samskalicky commented on a change in pull request #17270: Dynamic custom operator GPU support URL: https://github.com/apache/incubator-mxnet/pull/17270#discussion_r369381816
########## File path: example/extensions/lib_custom_op/relu_lib.cu ########## @@ -0,0 +1,195 @@ +/* + * 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) 2020 by Contributors + * \file relu_lib.cu + * \brief simple custom relu operator implemented using CUDA function + */ + +#include <iostream> +#include "lib_api.h" + +__global__ void relu_gpu_forward(float *out, float *in, int64_t N) { + int tid = blockIdx.x * blockDim.x + threadIdx.x; + if (tid < N) + out[tid] = in[tid] > 0 ? in[tid] : 0; +} + +__global__ void relu_gpu_backward(float *out, float *in, int64_t N) { + int tid = blockIdx.x * blockDim.x + threadIdx.x; + if (tid < N) + out[tid] = in[tid] > 0 ? 1 : 0; +} + +MXReturnValue forwardCPU(std::map<std::string, std::string> attrs, + std::vector<MXTensor> inputs, + std::vector<MXTensor> outputs, + OpResource res) { + float* in_data = inputs[0].data<float>(); + float* out_data = outputs[0].data<float>(); + for (int i=0; i<inputs[0].size(); i++) { + out_data[i] = in_data[i] > 0 ? in_data[i] : 0; + } + return MX_SUCCESS; +} + +MXReturnValue backwardCPU(std::map<std::string, std::string> attrs, + std::vector<MXTensor> inputs, + std::vector<MXTensor> outputs, + OpResource res) { + float* in_data = inputs[0].data<float>(); + float* out_data = outputs[0].data<float>(); + for (int i=0; i<inputs[0].size(); i++) { + out_data[i] = in_data[i] > 0 ? 1 : 0; + } + return MX_SUCCESS; +} + +MXReturnValue forwardGPU(std::map<std::string, std::string> attrs, + std::vector<MXTensor> inputs, + std::vector<MXTensor> outputs, + OpResource res) { + float* in_data = inputs[0].data<float>(); + float* out_data = outputs[0].data<float>(); + + // test on memory resource allocation + void *workspace_cpu = res.alloc_cpu(8 * sizeof(float)); + void *workspace_gpu = res.alloc_gpu(8 * sizeof(float)); Review comment: its great that you're testing calling these functions, but you dont do anything with the allocated space. lets either use it for something, or not alloc at all. ---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
