+_loop_col: + cmp col, width + jge _end_col + + FILTER_H4 x0, x1, x3 + movh [dst + col], x1 + add col, 8 + + jmp _loop_col + +_end_col: + test widthleft, widthleft + jz _next_row
Again, the loop condition should be at the end; this is extremely overcomplicated and involves many redundant instructions and lines of code. This should look more like: +_loop_col: + FILTER_H4 x0, x1, x3 + movh [dst + col], x1 + add col, 8 + cmp col, width + jl loop_col Jason _______________________________________________ x265-devel mailing list [email protected] https://mailman.videolan.org/listinfo/x265-devel
