin in order to understand their role in the communication protocol. If the tree structure needs to adapt to membership, network conditions, and / or message size, tree structure updates must be distributed before collective operations begin. This often requires hard synchronization when switching trees, interrupting network traffic. For scatter communication patterns, the organization of data in buffers can affect the performance of operations. For example, each stage in the algorithm may need to calculate different memory offsets and access different memory areas to compile a subset of buffers for their subtrees.

[0017] In an exemplary embodiment, an improved broadcast and scatter algorithm is provided that does not require members other than the root to have prior knowledge of the tree structure. The improved broadcast and scatter algorithm dynamically adapts to the current network environment without synchronization. In addition, the improved broadcast and scatter algorithm is configured to manage the data to be transmitted during the broadcast and scatter algorithm and improve performance.

[0018] In an exemplary embodiment, only the originating participant ("root") knows the tree structure when initiating a broadcast and / or scatter operation. This allows the originating participant ("root") to dynamically adjust the tree structure on a message-by-message basis without synchronization with other communication participants. The root encodes the tree structure for its communication operation in the header of messages sent to its children. Child nodes that are non-originating participants receive messages from their parents in the tree that contain instructions for the next hop in the tree relative to them. The messages contain headers describing the subtree structure at and below that point in the tree, and instructions to prune data that is irrelevant to the next stage in the communication operation. Non-origin participants need only unpack those instructions to send to their children in the tree, if applicable, without considering the tree structure above them or below them. Furthermore, the data in each message is organized to optimize memory references in the scatter operation as it progresses down the tree. In one exemplary embodiment, the method can be used for broadcast operation, scatter operation with regular size and irregular size messages per participant, and a combination of the two in combined operation.

[0019] Various aspects of the present disclosure are described through text, flowcharts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. For any flowchart, depending on the technology involved, operations may be performed in an order different from that shown in a given flowchart. For example, depending again on the technology involved, two operations shown in successive flowchart blocks may be performed in the reverse order, as a single integrated step, simultaneously, or in an at least partially overlapping manner.

[0020] A computer program product embodiment ("CPP embodiment" or "CPP") is a term used in this disclosure to describe any set of one or more storage media (also referred to as "media") collectively contained in one or more storage devices that collectively contain machine-readable code corresponding to instructions and / or data for performing the computer operations specified in a given CPP claim. A "storage device" is any tangible device that can hold and store instructions for use by a computer processor. The computer-readable storage medium may be, but is not limited to, an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the foregoing. Some known types of storage devices that include these media include diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanically encoded devices (such as punch cards or pits / lands formed on a major surface of a disk), or any suitable combination of the foregoing. Computer-readable storage media, as the term is used in this disclosure, is not to be construed as storage in the form of transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide, light pulses passing through fiber optic cables, electrical signals communicated through wires, and / or other transmission media.As will be appreciated by those skilled in the art, data is typically moved at some infrequent time during the normal operation of a storage device, such as during access, defragmentation, or garbage collection, but this does not make the storage device temporary because the data is not temporary while it is stored.

[0021] Computing environment 100 comprises an example of an environment for execution of at least a portion of computer code involved in performing the methods of the present invention, e.g., broadcast and scatter operations 150. In addition to block 150, computing environment 100 includes, for example, computer 101, wide area network (WAN) 102, end user device (EUD) 103, remote server 104, public cloud 105, and private cloud 106. In this embodiment, computer 101 includes a processor set 110 (including processing circuitry 120 and cache 121), a communications fabric 111, volatile memory 112, persistent storage 113 (including operating system 122 and the above-identified block 150), a peripheral device set 114 (including a user interface (UI) device set 123, storage 124, and an Internet of Things (IoT) sensor set 125), and a network module 115. Remote server 104 includes a remote database 130. The public cloud 105 includes a gateway 140, a cloud orchestration module 141, a set of host physical machines 142, a set of virtual machines 143, and a set of containers 144.

