LSTM Layer Functions

Machine-readable model

• arm_lstm_unidirectional_f32functionUnidirectional LSTM inference.
• arm_gru_unidirectional_f32functionUnidirectional GRU layer for float32 input, output and state.
• arm_lstm_unidirectional_f32_temp1_get_buffer_sizefunctionGet size of the temp1 scratch buffer required by armlstmunidirectionalf32().
• arm_lstm_unidirectional_f32_temp2_get_buffer_sizefunctionGet size of the temp2 scratch buffer required by armlstmunidirectionalf32().
• arm_gru_unidirectional_f32_temp1_get_buffer_sizefunctionGet size of the temp1 scratch buffer required by armgruunidirectionalf32().
• arm_lstm_unidirectional_f16functionUnidirectional LSTM inference.
• arm_gru_unidirectional_f16functionUnidirectional GRU layer for float16 input, output and state.
• arm_lstm_unidirectional_f16_temp1_get_buffer_sizefunctionGet size of the temp1 scratch buffer required by armlstmunidirectionalf16().
• arm_lstm_unidirectional_f16_temp2_get_buffer_sizefunctionGet size of the temp2 scratch buffer required by armlstmunidirectionalf16().
• arm_gru_unidirectional_f16_temp1_get_buffer_sizefunctionGet size of the temp1 scratch buffer required by armgruunidirectionalf16().

function

arm_lstm_unidirectional_f32

C

Unidirectional LSTM inference.

Include/arm_nnfunctions_flt.h:1781

arm_cmsis_nn_status arm_lstm_unidirectional_f32(
    const float32_t *input,
    float32_t *output,
    const cmsis_nn_lstm_params_f32 *params,
    cmsis_nn_lstm_context_f32 *buffers
)

Unidirectional LSTM inference.

Note

On the MVE float path a NaN cell state yields a NaN hidden state, as tanh returns NaN unchanged there (#635). With cell clipping enabled the clip removes a NaN cell state first.

Parameters

Parameters of arm_lstm_unidirectional_f32

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input sequence tensor.
output	float32_t *	out	Pointer to the output sequence tensor.
params	const cmsis_nn_lstm_params_f32 *	in	LSTM parameters and weights.
buffers	cmsis_nn_lstm_context_f32 *	in, out	Mutable LSTM scratch and state buffers. temp1 and temp2 are sized by `arm_lstm_unidirectional_f32_temp1_get_buffer_size()` / `arm_lstm_unidirectional_f32_temp2_get_buffer_size()`, which report 0: the float implementation never dereferences them and both may be NULL.

Returns

Returns of arm_lstm_unidirectional_f32

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_gru_unidirectional_f32

C

Unidirectional GRU layer for float32 input, output and state.

Include/arm_nnfunctions_flt.h:1812

arm_cmsis_nn_status arm_gru_unidirectional_f32(
    const float32_t *input,
    float32_t *output,
    const cmsis_nn_gru_params_f32 *params,
    cmsis_nn_gru_context_f32 *buffers
)

Unidirectional GRU layer for float32 input, output and state.

Implements the reset-after GRU (Keras / TFLite default) when params->reset_after is non-zero, and the pre-reset variant otherwise. The hidden state is zero-initialised for the first time step, unless buffers->hidden_state is supplied for streaming state carry (batch_size == 1), in which case it seeds the initial state and receives the final hidden state on return.

Note

NaN contract: a NaN in input, the previous hidden state, or the candidate gate’s weight or bias reaches every output unit it feeds, on the scalar and MVE legs alike and at the shipped -Ofast: the MVE block re-establishes NaN after the table tanh with an integer-domain test that fast-math cannot elide (#251). A NaN confined to the update or reset gate’s weight or bias does not reach the output: the scalar sigmoid maps NaN to 1.0 (see the note on arm_nn_sigmoid_scalar_f32 in arm_nnsupportfunctions_flt.h). NaN payloads and signs are not preserved on the MVE leg (default NaN, architectural). Inf follows the arithmetic.

