table size = 8, offset = 0, iterations count = 20000000 x86 911ms (seedup: 1.00): ok bswap 941ms (seedup: 0.97): ok bswap2 1152ms (seedup: 0.79): ok sse 841ms (seedup: 1.08): ok sse2 841ms (seedup: 1.08): ok table size = 16, offset = 0, iterations count = 10000000 x86 711ms (seedup: 1.00): ok bswap 570ms (seedup: 1.25): ok bswap2 531ms (seedup: 1.34): ok sse 611ms (seedup: 1.16): ok sse2 621ms (seedup: 1.14): ok table size = 32, offset = 0, iterations count = 10000000 x86 1061ms (seedup: 1.00): ok bswap 681ms (seedup: 1.56): ok bswap2 651ms (seedup: 1.63): ok sse 531ms (seedup: 2.00): ok sse2 1041ms (seedup: 1.02): ok table size = 64, offset = 0, iterations count = 10000000 x86 1962ms (seedup: 1.00): ok bswap 1032ms (seedup: 1.90): ok bswap2 871ms (seedup: 2.25): ok sse 781ms (seedup: 2.51): ok sse2 781ms (seedup: 2.51): ok table size = 128, offset = 0, iterations count = 10000000 x86 3705ms (seedup: 1.00): ok bswap 1452ms (seedup: 2.55): ok bswap2 1302ms (seedup: 2.85): ok sse 1312ms (seedup: 2.82): ok sse2 1292ms (seedup: 2.87): ok table size = 256, offset = 0, iterations count = 2000000 x86 1472ms (seedup: 1.00): ok bswap 510ms (seedup: 2.89): ok bswap2 441ms (seedup: 3.34): ok sse 471ms (seedup: 3.13): ok sse2 470ms (seedup: 3.13): ok table size = 512, offset = 0, iterations count = 2000000 x86 2854ms (seedup: 1.00): ok bswap 931ms (seedup: 3.07): ok bswap2 791ms (seedup: 3.61): ok sse 901ms (seedup: 3.17): ok sse2 972ms (seedup: 2.94): ok table size = 1024, offset = 0, iterations count = 1000000 x86 2814ms (seedup: 1.00): ok bswap 921ms (seedup: 3.06): ok bswap2 741ms (seedup: 3.80): ok sse 871ms (seedup: 3.23): ok sse2 871ms (seedup: 3.23): ok table size = 2048, offset = 0, iterations count = 200000 x86 1111ms (seedup: 1.00): ok bswap 371ms (seedup: 2.99): ok bswap2 290ms (seedup: 3.83): ok sse 341ms (seedup: 3.26): ok sse2 340ms (seedup: 3.27): ok table size = 4096, offset = 0, iterations count = 100000 x86 1111ms (seedup: 1.00): ok bswap 351ms (seedup: 3.17): ok bswap2 290ms (seedup: 3.83): ok sse 341ms (seedup: 3.26): ok sse2 340ms (seedup: 3.27): ok table size = 8192, offset = 0, iterations count = 100000 x86 2233ms (seedup: 1.00): ok bswap 691ms (seedup: 3.23): ok bswap2 571ms (seedup: 3.91): ok sse 681ms (seedup: 3.28): ok sse2 680ms (seedup: 3.28): ok