Slide 1 Slide 2 Slide 3 Slide 4 Slide 5 Slide 6 Slide 7 Slide 8 Slide 9 Slide 10 Slide 11 Slide 12 Slide 13 Slide 14 Slide 15 Slide 16 Slide 17 Slide 18 Slide 19 Slide 20 Slide 21 Slide 22 Slide 23 Slide 24 Slide 25 Slide 26 Slide 27 Slide 28 Slide 29 Slide 30 Slide 31 Slide 32 Slide 33 Slide 34 Slide 35 Slide 36 Slide 37 Slide 38 Slide 39 Slide 40 Product List
Migrating from 8/16-bit MCUs to 32-bit ARMs Slide 13
The Data Bypass buffer represents an attempt to compromise the Von Neumann architecture of the ARM7 core with the benefits of the Harvard architecture. With the ARM7, a signal specifies whether a specific fetch is for data or instruction. The MAM uses this signal to determine when a data read occurs. For each data read that’s not already fetched, the MAM stores 128-bits in the data bypass latch. So, in the case of a later data read, this request is satisfied from the Data Bypass buffer which will contain the data requested if it is sequential to the last data fetched. This is all accomplished without emptying the instruction buffer, which is still resident in the Prefetch buffer, so instructions continue immediately following the data load from the data bypass buffer.
PTM Published on: 2011-11-02