[0022] Computer 101 may take the form of a desktop computer, a laptop computer, a tablet computer, a smartphone, a smartwatch or other wearable computer, a mainframe computer, a quantum computer, or any other form of computer or mobile device now known or later developed that is capable of executing programs, accessing a network, or querying a database, such as remote database 130. As is well understood in the field of computer technology, and depending on the technology, execution of a computer-implemented method may be distributed among multiple computers and / or multiple locations. However, in this presentation of computing environment 100, to keep the presentation as simple as possible, the detailed discussion focuses on a single computer, specifically computer 101. Although computer 101 is not shown in FIG. 1 within a cloud, it may be located within a cloud. However, computer 101 is not required to reside within a cloud except to any extent that may be expressly indicated.

[0023] Processor set 110 includes one or more computer processors of any type now known or to be developed in the future. Processing circuitry 120 may be distributed across multiple packages, e.g., multiple tailored integrated circuit chips. Processing circuitry 120 may implement multiple processor threads and / or multiple processor cores. Cache 121 is memory located within the processor chip package and is typically used for data or code that should be available for fast access by threads or cores executing on processor set 110. Cache memory is typically organized into multiple levels depending on relative proximity to the processing circuitry. Alternatively, some or all caches for a processor set may be located “off-chip.” In some computing environments, processor set 110 may be designed to operate with qubits and perform quantum computing.

[0024] Computer-readable program instructions are typically loaded onto computer 101 and cause processor set 110 of computer 101 to execute a series of operational steps, thereby enabling a computer-implemented method, such that the instructions so executed instantiate the methods specified in the computer-implemented method flowcharts and / or descriptions contained herein (collectively referred to as the "methods of the present invention"). These computer-readable program instructions are stored in various types of computer-readable storage media, such as cache 121 and other storage media discussed below. The program instructions and associated data are accessed by processor set 110 to control and direct the execution of the methods of the present invention. In computing environment 100, at least a portion of the instructions for executing the methods of the present invention may be stored in block 150 in persistent storage 113.

[0025] Communications fabric 111 is the signal-conducting pathway that allows various components of computer 101 to communicate with one another. Typically, this fabric is made up of switches and conductive pathways, such as those that make up buses, bridges, physical input / output ports, and the like. Other types of signal communication pathways may be used, such as fiber optic and / or wireless communication pathways.

[0026] Volatile memory 112 may be any type of volatile memory now known or later developed. Examples include dynamic random access memory (RAM) or static RAM. Typically, volatile memory is characterized by random access, although this is not required unless expressly stated. In computer 101, volatile memory 112 is located in a single package and is internal to computer 101; however, alternatively or additionally, volatile memory may be distributed across multiple packages and / or located external to computer 101.

[0027] Persistent storage 113 is any form of non-volatile storage for a computer, now known or later developed. The non-volatility of this storage means that stored data is maintained regardless of whether power is supplied to computer 101 and / or to persistent storage 113 directly. While persistent storage 113 can be read-only memory (ROM), typically at least a portion of persistent storage allows data to be written, data to be deleted, and data to be rewritten. Some well-known forms of persistent storage include magnetic disks and solid-state storage devices. Operating system 122 can take several forms, including various known proprietary operating systems or open-source Portable Operating System Interface types that employ a kernel. The code contained in block 150 typically includes at least a portion of the computer code involved in performing the methods of the present invention.

[0028] The peripheral device set 114 includes a set of peripheral devices of the computer 101. Data communication connections between the peripheral devices and other components of the computer 101 can be implemented in various ways, such as Bluetooth connections, Near-Field Communication (NFC) connections, connections made by cable (such as a universal serial bus (USB)-type cable), insertion-type connections (e.g., a secure digital (SD) card), connections made through a local area communication network, and even connections made through a wide area network such as the Internet. In various embodiments, the UI device set 123 can include components such as a display screen, speakers, microphones, wearable devices (such as goggles and smartwatches), keyboards, mice, printers, touchpads, game controllers, and haptic devices. The storage 124 can be external storage, such as an external hard drive, or insertable storage, such as an SD card. The storage 124 can be persistent and / or volatile. In some embodiments, storage 124 may take the form of a quantum computing storage device for storing data in the form of qubits. In embodiments where computer 101 is required to have a large amount of storage (e.g., where computer 101 stores and manages large databases locally), this storage may be provided by a peripheral storage device designed to store very large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. IoT sensor set 125 is made up of sensors that may be used in Internet of Things applications. For example, one sensor may be a thermometer and another may be a motion detector.

