11 results about "Message Passing Interface" patented technology

The invention provides a simulation scene multi-target calculation method and device based on parallel scheduling and a server, and relates to the technical field of industrial simulation application, and the method comprises the steps: obtaining a parameter set of a plurality of simulation tasks, and carrying out the task clustering processing of the parameter set according to the parameter similarity, and obtaining a plurality of task clusters; all the task clusters are distributed to different computing nodes, parallel solving processing of simulation tasks is carried out on the task clusters in all the computing nodes on the basis of a self-adaptive tuning model of a message passing interface, and local simulation results corresponding to all the computing nodes are obtained; and carrying out convergence and recombination processing on the local simulation results to obtain a complete simulation result data set, carrying out compression and indexed storage processing on the simulation result data set to generate a lightweight simulation result, and carrying out streaming visualization processing on the lightweight simulation result to obtain a target interactive simulation visualization result. According to the method, the simulation efficiency of simulation scene multi-target calculation can be remarkably improved.

The invention relates to a virtual consistency multi-node message passing interface expansion method, device and equipment. The method comprises the following steps: deploying a distributed file system client at each computing node of a multi-node cluster, creating a unified virtual directory mounting point, transparently converting a file operation request under the unified virtual directory mounting point into a corresponding network protocol, and docking a global unified data storage pool, the unified virtual directory mounting point is used for providing consistent file views for all the computing nodes; pointing a file read-write path prefix of the message passing interface process to the unified virtual directory mounting point; and in response to the received user operation request, allocating computing nodes to the user operation request, ensuring that all the allocated computing nodes are mounted to the distributed file system, and starting a message passing interface process. By adopting the method, the consistency of the cross-node file view can be solved from the system level on the premise of not changing the communication logic.

A method for performing a message passing interface (MPI) collective operation in a network, wherein the network comprises a plurality of interconnected nodes, the method comprising: receiving, at a node of the plurality of interconnected nodes, MPI collective operation information identifying the MPI collective operation to be performed, and a graph of the network; determining a number of algorithmic steps of the MPI collective operation based on the MPI collective operation and the graph of the network; determining an initialisation process for the algorithmic steps; determining a finalisation process for the algorithmic steps; determining, for each of the algorithmic steps: a subset of nodes of the plurality of interconnected nodes for the node to communicate with; one or more portions of data for the node to send to and receive from the nodes within the subset of nodes; and initialising the MPI collective operation based on the determined subset, initialisation process and finalisation process, and the one or more portions of data.

The invention provides a cross-architecture parallel scheduling method and system for heterogeneous computing power resources. The method comprises the following steps: establishing and maintaining a resource database containing node architecture types, single-core computing efficiency and current available resources; receiving parallel computing jobs, analyzing the total computing workload of the jobs and a job completion time limit constraint set by a user, running an optimization algorithm based on the resource database, outputting a minimum core number set required by meeting the time limit constraint, and determining a corresponding candidate node group; starting a parallel process of the job on each computing node in the candidate node group, and appointing a management process on one node as a main process for coordinating the overall execution of the job; in the job execution process, the parallel process running on each node performs cross-node data exchange and synchronization through the collective communication operation of the message passing interface, and the host process is responsible for synchronous control. According to the method, seamless integration and efficient parallel computing of heterogeneous computing power resources can be realized.

A method and apparatus are provided for facilitating a datatype engine (DTE) to support high performance computing. A network interface card (NIC) receives, via a message passing interface, a command to read data from a host memory. The NIC determines that the command indicates a first datatype descriptor stored in the NIC. The NIC forms, based on the command, a packet which indicates a base address and a length associated with the data to be read from the host memory and passes the packet to the DTE. The DTE generates a plurality of read requests comprising offsets from the base address and corresponding lengths based on the first datatype descriptor. The DTE passes the plurality of read requests to a direct memory access module, thereby allowing the NIC to access the host memory while eliminating copies of the data on the host during transfer of the command across a network.

The application provides a simulation scene multi-target calculation method and device based on parallel scheduling and a server, relates to the technical field of industrial simulation application, and comprises the following steps: obtaining a parameter set of multiple simulation tasks, performing task clustering processing on the parameter set according to parameter similarity, and obtaining multiple task clusters; distributing each task cluster to different computing nodes, performing parallel solving processing of the simulation tasks on the task clusters in each computing node based on an adaptive optimization model of a message passing interface, and obtaining a local simulation result corresponding to each computing node; performing gathering and reorganization processing on the local simulation result, obtaining a complete simulation result dataset, performing compression and index storage processing on the simulation result dataset, generating a lightweight simulation result, performing stream visual processing on the lightweight simulation result, and obtaining a target interactive simulation visual result. The application can significantly improve the simulation efficiency of simulation scene multi-target calculation.

