0 0 0x01 -1 0 33135533657 120048302441639
implementation   native         byteswap       
scalar           6367161550     4432439001     
superscalar      6641348821     5300801192     
superscalar4     8815841301     6261314034     
sse2             10608956507    6618455695     
ssse3            10609681074    10587675196    
avx2             17535698070    17570723950    
fastest          avx2           avx2           
