RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-02-07 23:32:33 +00:00
Code Issues Projects Releases Wiki Activity

avcodec/x86/flacdsp: fix bug in decorrelation

Browse Source 
Fixes #9297
This commit is contained in:
Paul B Mahol 2022-09-03 23:41:38 +02:00
parent ea5b375e0e
commit 1e202d89c9
2 changed files with 46 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
libavcodec/x86/flacdsp.asm
View File

@ -23,6 +23,10 @@
%include "libavutil/x86/x86util.asm" %include "libavutil/x86/x86util.asm"
SECTION_RODATA
vector: db 0,1,4,5,8,9,12,13,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,0,1,4,5,8,9,12,13,
SECTION .text SECTION .text
%macro PMACSDQL 5 %macro PMACSDQL 5
@ -89,6 +93,9 @@ LPC_32 sse4
;---------------------------------------------------------------------------------- ;----------------------------------------------------------------------------------
%macro FLAC_DECORRELATE_16 3-4 %macro FLAC_DECORRELATE_16 3-4
cglobal flac_decorrelate_%1_16, 2, 4, 4, out, in0, in1, len cglobal flac_decorrelate_%1_16, 2, 4, 4, out, in0, in1, len
%ifidn %1, indep2
VBROADCASTI128 m2, [vector]
%endif
%if ARCH_X86_32 %if ARCH_X86_32
mov lend, lenm mov lend, lenm
%endif %endif
@ -112,11 +119,17 @@ align 16
%endif %endif
%ifnidn %1, indep2 %ifnidn %1, indep2
p%4d m2, m0, m1 p%4d m2, m0, m1
packssdw m%2, m%2
packssdw m%3, m%3
punpcklwd m%2, m%3
psllw m%2, m3
%else
pslld m%2, m3
pslld m%3, m3
pshufb m%2, m%2, m2
pshufb m%3, m%3, m2
punpcklwd m%2, m%3
%endif %endif
packssdw m%2, m%2
packssdw m%3, m%3
punpcklwd m%2, m%3
psllw m%2, m3
mova [outq + lenq], m%2 mova [outq + lenq], m%2
add lenq, 16 add lenq, 16
jl .loop jl .loop
@ -292,7 +305,7 @@ align 16
REP_RET REP_RET
%endmacro %endmacro
INIT_XMM sse2 INIT_XMM ssse3
FLAC_DECORRELATE_16 indep2, 0, 1 ; Reuse stereo 16bits macro FLAC_DECORRELATE_16 indep2, 0, 1 ; Reuse stereo 16bits macro
FLAC_DECORRELATE_INDEP 32, 2, 3, d FLAC_DECORRELATE_INDEP 32, 2, 3, d
FLAC_DECORRELATE_INDEP 16, 4, 3, w FLAC_DECORRELATE_INDEP 16, 4, 3, w

