arm64: int32_to_float_fmul neon asm

3% faster dts decoding on a cortex-a57.

                                 cortex-a57   cortex-a53
int32_to_float_fmul_array8_c:    1270.9       4475.6
int32_to_float_fmul_array8_neon:  328.6        569.2
int32_to_float_fmul_scalar_c:     928.5       4119.6
int32_to_float_fmul_scalar_neon:  309.1        524.1

1 files changed, 43 insertions, 0 deletions

diff --git a/libavcodec/aarch64/fmtconvert_init.c b/libavcodec/aarch64/fmtconvert_init.c
new file mode 100644
index 0000000000..0a55a1b88c
--- /dev/null
+++ b/libavcodec/aarch64/fmtconvert_init.c
@@ -0,0 +1,43 @@
+/*
+ * ARM optimized Format Conversion Utils
+ *
+ * This file is part of Libav.
+ *
+ * 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
+ * Lesser General Public License for more details.
+ *
+ * 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 <stdint.h>
+
+#include "libavutil/attributes.h"
+#include "libavutil/aarch64/cpu.h"
+#include "libavcodec/avcodec.h"
+#include "libavcodec/fmtconvert.h"
+
+void ff_int32_to_float_fmul_array8_neon(FmtConvertContext *c, float *dst,
+                                        const int32_t *src, const float *mul,
+                                        int len);
+void ff_int32_to_float_fmul_scalar_neon(float *dst, const int32_t *src,
+                                        float mul, int len);
+
+av_cold void ff_fmt_convert_init_aarch64(FmtConvertContext *c,
+                                         AVCodecContext *avctx)
+{
+    int cpu_flags = av_get_cpu_flags();
+
+    if (have_neon(cpu_flags)) {
+        c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_neon;
+        c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_neon;
+    }
+}