Method for instruction buffering based on SPM in embedded system
A technology of embedded system and implementation method, applied in the direction of concurrent instruction execution, sustainable building, energy-saving computing, etc., can solve the problem of inability to enter the sleep state, and achieve the effects of high speed, reduced energy consumption, and low energy consumption
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045] The present invention is an implementation method of SPM-based instruction buffering in an embedded system, and its specific implementation process will be described below in conjunction with the accompanying drawings.
[0046] 1) SPM space division:
[0047] According to the characteristics of ScratchPad Memory, the SRAM space is divided into blocks with a size of 4k as the smallest unit. There are visible differences in the physical characteristics of each bank of ScratchPad SRAM. Different banks have different access speeds. These banks can be divided into fast banks with fast access speeds and slow banks with slow access speeds. In order to reduce internal fragmentation, the division of space in each bank is not completely consistent.
[0048] For an SPM with m fast banks and n slow banks, the bank numbers of the fast banks are QB0 to QBm-1, and the space is divided into logical blocks each with a size of 4k, which is the minimum physical size of ScratchPadSRAM Us...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 