Mesa fails to optimize the sum of multiple vector multiplications into a matrix multiplication
Submitted by Samuel Rødal
Assigned to Ian Romanick
vec3(v.znf1+v.ynf2+v.x*nf3) could be optimized as v.zyx * mat3(nf1, nf2, nf3)
This gives a significant performance improvement at least on r600.
To upload designs, you'll need to enable LFS and have an admin enable hashed storage. More information