Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 1 | // |
| 2 | // Copyright © 2017 Arm Ltd. All rights reserved. |
| 3 | // SPDX-License-Identifier: MIT |
| 4 | // |
| 5 | #pragma once |
| 6 | |
Sadik Armagan | a097d2a | 2021-11-24 15:47:28 +0000 | [diff] [blame] | 7 | #include <CommonTestUtils.hpp> |
Mike Kelly | 386ff1a | 2021-03-29 15:04:50 +0100 | [diff] [blame] | 8 | |
Matthew Bentham | 246bd46 | 2020-01-20 16:16:06 +0000 | [diff] [blame] | 9 | #include <armnn/Descriptors.hpp> |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 10 | #include <armnn/INetwork.hpp> |
Matthew Bentham | 246bd46 | 2020-01-20 16:16:06 +0000 | [diff] [blame] | 11 | #include <armnn/IRuntime.hpp> |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 12 | |
Aron Virginas-Tar | 48623a0 | 2019-10-22 10:00:28 +0100 | [diff] [blame] | 13 | #include <Profiling.hpp> |
| 14 | #include <QuantizeHelper.hpp> |
| 15 | #include <ResolveType.hpp> |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 16 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 17 | #include <doctest/doctest.h> |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 18 | |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 19 | #include <vector> |
| 20 | |
| 21 | namespace |
| 22 | { |
| 23 | |
| 24 | using namespace armnn; |
| 25 | |
| 26 | template<typename T> |
| 27 | bool ConstantUsageTest(const std::vector<BackendId>& computeDevice, |
| 28 | const TensorInfo& commonTensorInfo, |
| 29 | const std::vector<T>& inputData, |
| 30 | const std::vector<T>& constantData, |
| 31 | const std::vector<T>& expectedOutputData) |
| 32 | { |
| 33 | // Create runtime in which test will run |
| 34 | IRuntime::CreationOptions options; |
| 35 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 36 | |
| 37 | // Builds up the structure of the network. |
| 38 | INetworkPtr net(INetwork::Create()); |
| 39 | |
| 40 | IConnectableLayer* input = net->AddInputLayer(0); |
| 41 | IConnectableLayer* constant = net->AddConstantLayer(ConstTensor(commonTensorInfo, constantData)); |
| 42 | IConnectableLayer* add = net->AddAdditionLayer(); |
| 43 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 44 | |
| 45 | input->GetOutputSlot(0).Connect(add->GetInputSlot(0)); |
| 46 | constant->GetOutputSlot(0).Connect(add->GetInputSlot(1)); |
| 47 | add->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 48 | |
| 49 | // Sets the tensors in the network. |
| 50 | input->GetOutputSlot(0).SetTensorInfo(commonTensorInfo); |
| 51 | constant->GetOutputSlot(0).SetTensorInfo(commonTensorInfo); |
| 52 | add->GetOutputSlot(0).SetTensorInfo(commonTensorInfo); |
| 53 | |
| 54 | // optimize the network |
| 55 | IOptimizedNetworkPtr optNet = Optimize(*net, computeDevice, runtime->GetDeviceSpec()); |
| 56 | |
| 57 | // Loads it into the runtime. |
| 58 | NetworkId netId; |
| 59 | runtime->LoadNetwork(netId, std::move(optNet)); |
| 60 | |
| 61 | // Creates structures for input & output. |
| 62 | std::vector<T> outputData(inputData.size()); |
| 63 | |
| 64 | InputTensors inputTensors |
| 65 | { |
| 66 | {0, ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())} |
| 67 | }; |
| 68 | OutputTensors outputTensors |
| 69 | { |
| 70 | {0, Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 71 | }; |
| 72 | |
| 73 | // Does the inference. |
| 74 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 75 | |
| 76 | // Checks the results. |
| 77 | return outputData == expectedOutputData; |
| 78 | } |
| 79 | |
| 80 | inline bool ConstantUsageFloat32Test(const std::vector<BackendId>& backends) |
| 81 | { |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 82 | TensorInfo commonTensorInfo({ 2, 3 }, DataType::Float32); |
| 83 | commonTensorInfo.SetConstant(true); |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 84 | |
| 85 | return ConstantUsageTest(backends, |
| 86 | commonTensorInfo, |
| 87 | std::vector<float>{ 1.f, 2.f, 3.f, 4.f, 5.f, 6.f }, // Input. |
| 88 | std::vector<float>{ 6.f, 5.f, 4.f, 3.f, 2.f, 1.f }, // Const input. |
| 89 | std::vector<float>{ 7.f, 7.f, 7.f, 7.f, 7.f, 7.f } // Expected output. |
| 90 | ); |
| 91 | } |
| 92 | |
| 93 | inline bool ConstantUsageUint8Test(const std::vector<BackendId>& backends) |
| 94 | { |
Derek Lamberti | f90c56d | 2020-01-10 17:14:08 +0000 | [diff] [blame] | 95 | TensorInfo commonTensorInfo({ 2, 3 }, DataType::QAsymmU8); |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 96 | |
| 97 | const float scale = 0.023529f; |
| 98 | const int8_t offset = -43; |
| 99 | |
| 100 | commonTensorInfo.SetQuantizationScale(scale); |
| 101 | commonTensorInfo.SetQuantizationOffset(offset); |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 102 | commonTensorInfo.SetConstant(true); |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 103 | |
| 104 | return ConstantUsageTest(backends, |
| 105 | commonTensorInfo, |
Aron Virginas-Tar | 48623a0 | 2019-10-22 10:00:28 +0100 | [diff] [blame] | 106 | armnnUtils::QuantizedVector<uint8_t>({ 1.f, 2.f, 3.f, 4.f, 5.f, 6.f }, scale, offset), // Input. |
| 107 | armnnUtils::QuantizedVector<uint8_t>({ 6.f, 5.f, 4.f, 3.f, 2.f, 1.f }, scale, offset), // Const input. |
| 108 | armnnUtils::QuantizedVector<uint8_t>({ 7.f, 7.f, 7.f, 7.f, 7.f, 7.f }, scale, offset) // Expected output. |
Aron Virginas-Tar | 7010400 | 2018-10-24 15:33:28 +0100 | [diff] [blame] | 109 | ); |
| 110 | } |
| 111 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 112 | // Utility function to find the number of instances of a substring within a string. |
| 113 | int SubStringCounter(std::string& string, std::string&& substring) |
| 114 | { |
| 115 | std::size_t found = 0; |
| 116 | int count = 0; |
| 117 | // Look for the substring starting from where we last found the substring |
| 118 | while((found = string.find(substring, found)) != std::string::npos) |
| 119 | { |
| 120 | count++; |
| 121 | // Offset by substring length to avoid finding the same substring twice |
| 122 | found += substring.length(); |
| 123 | } |
| 124 | return count; |
| 125 | } |
| 126 | |
Nattapat Chaimanowong | 1fcb4ff | 2019-01-24 15:25:26 +0000 | [diff] [blame] | 127 | template<DataType ArmnnIType, DataType ArmnnOType, |
| 128 | typename TInput = ResolveType<ArmnnIType>, typename TOutput = ResolveType<ArmnnOType>> |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 129 | void EndToEndLayerTestImpl(INetworkPtr network, |
