Lines Matching refs:we
233 @ Depending on the width of the loop filter, we either use d16-d19
432 @ matter for the flat8out part below, since we only update those pixels
727 @ Move r0/r12 forward by 2 pixels; we don't need to rewrite the
818 @ Even though only 6 pixels per row have been changed, we write the
835 @ If we didn't need to do the flat8in part, we use the same writeback
886 @ If we did the flat8out part, we get the output in
911 @ If we didn't do the flat8out part, the output is left in the
972 @ we can't take advantage of q registers for the transpose, since