shavite is faster, echo doesn't really change due to the reg. overload
This changes allow custom lauchbounds without other code changes and improve
the portability against different devices.
also set a minimum throughput to 1024 for these algos (shared mem req. size)
Previous echo commit was only increasing linux performance, and reducing
windows perf compared to the 1.4.9, this one seems to give at least
the 1.4.9 on windows, and the same on linux...
Shavite optimisation seems ok on both (use now 64 registers)
the launch_bounds will force the number of registers, so remove specific
Makefile rules on linux...
manual "cherry pick" with fixed line endings and some adaptations
Original Commit :
Removed sharedmem and reduced calculations with precalcing (ECHO hash).
750ti + 20KHASH(x11)
tpruvot notes:
Real change is more of 10 KH/s on stock clocks (but real)
launch bounds disabled, no perf increase with 64 registers
echo : 40.056ms -> 39.241ms
cube : 14.490ms -> 13.511ms
cube hash change look like useless (__device__ code in generally inlined)
but the reality proves that cuda documentation is wrong...
tpruvot: fixed dos lines ending in echo,
and used my style for cuda function attributes
Project was updated for VS2013 and CUDA SDK 6.5
add also a --cputest function to dump cpu hash results
TODO: x15 is not fully functional, but first loop seems ok
Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com>
