Iago Toral Quiroga writes:
> So that it has the same semantics as the scalar backend implementation. The
> helper will now take a simd width (which is always 8 in vec4 mode) and step
> as many scalar components as specified by that width, respecting the size of
> the scalar
So that it has the same semantics as the scalar backend implementation. The
helper will now take a simd width (which is always 8 in vec4 mode) and step
as many scalar components as specified by that width, respecting the size of
the scalar channels.
---
src/mesa/drivers/dri/i965/brw_ir_vec4.h