kevmay01 | 2b4d88e | 2019-01-24 14:05:09 +0000 | [diff] [blame] | 130 | const std::map<int, std::vector<TInput>>& inputTensorData, |
| 131 | const std::map<int, std::vector<TOutput>>& expectedOutputData, |
Jan Eilers | bca73e1 | 2020-03-11 12:52:46 +0000 | [diff] [blame] | 132 | std::vector<BackendId> backends, |
| 133 | float tolerance = 0.000001f) |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 134 | { |
| 135 | // Create runtime in which test will run |
| 136 | IRuntime::CreationOptions options; |
| 137 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 138 | |
| 139 | // optimize the network |
| 140 | IOptimizedNetworkPtr optNet = Optimize(*network, backends, runtime->GetDeviceSpec()); |
| 141 | |
| 142 | // Loads it into the runtime. |
| 143 | NetworkId netId; |
| 144 | runtime->LoadNetwork(netId, std::move(optNet)); |
| 145 | |
| 146 | InputTensors inputTensors; |
| 147 | inputTensors.reserve(inputTensorData.size()); |
| 148 | for (auto&& it : inputTensorData) |
| 149 | { |
| 150 | inputTensors.push_back({it.first, |
| 151 | ConstTensor(runtime->GetInputTensorInfo(netId, it.first), it.second.data())}); |
| 152 | } |
| 153 | OutputTensors outputTensors; |
| 154 | outputTensors.reserve(expectedOutputData.size()); |
kevmay01 | 2b4d88e | 2019-01-24 14:05:09 +0000 | [diff] [blame] | 155 | std::map<int, std::vector<TOutput>> outputStorage; |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 156 | for (auto&& it : expectedOutputData) |
| 157 | { |
kevmay01 | 2b4d88e | 2019-01-24 14:05:09 +0000 | [diff] [blame] | 158 | std::vector<TOutput> out(it.second.size()); |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 159 | outputStorage.emplace(it.first, out); |
| 160 | outputTensors.push_back({it.first, |
| 161 | Tensor(runtime->GetOutputTensorInfo(netId, it.first), |
| 162 | outputStorage.at(it.first).data())}); |
| 163 | } |
| 164 | |
| 165 | // Does the inference. |
| 166 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 167 | |
| 168 | // Checks the results. |
| 169 | for (auto&& it : expectedOutputData) |
| 170 | { |
kevmay01 | 2b4d88e | 2019-01-24 14:05:09 +0000 | [diff] [blame] | 171 | std::vector<TOutput> out = outputStorage.at(it.first); |
Aron Virginas-Tar | f97f6da | 2019-10-01 18:35:44 +0100 | [diff] [blame] | 172 | for (unsigned int i = 0; i < out.size(); ++i) |
Nattapat Chaimanowong | 1fcb4ff | 2019-01-24 15:25:26 +0000 | [diff] [blame] | 173 | { |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 174 | CHECK_MESSAGE(Compare<ArmnnOType>(it.second[i], out[i], tolerance) == true, |
Teresa Charlin | 2e3f4d2 | 2020-07-29 14:29:20 +0100 | [diff] [blame] | 175 | "Actual output: " << out[i] << ". Expected output:" << it.second[i]); |
| 176 | |
Nattapat Chaimanowong | 1fcb4ff | 2019-01-24 15:25:26 +0000 | [diff] [blame] | 177 | } |
narpra01 | b9546cf | 2018-11-20 15:21:28 +0000 | [diff] [blame] | 178 | } |
| 179 | } |
| 180 | |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 181 | inline void ImportNonAlignedInputPointerTest(std::vector<BackendId> backends) |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 182 | { |
| 183 | using namespace armnn; |
| 184 | |
| 185 | // Create runtime in which test will run |
| 186 | IRuntime::CreationOptions options; |
| 187 | IRuntimePtr runtime(armnn::IRuntime::Create(options)); |
| 188 | |
| 189 | // build up the structure of the network |
| 190 | INetworkPtr net(INetwork::Create()); |
| 191 | |
| 192 | IConnectableLayer* input = net->AddInputLayer(0); |
| 193 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 194 | ActivationDescriptor descriptor; |
| 195 | descriptor.m_Function = ActivationFunction::Square; |
| 196 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 197 | |
| 198 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 199 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 200 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 201 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 202 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 203 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 204 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 205 | |
| 206 | // Optimize the network |
| 207 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 208 | CHECK(optNet); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 209 | |
| 210 | // Loads it into the runtime. |
| 211 | NetworkId netId; |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 212 | std::string ignoredErrorMessage; |
| 213 | // Enable Importing |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 214 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Undefined); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 215 | runtime->LoadNetwork(netId, std::move(optNet), ignoredErrorMessage, networkProperties); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 216 | |
| 217 | // Creates structures for input & output |
| 218 | std::vector<float> inputData |
| 219 | { |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 220 | 1.0f, 2.0f, 3.0f, 4.0f |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 221 | }; |
| 222 | |
| 223 | // Misaligned input |
Aron Virginas-Tar | d9f7c8b | 2019-09-13 13:37:03 +0100 | [diff] [blame] | 224 | float* misalignedInputData = reinterpret_cast<float*>(reinterpret_cast<char*>(inputData.data()) + 1); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 225 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 226 | std::vector<float> outputData(4); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 227 | |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 228 | // Aligned output |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 229 | float* alignedOutputData = outputData.data(); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 230 | |
| 231 | InputTensors inputTensors |
| 232 | { |
| 233 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), misalignedInputData)}, |
| 234 | }; |
| 235 | OutputTensors outputTensors |
| 236 | { |
| 237 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), alignedOutputData)} |
| 238 | }; |
| 239 | |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 240 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 241 | |
