Fast fourier transformation (FFT) parallel method based on multi-core digital signal processor (DSP) platform
A platform and multi-core technology, applied in the field of fast Fourier transform FFT processing, can solve problems such as algorithm complexity, waste of resources, and discussion of algorithm scalability solutions, and achieve the effect of improving computing efficiency and low communication distance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0064] Taking the number of processors P=4 as an example, set processor 0 as the main processor, and processors P0, P1, P2, and P3 are connected together to form a mesh network structure. The parallel FFT algorithm is implemented on the TMS320C6474EVM board, Figure 4 It is a data interaction diagram between 4 cores. SRIO (Serial Rapid I / O, fast serial input and output) interface is used for data communication between processor P0 and processor P1, between processor P2 and processor P3; between processor P0 and processor P2 1. The processor P1 and the processor P3 use an EDMA3 (Enhanced DMAversion3 Enhanced Direct Memory Access) interface for data communication.
[0065] The specific implementation steps of 4 cores are as follows:
[0066] The first step: preprocessing. Processor P0 first performs bit inversion on the data, and then evenly distributes the inverted data to 4 processor units through the SRIO interface or EDMA3, and each processor unit obtains N / 4 data. See ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com