/*
- * This file is part of FFmpeg.
+ * Copyright (C) 2009 Loren Merritt <lorenm@u.washignton.edu>
*
- * FFmpeg is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
+ * This file is part of Libav.
*
- * FFmpeg is distributed in the hope that it will be useful,
+ * Libav is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * Libav is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
*
- * You should have received a copy of the GNU General Public License along
- * with FFmpeg; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with Libav; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
+#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
-#include "libavutil/x86_cpu.h"
+#include "libavutil/mem.h"
+#include "libavutil/x86/asm.h"
#include "libavfilter/gradfun.h"
+#if HAVE_INLINE_ASM
+
DECLARE_ALIGNED(16, static const uint16_t, pw_7f)[8] = {0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F};
DECLARE_ALIGNED(16, static const uint16_t, pw_ff)[8] = {0xFF,0xFF,0xFF,0xFF,0xFF,0xFF,0xFF,0xFF};
-void ff_gradfun_filter_line_mmx2(uint8_t *dst, uint8_t *src, uint16_t *dc, int width, int thresh, const uint16_t *dithers)
+#if HAVE_MMXEXT_INLINE
+static void gradfun_filter_line_mmxext(uint8_t *dst, uint8_t *src, uint16_t *dc,
+ int width, int thresh,
+ const uint16_t *dithers)
{
-#if HAVE_MMX
intptr_t x;
if (width & 3) {
x = width & ~3;
"rm"(thresh), "m"(*dithers), "m"(*pw_7f)
:"memory"
);
-#endif
}
+#endif
-void ff_gradfun_filter_line_ssse3(uint8_t *dst, uint8_t *src, uint16_t *dc, int width, int thresh, const uint16_t *dithers)
+#if HAVE_SSSE3_INLINE
+static void gradfun_filter_line_ssse3(uint8_t *dst, uint8_t *src, uint16_t *dc, int width, int thresh, const uint16_t *dithers)
{
-#if HAVE_SSSE3
intptr_t x;
if (width & 7) {
// could be 10% faster if I somehow eliminated this
"rm"(thresh), "m"(*dithers), "m"(*pw_7f)
:"memory"
);
-#endif // HAVE_SSSE3
}
+#endif /* HAVE_SSSE3_INLINE */
-void ff_gradfun_blur_line_sse2(uint16_t *dc, uint16_t *buf, uint16_t *buf1, uint8_t *src, int src_linesize, int width)
+#if HAVE_SSE2_INLINE
+static void gradfun_blur_line_sse2(uint16_t *dc, uint16_t *buf, uint16_t *buf1, uint8_t *src, int src_linesize, int width)
{
-#if HAVE_SSE
#define BLURV(load)\
intptr_t x = -2*width;\
__asm__ volatile(\
} else {
BLURV("movdqa");
}
-#endif // HAVE_SSE
+}
+#endif /* HAVE_SSE2_INLINE */
+
+#endif /* HAVE_INLINE_ASM */
+
+av_cold void ff_gradfun_init_x86(GradFunContext *gf)
+{
+ int cpu_flags = av_get_cpu_flags();
+
+#if HAVE_MMXEXT_INLINE
+ if (cpu_flags & AV_CPU_FLAG_MMXEXT)
+ gf->filter_line = gradfun_filter_line_mmxext;
+#endif
+#if HAVE_SSSE3_INLINE
+ if (cpu_flags & AV_CPU_FLAG_SSSE3)
+ gf->filter_line = gradfun_filter_line_ssse3;
+#endif
+#if HAVE_SSE2_INLINE
+ if (cpu_flags & AV_CPU_FLAG_SSE2)
+ gf->blur_line = gradfun_blur_line_sse2;
+#endif
}