| 242 | // Do the inference and expect it to fail with a ImportMemoryException |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 243 | CHECK_THROWS_AS(runtime->EnqueueWorkload(netId, inputTensors, outputTensors), MemoryImportException); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 244 | } |
| 245 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 246 | inline void ExportNonAlignedOutputPointerTest(std::vector<BackendId> backends) |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 247 | { |
| 248 | using namespace armnn; |
| 249 | |
| 250 | // Create runtime in which test will run |
| 251 | IRuntime::CreationOptions options; |
| 252 | IRuntimePtr runtime(armnn::IRuntime::Create(options)); |
| 253 | |
| 254 | // build up the structure of the network |
| 255 | INetworkPtr net(INetwork::Create()); |
| 256 | |
| 257 | IConnectableLayer* input = net->AddInputLayer(0); |
| 258 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 259 | ActivationDescriptor descriptor; |
| 260 | descriptor.m_Function = ActivationFunction::Square; |
| 261 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 262 | |
| 263 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 264 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 265 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 266 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 267 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 268 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 269 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 270 | |
| 271 | // Optimize the network |
| 272 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 273 | CHECK(optNet); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 274 | |
| 275 | // Loads it into the runtime. |
| 276 | NetworkId netId; |
| 277 | std::string ignoredErrorMessage; |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 278 | // Enable Importing and Exporting |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 279 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Malloc); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 280 | runtime->LoadNetwork(netId, std::move(optNet), ignoredErrorMessage, networkProperties); |
| 281 | |
| 282 | // Creates structures for input & output |
| 283 | std::vector<float> inputData |
| 284 | { |
| 285 | 1.0f, 2.0f, 3.0f, 4.0f, 5.0f |
| 286 | }; |
| 287 | |
| 288 | // Aligned input |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 289 | float* alignedInputData = inputData.data(); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 290 | |
| 291 | std::vector<float> outputData(5); |
| 292 | |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 293 | // Misaligned output |
Aron Virginas-Tar | d9f7c8b | 2019-09-13 13:37:03 +0100 | [diff] [blame] | 294 | float* misalignedOutputData = reinterpret_cast<float*>(reinterpret_cast<char*>(outputData.data()) + 1); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 295 | |
| 296 | InputTensors inputTensors |
| 297 | { |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 298 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), alignedInputData)}, |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 299 | }; |
| 300 | OutputTensors outputTensors |
| 301 | { |
| 302 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), misalignedOutputData)} |
| 303 | }; |
| 304 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 305 | // Do the inference and expect it to fail with a ExportMemoryException |
| 306 | if (backends[0] == Compute::CpuAcc) |
| 307 | { |
| 308 | // For CpuAcc the NeonTensorHandle will throw its own exception on misaligned memory |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 309 | CHECK_THROWS_AS(runtime->EnqueueWorkload(netId, inputTensors, outputTensors), MemoryImportException); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 310 | } |
| 311 | else |
| 312 | { |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 313 | CHECK_THROWS_AS(runtime->EnqueueWorkload(netId, inputTensors, outputTensors), MemoryExportException); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 314 | } |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 315 | } |
| 316 | |
| 317 | inline void ImportAlignedPointerTest(std::vector<BackendId> backends) |
| 318 | { |
| 319 | using namespace armnn; |
| 320 | |
| 321 | // Create runtime in which test will run |
| 322 | IRuntime::CreationOptions options; |
| 323 | IRuntimePtr runtime(armnn::IRuntime::Create(options)); |
| 324 | |
| 325 | // build up the structure of the network |
| 326 | INetworkPtr net(INetwork::Create()); |
| 327 | |
| 328 | IConnectableLayer* input = net->AddInputLayer(0); |
| 329 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 330 | ActivationDescriptor descriptor; |
| 331 | descriptor.m_Function = ActivationFunction::Square; |
| 332 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 333 | |
| 334 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 335 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 336 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 337 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 338 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 339 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 340 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 341 | |
| 342 | // Optimize the network |
| 343 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 344 | CHECK(optNet); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 345 | |
| 346 | // Loads it into the runtime. |
| 347 | NetworkId netId; |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 348 | std::string ignoredErrorMessage; |
| 349 | // Enable Importing |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 350 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Malloc); |
David Monahan | 4f1e8e4 | 2019-09-04 09:22:10 +0100 | [diff] [blame] | 351 | runtime->LoadNetwork(netId, std::move(optNet), ignoredErrorMessage, networkProperties); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 352 | |
| 353 | // Creates structures for input & output |
| 354 | std::vector<float> inputData |
| 355 | { |
| 356 | 1.0f, 2.0f, 3.0f, 4.0f |
| 357 | }; |
| 358 | |
| 359 | std::vector<float> outputData(4); |
| 360 | |
James Conroy | 57d10b7 | 2019-10-25 09:44:14 +0100 | [diff] [blame] | 361 | std::vector<float> expectedOutput |
