Hi,
I would like to know the feature of C6657.
Now our customer is evaluating Keystone device (C6657) performance. I need the information for the below.
* Arithmetic calcuration : 32MACS/Core/cycle, seven stage pipeline --- are these data right?
* L1 cache : Can the address on L1cache be locked?
* L2 cache : Can the address on L2 cache be locked?
* Memory latency : How many clock for each cache? L1P: 3(1) clk, L1D:3(1)clk, L2:4(2) clk, Core Access Time : 1 cycle , Are these data right? Then, how about L3?
* Cache coherency : L1P : No, L1D: HW support, L2: HW support, external memory : No, Are these data right?
I appreciate quick reply.
Best regards,
Michi