ffmpeg/FFmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2024-09-19 21:06:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

libavcodec/hevc: reuse scale_store on idct32x32_neon

Browse Source 
Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
xufuji456 2023-02-24 20:31:29 +08:00 committed by Martin Storsjö
parent 4b4de07721
commit 05438db024
1 changed files with 2 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
libavcodec/arm/hevcdsp_idct_neon.S
View File

@ -876,28 +876,14 @@ function func_tr_32x4_\name
movrel r9, trans + 32
vld1.s16 {q0}, [r9, :128]!
vld1.s16 {q1}, [r9, :128]
add r4, sp, #2048
bl tr_block1
add r4, sp, #2048
vld1.s16 {q14-q15}, [r4, :128]!
butterfly32 q14, q10, q15, q11
scale32 d22, d23, d20, d21, q1, q14, q10, q15, \shift
vld1.s16 {q14-q15}, [r4, :128]!
butterfly32 q14, q12, q15, q13
scale32 d2, d3, d28, d29, q1, q14, q12, q15, \shift
transpose8_4x4 d22, d20, d2, d28
transpose8_4x4 d29, d3, d21, d23
mov r1, r11
mov r2, #64
mov r8, #-64
add r3, r11, #(56 + 3 * 64)
store16 d22, d23, d20, d21, d2, d3, d28, d29, r8
@ reload multiplication coefficiens to q1
vld1.s16 {q1}, [r9, :128]
scale_store \shift
bl tr_block2
add r1, r11, #8