x64 always has MMX, MMXEXT, SSE and SSE2 and this means
that some functions for MMX, MMXEXT, SSE and 3dnow are always
overridden by other functions (unless one e.g. explicitly
disables SSE2). This commit therefore disables such CAVS-dsp
functions at compile-time.
Signed-off-by: Andreas Rheinhardt <andreas.rheinha...@outlook.com>
---
libavcodec/x86/cavsdsp.c | 20 +++++++++++++++-----
libavcodec/x86/cavsidct.asm | 2 ++
2 files changed, 17 insertions(+), 5 deletions(-)
diff --git a/libavcodec/x86/cavsdsp.c b/libavcodec/x86/cavsdsp.c
index f974f93fc0..fea9daa0ff 100644
--- a/libavcodec/x86/cavsdsp.c
+++ b/libavcodec/x86/cavsdsp.c
@@ -38,6 +38,7 @@
#if HAVE_MMX_EXTERNAL
+#if ARCH_X86_32
void ff_cavs_idct8_mmx(int16_t *out, const int16_t *in);
static void cavs_idct8_add_mmx(uint8_t *dst, int16_t *block, ptrdiff_t stride)
@@ -46,6 +47,7 @@ static void cavs_idct8_add_mmx(uint8_t *dst, int16_t *block,
ptrdiff_t stride)
ff_cavs_idct8_mmx(b2, block);
ff_add_pixels_clamped_mmx(b2, dst, stride);
}
+#endif /* ARCH_X86_32 */
void ff_cavs_idct8_sse2(int16_t *out, const int16_t *in);
@@ -335,11 +337,13 @@ static void put_cavs_qpel8_mc00_mmx(uint8_t *dst, const
uint8_t *src,
ff_put_pixels8_mmx(dst, src, stride, 8);
}
+#if ARCH_X86_32
static void avg_cavs_qpel8_mc00_mmx(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride)
{
ff_avg_pixels8_mmx(dst, src, stride, 8);
}
+#endif
static void avg_cavs_qpel8_mc00_mmxext(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride)
@@ -347,6 +351,7 @@ static void avg_cavs_qpel8_mc00_mmxext(uint8_t *dst, const
uint8_t *src,
ff_avg_pixels8_mmxext(dst, src, stride, 8);
}
+#if ARCH_X86_32
static void put_cavs_qpel16_mc00_mmx(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride)
{
@@ -364,6 +369,7 @@ static void avg_cavs_qpel16_mc00_mmxext(uint8_t *dst, const
uint8_t *src,
{
ff_avg_pixels16_mmxext(dst, src, stride, 16);
}
+#endif
static void put_cavs_qpel16_mc00_sse2(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride)
@@ -382,13 +388,15 @@ static av_cold void cavsdsp_init_mmx(CAVSDSPContext *c,
AVCodecContext *avctx)
{
#if HAVE_MMX_EXTERNAL
- c->put_cavs_qpel_pixels_tab[0][0] = put_cavs_qpel16_mc00_mmx;
c->put_cavs_qpel_pixels_tab[1][0] = put_cavs_qpel8_mc00_mmx;
+#if ARCH_X86_32
+ c->put_cavs_qpel_pixels_tab[0][0] = put_cavs_qpel16_mc00_mmx;
c->avg_cavs_qpel_pixels_tab[0][0] = avg_cavs_qpel16_mc00_mmx;
c->avg_cavs_qpel_pixels_tab[1][0] = avg_cavs_qpel8_mc00_mmx;
c->cavs_idct8_add = cavs_idct8_add_mmx;
c->idct_perm = FF_IDCT_PERM_TRANSPOSE;
+#endif /* ARCH_X86_32 */
#endif /* HAVE_MMX_EXTERNAL */
}
@@ -408,7 +416,7 @@ CAVS_MC(avg_, 8, mmxext)
CAVS_MC(avg_, 16, mmxext)
#endif /* HAVE_MMXEXT_INLINE */
-#if HAVE_AMD3DNOW_INLINE
+#if ARCH_X86_32 && HAVE_AMD3DNOW_INLINE
QPEL_CAVS(put_, PUT_OP, 3dnow)
QPEL_CAVS(avg_, AVG_3DNOW_OP, 3dnow)
@@ -425,7 +433,7 @@ static av_cold void cavsdsp_init_3dnow(CAVSDSPContext *c,
DSPFUNC(avg, 0, 16, 3dnow);
DSPFUNC(avg, 1, 8, 3dnow);
}
-#endif /* HAVE_AMD3DNOW_INLINE */
+#endif /* ARCH_X86_32 && HAVE_AMD3DNOW_INLINE */
av_cold void ff_cavsdsp_init_x86(CAVSDSPContext *c, AVCodecContext *avctx)
{
@@ -434,10 +442,10 @@ av_cold void ff_cavsdsp_init_x86(CAVSDSPContext *c,
AVCodecContext *avctx)
if (X86_MMX(cpu_flags))
cavsdsp_init_mmx(c, avctx);
-#if HAVE_AMD3DNOW_INLINE
+#if ARCH_X86_32 && HAVE_AMD3DNOW_INLINE
if (INLINE_AMD3DNOW(cpu_flags))
cavsdsp_init_3dnow(c, avctx);
-#endif /* HAVE_AMD3DNOW_INLINE */
+#endif /* ARCH_X86_32 && HAVE_AMD3DNOW_INLINE */
#if HAVE_MMXEXT_INLINE
if (INLINE_MMXEXT(cpu_flags)) {
DSPFUNC(put, 0, 16, mmxext);
@@ -448,7 +456,9 @@ av_cold void ff_cavsdsp_init_x86(CAVSDSPContext *c,
AVCodecContext *avctx)
#endif
#if HAVE_MMX_EXTERNAL
if (EXTERNAL_MMXEXT(cpu_flags)) {
+#if ARCH_X86_32
c->avg_cavs_qpel_pixels_tab[0][0] = avg_cavs_qpel16_mc00_mmxext;
+#endif
c->avg_cavs_qpel_pixels_tab[1][0] = avg_cavs_qpel8_mc00_mmxext;
}
#endif
diff --git a/libavcodec/x86/cavsidct.asm b/libavcodec/x86/cavsidct.asm
index 6c768c2646..070b46a6cc 100644
--- a/libavcodec/x86/cavsidct.asm
+++ b/libavcodec/x86/cavsidct.asm
@@ -107,6 +107,7 @@ SECTION .text
SUMSUB_BA w, 1, 0 ; m1 = dst3, m0 = dst4
%endmacro
+%if ARCH_X86_32
INIT_MMX mmx
cglobal cavs_idct8, 2, 4, 8, 8 * 16, out, in, cnt, tmp
mov cntd, 2
@@ -168,6 +169,7 @@ cglobal cavs_idct8, 2, 4, 8, 8 * 16, out, in, cnt, tmp
jg .loop_2
RET
+%endif
INIT_XMM sse2
cglobal cavs_idct8, 2, 2, 8 + ARCH_X86_64, 0 - 8 * 16, out, in
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
