hwcontext_cuda: implement frames_get_constraints

[ffmpeg] / libavutil / float_dsp.h

diff --git a/libavutil/float_dsp.h b/libavutil/float_dsp.h
index ec57b36f791475aefb9a4d945102594d41b9ef93..3142df4fd35084ffd950877be524851d6b1fa412 100644 (file)
--- a/libavutil/float_dsp.h
+++ b/libavutil/float_dsp.h
@@ -19,6 +19,8 @@
 #ifndef AVUTIL_FLOAT_DSP_H
 #define AVUTIL_FLOAT_DSP_H
 
+#include "config.h"
+
 typedef struct AVFloatDSPContext {
     /**
      * Calculate the product of two vectors of floats and store the result in
@@ -111,7 +113,7 @@ typedef struct AVFloatDSPContext {
      *             constraints: 32-byte aligned
      * @param src1 second input vector
      *             constraints: 32-byte aligned
-     * @param src1 third input vector
+     * @param src2 third input vector
      *             constraints: 32-byte aligned
      * @param len  number of elements in the input
      *             constraints: multiple of 16
@@ -130,8 +132,6 @@ typedef struct AVFloatDSPContext {
      *             constraints: 32-byte aligned
      * @param src1 second input vector
      *             constraints: 32-byte aligned
-     * @param src1 third input vector
-     *             constraints: 32-byte aligned
      * @param len  number of elements in the input
      *             constraints: multiple of 16
      */
@@ -146,8 +146,30 @@ typedef struct AVFloatDSPContext {
      * @param len length of vectors, multiple of 4
      */
     void (*butterflies_float)(float *restrict v1, float *restrict v2, int len);
+
+    /**
+     * Calculate the scalar product of two vectors of floats.
+     *
+     * @param v1  first vector, 16-byte aligned
+     * @param v2  second vector, 16-byte aligned
+     * @param len length of vectors, multiple of 4
+     *
+     * @return sum of elementwise products
+     */
+    float (*scalarproduct_float)(const float *v1, const float *v2, int len);
 } AVFloatDSPContext;
 
+/**
+ * Return the scalar product of two vectors.
+ *
+ * @param v1  first input vector
+ * @param v2  first input vector
+ * @param len number of elements
+ *
+ * @return sum of elementwise products
+ */
+float avpriv_scalarproduct_float_c(const float *v1, const float *v2, int len);
+
 /**
  * Initialize a float DSP context.
  *
@@ -157,6 +179,7 @@ typedef struct AVFloatDSPContext {
 void avpriv_float_dsp_init(AVFloatDSPContext *fdsp, int strict);
 
 
+void ff_float_dsp_init_aarch64(AVFloatDSPContext *fdsp);
 void ff_float_dsp_init_arm(AVFloatDSPContext *fdsp);
 void ff_float_dsp_init_ppc(AVFloatDSPContext *fdsp, int strict);
 void ff_float_dsp_init_x86(AVFloatDSPContext *fdsp);