[0029] Network module 115 is a collection of computer software, hardware, and firmware that enables computer 101 to communicate with other computers over WAN 102. Network module 115 may include hardware such as a modem or Wi-Fi signal transceiver, software for packetizing and / or depacketizing data for communication network transmission, and / or web browser software for communicating data over the Internet. In some embodiments, the network control and network forwarding functions of network module 115 are performed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing Software-Defined Networking (SDN)), the control and forwarding functions of network module 115 are performed on physically separate devices, such that the control function manages multiple different network hardware devices. Computer-readable program instructions for performing the methods of the invention may be downloaded to computer 101, typically from an external computer or external storage device, through a network adapter card or network interface included in network module 115.

[0030] WAN 102 is any wide area network (e.g., the Internet) capable of communicating computer data over non-local distances by any now known or later developed technology for communicating computer data. In some embodiments, a WAN may be replaced and / or supplemented by a local area network (LAN) designed to communicate data between devices located in a local area, such as a Wi-Fi network. WANs and / or LANs typically include copper transmission cables, optical fiber transmissions, wireless transmissions, and computer hardware such as routers, firewalls, switches, gateway computers, and edge servers.

[0031] End-user device (EUD) 103 is any computer system used and controlled by an end user (e.g., a customer of the enterprise operating computer 101) and may take any of the forms discussed above in connection with computer 101. EUD 103 typically receives useful and useful data from the operation of computer 101. For example, in a hypothetical case where computer 101 is designed to provide recommendations to the end user, the recommendations would typically be communicated from computer 101's network module 115 over WAN 102 to EUD 103. In this manner, EUD 103 can display or otherwise present the recommendations to the end user. In some embodiments, EUD 103 may be a client device, such as a thin client, a heavy client, a mainframe computer, a desktop computer, and the like.

[0032] Remote server 104 is any computer system that provides at least some data and / or functionality to computer 101. Remote server 104 may be controlled and used by the same entity that operates computer 101. Remote server 104 represents a machine that collects and stores useful and useful data for use by other computers, such as computer 101. For example, in the hypothetical case where computer 101 is designed and programmed to provide recommendations based on past data, then this past data may be provided to computer 101 from remote database 130 of remote server 104.

[0033] A public cloud 105 is any computer system available for use by multiple entities that provides on-demand availability of computer system resources and / or other computer functionality, particularly data storage (cloud storage) and computing power, without direct active management by users. Cloud computing typically leverages resource sharing to achieve coherence and economies of scale. Direct active management of the computing resources of the public cloud 105 is performed by computer hardware and / or software in a cloud orchestration module 141. The computing resources provided by the public cloud 105 are typically implemented by virtual computing environments running on various computers comprising a host physical machine set 142, which is the universe of physical computers within and / or available in the public cloud 105. A virtual computing environment (VCE) typically takes the form of virtual machines from a virtual machine set 143 and / or containers from a container set 144. It is understood that these VCEs may be stored as images and transferred among and between various hosts of physical machines either as images or after instantiation of the VCE. Cloud orchestration module 141 manages the transfer and storage of images, deploys new instantiations of VCEs, and manages active instantiations of VCE deployments. Gateway 140 is a collection of computer software, hardware, and firmware that enables public cloud 105 to communicate over WAN 102.

[0034] Some further discussion of virtualized computing environments (VCEs) is now provided. A VCE can be stored as an "image." A new, active instance of a VCE can be instantiated from an image. Two well-known types of VCEs are virtual machines and containers. A container is a VCE that uses operating system-level virtualization. This refers to a feature of an operating system in which the kernel allows the existence of multiple isolated user space instances, called containers. These isolated user space instances typically behave as actual computers from the perspective of programs running within them. A computer program running on a typical operating system can utilize all of the computer's resources, such as connected devices, files and folders, network shares, CPU power, and quantifiable hardware capabilities. However, a program running inside a container can only use the contents of the container and of the devices assigned to the container; this feature is known as containerization.