| 362 | { |
| 363 | 1.0f, 4.0f, 9.0f, 16.0f |
| 364 | }; |
| 365 | |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 366 | InputTensors inputTensors |
| 367 | { |
| 368 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 369 | }; |
| 370 | OutputTensors outputTensors |
| 371 | { |
| 372 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 373 | }; |
| 374 | |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 375 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 376 | |
| 377 | // Do the inference |
| 378 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 379 | |
| 380 | // Retrieve the Profiler.Print() output to get the workload execution |
| 381 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 382 | std::stringstream ss; |
| 383 | profilerManager.GetProfiler()->Print(ss);; |
| 384 | std::string dump = ss.str(); |
| 385 | |
David Monahan | 3fb7e10 | 2019-08-20 11:25:29 +0100 | [diff] [blame] | 386 | // Contains ActivationWorkload |
| 387 | std::size_t found = dump.find("ActivationWorkload"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 388 | CHECK(found != std::string::npos); |
James Conroy | 57d10b7 | 2019-10-25 09:44:14 +0100 | [diff] [blame] | 389 | |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 390 | // Contains SyncMemGeneric |
| 391 | found = dump.find("SyncMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 392 | CHECK(found != std::string::npos); |
James Conroy | 57d10b7 | 2019-10-25 09:44:14 +0100 | [diff] [blame] | 393 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 394 | // Does not contain CopyMemGeneric |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 395 | found = dump.find("CopyMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 396 | CHECK(found == std::string::npos); |
James Conroy | 57d10b7 | 2019-10-25 09:44:14 +0100 | [diff] [blame] | 397 | |
| 398 | // Check output is as expected |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 399 | CHECK(outputData == expectedOutput); |
Ferran Balaguer | dcaa610 | 2019-08-21 13:28:38 +0100 | [diff] [blame] | 400 | } |
| 401 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 402 | inline void ImportOnlyWorkload(std::vector<BackendId> backends) |
| 403 | { |
| 404 | using namespace armnn; |
| 405 | |
| 406 | IRuntime::CreationOptions options; |
| 407 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 408 | |
| 409 | // Builds up the structure of the network. |
| 410 | INetworkPtr net(INetwork::Create()); |
| 411 | |
| 412 | IConnectableLayer* input = net->AddInputLayer(0); |
| 413 | |
| 414 | ActivationDescriptor descriptor; |
| 415 | descriptor.m_Function = ActivationFunction::Square; |
| 416 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
| 417 | |
| 418 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 419 | |
| 420 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 421 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 422 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 423 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 424 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 425 | |
| 426 | // optimize the network |
| 427 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 428 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 429 | INFO("Load Network"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 430 | // Load it into the runtime. It should pass. |
| 431 | NetworkId netId; |
| 432 | std::string ignoredErrorMessage; |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 433 | |
| 434 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Undefined); |
| 435 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 436 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 437 | == Status::Success); |
| 438 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 439 | INFO("Generate Data"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 440 | // Creates structures for input & output |
| 441 | std::vector<float> inputData |
| 442 | { |
| 443 | 1.0f, 2.0f, 3.0f, 4.0f |
| 444 | }; |
| 445 | |
| 446 | std::vector<float> outputData(4); |
| 447 | |
| 448 | std::vector<float> expectedOutput |
| 449 | { |
| 450 | 1.0f, 4.0f, 9.0f, 16.0f |
| 451 | }; |
| 452 | |
David Monahan | 646bc8a | 2022-01-31 14:29:14 +0000 | [diff] [blame^] | 453 | INFO("Create Inference"); |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 454 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 455 | InputTensors inputTensors |
| 456 | { |
| 457 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 458 | }; |
| 459 | OutputTensors outputTensors |
| 460 | { |
| 461 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 462 | }; |
| 463 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 464 | INFO("Get Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 465 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 466 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 467 | INFO("Run Inference"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 468 | // Do the inference |
| 469 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 470 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 471 | INFO("Print Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 472 | // Retrieve the Profiler.Print() output to get the workload execution |
| 473 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 474 | std::stringstream ss; |
| 475 | profilerManager.GetProfiler()->Print(ss);; |
| 476 | std::string dump = ss.str(); |
| 477 | |
| 478 | // Check there are no SyncMemGeneric workloads as we didn't export |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 479 | INFO("Find SyncMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 480 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 481 | CHECK(count == 0); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 482 | |
| 483 | // Should only be 1 CopyMemGeneric for the output as we imported |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 484 | INFO("Find CopyMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 485 | count = SubStringCounter(dump, "CopyMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 486 | CHECK(count == 1); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 487 | |
