A GPU display memory management method with achain structure

A management method and chain technology, applied in image memory management, electrical digital data processing, processor architecture/configuration, etc., can solve the problems of low operation efficiency, low memory utilization, low security, etc., and improve security. , save memory resources and ensure the effect of efficiency

Inactive Publication Date: 2019-02-22
CHINESE AERONAUTICAL RADIO ELECTRONICS RES INST
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problems of low video memory utilization, low operating efficiency, and low security in traditional methods, the purpose of the present inventio

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 GPU display memory management method with achain structure
  • A GPU display memory management method with achain structure
  • A GPU display memory management method with achain structure

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0036] The present invention will be further described in detail below with reference to the drawings and embodiments.

[0037] The GPU video memory management method of the chain structure shown in this embodiment is aimed at the field of embedded systems, using heap objects as the video memory management unit, based on a linked list structure, based on "first adaptation" and "near idle It features video memory management algorithms such as "video memory block merging" and realizes video memory management functions such as video memory space initialization, video memory application, and video memory release.

[0038] Such as figure 1 As shown, the chain structure is composed of a heap object and a block of video memory. The block structure contains a pointer to the actual video memory space. The forward third pointer and the backward fourth pointer enable the block to form a doubly linked list. , Each free block also has a fifth pointer to the next free block and a sixth pointer t...

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 relates to a GPU display memory management method with a chain structure, comprising the following steps: 1) establishing heap objects in the GPU display memory space, wherein each heapobject is composed of at least one display memory block; and establishing a global linked list and an idle linked list; 2) when freeing the display memory space, marking the display memory block wherethe incoming address is located as idle, querying whether the front and back display memory blocks of the current display memory block are idle display memory blocks, if so, performing merging, and updating the global link list and the idle link list. The invention adopts a merging algorithm of adjacent idle blocks, which ensures the efficiency, reduces the generation of display memory fragmentsand improves the use efficiency of the display memory.

Description

technical field [0001] The invention belongs to the field of graphics processor drivers, and relates to a method for managing on-chip video memory on a GPU chip. Background technique [0002] Graphics processing units (GPUs) are widely used in various fields that require graphics generation and display, such as industry, medical care, and consumer electronics. The most common application scenario is that the central processing unit (CPU) interacts with the GPU through the PCI or PCIE bus for data and commands. , the GPU is responsible for drawing graphics and outputting them. In the process of 3D graphics generation, a large amount of data needs to be moved from the CPU local memory to the GPU or from the GPU to the CPU memory. Limited by memory bandwidth and PCI / PCIE bus bandwidth, the speed at which the GPU reads and writes data from the CPU local memory Far lower than the speed at which the GPU can read and write data from the on-chip video memory. Taking the commonly us...

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
IPC IPC(8): G06F9/50G06T1/20G06T1/60
CPCG06F9/5016G06F9/5061G06F2209/5012G06T1/20G06T1/60
Inventor 廖科时洋洋李少光
Owner CHINESE AERONAUTICAL RADIO ELECTRONICS RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap