The Linux driver DPAA2 qDMA reference code seems to be just using one (1) hardware frame queue for all of its software channels. We also followed the same algorithm as that of the driver and the speed in LS1088ARDB is not that impressive. It seems we are only using 1 DMA engine, but the low level DPAA2 HW reference manual mentions there are 8 engines. We need to boost our throughput by tapping into those engines or multiple channels or whatever to do parallel/concurrent transfers. How do we do that, given that we can't directly access qDMA and we do it via SW portals?
Also, it's mentioned that a DPDMAI object has only two priorities. Are these priorities DMA channels themselves?