exa2pro/starpu-max: porting work to Maxeler DFE @ 0eb9ac3d71ed298a4d804cc6d5cddd9961e48ea3

Samuel Thibault f99ef13c88 Add CUDA kernel submission pipelining, to overlap costs and allow concurrent		%!s(int64=12) %!d(string=hai) anos
..
gpu_concurrency.c	f99ef13c88 Add CUDA kernel submission pipelining, to overlap costs and allow concurrent	%!s(int64=12) %!d(string=hai) anos
long_kernel.cu	092f322b1c Add CUDA concurrent kernel execution support through the STARPU_NWORKER_PER_CUDA environment variable.	%!s(int64=12) %!d(string=hai) anos
overlap.c	bc3fd88dfd replace 0 with macro part 4	%!s(int64=13) %!d(string=hai) anos