Audio data processing method, DSP audio architecture, equipment and medium

Abstract

The invention provides an audio data processing method, a DSP audio architecture, equipment and a medium. The method comprises the steps: enabling a decoding unit of the DSP audio architecture to decode instructions stored in a CODE SRAM one by one according to the time sequence of time slices divided in advance, obtaining a control electric signal, and controlling a carrying assembly to alternately carry the audio data stored in a DATA SRAM to a first register block or a second register block based on a ping-pong mechanism; controlling an arithmetic unit to process the audio data carried to the first register block or the second register block in parallel; and sharing a processing result obtained by parallel processing to the shared register group or returned to the DATA SRAM. By means of a ping-pong mechanism, audio data in front and back time slices are alternately carried to the first register block and the second register block for parallel processing, and efficient processing of the audio data is ensured while the area of a DSP audio architecture is reduced.

Description

technical field [0001] The present invention relates to the technical field of audio processing, in particular to an audio data processing method, device and medium based on a DSP audio architecture. Background technique [0002] DSP (Digital Signal Processor) architecture is a microprocessor for digital signal processing. As a typical digital signal, audio data cannot be separated from the processing of DSP architecture. [0003] Please refer to figure 1 , the current DSP architecture for efficient processing of audio data usually consists of multiple DSRAMs (dual-ported Static Random-Access Memory, dual-port static random access memory) and a single SRAM (StaticRandom-Access Memory, static random access memory) Composition, multiple DSRAMs are used to store data, a single SRAM is used to store instructions, and the instructions in a single SRAM access and operate on the data in multiple DSRAMs to realize the processing of audio data. Moreover, in order to access multipl...

AI Technical Summary

Problems solved by technology

Moreover, in order to access multiple DSRAMs with large memory spaces at the same time to efficiently process audio data, the SRAM stores a larger instruction bit width, so that the SARM has a larger area, resulting in an increase in the area of ​​​​the DSP architecture; in addition, multiple DSRAMs also will result in an increase in the area of ​​the DSP architecture

As a result, for smaller audio processing equipment, the large-area DSP architecture has the disadvantage of being difficult to apply

Images