This function gives the same result as regular XXH64(), but with the difference that it only works on single 64-bit values, which makes it possible to reduce it to just a couple of lines; mostly the "bit mixing" part (functions finalize()/avalanche()) is left.
This performs a little bit better than calling the original function on an 8-byte slice because the compiler (at least GCC) does not fully inline the original function (finalize() remains a function call).
This speeds up index generation by a couple of percent: 163 are reduced to 159 seconds for CHM13.
ksahlin
commented
9 months ago
This function gives the same result as regular XXH64(), but with the difference that it only works on single 64-bit values, which makes it possible to reduce it to just a couple of lines; mostly the "bit mixing" part (functions finalize()/avalanche()) is left.
This performs a little bit better than calling the original function on an 8-byte slice because the compiler (at least GCC) does not fully inline the original function (finalize() remains a function call).
This speeds up index generation by a couple of percent: 163 are reduced to 159 seconds for CHM13.