Parameters

Parameters of arm_gru_unidirectional_f32

Name	Type	Direction	Description
input	const float32_t *	in	Input sequence tensor. Must not overlap `output`: earlier outputs are re-read as the recurrent state for later time steps, so aliasing corrupts silently.
output	float32_t *	out	Output (hidden-state) sequence tensor.
params	const cmsis_nn_gru_params_f32 *	in	Struct describing the GRU operator.
buffers	cmsis_nn_gru_context_f32 *	in, out	Scratch buffers. May be NULL when `reset_after` != 0. temp1 is sized by `arm_gru_unidirectional_f32_temp1_get_buffer_size()`.

Returns

Returns of arm_gru_unidirectional_f32

Description
ARM_CMSIS_NN_SUCCESS on success, ARM_CMSIS_NN_ARG_ERROR otherwise.

function

arm_lstm_unidirectional_f32_temp1_get_buffer_size

C

Get size of the temp1 scratch buffer required by armlstmunidirectionalf32().

Include/arm_nnfunctions_flt.h:1833

int32_t arm_lstm_unidirectional_f32_temp1_get_buffer_size(const cmsis_nn_lstm_params_f32 *lstm_params)

Get size of the temp1 scratch buffer required by arm_lstm_unidirectional_f32().

Note

This query reports its invalid input as -1, following the integer LSTM temp sizers (arm_lstm_unidirectional_s8_temp1_get_buffer_size()), not the 0 used by the float convolution and fully-connected queries in this header.

Parameters

Parameters of arm_lstm_unidirectional_f32_temp1_get_buffer_size

Name	Type	Direction	Description
lstm_params	const cmsis_nn_lstm_params_f32 *	in	LSTM operator parameters, i.e. the same `cmsis_nn_lstm_params_f32` passed to `arm_lstm_unidirectional_f32()`. No field is read.

Returns

Returns of arm_lstm_unidirectional_f32_temp1_get_buffer_size

Description

0 for any non-NULL lstm_params, on every build target: the float32 implementation computes its gate values per hidden unit in automatics and never dereferences temp1 or temp2, so both context pointers may be NULL. Returns -1 only for a NULL lstm_params. The query exists so arena-sizing code can treat every LSTM variant alike; a future implementation that starts staging gate vectors would change this figure, so size from the query rather than hard-coding 0.

function

arm_lstm_unidirectional_f32_temp2_get_buffer_size

C

Get size of the temp2 scratch buffer required by armlstmunidirectionalf32().

Include/arm_nnfunctions_flt.h:1842

int32_t arm_lstm_unidirectional_f32_temp2_get_buffer_size(const cmsis_nn_lstm_params_f32 *lstm_params)

Get size of the temp2 scratch buffer required by arm_lstm_unidirectional_f32(). The contract is identical to arm_lstm_unidirectional_f32_temp1_get_buffer_size(), and the answer is the same 0 (temp2 is likewise never dereferenced).

Note

This query reports its invalid input as -1, following the integer LSTM temp sizers (arm_lstm_unidirectional_s8_temp1_get_buffer_size()), not the 0 used by the float convolution and fully-connected queries in this header.

Parameters

Parameters of arm_lstm_unidirectional_f32_temp2_get_buffer_size

Name	Type	Direction	Description
lstm_params	const cmsis_nn_lstm_params_f32 *	in	LSTM operator parameters, i.e. the same `cmsis_nn_lstm_params_f32` passed to `arm_lstm_unidirectional_f32()`. No field is read.

Returns

Returns of arm_lstm_unidirectional_f32_temp2_get_buffer_size

Description

0 for any non-NULL lstm_params, on every build target: the float32 implementation computes its gate values per hidden unit in automatics and never dereferences temp1 or temp2, so both context pointers may be NULL. Returns -1 only for a NULL lstm_params. The query exists so arena-sizing code can treat every LSTM variant alike; a future implementation that starts staging gate vectors would change this figure, so size from the query rather than hard-coding 0.

function

arm_gru_unidirectional_f32_temp1_get_buffer_size

C

Get size of the temp1 scratch buffer required by armgruunidirectionalf32().

Include/arm_nnfunctions_flt.h:1863

int32_t arm_gru_unidirectional_f32_temp1_get_buffer_size(const cmsis_nn_gru_params_f32 *gru_params)

Get size of the temp1 scratch buffer required by arm_gru_unidirectional_f32().

