Stowage/ffmpeg
2
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2026-02-16 03:20:25 +00:00
Code Issues Projects Releases Packages Wiki Activity

avcodec/x86/hevc/add_res: Avoid unnecessary modification

Browse source 
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
This commit is contained in:
Andreas Rheinhardt 2025-10-30 09:58:13 +01:00
parent f4d9fb0bd0
commit d355749ca6
1 changed files with 14 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

32
libavcodec/x86/hevc/add_res.asm
View file

@ -27,9 +27,9 @@ cextern pw_1023
%define max_pixels_10 pw_1023
; the add_res macros and functions were largely inspired by h264_idct.asm from the x264 project
%macro ADD_RES_MMX_4_8 0
mova m0, [r1]
mova m2, [r1+8]
%macro ADD_RES_MMX_4_8 1
mova m0, [r1+%1]
mova m2, [r1+%1+8]
movd m1, [r0]
movd m3, [r0+r2]
@ -50,27 +50,26 @@ INIT_MMX mmxext
; void ff_hevc_add_residual_4_8_mmxext(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
cglobal hevc_add_residual_4_8, 3, 3, 6
pxor m4, m4
ADD_RES_MMX_4_8
add r1, 16
ADD_RES_MMX_4_8 0
lea r0, [r0+r2*2]
ADD_RES_MMX_4_8
ADD_RES_MMX_4_8 16
RET
%macro ADD_RES_SSE_8_8 0
%macro ADD_RES_SSE_8_8 1
movq m0, [r0]
movq m1, [r0+r2]
punpcklbw m0, m4
punpcklbw m1, m4
paddsw m0, [r1]
paddsw m1, [r1+16]
paddsw m0, [r1+%1]
paddsw m1, [r1+%1+16]
packuswb m0, m1
movq m2, [r0+r2*2]
movq m3, [r0+r3]
punpcklbw m2, m4
punpcklbw m3, m4
paddsw m2, [r1+32]
paddsw m3, [r1+48]
paddsw m2, [r1+%1+32]
paddsw m3, [r1+%1+48]
packuswb m2, m3
movq [r0], m0
@ -124,10 +123,9 @@ INIT_XMM sse2
cglobal hevc_add_residual_8_8, 3, 4, 5
pxor m4, m4
lea r3, [r2*3]
ADD_RES_SSE_8_8
add r1, 64
ADD_RES_SSE_8_8 0
lea r0, [r0+r2*4]
ADD_RES_SSE_8_8
ADD_RES_SSE_8_8 64
RET
; void ff_hevc_add_residual_16_8_<opt>(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
@ -292,9 +290,8 @@ cglobal hevc_add_residual_4_10, 3, 3, 6
pxor m2, m2
mova m3, [max_pixels_10]
ADD_RES_MMX_4_10 r0, r2, r1
add r1, 16
lea r0, [r0+2*r2]
ADD_RES_MMX_4_10 r0, r2, r1
ADD_RES_MMX_4_10 r0, r2, r1+16
RET
INIT_XMM sse2
@ -305,8 +302,7 @@ cglobal hevc_add_residual_8_10, 3, 4, 6
ADD_RES_SSE_8_10 r0, r2, r3, r1
lea r0, [r0+r2*4]
add r1, 64
ADD_RES_SSE_8_10 r0, r2, r3, r1
ADD_RES_SSE_8_10 r0, r2, r3, r1+64
RET
cglobal hevc_add_residual_16_10, 3, 5, 6