OK thanks for the info. In that case the following compiler flags should be better: -march=athlon64-sse3 -mpopcnt -DHAVE_CTZ -DHAVE_POPCNTModern Times wrote:The Phenom II does have the popcount instruction.petero2 wrote:OK, I see, thanks for testing. I think it is the popcount instruction that makes the most speed difference and since the Phenom II doesn't have such an instruction your results make sense.IWB wrote:The special Athlon version is not nessesary. The differences to the "old" version are so small and you limit even more the hardware basis ...
Here is a new version: http://dl.dropboxusercontent.com/u/8968 ... 64-pop.exe










