SPRAD45B July 2022 – December 2024 AM623 , AM625
This section provides round-trip read latency measurements for processors in AM62x to various memory destinations in the system. The measurements where made on the AM62x platform using bare-metal silicon verification tests. The tests execute on A53, M4F and R5F processors out of LPDDR4. Each test includes a loop of 8192 iterations to read a total of 32 KiB of data. The number of cycles for each access were counted and divided by the respective processor clock frequency to obtain latency time. Table 3-4 shows the average latency results.
Memory | Arm-Cortex-A53 (Avg ns) | Arm-Cortex-R5F WKUP (Avg ns) | Arm-Cortex-M4F MCU (Avg ns) |
---|---|---|---|
LPDDR4 | 219 | 228 | 350 |
OCSRAM MAIN | 127 | 70 | 170 |
R5F WKUP TCM | 104 | 2.5 | 180 |
M4F MCU TCM | 263 | 233 | 10 |
Tests were done at 0.75V VDD_CORE, 1.25Ghz A53 cores, 400MHz R5F core, 400MHz M4F cores, and 1600MT/s LPDDR4. Tightly-Coupled Memory, or TCM, is RAM that is directly attached to an ARM Cortex core. ARM architecture provides a local internal low latency path and also allows external access to the memory through SoC bus infrastructure.