Home
last modified time | relevance | path

Searched refs:lhs_scale (Results 1 – 3 of 3) sorted by relevance

/external/gemmlowp/doc/
Dquantization.md148 above equation (3), with some already-known quantization parameters `lhs_scale`,
153 lhs_real_value[i] = lhs_scale * (lhs_quantized_value[i] - lhs_zero_point)
163 lhs_scale * (lhs_quantized_value[i] - lhs_zero_point) *
166 = lhs_scale * rhs_scale * Sum_over_i(
195 (lhs_scale * rhs_scale / result_scale) *
247 (lhs_scale * rhs_scale / result_scale) * int32_accumulator (7)
250 The difficulty here is of course that `(lhs_scale * rhs_scale / result_scale)`
271 (lhs_scale * rhs_scale / result_scale) * int32_accumulator
/external/tensorflow/tensorflow/compiler/mlir/tosa/transforms/
Dlegalize_common.cc647 double lhs_scale, rhs_scale, result_scale; in convertConcatV2Op() local
657 lhs_scale = static_cast<double>(lhs_quant_type.getScale()); in convertConcatV2Op()
665 if (lhs_scale != result_scale) { in convertConcatV2Op()
670 lhs_scale / result_scale, lhs_zeropoint, in convertConcatV2Op()
/external/tensorflow/tensorflow/compiler/mlir/tosa/g3doc/
Dlegalization.md3180 double lhs_scale = double(1 << input_shift) * %lhs.scale / max_scale_2x
3184 compute_scale_32(lhs_scale, lhs_multiplier, lhs_shift)