NMSIS-NN  Version 1.3.1
NMSIS NN Software Library
LSTM Layer Functions

Get size of additional buffer required by riscv_svdf_s8() for Arm(R) Helium Architecture case. Refer to riscv_svdf_s8_get_buffer_size() for function argument details. More...

Functions

riscv_nmsis_nn_status riscv_lstm_unidirectional_s16 (const int16_t *input, int16_t *output, const nmsis_nn_lstm_params *params, nmsis_nn_lstm_context *buffers)
 LSTM unidirectional function with 16 bit input and output and 16 bit gate output, 64 bit bias. More...
 
riscv_nmsis_nn_status riscv_lstm_unidirectional_s8 (const int8_t *input, int8_t *output, const nmsis_nn_lstm_params *params, nmsis_nn_lstm_context *buffers)
 LSTM unidirectional function with 8 bit input and output and 16 bit gate output, 32 bit bias. More...
 

Detailed Description

Get size of additional buffer required by riscv_svdf_s8() for Arm(R) Helium Architecture case. Refer to riscv_svdf_s8_get_buffer_size() for function argument details.

Note
Intended for compilation on Host. If compiling for an Arm target, use riscv_svdf_s8_get_buffer_size().

Function Documentation

◆ riscv_lstm_unidirectional_s16()

riscv_nmsis_nn_status riscv_lstm_unidirectional_s16 ( const int16_t *  input,
int16_t *  output,
const nmsis_nn_lstm_params params,
nmsis_nn_lstm_context buffers 
)

LSTM unidirectional function with 16 bit input and output and 16 bit gate output, 64 bit bias.

Parameters
[in]inputPointer to input data
[out]outputPointer to output data
[in]paramsStruct containing all information about the lstm operator, see riscv_nn_types.
[in]buffersStruct containing pointers to all temporary scratch buffers needed for the lstm operator, see riscv_nn_types.
Returns
The function returns RISCV_NMSIS_NN_SUCCESS
  1. Supported framework: TensorFlow Lite Micro

◆ riscv_lstm_unidirectional_s8()

riscv_nmsis_nn_status riscv_lstm_unidirectional_s8 ( const int8_t *  input,
int8_t *  output,
const nmsis_nn_lstm_params params,
nmsis_nn_lstm_context buffers 
)

LSTM unidirectional function with 8 bit input and output and 16 bit gate output, 32 bit bias.

Parameters
[in]inputPointer to input data
[out]outputPointer to output data
[in]paramsStruct containing all information about the lstm operator, see riscv_nn_types.
[in]buffersStruct containing pointers to all temporary scratch buffers needed for the lstm operator, see riscv_nn_types.
Returns
The function returns RISCV_NMSIS_NN_SUCCESS
  1. Supported framework: TensorFlow Lite Micro