[0035] A private cloud 106 is similar to a public cloud 105, except that its computing resources are available only for use by a single enterprise. While the private cloud 106 is shown in communication with the WAN 102, in other embodiments, the private cloud may be completely disconnected from the Internet and accessible only through a local / private network. A hybrid cloud is a composite of multiple clouds of different types (e.g., private, community, or public cloud types), often each implemented by a different vendor. While each of the multiple clouds remains a separate, discrete entity, the larger hybrid cloud architecture is bound together by standardized or proprietary technologies that enable orchestration, management, and / or data / application portability between the constituent clouds. In this embodiment, both the public cloud 105 and the private cloud 106 are part of a larger hybrid cloud.

[0036] 2, a block diagram of a tree structure 200 for use in conjunction with one or more embodiments of the present invention is shown. In an exemplary embodiment, tree structure 200 includes a root node 202, also referred to as an origin node or origin participant, and multiple child nodes 204, also referred to as participant nodes. As shown, one or more of the multiple child nodes 204 may have child nodes 206 subordinate to them, which in turn may have child nodes 208 subordinate to them. In an exemplary embodiment, each of the nodes (root node 202 and child nodes 204, 206, and 208) may be embodied in computer 101, as shown in FIG. 1.

[0037] In an exemplary embodiment, before initiating a distributed communication operation, such as a broadcast or scatter operation, the originating participant 200 obtains a tree structure 200 that will be used for the distributed communication operation. In one embodiment, the tree structure 200 is known only by the originating participant 202 and is unknown to other participant nodes. In an exemplary embodiment, the tree structure 200 may vary from communication operation to communication operation, even for the same set of participants. The tree structure need not be a regular pattern but may be irregular based on external inputs, such as network conditions. The method for creating the tree structure 200 is outside the scope of the present invention, and any of a variety of known techniques may be used to create the tree structure 200.

[0038] Referring now to Figure 3, a block diagram illustrating a broadcast operation in accordance with one or more embodiments of the present invention is shown. In a broadcast operation, an originating participant 300 adds a header 302 to a message payload 306 at a known location, either before or after the message payload 306. The header 302 describes the base address of the data payload 306, the length of the data payload 306, and the subtree structure 308 for the receiving participant ("child"). As shown, the headers 312, 322, and 342 sent to child nodes 310, 320, and 340, respectively, are different from one another because each contains a different subtree structure 308. In one embodiment, a cached subtree structure is used, and a marker identifying the cached subtree is sent in place of the subtree structure for the receiving participant.

[0039] In an exemplary embodiment, once origin participant 300 assembles data payload 306 and header, origin participant 300 initiates a broadcast operation. Origin participant 300 sends header 312 and data payload 306 to child node 310, sends header 322 and data payload 306 to child node 320, and sends header 342 and data payload 306 to child node 340.

[0040] In an exemplary embodiment, child participants receive data payloads from their parent that are unknown to them prior to the start of the messaging protocol. The child participants inspect the data payloads to discover the structure of the data payloads and, if applicable, the type of the subtree below them. In an exemplary embodiment, when a child participant receives header and data payload 306, the child participant prunes headers of subtree information that is not relevant to their destination subtree and transmits new headers and data payloads to its child nodes. For example, after node 310 receives header 312 and data payload 306, node 310 prunes header 312 to create header 332 and header 352, which are transmitted along with data payload 306 to nodes 330 and 350, respectively.

[0041] If the child is a terminal node, such as node 370, propagation of payload data 306 ends. If acknowledgment is required, each node sends an acknowledgment message to its immediate parent (i.e., from whom it received the message). If the child is a non-terminal and acknowledgment is required, the node waits until it receives an acknowledgment message from its subtree, then forwards the acknowledgment for that message to its immediate parent. In an exemplary embodiment, the propagation pattern continues until all participants have received the data payload intended for them and sent any required acknowledgments.

[0042] 4, a block diagram illustrating a scatter operation 400 in accordance with one or more embodiments of the present invention is shown. In an exemplary embodiment, when an originating participant 402 initiates a scatter operation 400, the originating participant 402 obtains a tree structure to be used for the scatter operation 400. The tree structure includes a number of nodes 403, 404, 405, 406, 407, 408, and 409.

