[Cryptech Tech] STM32 FMC problem

[Pavel Shatov]

On 12.08.2015 23:40, Randy Bush wrote:
> the scary thing is that i actually followed your problem discussion. :)
>
>> Using DMA to transfer 32 bits at a time is not very efficient
>
> fine for test, and so that the boston boys can test porting to stm32;
> but not fine for alpha.  do we believe that how you clock the artix-7
> x00t will ameliorate this problem?

Well, the problem as I see it, is that STM32 doesn't handle 
variable-latency transfers over FMC very well. This variable latency 
arises, because data transfer over FMC runs at its own frequency, while 
cores in FPGA can work at some another frequency. One possible solution 
is to clock cores in FPGA using FMC_CLK. This will make whole system 
synchronous. This was actually not possible with iMX6Q, because it could 
only generate EIM_BCLK during read/write transactions. STM32 on the 
other hand can generate FMC_CLK continuously.

> randy
>

-- 
With best regards,
Pavel Shatov