| 488 | // Check the output is correct |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 489 | CHECK(std::equal(outputData.begin(), outputData.end(), expectedOutput.begin(), expectedOutput.end())); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 490 | } |
| 491 | |
| 492 | inline void ExportOnlyWorkload(std::vector<BackendId> backends) |
| 493 | { |
| 494 | using namespace armnn; |
| 495 | |
| 496 | IRuntime::CreationOptions options; |
| 497 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 498 | |
| 499 | // Builds up the structure of the network. |
| 500 | INetworkPtr net(INetwork::Create()); |
| 501 | |
| 502 | IConnectableLayer* input = net->AddInputLayer(0); |
| 503 | |
| 504 | ActivationDescriptor descriptor; |
| 505 | descriptor.m_Function = ActivationFunction::Square; |
| 506 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
| 507 | |
| 508 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 509 | |
| 510 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 511 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 512 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 513 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 514 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 515 | |
| 516 | // optimize the network |
| 517 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 518 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 519 | INFO("Load Network"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 520 | // Load it into the runtime. It should pass. |
| 521 | NetworkId netId; |
| 522 | std::string ignoredErrorMessage; |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 523 | INetworkProperties networkProperties(false, MemorySource::Undefined, MemorySource::Malloc); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 524 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 525 | == Status::Success); |
| 526 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 527 | INFO("Generate Data"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 528 | // Creates structures for input & output |
| 529 | std::vector<float> inputData |
| 530 | { |
| 531 | 1.0f, 2.0f, 3.0f, 4.0f |
| 532 | }; |
| 533 | |
| 534 | std::vector<float> outputData(4); |
| 535 | |
| 536 | std::vector<float> expectedOutput |
| 537 | { |
| 538 | 1.0f, 4.0f, 9.0f, 16.0f |
| 539 | }; |
| 540 | |
David Monahan | 646bc8a | 2022-01-31 14:29:14 +0000 | [diff] [blame^] | 541 | INFO("Create Inference"); |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 542 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 543 | InputTensors inputTensors |
| 544 | { |
| 545 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 546 | }; |
| 547 | OutputTensors outputTensors |
| 548 | { |
| 549 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 550 | }; |
| 551 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 552 | INFO("Get Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 553 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 554 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 555 | INFO("Run Inference"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 556 | // Do the inference |
| 557 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 558 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 559 | INFO("Print Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 560 | // Retrieve the Profiler.Print() output to get the workload execution |
| 561 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 562 | std::stringstream ss; |
| 563 | profilerManager.GetProfiler()->Print(ss);; |
| 564 | std::string dump = ss.str(); |
| 565 | |
| 566 | // Check there is a SyncMemGeneric workload as we exported |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 567 | INFO("Find SyncMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 568 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 569 | CHECK(count == 1); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 570 | |
| 571 | // Should be 1 CopyMemGeneric for the output as we did not import |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 572 | INFO("Find CopyMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 573 | count = SubStringCounter(dump, "CopyMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 574 | CHECK(count == 1); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 575 | |
| 576 | // Check the output is correct |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 577 | CHECK(std::equal(outputData.begin(), outputData.end(), expectedOutput.begin(), expectedOutput.end())); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 578 | } |
| 579 | |
| 580 | inline void ImportAndExportWorkload(std::vector<BackendId> backends) |
| 581 | { |
| 582 | using namespace armnn; |
| 583 | |
| 584 | IRuntime::CreationOptions options; |
| 585 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 586 | |
| 587 | // Builds up the structure of the network. |
| 588 | INetworkPtr net(INetwork::Create()); |
| 589 | |
| 590 | IConnectableLayer* input = net->AddInputLayer(0); |
| 591 | |
| 592 | ActivationDescriptor descriptor; |
| 593 | descriptor.m_Function = ActivationFunction::Square; |
| 594 | IConnectableLayer* pooling = net->AddActivationLayer(descriptor); |
| 595 | |
| 596 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 597 | |
| 598 | input->GetOutputSlot(0).Connect(pooling->GetInputSlot(0)); |
| 599 | pooling->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 600 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 601 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 602 | pooling->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 603 | |
| 604 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 605 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 606 | INFO("Load Network"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 607 | // Load it into the runtime. It should pass. |
| 608 | NetworkId netId; |
| 609 | std::string ignoredErrorMessage; |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 610 | |
| 611 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Malloc); |
| 612 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 613 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 614 | == Status::Success); |