[0043] After the tree structure is obtained, the origin participant 402 creates a message 410 that includes multiple headers 412, 416, 424 and multiple data payloads 414, 418, 420, 422, 426, 428, 430. In an exemplary embodiment, the origin participant 402 creates a data payload 414, 418, 420, 422, 426, 428, 430 for each node 403, 404, 405, 406, 407, 408, and 409 in the tree structure. Similarly, the origin participant 402 creates a header 412, 416, 424 for each node 403, 406, 404 in the tree structure that has at least one child node. In an exemplary embodiment, the header 412, 416, 424 for each node 403, 406, 404 includes a description of the subtree of the tree structure that is subordinate to the node 403, 406, 404. The header 412, 416, 424 may also describe the base address of the data payload 414, 418, 420, 422, 426, 428, 430, the length of the data payload 414, 418, 420, 422, 426, 428, 430.

[0044] In an exemplary embodiment, message 410 is constructed by origin participant 402 such that the portions of message 410 to be sent to each child node are contiguous. For example, as shown, headers 412, 416 and data payloads 414, 418, 420, 422 sent to child node 403 are contiguous. Similarly, header 424 and data payloads 426, 428 to be sent to child node 404 are contiguous. In one embodiment, a cached subtree structure is used, and a marker identifying the cached subtree is sent in place of the subtree structure for the receiving participant.

[0045] When a child node receives a portion of message 410, the child node is configured to extract the data it needs and separate the remaining header and data payload using information from the header for the child node. For example, when child node 403 receives a portion of the message from origin participant 402, child node 403 extracts the data payload 414 it needs and uses information in header 412 to separate the remaining portion of message 410 into separate portions. The child node then propagates the message portions, i.e., it sends only the subset of headers and data payloads destined for a particular subtree to that subtree. For example, child node 403 sends header 416 and data payloads 418 and 420 to child node 406 and sends data payload 422 to child node 407.

[0046] 5, a block diagram illustrating a combined broadcast and scatter operation 500 in accordance with one or more embodiments of the present invention is shown. In an exemplary embodiment, when an originating participant 502 initiates a combined broadcast scatter operation 500, the originating participant 502 obtains a tree structure to be used for the combined broadcast scatter operation 500. The tree structure includes a number of nodes 503, 504, 505, 506, 507, 508, and 509.

[0047] After the tree structure is obtained, the origin participant 502 creates a message 510 that includes a broadcast header 512, a broadcast data payload 514, multiple scatter headers 516, 520, 528, and multiple scatter data payloads 518, 522, 524, 526, 530, 532, 534. In an exemplary embodiment, the origin participant 502 creates scatter data payloads 518, 522, 524, 526, 530, 532, 534 for each node 503, 504, 505, 506, 507, 508, and 509 in the tree structure. Similarly, the origin participant 502 creates scatter headers 516, 520, 528 for each node 503, 506, 504 in the tree structure that has at least one child node. In an exemplary embodiment, the scatter header 516, 520, 528 for each node 503, 506, 504 includes a description of the subtree of the tree structure that is subordinate to the node 503, 506, 504. The scatter header 516, 520, 528 may also describe the base address of the scatter data payload 518, 522, 524, 526, 530, 532, 534, the length of the scatter data payload 518, 522, 524, 526, 530, 532, 534.

[0048] In an exemplary embodiment, message 510 is constructed by origin participant 502 so that the portions of message 510 to be sent to each child node are contiguous. For example, as shown, headers 516, 520 and data payloads 518, 522, 524, 526 to be sent to child node 503 are contiguous. Similarly, header 528 and data payloads 530, 532 to be sent to child node 504 are contiguous.

[0049] When a child node receives a portion of message 510, the child node is configured to inspect the header corresponding to the child node to discover the structure of the data payload and, if applicable, the type of the subtree below the child node. The child node is further configured to extract a copy of the broadcast payload 514 for its consumption and to remove the scatter payload corresponding to the child node. For example, child node 503 would inspect broadcast header 512 to extract a copy of broadcast payload 514 and inspect scatter header 516 to extract scatter payload 518. Based on the information in broadcast header 512 and scatter header 516, child node 503 would create a message and send it to child nodes 506 and 507.

