This is the main stuff that x86mph offers. But there are some more utilities not listed here.

As we are working with SSE, which is kind with 16-byte-aligned memory, x86mph includes “amalloc” and “afree”, which allows to allocate memory specifying a special alignment (it has to be power of two)

A high-featured transformation and lightning engine (TnL) that takes care of transforming your vertices for rendering, calculating lights (including Specular reflection; directional, point, and spot lightning), fog effects, and more....

Matrix function to make matrix calculations. For example, multipliying 4x4 matrices, which are very common when working on games or other 3D programs.

Vector calculation: adding, substracting, multiplying, dividing

Transorms images from 32-bit to 64-bit and from 64-bit to 32-bit. Also allows to swap channels (i.e. RGBA -> ABGR)

Inverts channels, including 32-bit and 64-bit images

Take the maximum advantage of the x87 FPU by using it's instructions: Sine, Cosine, Tangent, and Logarithm.