| 615 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 616 | INFO("Generate Data"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 617 | // Creates structures for input & output |
| 618 | std::vector<float> inputData |
| 619 | { |
| 620 | 1.0f, 2.0f, 3.0f, 4.0f |
| 621 | }; |
| 622 | |
| 623 | std::vector<float> outputData(4); |
| 624 | |
| 625 | std::vector<float> expectedOutput |
| 626 | { |
| 627 | 1.0f, 4.0f, 9.0f, 16.0f |
| 628 | }; |
| 629 | |
David Monahan | 646bc8a | 2022-01-31 14:29:14 +0000 | [diff] [blame^] | 630 | INFO("Create inference"); |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 631 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 632 | InputTensors inputTensors |
| 633 | { |
| 634 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 635 | }; |
| 636 | OutputTensors outputTensors |
| 637 | { |
| 638 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 639 | }; |
| 640 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 641 | INFO("Get Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 642 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 643 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 644 | INFO("Run Inference"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 645 | // Do the inference |
| 646 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 647 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 648 | INFO("Print Profiler"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 649 | // Retrieve the Profiler.Print() output to get the workload execution |
| 650 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 651 | std::stringstream ss; |
| 652 | profilerManager.GetProfiler()->Print(ss);; |
| 653 | std::string dump = ss.str(); |
| 654 | |
| 655 | // Check there is a SyncMemGeneric workload as we exported |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 656 | INFO("Find SyncMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 657 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 658 | CHECK(count == 1); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 659 | |
| 660 | // Shouldn't be any CopyMemGeneric workloads |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 661 | INFO("Find CopyMemGeneric"); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 662 | count = SubStringCounter(dump, "CopyMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 663 | CHECK(count == 0); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 664 | |
| 665 | // Check the output is correct |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 666 | CHECK(std::equal(outputData.begin(), outputData.end(), expectedOutput.begin(), expectedOutput.end())); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 667 | } |
| 668 | |
| 669 | inline void ExportOutputWithSeveralOutputSlotConnectionsTest(std::vector<BackendId> backends) |
| 670 | { |
| 671 | using namespace armnn; |
| 672 | |
| 673 | // Create runtime in which test will run |
| 674 | IRuntime::CreationOptions options; |
| 675 | IRuntimePtr runtime(armnn::IRuntime::Create(options)); |
| 676 | |
| 677 | // build up the structure of the network |
| 678 | INetworkPtr net(INetwork::Create()); |
| 679 | |
| 680 | IConnectableLayer* input = net->AddInputLayer(0); |
| 681 | |
| 682 | ActivationDescriptor descriptor; |
| 683 | descriptor.m_Function = ActivationFunction::Square; |
| 684 | IConnectableLayer* activation = net->AddActivationLayer(descriptor); |
| 685 | |
| 686 | IConnectableLayer* output0 = net->AddOutputLayer(0); |
| 687 | IConnectableLayer* output1 = net->AddOutputLayer(1); |
| 688 | |
| 689 | input->GetOutputSlot(0).Connect(activation->GetInputSlot(0)); |
| 690 | activation->GetOutputSlot(0).Connect(output0->GetInputSlot(0)); |
| 691 | activation->GetOutputSlot(0).Connect(output1->GetInputSlot(0)); |
| 692 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 693 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 4, 1 }, DataType::Float32, 0.0f, 0, true)); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 694 | activation->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 4, 1 }, DataType::Float32)); |
| 695 | |
| 696 | // Optimize the network |
| 697 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 698 | |
| 699 | // Loads it into the runtime. |
| 700 | NetworkId netId; |
| 701 | std::string ignoredErrorMessage; |
| 702 | // Enable Importing |
Francis Murtagh | 73d3e2e | 2021-04-29 14:23:04 +0100 | [diff] [blame] | 703 | INetworkProperties networkProperties(false, MemorySource::Malloc, MemorySource::Malloc); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 704 | runtime->LoadNetwork(netId, std::move(optNet), ignoredErrorMessage, networkProperties); |
| 705 | |
| 706 | // Creates structures for input & output |
| 707 | std::vector<float> inputData |
| 708 | { |
| 709 | 1.0f, 2.0f, 3.0f, 4.0f |
| 710 | }; |
| 711 | |
| 712 | std::vector<float> outputData0(4); |
| 713 | std::vector<float> outputData1(4); |
| 714 | |
Narumol Prangnawarat | 3b90af6 | 2020-06-26 11:00:21 +0100 | [diff] [blame] | 715 | std::vector<float> expectedOutput |
| 716 | { |
| 717 | 1.0f, 4.0f, 9.0f, 16.0f |
| 718 | }; |
| 719 | |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 720 | InputTensors inputTensors |
| 721 | { |
| 722 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 723 | }; |
| 724 | OutputTensors outputTensors |
| 725 | { |
| 726 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData0.data())}, |
| 727 | {1,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 1), outputData1.data())} |
| 728 | }; |
| 729 | |
| 730 | // The result of the inference is not important, just the fact that there |
| 731 | // should not be CopyMemGeneric workloads. |
| 732 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 733 | |
| 734 | // Do the inference |
| 735 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors); |
| 736 | |
| 737 | // Retrieve the Profiler.Print() output to get the workload execution |
| 738 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 739 | std::stringstream ss; |
| 740 | profilerManager.GetProfiler()->Print(ss); |
| 741 | std::string dump = ss.str(); |
| 742 | |
| 743 | std::size_t found = std::string::npos; |
| 744 | |
| 745 | if (backends[0] == Compute::CpuRef) |
| 746 | { |
| 747 | found = dump.find("RefActivationWorkload"); |
| 748 | } |
| 749 | else if (backends[0] == Compute::CpuAcc) |
