Parallella Community

Dear Forum members.

I am trying to perform array access in the column fashion. Existing e_dma_copy function can only copy values in the row major form. Hence, I have to use a for loop to access variables in the column major form and copy to local memory. I would like to know if there is any neat way of doing this without modifying the input?

Any help really appreciated.

You're looking for the 2D DMA. Fasten your seat belt. It's not trivial, but here's some guidance: viewtopic.php?f=23&t=1936&p=11769

You can do some interesting things with the 2D DMA, but what you're asking for should be straight forward.

How about efficiency ? I mean bandwidth and nomenclature here aren't necessarily optimal: it's DMA that transfers data from a memory or device to memory or device, but it has to flow over the Epiphany network, the FPGA serializer blocks as well as the Epiphany memory-to-network unit and the (most appropriately so called) ARM Zynq processor DMA unit.

I get it that the way to access data from a large in memory data set as columns or rows in a fixed sized array holds some interest, but all these operations involved aren't the same tradeoffs as a "regular" DMA engine, where it's about memory banks and pages, startup time, possibly the data elements size, and the provisions of the cache(s) that can accelerate certain parts of the data access.

Purely as a tool to instruct the Parallella's infrastructure to feed you a stride vector, fine, of course.

Theo V.

It is better than blocking CPU and getting access from main memory.