[0050] In an exemplary embodiment, a child node propagates only portions of a message to each child node that is subordinate to it, i.e., a child node sends only a subset of the headers and data payloads intended for a particular subtree to that subtree. For example, child node 503 sends broadcast header 512, broadcast data payload 514, scatter header 520, and scatter data payloads 522 and 524 to child node 506, and sends broadcast header 512, broadcast data payload 514, and scatter data payload 526 to child node 507.

[0051] In an exemplary embodiment, each child node may be configured to add additional data to the headers and / or data payloads propagated to its subtree. In addition, each child node may be configured to modify the tree structure for its subtree. For example, a child node may have knowledge that a node in its subtree is offline or experiencing unexpected performance issues, in which case the child node may replace a node in its subtree with a different node.

[0052] 6, a flowchart of a method 600 for initiating a distributed communication operation in accordance with one or more embodiments of the present invention is shown. In an exemplary embodiment, the distributed communication operation is one of a broadcast operation, a scatter operation, or a combination of broadcast and scatter operations. As shown, method 600 comprises receiving a request to perform the distributed communication operation, as indicated at block 602. Next, method 600 comprises obtaining a tree structure for performing the distributed communication operation, as indicated at block 604. In an exemplary embodiment, the computing system initiating the distributed communication operation is a root node of the tree structure.

[0053] As indicated at block 606, method 600 also includes creating a message having header information and a payload for the distributed communication operation. In an exemplary embodiment, the message is created by organizing the header information and the payload based on a tree structure. In one embodiment, the header information and the payload are organized such that the portion of the header information and the portion of the payload data to be sent to the child nodes are contiguous. Method 600 further includes sending a portion of the message to each child node of the first computing system, as indicated at block 608, where the portion sent to each child node is unique. In an exemplary embodiment, the portion of the message sent to each child node includes a child header that defines the subtree structure of the child node.

[0054] In one embodiment, the distributed communication operation is a broadcast operation, and the payload of the message sent to each child includes a broadcast payload that is the same for each child node. In another embodiment, the distributed communication operation is a scatter operation, and the portion of the message sent to each child includes a scatter payload obtained based on the payload. The scatter payload sent to each child node is different from the scatter payload sent to other child nodes.

[0055] 7, a flowchart of a method 700 for performing a distributed communication operation in accordance with one or more embodiments of the present invention is shown. As indicated by block 702, method 700 begins with a child node receiving a distributed communication operation message from a parent node. In an exemplary embodiment, the distributed communication operation is one of a broadcast operation, a scatter operation, or a combination of broadcast and scatter operations. When the child node receives the distributed communication operation message, it obtains information about its subtree from the header of the distributed communication operation message. Next, based on the subtree information, method 700 determines whether the child node is a terminal node, as indicated by decision block 704.

[0056] Based on a determination that the child node is a terminal node, method 700 proceeds to block 710, where the child node extracts the data payload required by the child node. Based on a determination that the child node is not a terminal node, method 700 proceeds to block 706, where the child node obtains subtree data from the message header and creates a message for each node subordinate to the child node. In an exemplary embodiment, the message created for each node includes only the header information and payload data required for the subtree corresponding to the destination child node. The message sent to each child node may include one or more of a broadcast header, a scatter header, a broadcast payload, and a scatter payload. Next, as indicated at block 708, method 700 includes sending a message to each node subordinate to the child node that is subordinate to the child node. Method 700 further includes sending an acknowledgment message to the parent node, as indicated at block 712.

[0057] Technical advantages and benefits include methods, systems, and computer program products for executing distributed communication operations using an execution tree configured to dynamically adapt based on network and computing conditions. The method for executing distributed communication operations only requires the originating participant, i.e., the root node, to have knowledge of the tree structure used to execute the distributed communication operations. As a result, different distributed communication operations can be executed using different tree structures, and the tree structure can be updated without synchronizing tree structure knowledge to each node of the tree.

