Function arm_convolve_1x1_s8_fast

Function Documentation

arm_cmsis_nn_status arm_convolve_1x1_s8_fast(const cmsis_nn_context *ctx, const cmsis_nn_context *weight_sum_ctx, const cmsis_nn_conv_params *conv_params, const cmsis_nn_per_channel_quant_params *quant_params, const cmsis_nn_dims *input_dims, const int8_t *input_data, const cmsis_nn_dims *filter_dims, const int8_t *filter_data, const cmsis_nn_dims *bias_dims, const int32_t *bias_data, const cmsis_nn_dims *output_dims, int8_t *output_data)

Fast s8 version for 1x1 convolution (non-square shape)

  • Supported framework : TensorFlow Lite Micro

  • The following constrains on the arguments apply

    1. conv_params->padding.w = conv_params->padding.h = 0

    2. conv_params->stride.w = conv_params->stride.h = 1

Parameters:

  • ctx – [inout] Function context that contains the additional buffer if required by the function. arm_convolve_1x1_s8_fast_get_buffer_size will return the buffer_size if required. The caller is expected to clear the buffer, if applicable, for security reasons.

  • weight_sum_ctx – [in] Per-output-channel weight sums, supplied by the caller. This function only reads the buffer and never writes it, so it is filled once and may then be reused for as long as filter_data, bias_data and conv_params->input_offset are unchanged - see arm_convolve_weight_sum() for the layout and the full reuse rules. Fill it with arm_convolve_weight_sum(), passing conv_params->input_offset as lhs_offset and the same bias_data given here. That helper returns ARM_CMSIS_NN_NO_IMPL_ERROR on non-MVE builds, which is not a failure. This function currently dereferences weight_sum_ctx->buf on nearly every build, not only under MVE, and does not check it for NULL, so pass a valid context regardless of the target. The sole exception is an Arm Compiler build (__ARMCC_VERSION >= 6010050) with ARM_MATH_DSP and without ARM_MATH_MVEI, where supplying ctx->buf selects a buffered path that never reads weight_sum_ctx. builds with the MVE extension (ARM_MATH_MVEI), where an unfilled buffer yields wrong output while still returning ARM_CMSIS_NN_SUCCESS. None of this is a guarantee about future versions. Sized by arm_convolve_s8_get_weights_sum_size(): output_dims->c * sizeof(int32_t) where the sums are used, 0 otherwise. The caller is expected to clear the buffer, if applicable, for security reasons.

  • conv_params – [in] Convolution parameters (e.g. strides, dilations, pads,…). Range of conv_params->input_offset : [-127, 128] Range of conv_params->output_offset : [-128, 127]

  • quant_params – [in] Per-channel quantization info. It contains the multiplier and shift values to be applied to each output channel

  • input_dims – [in] Input (activation) tensor dimensions. Format: [N, H, W, C_IN]

  • input_data – [in] Input (activation) data pointer. Data type: int8

  • filter_dims – [in] Filter tensor dimensions. Format: [C_OUT, 1, 1, C_IN]

  • filter_data – [in] Filter data pointer. Data type: int8

  • bias_dims – [in] Bias tensor dimensions. Format: [C_OUT]

  • bias_data – [in] Optional bias data pointer. Data type: int32

  • output_dims – [in] Output tensor dimensions. Format: [N, H, W, C_OUT]

  • output_data – [out] Output data pointer. Data type: int8

Returns:

The function returns either ARM_CMSIS_NN_ARG_ERROR if argument constraints fail. or, ARM_CMSIS_NN_SUCCESS on successful completion.