| 750 | { |
| 751 | found = dump.find("NeonActivationWorkload"); |
| 752 | } |
| 753 | else if (backends[0] == Compute::GpuAcc) |
| 754 | { |
| 755 | found = dump.find("ClActivationWorkload"); |
| 756 | } |
| 757 | |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 758 | CHECK(found != std::string::npos); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 759 | // No contains SyncMemGeneric |
| 760 | found = dump.find("SyncMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 761 | CHECK(found == std::string::npos); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 762 | // Contains CopyMemGeneric |
| 763 | found = dump.find("CopyMemGeneric"); |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 764 | CHECK(found != std::string::npos); |
Narumol Prangnawarat | 3b90af6 | 2020-06-26 11:00:21 +0100 | [diff] [blame] | 765 | |
| 766 | // Check that the outputs are correct |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 767 | CHECK(std::equal(outputData0.begin(), outputData0.end(), |
| 768 | expectedOutput.begin(), expectedOutput.end())); |
| 769 | CHECK(std::equal(outputData1.begin(), outputData1.end(), |
| 770 | expectedOutput.begin(), expectedOutput.end())); |
Ferran Balaguer | 83239f9 | 2019-09-19 11:49:25 +0100 | [diff] [blame] | 771 | } |
| 772 | |
David Monahan | 0a99a14 | 2020-03-13 07:52:54 +0000 | [diff] [blame] | 773 | inline void StridedSliceInvalidSliceEndToEndTest(std::vector<BackendId> backends) |
| 774 | { |
| 775 | using namespace armnn; |
| 776 | |
| 777 | // Create runtime in which test will run |
| 778 | IRuntime::CreationOptions options; |
| 779 | IRuntimePtr runtime(armnn::IRuntime::Create(options)); |
| 780 | |
| 781 | // build up the structure of the network |
| 782 | INetworkPtr net(INetwork::Create()); |
| 783 | |
| 784 | IConnectableLayer* input = net->AddInputLayer(0); |
| 785 | |
| 786 | // Configure a strided slice with a stride the same size as the input but with a ShrinkAxisMask on the first |
| 787 | // dim of the output to make it too small to hold the specified slice. |
| 788 | StridedSliceDescriptor descriptor; |
| 789 | descriptor.m_Begin = {0, 0}; |
| 790 | descriptor.m_End = {2, 3}; |
| 791 | descriptor.m_Stride = {1, 1}; |
| 792 | descriptor.m_BeginMask = 0; |
| 793 | descriptor.m_EndMask = 0; |
| 794 | descriptor.m_ShrinkAxisMask = 1; |
| 795 | IConnectableLayer* stridedSlice = net->AddStridedSliceLayer(descriptor); |
| 796 | |
| 797 | IConnectableLayer* output0 = net->AddOutputLayer(0); |
| 798 | |
| 799 | input->GetOutputSlot(0).Connect(stridedSlice->GetInputSlot(0)); |
| 800 | stridedSlice->GetOutputSlot(0).Connect(output0->GetInputSlot(0)); |
| 801 | |
Cathal Corbett | 5b8093c | 2021-10-22 11:12:07 +0100 | [diff] [blame] | 802 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 2, 3 }, DataType::Float32, 0.0f, 0, true)); |
David Monahan | 0a99a14 | 2020-03-13 07:52:54 +0000 | [diff] [blame] | 803 | stridedSlice->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 3 }, DataType::Float32)); |
| 804 | |
| 805 | // Attempt to optimize the network and check that the correct exception is thrown |
Sadik Armagan | 1625efc | 2021-06-10 18:24:34 +0100 | [diff] [blame] | 806 | CHECK_THROWS_AS(Optimize(*net, backends, runtime->GetDeviceSpec()), armnn::LayerValidationException); |
David Monahan | 0a99a14 | 2020-03-13 07:52:54 +0000 | [diff] [blame] | 807 | } |
| 808 | |
David Monahan | 646bc8a | 2022-01-31 14:29:14 +0000 | [diff] [blame^] | 809 | inline void ForceImportWithAlignedBuffersEndToEndTest(std::vector<BackendId> backends) |
| 810 | { |
| 811 | /** |
| 812 | * This test is similar to the Import tests above, we create a network with a square function and pass in a vector |
| 813 | * with 4 floats, square them. and validate the output. We then check the profiling logs to see if input/output |
| 814 | * tensors are copied (CopyMemGeneric) or imported (SyncMemGeneric) |
| 815 | * In this case all inputs and outputs should be imported |
| 816 | */ |
| 817 | using namespace armnn; |
| 818 | IRuntime::CreationOptions options; |
| 819 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 820 | |
| 821 | // Builds up the structure of the network. |
| 822 | INetworkPtr net(INetwork::Create()); |
| 823 | IConnectableLayer* input = net->AddInputLayer(0); |
| 824 | ActivationDescriptor descriptor; |
| 825 | descriptor.m_Function = ActivationFunction::Square; |
| 826 | IConnectableLayer* activationLayer = net->AddActivationLayer(descriptor); |
| 827 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 828 | input->GetOutputSlot(0).Connect(activationLayer->GetInputSlot(0)); |
| 829 | activationLayer->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 830 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
| 831 | activationLayer->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 832 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 833 | INFO("Load Network"); |
| 834 | |
| 835 | // Load it into the runtime. It should pass. |
| 836 | NetworkId netId; |
| 837 | std::string ignoredErrorMessage; |
| 838 | INetworkProperties networkProperties(false, MemorySource::Undefined, MemorySource::Undefined); |
| 839 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
| 840 | == Status::Success); |
| 841 | INFO("Generate Data"); |
| 842 | |
| 843 | // Creates structures for input & output |
| 844 | std::vector<float> inputData |
| 845 | { |
| 846 | 1.0f, 2.0f, 3.0f, 4.0f |
| 847 | }; |
| 848 | std::vector<float> outputData(4); |
| 849 | std::vector<float> expectedOutput |
| 850 | { |
| 851 | 1.0f, 4.0f, 9.0f, 16.0f |
| 852 | }; |
| 853 | |
| 854 | // Check our input and output pointers are actually aligned |
| 855 | uintptr_t alignment = GetDataTypeSize(DataType::Float32); |
| 856 | CHECK(!(reinterpret_cast<uintptr_t>(inputData.data()) % alignment)); |
| 857 | CHECK(!(reinterpret_cast<uintptr_t>(outputData.data()) % alignment)); |
| 858 | |
| 859 | INFO("Create Inference"); |
| 860 | InputTensors inputTensors |
| 861 | { |
| 862 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 863 | }; |
| 864 | OutputTensors outputTensors |
| 865 | { |
| 866 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 867 | }; |
| 868 | |
| 869 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 870 | std::vector<ImportedInputId> importedInputIds = |
