m4x4 - vs

Computes the product of a 4-component vector and a 4x4 matrix.

Syntax

where

• dst is the destination register.
• src0 is a source register.
• src1 is a source register that represents a 4x4 matrix. This means it represents 4 constant registers.

Remarks

The xyzw (default) mask is required for the destination register. Negate and swizzle modifiers are allowed for src0, but not for src1.

Swizzle and negate modifiers are invalid for the src0 register. The dest and src0 registers cannot be the same.

The following code fragment shows the operations performed.

dest.x = (src0.x * src1.x) + (src0.y * src1.y) + (src0.z * src1.z) + 
		(src0.w * src1.w);
dest.y = (src0.x * src2.x) + (src0.y * src2.y) + (src0.z * src2.z) + 
		(src0.w * src2.w);
dest.z = (src0.x * src3.x) + (src0.y * src3.y) + (src0.z * src3.z) + 
		(src0.w * src3.w);
dest.w = (src0.x * src4.x) + (src0.y * src4.y) + (src0.z * src4.z) + 
		(src0.w * src4.w);

The input vector is in register src0. The input 4x4 matrix is in register src1, and the next three higher registers, as shown in the expansion below.

This operation is commonly used for transforming a position by a projection matrix. This instruction is implemented as a series of dot products as shown here.

m4x4   r0.xyzw, r1, c0    will be expanded to:

dp4   r0.x, r1, c0
dp4   r0.y, r1, c1
dp4   r0.z, r1, c2
dp4   r0.w, r1, c3