Note

On the pre-reset path a 0 is only returned for the degenerate hidden_size == 0, which arm_gru_unidirectional_f32() rejects with ARM_CMSIS_NN_ARG_ERROR before any buffer access - so a 0 there never corresponds to a runnable call.

Note

This query reports an out-of-range shape as -1, following the integer LSTM temp sizers, not the 0 used by the float convolution and fully-connected queries in this header.

Parameters

Parameters of arm_gru_unidirectional_f32_temp1_get_buffer_size

Name	Type	Direction	Description
gru_params	const cmsis_nn_gru_params_f32 *	in	GRU operator parameters, i.e. the same `cmsis_nn_gru_params_f32` passed to `arm_gru_unidirectional_f32()`. Only reset_after and hidden_size are read.

Returns

Returns of arm_gru_unidirectional_f32_temp1_get_buffer_size

Description

Required buffer size in bytes: hidden_size * sizeof(float32_t) when reset_after == 0 (the pre-reset formulation stages the r . h_prev vector in temp1; the vector is reused across batches and time steps, so neither batch_size nor time_steps enters), and 0 when reset_after != 0 (temp1 is never dereferenced and may be NULL). Returns -1 if gru_params is NULL, if hidden_size is negative, or if the byte count would not fit in an int32_t. The figure and the range checks are the same on every build target.

function

arm_lstm_unidirectional_f16

C

Unidirectional LSTM inference.

Include/arm_nnfunctions_flt.h:3558

arm_cmsis_nn_status arm_lstm_unidirectional_f16(
    const float16_t *input,
    float16_t *output,
    const cmsis_nn_lstm_params_f16 *params,
    cmsis_nn_lstm_context_f16 *buffers
)

Unidirectional LSTM inference.

Note

On the MVE float path a NaN cell state yields a NaN hidden state, as tanh returns NaN unchanged there (#635). With cell clipping enabled the clip removes a NaN cell state first.

Parameters

Parameters of arm_lstm_unidirectional_f16

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input sequence tensor.
output	float16_t *	out	Pointer to the output sequence tensor.
params	const cmsis_nn_lstm_params_f16 *	in	LSTM parameters and weights.
buffers	cmsis_nn_lstm_context_f16 *	in, out	Mutable LSTM scratch and state buffers. temp1 and temp2 are sized by `arm_lstm_unidirectional_f32_temp1_get_buffer_size()` / `arm_lstm_unidirectional_f32_temp2_get_buffer_size()`, which report 0: the float implementation never dereferences them and both may be NULL.

Returns

Returns of arm_lstm_unidirectional_f16

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_gru_unidirectional_f16

C

Unidirectional GRU layer for float16 input, output and state.

Include/arm_nnfunctions_flt.h:3589

arm_cmsis_nn_status arm_gru_unidirectional_f16(
    const float16_t *input,
    float16_t *output,
    const cmsis_nn_gru_params_f16 *params,
    cmsis_nn_gru_context_f16 *buffers
)

Unidirectional GRU layer for float16 input, output and state.

Implements the reset-after GRU (Keras / TFLite default) when params->reset_after is non-zero, and the pre-reset variant otherwise. The hidden state is zero-initialised for the first time step, unless buffers->hidden_state is supplied for streaming state carry (batch_size == 1), in which case it seeds the initial state and receives the final hidden state on return.

Note

NaN contract: a NaN in input, the previous hidden state, or the candidate gate’s weight or bias reaches every output unit it feeds, on the scalar and MVE legs alike and at the shipped -Ofast: the MVE block re-establishes NaN after the table tanh with an integer-domain test that fast-math cannot elide (#251). A NaN confined to the update or reset gate’s weight or bias does not reach the output: the scalar sigmoid maps NaN to 1.0 (see the note on arm_nn_sigmoid_scalar_f32 in arm_nnsupportfunctions_flt.h). NaN payloads and signs are not preserved on the MVE leg (default NaN, architectural). Inf follows the arithmetic.