45
libavcodec/x86/flacdsp_init.c
View File

@ -34,7 +34,9 @@ void ff_flac_decorrelate_ls_##fmt##_##opt(uint8_t **out, int32_t **in, int chann
void ff_flac_decorrelate_rs_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \ void ff_flac_decorrelate_rs_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \
int len, int shift); \ int len, int shift); \
void ff_flac_decorrelate_ms_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \ void ff_flac_decorrelate_ms_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \
int len, int shift); \ int len, int shift);
#define DECORRELATE_IFUNCS(fmt, opt) \
void ff_flac_decorrelate_indep2_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \ void ff_flac_decorrelate_indep2_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \
int len, int shift); \ int len, int shift); \
void ff_flac_decorrelate_indep4_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \ void ff_flac_decorrelate_indep4_##fmt##_##opt(uint8_t **out, int32_t **in, int channels, \
@ -48,6 +50,10 @@ DECORRELATE_FUNCS(16, sse2);
DECORRELATE_FUNCS(16, avx); DECORRELATE_FUNCS(16, avx);
DECORRELATE_FUNCS(32, sse2); DECORRELATE_FUNCS(32, sse2);
DECORRELATE_FUNCS(32, avx); DECORRELATE_FUNCS(32, avx);
DECORRELATE_IFUNCS(16, ssse3);
DECORRELATE_IFUNCS(16, avx);
DECORRELATE_IFUNCS(32, ssse3);
DECORRELATE_IFUNCS(32, avx);
av_cold void ff_flacdsp_init_x86(FLACDSPContext *c, enum AVSampleFormat fmt, int channels) av_cold void ff_flacdsp_init_x86(FLACDSPContext *c, enum AVSampleFormat fmt, int channels)
{ {
@ -56,31 +62,36 @@ av_cold void ff_flacdsp_init_x86(FLACDSPContext *c, enum AVSampleFormat fmt, int
if (EXTERNAL_SSE2(cpu_flags)) { if (EXTERNAL_SSE2(cpu_flags)) {
if (fmt == AV_SAMPLE_FMT_S16) { if (fmt == AV_SAMPLE_FMT_S16) {
if (channels == 2)
c->decorrelate[0] = ff_flac_decorrelate_indep2_16_sse2;
else if (channels == 4)
c->decorrelate[0] = ff_flac_decorrelate_indep4_16_sse2;
else if (channels == 6)
c->decorrelate[0] = ff_flac_decorrelate_indep6_16_sse2;
else if (ARCH_X86_64 && channels == 8)
c->decorrelate[0] = ff_flac_decorrelate_indep8_16_sse2;
c->decorrelate[1] = ff_flac_decorrelate_ls_16_sse2; c->decorrelate[1] = ff_flac_decorrelate_ls_16_sse2;
c->decorrelate[2] = ff_flac_decorrelate_rs_16_sse2; c->decorrelate[2] = ff_flac_decorrelate_rs_16_sse2;
c->decorrelate[3] = ff_flac_decorrelate_ms_16_sse2; c->decorrelate[3] = ff_flac_decorrelate_ms_16_sse2;
} else if (fmt == AV_SAMPLE_FMT_S32) { } else if (fmt == AV_SAMPLE_FMT_S32) {
if (channels == 2)
c->decorrelate[0] = ff_flac_decorrelate_indep2_32_sse2;
else if (channels == 4)
c->decorrelate[0] = ff_flac_decorrelate_indep4_32_sse2;
else if (channels == 6)
c->decorrelate[0] = ff_flac_decorrelate_indep6_32_sse2;
else if (ARCH_X86_64 && channels == 8)
c->decorrelate[0] = ff_flac_decorrelate_indep8_32_sse2;
c->decorrelate[1] = ff_flac_decorrelate_ls_32_sse2; c->decorrelate[1] = ff_flac_decorrelate_ls_32_sse2;
c->decorrelate[2] = ff_flac_decorrelate_rs_32_sse2; c->decorrelate[2] = ff_flac_decorrelate_rs_32_sse2;
c->decorrelate[3] = ff_flac_decorrelate_ms_32_sse2; c->decorrelate[3] = ff_flac_decorrelate_ms_32_sse2;
} }
} }
if (EXTERNAL_SSSE3(cpu_flags)) {
if (fmt == AV_SAMPLE_FMT_S16) {
if (channels == 2)
c->decorrelate[0] = ff_flac_decorrelate_indep2_16_ssse3;
else if (channels == 4)
c->decorrelate[0] = ff_flac_decorrelate_indep4_16_ssse3;
else if (channels == 6)
c->decorrelate[0] = ff_flac_decorrelate_indep6_16_ssse3;
else if (ARCH_X86_64 && channels == 8)
c->decorrelate[0] = ff_flac_decorrelate_indep8_16_ssse3;
} else if (fmt == AV_SAMPLE_FMT_S32) {
if (channels == 2)
c->decorrelate[0] = ff_flac_decorrelate_indep2_32_ssse3;
else if (channels == 4)
c->decorrelate[0] = ff_flac_decorrelate_indep4_32_ssse3;
else if (channels == 6)
c->decorrelate[0] = ff_flac_decorrelate_indep6_32_ssse3;
else if (ARCH_X86_64 && channels == 8)
c->decorrelate[0] = ff_flac_decorrelate_indep8_32_ssse3;
}
}
if (EXTERNAL_SSE4(cpu_flags)) { if (EXTERNAL_SSE4(cpu_flags)) {
c->lpc32 = ff_flac_lpc_32_sse4; c->lpc32 = ff_flac_lpc_32_sse4;
} }