dcadsp: add int8x8_fmul_int32 to dsp context

It is currently declared as a macro who is set to inlinable functions,
among which a Neon and a default C implementations.

Add a DSP parameter to each inline function, unused except by the
default C implementation which calls a function from the DSP context.

On an Arrandale CPU, gain for an inlined SSE2 function vs. a call:
- Win32: 29 to 26 cycles
- Win64: 25 to 23 cycles

Signed-off-by: Janne Grunau <janne-libav@jannau.net>

1 files changed, 9 insertions, 0 deletions

diff --git a/libavcodec/dcadsp.c b/libavcodec/dcadsp.c
index 57d716e402..b98486422b 100644
--- a/libavcodec/dcadsp.c
+++ b/libavcodec/dcadsp.c
@@ -24,6 +24,14 @@
 #include "libavutil/intreadwrite.h"
 #include "dcadsp.h"
 
+static void int8x8_fmul_int32_c(float *dst, const int8_t *src, int scale)
+{
+    float fscale = scale / 16.0;
+    int i;
+    for (i = 0; i < 8; i++)
+        dst[i] = src[i] * fscale;
+}
+
 static void dca_lfe_fir_c(float *out, const float *in, const float *coefs,
                           int decifactor, float scale)
 {
@@ -78,5 +86,6 @@ av_cold void ff_dcadsp_init(DCADSPContext *s)
 {
     s->lfe_fir = dca_lfe_fir_c;
     s->qmf_32_subbands = dca_qmf_32_subbands;
+    s->int8x8_fmul_int32 = int8x8_fmul_int32_c;
     if (ARCH_ARM) ff_dcadsp_init_arm(s);
 }