Function arm_elementwise_add_fp16

Function Documentation

arm_cmsis_nn_status arm_elementwise_add_fp16(const float16_t *input_1_vect, const float16_t *input_2_vect, float16_t *output, const float16_t out_activation_min, const float16_t out_activation_max, const int32_t block_size)

Legacy float16 elementwise add with fused clamp, kept only for source compatibility with callers that predate arm_elementwise_add_f16(). New code should call arm_elementwise_add_f16() instead.

This entry does NOT share the contract of arm_elementwise_add_f16():

Note

The clamp does not propagate NaN. Both the Helium path (vminnm/vmaxnm) and the scalar path (the non-propagating MIN/MAX clamp helper) bound against out_activation_max first, so a NaN produced by the addition comes back as out_activation_max. arm_elementwise_add_f16() documents TensorFlow Lite NaN propagation; this entry does not implement it.

Warning

No argument validation is performed. A NULL input_1_vect, input_2_vect or output is dereferenced rather than reported. A block_size of 0 writes nothing and still returns ARM_CMSIS_NN_SUCCESS, where arm_elementwise_add_f16() returns ARM_CMSIS_NN_ARG_ERROR.

Parameters:

  • input_1_vect – [in] Pointer to the first input vector. Must not be NULL.

  • input_2_vect – [in] Pointer to the second input vector. Must not be NULL.

  • output – [out] Pointer to the output vector. Must not be NULL.

  • out_activation_min – [in] Minimum output clamp value.

  • out_activation_max – [in] Maximum output clamp value.

  • block_size – [in] Number of elements to process.

Returns:

ARM_CMSIS_NN_SUCCESS unconditionally.