[FFmpeg-devel] [PATCH 1/2] Add vector_fmul_step_scalar for WMA

[Mans Rullgard]

---
 libavcodec/dsputil.c |   16 ++++++++++++++++
 libavcodec/dsputil.h |    3 +++
 2 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/libavcodec/dsputil.c b/libavcodec/dsputil.c
index 894e592..d55f889 100644
--- a/libavcodec/dsputil.c
+++ b/libavcodec/dsputil.c
@@ -4074,6 +4074,21 @@ static void vector_fmul_add_c(float *dst, const float *src0, const float *src1,
         dst[i] = src0[i] * src1[i] + src2[i];
 }
 
+static void vector_fmul_step_scalar_c(float *dst, const float *src0,
+                                      const float *src1, float src2,
+                                      int shift, int len)
+{
+    int i;
+    if (shift >= 0) {
+        for (i = 0; i < len; i++)
+            dst[i] = src0[i] * src1[i<<shift] * src2;
+    } else {
+        shift = -shift;
+        for (i = 0; i < len; i++)
+            dst[i] = src0[i] * src1[i>>shift] * src2;
+    }
+}
+
 void ff_vector_fmul_window_c(float *dst, const float *src0, const float *src1, const float *win, float add_bias, int len){
     int i,j;
     dst += len;
@@ -4799,6 +4814,7 @@ void dsputil_init(DSPContext* c, AVCodecContext *avctx)
     c->scalarproduct_float = scalarproduct_float_c;
     c->butterflies_float = butterflies_float_c;
     c->vector_fmul_scalar = vector_fmul_scalar_c;
+    c->vector_fmul_step_scalar = vector_fmul_step_scalar_c;
 
     c->vector_fmul_sv_scalar[0] = vector_fmul_sv_scalar_2_c;
     c->vector_fmul_sv_scalar[1] = vector_fmul_sv_scalar_4_c;
diff --git a/libavcodec/dsputil.h b/libavcodec/dsputil.h
index dd7b22d..e3a18e2 100644
--- a/libavcodec/dsputil.h
+++ b/libavcodec/dsputil.h
@@ -392,6 +392,9 @@ typedef struct DSPContext {
     void (*vector_fmul_add)(float *dst, const float *src0, const float *src1, const float *src2, int len);
     /* assume len is a multiple of 4, and arrays are 16-byte aligned */
     void (*vector_fmul_window)(float *dst, const float *src0, const float *src1, const float *win, float add_bias, int len);
+    void (*vector_fmul_step_scalar)(float *dst, const float *src0,
+                                    const float *src1, float src2,
+                                    int shift, int len);
     /* assume len is a multiple of 8, and arrays are 16-byte aligned */
     void (*int32_to_float_fmul_scalar)(float *dst, const int *src, float mul, int len);
     void (*vector_clipf)(float *dst /* align 16 */, const float *src /* align 16 */, float min, float max, int len /* align 16 */);
-- 
1.6.4.4