On 03/12/2015 03:16 PM, chen wrote:
I use 'pxor m7,m7' to replace your [pb_0], but it is same cycles in
IACA, the bottleneck on Port0
Not sure how about performance on old CPU
I would have used something like that but there are no available
registers by that point. They are used up on holding other
constants(pw_planar..) in the case of x86_64 and there just aren't
enough in x86_32. Performance on my old CPU seems unaffected by using
constants in registers or from memory.
_______________________________________________
x265-devel mailing list
[email protected]
https://mailman.videolan.org/listinfo/x265-devel
