triplekings commented on a change in pull request #14614: [MKLDNN] add quantized sum URL: https://github.com/apache/incubator-mxnet/pull/14614#discussion_r274240369
########## File path: src/operator/quantization/mkldnn/mkldnn_quantized_sum.cc ########## @@ -0,0 +1,206 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +/*! + * Copyright (c) 2019 by Contributors + * \file mkldnn_quantized_sum.cc + * \brief + */ + +#if MXNET_USE_MKLDNN == 1 +#include "./mkldnn_quantized_sum-inl.h" +#include "../../nn/mkldnn/mkldnn_ops-inl.h" +#include "../../nn/mkldnn/mkldnn_base-inl.h" +#include "../quantization_utils.h" + +namespace mxnet { +namespace op { + +DMLC_REGISTER_PARAMETER(RequantizeSumParam); + +static float GetScale(const NDArray& data, float min, float max) { + auto data_range = (data.dtype() == mshadow::kInt8) ? kInt8Range : kUint8Range; + return data_range / MaxAbs(min, max); +} + +static void MKLDNNQuantizedSumForward(const nnvm::NodeAttrs& attrs, const OpContext& ctx, + const std::vector<NDArray>& in_data, + const std::vector<OpReqType>& req, + const std::vector<NDArray>& out_data) { + const RequantizeSumParam& params = nnvm::get<RequantizeSumParam>(attrs.parsed); + // A, B, A_min, A_max, B_min, B_max + CHECK_EQ(in_data.size(), 6U); + // C, C_min, C_max + CHECK_EQ(out_data.size(), 3U); + + // Collect data min,max,absmax + const float dataA_min = in_data[quantized_sum_enum::kAMin].data().dptr<float>()[0]; + const float dataB_min = in_data[quantized_sum_enum::kBMin].data().dptr<float>()[0]; + const float dataA_max = in_data[quantized_sum_enum::kAMax].data().dptr<float>()[0]; + const float dataB_max = in_data[quantized_sum_enum::kBMax].data().dptr<float>()[0]; + const float dataA_absmax = MaxAbs(dataA_min, dataA_max); + const float dataB_absmax = MaxAbs(dataB_min, dataB_max); + + auto dataA_mem = in_data[quantized_sum_enum::kDataA].GetMKLDNNData(); + auto dataB_mem = in_data[quantized_sum_enum::kDataB].GetMKLDNNData(); + const bool dataA_int8 = (in_data[quantized_sum_enum::kDataA].dtype() == mshadow::kInt8) Review comment: OK ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
