[x265] Some more Arm64 patches to bring performance up on Graviton processors

[Pop, Sebastian]

Thanks Min Chen for your review.


> [MC] Why not LD1? same as STP


As you recommended, please see attached a patch that saves about 200 instructions by folding LDR+ADD into a post-increment LD1.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20220326/af9afd2c/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0005-arm64-use-better-addressing-modes-with-ld1-st1.patch
Type: text/x-patch
Size: 57634 bytes
Desc: 0005-arm64-use-better-addressing-modes-with-ld1-st1.patch
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20220326/af9afd2c/attachment-0001.bin>