* BFloat16 Dot Product
*/
-static float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2)
+float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2)
{
/* FPCR is ignored for BFDOT and BFMMLA. */
float_status bf_status = {
*/
uint64_t pmull_w(uint64_t op1, uint64_t op2);
+/**
+ * bfdotadd:
+ * @sum: addend
+ * @e1, @e2: multiplicand vectors
+ *
+ * BFloat16 2-way dot product of @e1 & @e2, accumulating with @sum.
+ * The @e1 and @e2 operands correspond to the 32-bit source vector
+ * slots and contain two Bfloat16 values each.
+ *
+ * Corresponds to the ARM pseudocode function BFDotAdd.
+ */
+float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2);
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */