GDB (genome database) based heterogeneous computing and debugging environment realizing system

Abstract

The invention relates to a GDB (genome database) based heterogeneous computing and debugging environment realizing system comprising a user interface module, a joint debugging control module, heterogeneous node debugging modules and parallel task distributing modules which are connected sequentially. The user interface module is used for interacting with users and receiving debugging operation commands from the users in a command line manner and feeding back the debugging result information. The joint debugging control module is used for starting and stopping the heterogeneous node debugging modules, distributing debugging tasks and recovering debugging results, and debugging and controlling parallel subtasks synchronously or asynchronously. The heterogeneous node debugging modules are used for executing debugging commands transmitted by the joint debugging control module; and the parallel task distributing modules are used for partitioning a computing task into a plurality of parallel subtasks and distributing and dispatching the parallel subtasks to execute on the corresponding heterogeneous node debugging modules. Compared with the prior art, the GDB based heterogeneous computing and debugging environment realizing system has the advantages of simplicity in operation, fast deployment and low cost and the like.

Description

technical field [0001] The invention relates to a realization system of a heterogeneous computing debugging environment, in particular to a realization system of a GDB-based heterogeneous computing debugging environment. Background technique [0002] Currently, heterogeneous computing is becoming a new form of parallel computing. Because a complex application task often has a variety of different computing requirements, for example, some parts require a large amount of CPU resources for calculation, and some parts require high-speed read and write operations on large-scale data. Scientific computing is suitable for vector computing. etc. These different computing needs can no longer be met by a single homogeneous parallel cluster in the past, so heterogeneous computing has emerged as the times require. The heterogeneous computing environment realizes different computing requirements by integrating acceleration components of different architectures, such as using multi-core ...

AI Technical Summary

Problems solved by technology

[0004] The lag of heterogeneous parallel program development technology will greatly affect the characteristics and efficiency of heterogeneous hardware, and limit the wide application of heterogeneous computing

Images