SPRUII0F May 2019 – June 2024 TMS320F28384D , TMS320F28384D-Q1 , TMS320F28384S , TMS320F28384S-Q1 , TMS320F28386D , TMS320F28386D-Q1 , TMS320F28386S , TMS320F28386S-Q1 , TMS320F28388D , TMS320F28388S
For a shared RAM, multiple accesses can happen at a given time. The maximum number of accesses to any shared RAM at any given time depends on the type of shared RAM. On this device, a combination of a fixed and round robin scheme is followed to arbitrate multiple access at any given time. Accesses from the same masters are arbitrated in a fixed priority manner, but the accesses from different masters are arbitrated using the round robin scheme.
The following is the order of fixed priority for CPU accesses:
The following is the order of fixed priority for CLA accesses:
Figure 3-17 represents the arbitration scheme on global shared memories:
Figure 3-18 represents the arbitration scheme on local shared memories.