aligned sse2 + avx2 isOneColor isOpaque isTransparent, toPremultipliedAlphaAvx2

[guzba]

before (sse2):

isOneColor ......................... 0.182 ms      0.201 ms    ±0.010  x1000
isTransparent ...................... 0.167 ms      0.189 ms    ±0.020  x1000
isOpaque ........................... 0.174 ms      0.188 ms    ±0.013  x1000

after (sse2):

isOneColor ......................... 0.168 ms      0.177 ms    ±0.012  x1000
isTransparent ...................... 0.157 ms      0.167 ms    ±0.010  x1000
isOpaque ........................... 0.162 ms      0.172 ms    ±0.015  x1000

after (avx2):

isOneColor ......................... 0.139 ms      0.144 ms    ±0.007  x1000
isTransparent ...................... 0.133 ms      0.139 ms    ±0.007  x1000
isOpaque ........................... 0.144 ms      0.149 ms    ±0.006  x1000

toPremultipliedAlpha ............... 1.003 ms      1.029 ms    ±0.042  x1000 [sse2]
toPremultipliedAlpha ............... 0.524 ms      0.548 ms    ±0.050  x1000 [avx2]