Parameters

Parameters of arm_gru_unidirectional_f16

Name	Type	Direction	Description
input	const float16_t *	in	Input sequence tensor. Must not overlap `output`: earlier outputs are re-read as the recurrent state for later time steps, so aliasing corrupts silently.
output	float16_t *	out	Output (hidden-state) sequence tensor.
params	const cmsis_nn_gru_params_f16 *	in	Struct describing the GRU operator.
buffers	cmsis_nn_gru_context_f16 *	in, out	Scratch buffers. May be NULL when `reset_after` != 0. temp1 is sized by `arm_gru_unidirectional_f16_temp1_get_buffer_size()`.

Returns

Returns of arm_gru_unidirectional_f16

Description
ARM_CMSIS_NN_SUCCESS on success, ARM_CMSIS_NN_ARG_ERROR otherwise.

function

arm_lstm_unidirectional_f16_temp1_get_buffer_size

C

Get size of the temp1 scratch buffer required by armlstmunidirectionalf16().

Include/arm_nnfunctions_flt.h:3605

int32_t arm_lstm_unidirectional_f16_temp1_get_buffer_size(const cmsis_nn_lstm_params_f16 *lstm_params)

Get size of the temp1 scratch buffer required by arm_lstm_unidirectional_f16(). The contract is identical to arm_lstm_unidirectional_f32_temp1_get_buffer_size(), and the answer is the same 0 on every build target (the float16 implementation likewise never dereferences temp1 or temp2, which may both be NULL).

Parameters

Parameters of arm_lstm_unidirectional_f16_temp1_get_buffer_size

Name	Type	Direction	Description
lstm_params	const cmsis_nn_lstm_params_f16 *	in	LSTM operator parameters, i.e. the same `cmsis_nn_lstm_params_f16` passed to `arm_lstm_unidirectional_f16()`. No field is read.

Returns

Returns of arm_lstm_unidirectional_f16_temp1_get_buffer_size

Description
0 for any non-NULL lstm_params, -1 for a NULL lstm_params.

function

arm_lstm_unidirectional_f16_temp2_get_buffer_size

C

Get size of the temp2 scratch buffer required by armlstmunidirectionalf16().

Include/arm_nnfunctions_flt.h:3613

int32_t arm_lstm_unidirectional_f16_temp2_get_buffer_size(const cmsis_nn_lstm_params_f16 *lstm_params)

Get size of the temp2 scratch buffer required by arm_lstm_unidirectional_f16(). The contract is identical to arm_lstm_unidirectional_f32_temp1_get_buffer_size(), and the answer is the same 0.

Parameters

Parameters of arm_lstm_unidirectional_f16_temp2_get_buffer_size

Name	Type	Direction	Description
lstm_params	const cmsis_nn_lstm_params_f16 *	in	LSTM operator parameters, i.e. the same `cmsis_nn_lstm_params_f16` passed to `arm_lstm_unidirectional_f16()`. No field is read.

Returns

Returns of arm_lstm_unidirectional_f16_temp2_get_buffer_size

Description
0 for any non-NULL lstm_params, -1 for a NULL lstm_params.

function

arm_gru_unidirectional_f16_temp1_get_buffer_size

C

Get size of the temp1 scratch buffer required by armgruunidirectionalf16().

Include/arm_nnfunctions_flt.h:3628

int32_t arm_gru_unidirectional_f16_temp1_get_buffer_size(const cmsis_nn_gru_params_f16 *gru_params)

Get size of the temp1 scratch buffer required by arm_gru_unidirectional_f16(). See arm_gru_unidirectional_f32_temp1_get_buffer_size() for the -1-on-invalid contract and the pre-reset degenerate-0 note; both apply here unchanged.

Parameters

Parameters of arm_gru_unidirectional_f16_temp1_get_buffer_size

Name	Type	Direction	Description
gru_params	const cmsis_nn_gru_params_f16 *	in	GRU operator parameters, i.e. the same `cmsis_nn_gru_params_f16` passed to `arm_gru_unidirectional_f16()`. Only reset_after and hidden_size are read.

Returns

Returns of arm_gru_unidirectional_f16_temp1_get_buffer_size

Description
Required buffer size in bytes: hidden_size * sizeof(float16_t) when reset_after == 0, 0 when reset_after != 0 (temp1 is never dereferenced and may be NULL). Half the figure `arm_gru_unidirectional_f32_temp1_get_buffer_size()` returns for the same shape - sizing an f16 layer with the f32 query over-allocates, and the reverse under-allocates.