[0058] Various embodiments of the present invention are described herein with reference to the associated drawings. Alternative embodiments of the present invention may be devised without departing from the scope of the present invention. Various connections and relationships (e.g., above, below, adjacent, etc.) are described between elements in the following description and in the drawings. These connections and / or relationships may be direct or indirect unless otherwise specified, and the present invention is not intended to be limiting in this respect. Thus, coupling between entities may refer to either direct or indirect couplings, and relationships between entities may be direct or indirect relationships. Furthermore, various tasks and processing steps described herein may be combined into a more comprehensive procedure or process having additional steps or functionality not described in detail herein.

[0059] One or more of the methods described herein may be implemented using any or a combination of the following technologies: discrete logic circuits having logic gates for implementing logical functions on data signals, application specific integrated circuits (ASICs) having appropriate combinatorial logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc., each of which is well known in the art.

[0060] For the sake of brevity, conventional techniques associated with making and using aspects of the present invention may or may not be described in detail herein. In particular, various aspects of computing systems and specific computer programs for implementing various technical features described herein are well known. Thus, for the sake of brevity, many conventional implementation details are only briefly mentioned herein or are omitted entirely without providing details of well-known systems and / or processes.

[0061] In some embodiments, various functions or operations may be performed at a given location and / or in conjunction with the operation of one or more devices or systems. In some embodiments, a portion of a given function or operation may be performed at a first device or location, and the remainder of the function or operation may be performed at one or more additional devices or locations.

[0062] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It can be further understood that the terms "comprises" and / or "comprising," when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components of elements, and / or groups thereof.

[0063] In the following claims, corresponding structure, material, acts, and equivalents of all means-plus-function or step-plus-function elements are intended to include any structure, material, or act for performing the function as specifically claimed in combination with other claimed elements. This disclosure has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the disclosed form. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the disclosure. The embodiments have been chosen and described to best explain the principles and practical application of the disclosure and to enable others skilled in the art to understand the disclosure in various embodiments with various modifications as suitable for the particular use contemplated.

[0064] The diagrams shown herein are exemplary. There may be many variations of the diagrams or the steps (or operations) described therein without departing from the scope of this disclosure. For example, operations may be performed in a different order, or operations may be added, deleted, or modified. Also, the term "coupled" describes having a signal path between two elements and does not imply a direct connection between elements with no intervening elements / connections between them. All of these variations are considered part of this disclosure.

[0065] The following definitions and abbreviations are to be used for interpreting the claims and the specification. As used herein, the terms "comprises," "comprising," "includes," "including," "has," "having," "contains," or "containing," or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a composition, mixture, process, method, article, or device that includes a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent in such composition, mixture, process, method, article, or device.

[0066] Additionally, the term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. The terms "at least one" and "one or more" are understood to include any integer greater than or equal to one, i.e., 1, 2, 3, 4, etc. The term "plurality" is understood to include any integer greater than or equal to two, i.e., 2, 3, 4, 5, etc. The term "connected" can include both an indirect "connected" and a direct "connected."

[0067] The terms "about," "substantially," "approximately," and variations thereof are intended to include the degree of error associated with measurement of a particular quantity based on equipment available at the time of filing this application. For example, "about" can include a range of ±8%, or 5%, or 2% of a given value.

[0068] The present invention may be a system, method and / or computer program product integrated at any possible level of technical detail. The computer program product may include one or more computer-readable storage media having computer-readable program instructions for causing a processor to carry out aspects of the present invention.

[0069] A computer-readable storage medium may be a tangible device that can hold and store instructions for use by an instruction-execution device. A computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge structures in grooves in which instructions are recorded, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as a transitory signal itself, such as an electric wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted over a wire.

[0070] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to each computing / processing device or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may comprise copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface within each computing / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions to a computer-readable storage medium within the respective computing / processing device for storage.

[0071] The computer-readable program instructions for carrying out the operations of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or either source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, or the like, and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be to an external computer (e.g., through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer readable program instructions to personalize the electronic circuitry by utilizing state information of the computer readable program instructions to perform aspects of the present invention.

