table size = 8, offset = 0, iterations count = 100000000 x86 2041ms (seedup: 1.00): ok bswap 1406ms (seedup: 1.45): ok bswap2 2027ms (seedup: 1.01): ok sse 2042ms (seedup: 1.00): ok sse2 2012ms (seedup: 1.01): ok pshufb 1957ms (seedup: 1.04): ok pshufb2 1978ms (seedup: 1.03): ok table size = 16, offset = 0, iterations count = 50000000 x86 1553ms (seedup: 1.00): ok bswap 859ms (seedup: 1.81): ok bswap2 932ms (seedup: 1.67): ok sse 1534ms (seedup: 1.01): ok sse2 1532ms (seedup: 1.01): ok pshufb 1489ms (seedup: 1.04): ok pshufb2 1495ms (seedup: 1.04): ok table size = 32, offset = 0, iterations count = 20000000 x86 880ms (seedup: 1.00): ok bswap 428ms (seedup: 2.06): ok bswap2 474ms (seedup: 1.86): ok sse 360ms (seedup: 2.44): ok sse2 834ms (seedup: 1.06): ok pshufb 265ms (seedup: 3.32): ok pshufb2 851ms (seedup: 1.03): ok table size = 64, offset = 0, iterations count = 20000000 x86 1248ms (seedup: 1.00): ok bswap 658ms (seedup: 1.90): ok bswap2 603ms (seedup: 2.07): ok sse 466ms (seedup: 2.68): ok sse2 483ms (seedup: 2.58): ok pshufb 336ms (seedup: 3.71): ok pshufb2 319ms (seedup: 3.91): ok table size = 128, offset = 0, iterations count = 10000000 x86 1380ms (seedup: 1.00): ok bswap 568ms (seedup: 2.43): ok bswap2 487ms (seedup: 2.83): ok sse 338ms (seedup: 4.08): ok sse2 348ms (seedup: 3.97): ok pshufb 194ms (seedup: 7.11): ok pshufb2 187ms (seedup: 7.38): ok table size = 256, offset = 0, iterations count = 5000000 x86 1299ms (seedup: 1.00): ok bswap 525ms (seedup: 2.47): ok bswap2 447ms (seedup: 2.91): ok sse 278ms (seedup: 4.67): ok sse2 279ms (seedup: 4.66): ok pshufb 137ms (seedup: 9.48): ok pshufb2 147ms (seedup: 8.84): ok table size = 512, offset = 0, iterations count = 2000000 x86 1006ms (seedup: 1.00): ok bswap 402ms (seedup: 2.50): ok bswap2 333ms (seedup: 3.02): ok sse 200ms (seedup: 5.03): ok sse2 201ms (seedup: 5.00): ok pshufb 91ms (seedup: 11.05): ok pshufb2 84ms (seedup: 11.98): ok table size = 1024, offset = 0, iterations count = 1000000 x86 985ms (seedup: 1.00): ok bswap 410ms (seedup: 2.40): ok bswap2 322ms (seedup: 3.06): ok sse 188ms (seedup: 5.24): ok sse2 187ms (seedup: 5.27): ok pshufb 82ms (seedup: 12.01): ok pshufb2 73ms (seedup: 13.49): ok table size = 2048, offset = 0, iterations count = 500000 x86 975ms (seedup: 1.00): ok bswap 397ms (seedup: 2.46): ok bswap2 324ms (seedup: 3.01): ok sse 183ms (seedup: 5.33): ok sse2 181ms (seedup: 5.39): ok pshufb 77ms (seedup: 12.66): ok pshufb2 67ms (seedup: 14.55): ok table size = 4096, offset = 0, iterations count = 300000 x86 1164ms (seedup: 1.00): ok bswap 470ms (seedup: 2.48): ok bswap2 382ms (seedup: 3.05): ok sse 218ms (seedup: 5.34): ok sse2 213ms (seedup: 5.46): ok pshufb 95ms (seedup: 12.25): ok pshufb2 76ms (seedup: 15.32): ok table size = 8192, offset = 0, iterations count = 100000 x86 790ms (seedup: 1.00): ok bswap 311ms (seedup: 2.54): ok bswap2 252ms (seedup: 3.13): ok sse 145ms (seedup: 5.45): ok sse2 143ms (seedup: 5.52): ok pshufb 61ms (seedup: 12.95): ok pshufb2 52ms (seedup: 15.19): ok