Unlock instant, AI-driven research and patent intelligence for your innovation.

GPU memory access method

A technology of memory access request and memory access address, applied in the field of GPU architecture and GPU memory access method design

Active Publication Date: 2014-12-10
ZHEJIANG UNIV CITY COLLEGE
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

By accessing memory in a fused manner, memory access latency can be hidden to a certain extent

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
  • GPU memory access method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with drawings and embodiments.

[0036] As shown in the accompanying drawings, the present invention includes:

[0037] 1) Perform memory access fusion for the requests sent by the stream processor;

[0038] 2) The stream processor sends the fused memory access request to the corresponding memory;

[0039] 3) Split the fused memory access request in the memory and read out the data;

[0040] 4) The read data in the memory forms a data block and returns it to the stream processor;

[0041] 5) The stream processor processes and stores the data blocks sent back.

[0042] In the above step 1), the memory access fusion of the request sent by the stream processor specifically includes:

[0043] 1.1) Put the request address issued by the stream processor in the GPU multi-core in an array;

[0044] 1.2) Sort the memory access addresses in the array from small to large. After sorting, if a certain memory a...

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 GPU memory access method. According to the GPU memory access method, requests sent by a stream processor are subjected to memory access fusion, the stream processor sends the fused memory access requests to corresponding memories, the fused memory access requests in the memories are split to read out data, the read-out data in the memories form data blocks to be sent back to the stream processor, and the stream processor processes and stores the returned data blocks. By means of the method, the memory access requests with identical intervals of memory access addresses are fused, memory access efficiency is improved, memory latency is hidden, and comprehensive performance of a GPU is improved. The method can be used in cooperation with an existing method, and therefore performance of a program can be improved to some extent.

Description

technical field [0001] The invention relates to the design field of a GPU architecture and a memory access method of the GPU, in particular to a memory access method on the GPU under the GPU architecture. Background technique [0002] The hardware structure of GPU is very different from that of CPU. The hardware of GPU is composed of memory and stream processor. GPU is actually an array of processor cores, each stream processor contains multiple cores, and a GPU device contains one or more stream processors, so the processor is scalable. If you add more stream processors to the device, the GPU can process more tasks at the same time, or for the same task, if there is sufficient parallelism, the GPU can complete the task faster. [0003] GPUs use high-speed memory with consistent bandwidth, but like all memory, there are severe memory access latencies. By accessing memory in a fused manner, memory access latency can be hidden to some extent. The original fused access is to...

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): G06F12/02
Inventor 吴明晖裴玉龙陈天洲李颂元孟静磊
Owner ZHEJIANG UNIV CITY COLLEGE
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com