+ /**
+ * Multiply a vector of floats by a scalar float and add to
+ * destination vector. Source and destination vectors must
+ * overlap exactly or not at all.
+ * @param dst result vector, 16-byte aligned
+ * @param src input vector, 16-byte aligned
+ * @param mul scalar value
+ * @param len length of vector, multiple of 4
+ */
+ void (*vector_fmac_scalar)(float *dst, const float *src, float mul,
+ int len);