RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

avcodec/x86/ac3dsp_init: Remove obsolete 3dnow, MMX(EXT), SSE functions 

x64 always has MMX, MMXEXT, SSE and SSE2 and this means
that some functions for MMX, MMXEXT and 3dnow are always
overridden by other functions (unless one e.g. explicitly
disables SSE2) for x64. So given that the only systems that
benefit from these functions are truely ancient 32bit x86s
they are removed.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
This commit is contained in:
Andreas Rheinhardt 2022-06-07 00:55:25 +02:00
parent e02ffed004
commit fd98594a88
2 changed files with 0 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
libavcodec/x86/ac3dsp.asm
View File

@ -63,14 +63,7 @@ cglobal ac3_exponent_min, 3, 4, 2, exp, reuse_blks, expn, offset
REP_RET
%endmacro
%define LOOP_ALIGN
INIT_MMX mmx
AC3_EXPONENT_MIN
%if HAVE_MMXEXT_EXTERNAL
%define LOOP_ALIGN ALIGN 16
INIT_MMX mmxext
AC3_EXPONENT_MIN
%endif
%if HAVE_SSE2_EXTERNAL
INIT_XMM sse2
AC3_EXPONENT_MIN
@ -81,60 +74,6 @@ AC3_EXPONENT_MIN
; void ff_float_to_fixed24(int32_t *dst, const float *src, unsigned int len)
;-----------------------------------------------------------------------------
; The 3DNow! version is not bit-identical because pf2id uses truncation rather
; than round-to-nearest.
INIT_MMX 3dnow
cglobal float_to_fixed24, 3, 3, 0, dst, src, len
movq m0, [pf_1_24]
.loop:
movq m1, [srcq ]
movq m2, [srcq+8 ]
movq m3, [srcq+16]
movq m4, [srcq+24]
pfmul m1, m0
pfmul m2, m0
pfmul m3, m0
pfmul m4, m0
pf2id m1, m1
pf2id m2, m2
pf2id m3, m3
pf2id m4, m4
movq [dstq ], m1
movq [dstq+8 ], m2
movq [dstq+16], m3
movq [dstq+24], m4
add srcq, 32
add dstq, 32
sub lend, 8
ja .loop
femms
RET
INIT_XMM sse
cglobal float_to_fixed24, 3, 3, 3, dst, src, len
movaps m0, [pf_1_24]
.loop:
movaps m1, [srcq ]
movaps m2, [srcq+16]
mulps m1, m0
mulps m2, m0
cvtps2pi mm0, m1
movhlps m1, m1
cvtps2pi mm1, m1
cvtps2pi mm2, m2
movhlps m2, m2
cvtps2pi mm3, m2
movq [dstq ], mm0
movq [dstq+ 8], mm1
movq [dstq+16], mm2
movq [dstq+24], mm3
add srcq, 32
add dstq, 32
sub lend, 8
ja .loop
emms
RET
INIT_XMM sse2
cglobal float_to_fixed24, 3, 3, 9, dst, src, len
movaps m0, [pf_1_24]

18
libavcodec/x86/ac3dsp_init.c
View File

@ -24,12 +24,8 @@
#include "libavutil/x86/cpu.h"
#include "libavcodec/ac3dsp.h"
void ff_ac3_exponent_min_mmx (uint8_t *exp, int num_reuse_blocks, int nb_coefs);
void ff_ac3_exponent_min_mmxext(uint8_t *exp, int num_reuse_blocks, int nb_coefs);
void ff_ac3_exponent_min_sse2 (uint8_t *exp, int num_reuse_blocks, int nb_coefs);
void ff_float_to_fixed24_3dnow(int32_t *dst, const float *src, unsigned int len);
void ff_float_to_fixed24_sse (int32_t *dst, const float *src, unsigned int len);
void ff_float_to_fixed24_sse2 (int32_t *dst, const float *src, unsigned int len);
int ff_ac3_compute_mantissa_size_sse2(uint16_t mant_cnt[6][16]);
@ -41,20 +37,6 @@ av_cold void ff_ac3dsp_init_x86(AC3DSPContext *c, int bit_exact)
{
int cpu_flags = av_get_cpu_flags();
if (EXTERNAL_MMX(cpu_flags)) {
c->ac3_exponent_min = ff_ac3_exponent_min_mmx;
}
if (EXTERNAL_AMD3DNOW(cpu_flags)) {
if (!bit_exact) {
c->float_to_fixed24 = ff_float_to_fixed24_3dnow;
}
}
if (EXTERNAL_MMXEXT(cpu_flags)) {
c->ac3_exponent_min = ff_ac3_exponent_min_mmxext;
}
if (EXTERNAL_SSE(cpu_flags)) {
c->float_to_fixed24 = ff_float_to_fixed24_sse;
}
if (EXTERNAL_SSE2(cpu_flags)) {
c->ac3_exponent_min = ff_ac3_exponent_min_sse2;
c->float_to_fixed24 = ff_float_to_fixed24_sse2;