<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html; charset=ISO-8859-1" http-equiv="Content-Type"> </head> <body text="#000000" bgcolor="#ffffff"> I update this in my branch <a href="http://cgit.freedesktop.org/%7Epodain/pixman/?h=neon_bilinear">http://cgit.freedesktop.org/~podain/pixman/?h=neon_bilinear</a> Fixed cache preload of src scanlines to work correctly and added cache preload for mask and dst scanlines. Some mistakes in comments are corrected. Thanks, Taekyun Kim On 09/21/2011 05:38 PM, Taekyun Kim wrote: <blockquote cite="mid:1316594285-2773-1-git-send-email-podain77@gmail.com" type="cite"> <pre wrap="">From: Taekyun Kim <a class="moz-txt-link-rfc2396E" href="mailto:tkq.kim@samsung.com"><tkq.kim@samsung.com></a> Hi, all Bilinear functions in pixman-arm-neon-asm-bilinear.S have lots of room for improvement. With some clean-up to bring tail/head scheme for them and did instruction scheduling for mostly used over_8888_8888. Passed make check. I'm not sure that the scheduling is done nicely, but at least I've got speed up on both cortex-a8 and a9 devices. Performance of before/after on cortex-a8 @ 1GHz << 2000 x 2000 with scale factor close to 1.x >> before : 39.71 Mpix/s after : 60.39 Mpix/s Performance of before/after on cortex-a9 @ 1.2GHz << 2000 x 2000 with scale factor close to 1.x >> before : 43.31 Mpix/s after : 65.83 Mpix/s I will do optimization of other functions too based on the perfstat results of popular cairo traces. -- Best Regards, Taekyun Kim Taekyun Kim (4): ARM: NEON: Some cleanup of bilinear scanline functions ARM: NEON: Bilinear macro template for instruction scheduling ARM: NEON: Replace old bilinear scanline generator with new template ARM: NEON: Instruction scheduling of bilinear over_8888_8888 pixman/pixman-arm-neon-asm-bilinear.S | 766 ++++++++++++++++++++++++++------- 1 files changed, 605 insertions(+), 161 deletions(-) </pre> </blockquote> </body> </html>