virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2025-01-29 22:00:58 +02:00
Code Issues Releases Activity

aarch64: me_cmp: Avoid using the non-unrolled codepath for the minimum unroll size

Browse Source 
Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
Martin Storsjö 2022-09-28 11:55:51 +03:00
parent 6f2ad7f951
commit 8089fe072e
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
libavcodec/aarch64/me_cmp_neon.S
View File

@ -471,7 +471,7 @@ function sse8_neon, export=1
movi v21.4s, #0
movi v20.4s, #0
cmp w4, #4
b.le 2f
b.lt 2f
// make 4 iterations at once
1:
@ -534,7 +534,7 @@ function sse4_neon, export=1
movi v16.4s, #0 // clear the result accumulator
cmp w4, #4
b.le 2f
b.lt 2f
// make 4 iterations at once
1:
@ -663,7 +663,7 @@ function vsse16_neon, export=1
cmp w4, #3 // check if we can make 3 iterations at once
usubl v31.8h, v0.8b, v1.8b // Signed difference of pix1[0] - pix2[0], first iteration
usubl2 v30.8h, v0.16b, v1.16b // Signed difference of pix1[0] - pix2[0], first iteration
b.le 2f
b.lt 2f
1: