Does anybody have a working algorithm or full copy of code that optimizes matrix multiplication in the x86 assembly language?

I know a basic algorithm in C:
for (i=0;i<BLOCK_SIZE;i++)
for (j=0;j<BLOCK_SIZE;j++)
for (k=0;k<BLOCK_SIZE;k++)
c[i*MAX+j] += a[i*MAX+k]*b[k*MAX+j];

but, does anybody know a faster one?

Not sure if it's faster but there is discussion and code concerning a fast 4x4 matrix mult. algorithm here.

I hate to bring this up, but you could look into the alrogithms used behind DirectX technology if it is available, it has a very highly optimized matrix multiplication alrgorithm.

If you need this for graphics programming than the chances of getting your code to run faster than the funcitons supplied by openGL and DX is slim. But I am sure www.google.com will help you out with this.