[0072] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0073] These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored on a computer-readable storage medium that can instruct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer-readable storage medium having instructions stored therein has an article of manufacture including instructions that implement aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0074] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be executed on the computer, other programmable apparatus, or other device to generate a computer-implemented process, such that the instructions executing on the computer, other programmable apparatus, or other device implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0075] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, including one or more executable instructions, that implements a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in an order other than that noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may possibly be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or that executes a combination of dedicated hardware and computer instructions.

[0076] While the descriptions of various embodiments of the present invention have been presented for illustrative purposes, they are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein has been chosen to best explain the principles, practical applications, or technical improvements of the embodiments over technologies found in the market, or to enable others skilled in the art to understand the embodiments described herein.

Claims

1. receiving, at a first computing system, a request to perform a distributed communications operation; obtaining a tree structure for performing the distributed communication operation by the first computing system, wherein the first computing system is a root node of the tree structure; the first computing system creating a message having header information and a payload for the distributed communication operation; and the first computing system sending a portion of the message to each child node of the first computing system, wherein the portion sent to each child node is unique.

1. A computer-implemented method comprising:

2. The method of claim 1 , wherein the portion of the message sent to each child node includes a child header that defines a subtree structure of the child node.

3. The method of claim 1 , wherein the distributed communication operation is a broadcast operation, and the payload of the message sent to each child comprises a broadcast payload.

4. The method of claim 1 , wherein the distributed communication operation is a scatter operation, and the portion of the message sent to each child includes a scatter payload obtained based on the payload.

5. The method of claim 1 , wherein the distributed communication operations are broadcast and scatter operations.

6. The method of claim 1 , wherein the message is created by organizing the header information and the payload according to the tree structure.

7. The method of claim 6 , wherein the header information and the payload are organized such that the portion of the header information and the portion of the payload data to be sent to a child node are contiguous.

8. a memory having computer-readable instructions; and one or more processors for executing the computer-readable instructions the computer-readable instructions comprising: receiving, by a first computing system, a request to perform a distributed communications operation; the first computing system obtaining a tree structure for performing the distributed communication operation, wherein the first computing system is a root node of the tree structure; the first computing system creating a message having header information and a payload for the distributed communication operation; and the first computing system sending a portion of the message to each child node of the first computing system, wherein the portion sent to each child node is unique. controlling the one or more processors to perform operations comprising: system.

9. The system of claim 8 , wherein the portion of the message sent to each child node includes a child header that defines a subtree structure of the child node.

10. The system of claim 8 , wherein the distributed communication operation is a broadcast operation, and the payload of the message sent to each child comprises a broadcast payload.

11. The system of claim 8 , wherein the distributed communication operation is a scatter operation, and the portion of the message sent to each child includes a scatter payload obtained based on the payload.

12. The system of claim 8 , wherein the distributed communication operations are broadcast and scatter operations.

13. The system of claim 8 , wherein the message is created by organizing the header information and the payload according to the tree structure.

14. The system of claim 13 , wherein the header information and the payload are organized such that a portion of the header information and a portion of the payload data to be sent to a child node are contiguous.

15. 1. A computer program product comprising a computer-readable storage medium having program instructions embodied thereon, the program instructions causing a processor to: receiving, by a first computing system, a request to perform a distributed communications operation; the first computing system obtaining a tree structure for performing the distributed communication operation, wherein the first computing system is a root node of the tree structure; the first computing system creating a message having header information and a payload for the distributed communication operation; and the first computing system sending a portion of the message to each child node of the first computing system, wherein the portion sent to each child node is unique. a computer program product executable by the processor to cause the processor to perform operations having the steps:

16. 16. The computer program product of claim 15, wherein the portion of the message sent to each child node includes a child header that defines a subtree structure of the child node.

17. 16. The computer program product of claim 15, wherein the distributed communication operation is a broadcast operation, and the payload of the message sent to each child comprises a broadcast payload.

18. 16. The computer program product of claim 15, wherein the distributed communication operation is a scatter operation, and the portion of the message sent to each child includes a scatter payload obtained based on the payload.

19. 16. The computer program product of claim 15, wherein the distributed communication operations are broadcast and scatter operations.

20. 16. The computer program product of claim 15, wherein the message is created by organizing the header information and the payload according to the tree structure.

Images