How mvNCProfile get the bandwidth data

[idata]

Hi,

Based on my understanding, the NCS has two level of memory: One is the global memory (4Gb LPDDR) and local buffer/cache inside the SHAVE processing units.

Since mvNCProfile can report the bandwidth number, I'm wondering this number get from the real data transmission from global memory to Myriad-2 SOC, or just the ''volume of data for a layer/layer processing time''Also, it would be good if anyone can provide a dataflow chart showing what's the dataflow between global memory, on-chip buffer, and processing engine, etc.

Thanks for your help~

[idata]

Another question (sorry I'm really the beginner of movidius and my focus is on the memory traffice side):

Is it possible for us to monitor the LPDDR memory traffic in a real-time fashion? Does movidius SDK provide such kind of API for us to use?Any suggestions would be appreciated.

Thanks

[idata]

@dabaixiong Unfortunately we cannot provide a dataflow chart at the moment and our SDK does not include a tool to monitor real time LPDDR memory traffic.