“High performance embedded computing is naturally split into high throughput front end processing tasks and high complexity back end processing tasks.  FPGAs are great at front end bit shuffling type operations but have proven challenging to use for high complexity algorithms, some requiring floating point scaling.  Microprocessors are great for the highly complex processing with 100k lines of code found at the back end.  However, none of the traditional products on the market today gives a satisfactory processing solution to the middle-end processing step where both massive throughput, low power, and complex floating point point math is needed.  This is where Adapteva’s Epiphany multicore architecture comes in, with just the right amount of flexibility to provide outstanding energy efficiency while not sacrificing the traditional C-programming model we have grown accustomed to.”