Variables | |
| const float32_t | arm_nn_exp_poly_coeffs_f32 [8] |
| Polynomial coefficients used by the float32 MVE exp approximation. | |
| const float32_t | arm_nn_exp2_lut256_f32 [257] |
LUT for 2^(i/256) used by the float32 LUT softmax approximation. | |
| const float32_t | arm_nn_tanh_lut256_f32 [257] |
LUT for tanh(x) sampled over x in [0, 4] for float32 helpers. | |
| const float32_t | arm_nn_exp_poly_coeffs_f16 [8] |
| Polynomial coefficients used by the float16 MVE exp approximation. | |
| const float32_t | arm_nn_tanh_approx_coeffs_f16 [3] |
| Coefficients used by the float16 tanh rational approximation. | |
| const uint16_t | arm_nn_exp2_lut256_f16 [257] |
Quantized binary16 LUT for 2^(i/256) used by float16 helpers. | |
| const uint16_t | arm_nn_tanh_lut256_f16 [257] |
Quantized binary16 LUT for tanh(x) with x in [0, 4]. | |