Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Data Stream Program Scheduling Method for x86 Multi-Core Processors

A multi-core processor and data flow technology, applied in the field of computer compilation, can solve the problems of not making full use of the local characteristics of data flow programs, low cache system utilization, and a large proportion of synchronization overhead, so as to reduce synchronization and communication overhead and improve Cache utilization, effect of optimized mapping

Active Publication Date: 2017-05-10
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, task division can ensure the load balance between processor cores, but it does not make full use of the locality characteristics of data flow programs, which not only makes the utilization rate of the cache system low, but also the parallel granularity of the program is too small when the program is running, and the synchronization overhead is high. Excessive proportion
On the other hand, different cores will interfere with each other during multi-core parallel scheduling. How to use the communication information between computing tasks in the data flow program to achieve inter-core optimization is also currently lacking.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Data Stream Program Scheduling Method for x86 Multi-Core Processors
  • A Data Stream Program Scheduling Method for x86 Multi-Core Processors
  • A Data Stream Program Scheduling Method for x86 Multi-Core Processors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not constitute a conflict with each other.

[0022] Such as figure 1 Shown is the structural frame diagram of this embodiment in the flow compilation system. After the data flow program is parsed by the front end of the data flow compiler, an intermediate representation—a synchronous data flow graph will be generated, followed by task division and scheduling and inter-core cache optimization. The two-level optimization process finally gen...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a data flow program scheduling method oriented to a multi-core system. The method comprises the following steps that task partitioning of mapping from calculation tasks to processor cores is determined, and software pipeline scheduling is constructed; according to structural characteristics of a multi-core processor and execution situations of a data flow program on the multi-core processor, cache optimization among the cores is conducted. According to the method, data flow parallel scheduling and optimization related to the cache structure of a multi-core framework are combined, and high parallelism of the multi-core processor is brought into full play; according to the hierarchical cache structure and the cache principle of the multi-core system, access of the calculation tasks to a communication cache region is optimized, and the throughput rate of a target program is further increased.

Description

technical field [0001] The invention belongs to the technical field of computer compilation, and in particular relates to a data stream program scheduling method for X86 multi-core processors. Background technique [0002] With the development of semiconductor technology, as a new computing platform, the multi / many-core platform provides powerful parallel computing capabilities for various applications, but it also exposes how to fully tap the parallelism of programs and how to make full use of resources. to the programmer. The dataflow programming model provides a feasible way to exploit the parallelism of multicore architectures. Mainstream applications in the field of multimedia processing like video / image processing, graphics, signaling, and networking have inspired stream programming languages ​​like StreamIt, Brook, CUDA, SPUR, and Cg. In the data flow programming model, the target application is represented as a data flow graph, the vertices in the graph represent c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F9/48G06F9/50
Inventor 于俊清李鹤唐九飞何云峰管涛
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products