The application belongs to the technical field of parallel discrete event simulation and network system simulation, and discloses an intelligent hybrid parallel synchronization method for large-scale distributed simulation, which collects key operation indexes such as neighborhood timestamp lower bound, next event time, round-trip delay quantile value, cross-partition event output rate and virtual time jitter, evaluates system load and communication state in real time, judges the best time to enter optimism or rollback conservation based on the collected key operation indexes, prevents frequent switching by using hysteresis mechanism and minimum residence time, sets time-bounded gates at the mode switching boundary, only allows events within the safe range to propagate, temporarily stores events exceeding the range and sends them in batches when the conditions are met, and thus guarantees causal consistency. The application takes into account real-time performance and robustness, shortens the global empty waiting time, facilitates real-time online acceleration and stable submission in a simulation platform and a message passing interface, and has both performance and interpretability.

The invention provides a non-viscous computational fluid mechanics method for parallel acceleration of ILU linear equation solution by using CUDA. The method comprises the following steps: S1, downloading a source code of an SU2 open source solver platform; s2, downloading and installing a CUDA (Compute Unified Device Architecture) Toolkit computing platform and a Visual Studio compiling tool; s3, downloading and installing a CMake environment, configuring environment options of a CUDA (Compute Unified Device Architecture) and an MPI (Message Passing Interface) through the CMake, and configuring an SU2 project by utilizing a command line tool of the CMake; a CUDA Toolkit and a Visual Studio are used to construct a non-viscous solver system based on SU2-CUDA-CFD (Compute Unified Device Architecture-Call Forwarding Detection); and S4, initializing the SU2 solver through an API function in the CUDA, and accelerating ILU iterative solution and post-processing in parallel. According to the method, the SU2 code is compiled in Windows / Linux in a cross-platform mode through CMake, various processes of a non-stick solver in the SU2 are achieved through a CUDA platform, the calculation time is greatly shortened, perfect matching of a calculation task and hardware capacity is achieved, stability is better, the solving process can be easily controlled and adjusted, and an accurate and reliable flow field solution is obtained.

This invention discloses a method for constructing a master-slave device message passing interface for a shared storage multi-core platform, relating to the field of data processing technology. The method includes the following steps: S1, constructing a mapping table for slave devices and initializing the message passing interface; S2, after initialization, constructing a data flow from the master device to the slave device; S3, based on the data flow from the master device to the slave device, extending the message passing interface into a heterogeneous core message passing interface, thus expanding the message passing interface for communication between the master and slave devices. This invention is based on MPI extensions and adapts to the multi-master-multi-slave application development mode in shared storage multi-core platforms. Furthermore, multiple master devices can access multiple slave devices through a unified interface, providing framework-level support for building complex and scalable heterogeneous core integration systems.

A unified mesh vertex indexing method for high-fidelity parallel full-core fast reactor simulation belongs to the fields of high performance computing and numerical simulation. Firstly, a constant is defined and a message passing interface (MPI) is initialized; processors then generate local hash tables concurrently to obtain local vertex numbers; next, a processor 0 generates a global hash table by MPI_Send( ) and MPI_Recv( ) functions, processes a conflict, and finally obtains global vertex numbers, thus building indexes. Local numbering and global numbering of mesh vertexes are realized with the hash table. Parallel processing of vertex numbering tasks of the processors is realized through the MPI. An innovative global vertex numbering method is provided for the processors. Large-scale parallel efficiency is improved. The research and development of large-scale high-fidelity numerical simulation software for a thermal fluid can be facilitated.

The application relates to a multi-node message passing interface extension method, device and equipment for virtual consistency. The method comprises the following steps: deploying a distributed file system client on each computing node of a multi-node cluster, creating a unified virtual directory mounting point, transparently converting a file operation request under the unified virtual directory mounting point into a corresponding network protocol, and connecting a global unified data storage pool, the unified virtual directory mounting point being used for providing a consistent file view for all computing nodes; prefixing a file read-write path of a message passing interface process to the unified virtual directory mounting point; in response to receiving a user job request, allocating a computing node for the user job request and ensuring that all allocated computing nodes have been mounted to the distributed file system, and starting the message passing interface process. The method can solve the consistency of cross-node file views from the system level without changing the communication logic.