On Saturday, 8 November 2014 16:31:25 UTC, sixvolts wrote: > > Any ideas how this compares to the wandboard quad? 4x Cortex-A9 vs 2x > Cortex-A15? > > A15 should be faster than A9 clock for clock. http://www.itproportal.com/2012/10/31/arm-cortex-a57-and-a53-vs-cortex-a8-a9-a15-and-a7-a-performance-analysis/ claims 2.5 DMIPs/clk for the A9 and 3.5 for the A15. Also the beagleboard-x15 is supposed to be clocked at 1.5GHZ while the wandboard quad only runs at 1GHz. So that would make the each core on the beaglboard x15 2.1 times as fast as on the wandboard quad.
Of course DMIPs are not the be all and end all of CPU performance but i'd expect the beagleboard X15 and wandboard quad to be broadly comparable in highly multithreaded workloads and the beagleboard x15 to be the clear winner in workloads with low thread count sections. This is also good for buildboxes because it means you can use a lower -j value which will result in less memory pressure. -- For more options, visit http://beagleboard.org/discuss --- You received this message because you are subscribed to the Google Groups "BeagleBoard" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