| 871 | runtime->ImportInputs(netId, inputTensors, MemorySource::Malloc); |
| 872 | std::vector<ImportedOutputId> importedOutputIds = |
| 873 | runtime->ImportOutputs(netId, outputTensors, MemorySource::Malloc); |
| 874 | // Do the inference and force the import as the memory is aligned. |
| 875 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors, importedInputIds, importedOutputIds); |
| 876 | |
| 877 | // Retrieve the Profiler.Print() output to get the workload execution |
| 878 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 879 | std::stringstream ss; |
| 880 | profilerManager.GetProfiler()->Print(ss);; |
| 881 | std::string dump = ss.str(); |
| 882 | |
| 883 | if (backends[0] == Compute::CpuAcc) |
| 884 | { |
| 885 | // Reconfigure has not been implemented for CpuAcc so it will always copy, this will break whenever |
| 886 | // reconfigure is implemented |
| 887 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 888 | CHECK(count == 0); |
| 889 | // Should be 2 CopyMemGeneric workloads |
| 890 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 891 | CHECK(count == 2); |
| 892 | } |
| 893 | else |
| 894 | { |
| 895 | // Check there is a SyncMemGeneric workload as we exported |
| 896 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 897 | CHECK(count == 1); |
| 898 | // Shouldn't be any CopyMemGeneric workloads |
| 899 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 900 | CHECK(count == 0); |
| 901 | } |
| 902 | // Check the output is correct |
| 903 | CHECK(std::equal(outputData.begin(), outputData.end(), expectedOutput.begin(), expectedOutput.end())); |
| 904 | } |
| 905 | |
| 906 | inline void ForceImportWithMisalignedInputBuffersEndToEndTest(std::vector<BackendId> backends) |
| 907 | { |
| 908 | /** |
| 909 | * This test is similar to the Import tests above, we create a network with a square function and pass in a vector |
| 910 | * with 4 floats, square them. and validate the output. We then check the profiling logs to see if input/output |
| 911 | * tensors are copied (CopyMemGeneric) or imported (SyncMemGeneric) |
| 912 | * In this case all only the output should be imported |
| 913 | */ |
| 914 | using namespace armnn; |
| 915 | |
| 916 | IRuntime::CreationOptions options; |
| 917 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 918 | |
| 919 | // Builds up the structure of the network. |
| 920 | INetworkPtr net(INetwork::Create()); |
| 921 | IConnectableLayer* input = net->AddInputLayer(0); |
| 922 | |
| 923 | ActivationDescriptor descriptor; |
| 924 | descriptor.m_Function = ActivationFunction::Square; |
| 925 | IConnectableLayer* activationLayer = net->AddActivationLayer(descriptor); |
| 926 | |
| 927 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 928 | |
| 929 | input->GetOutputSlot(0).Connect(activationLayer->GetInputSlot(0)); |
| 930 | activationLayer->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 931 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
| 932 | activationLayer->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 933 | |
| 934 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 935 | INFO("Load Network"); |
| 936 | // Load it into the runtime. It should pass. |
| 937 | NetworkId netId; |
| 938 | std::string ignoredErrorMessage; |
| 939 | INetworkProperties networkProperties(false, MemorySource::Undefined, MemorySource::Undefined); |
| 940 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
| 941 | == Status::Success); |
| 942 | INFO("Generate Data"); |
| 943 | |
| 944 | // This code looks a little funky but the idea is to create a buffer of floats but offset by the size of a char |
| 945 | // this will guarantee that the resultant buffer is misaligned and thus should always be copied. |
| 946 | auto memPtr = std::malloc(4 * sizeof(float) + sizeof(char)); |
| 947 | |
| 948 | float* misalignedMemPtr = reinterpret_cast<float*>(reinterpret_cast<char*>(memPtr) + 1); |
| 949 | |
| 950 | // Check if our pointer is truly misaligned |
| 951 | uintptr_t alignment = GetDataTypeSize(DataType::Float32); |
| 952 | CHECK (reinterpret_cast<uintptr_t>(misalignedMemPtr) % alignment); |
| 953 | |
| 954 | auto inputBuffer = reinterpret_cast<float*>(misalignedMemPtr); |
| 955 | for (int i = 0; i < 4; i++) |
| 956 | { |
| 957 | inputBuffer[i] = 1.0f + static_cast<float>(i); |
| 958 | } |
| 959 | |
| 960 | std::vector<float> outputData(4); |
| 961 | // Check our output buffer is aligned |
| 962 | CHECK(!(reinterpret_cast<uintptr_t>(outputData.data()) % alignment)); |
| 963 | |
| 964 | std::vector<float> expectedOutput |
| 965 | { |
| 966 | 1.0f, 4.0f, 9.0f, 16.0f |
| 967 | }; |
| 968 | |
| 969 | INFO("Create Inference"); |
| 970 | InputTensors inputTensors |
| 971 | { |
| 972 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), misalignedMemPtr)}, |
| 973 | }; |
| 974 | OutputTensors outputTensors |
| 975 | { |
| 976 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), outputData.data())} |
| 977 | }; |
| 978 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 979 | std::vector<ImportedInputId> importedInputIds = |
| 980 | runtime->ImportInputs(netId, inputTensors, MemorySource::Malloc); |
| 981 | std::vector<ImportedOutputId> importedOutputIds = |
| 982 | runtime->ImportOutputs(netId, outputTensors, MemorySource::Malloc); |
| 983 | |
| 984 | // Do the inference and force the import as the memory is misaligned. |
| 985 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors, importedInputIds, importedOutputIds); |
| 986 | |
| 987 | // Retrieve the Profiler.Print() output to get the workload execution |
| 988 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 989 | std::stringstream ss; |
| 990 | profilerManager.GetProfiler()->Print(ss);; |
| 991 | std::string dump = ss.str(); |
| 992 | |
| 993 | // GpuAcc is a different case to CpuRef and CpuAcc, it doesn't use the buffer directly but instead maps it to a |
| 994 | // new set of addresses within Gpu Memory. This will almost always be auto-aligned, so we don't need to check |
| 995 | // for imports/copies. Only that the output is correct. |
| 996 | if (backends[0] != Compute::GpuAcc) |
| 997 | { |
| 998 | if (backends[0] == Compute::CpuAcc) |
| 999 | { |
| 1000 | // Reconfigure has not been implemented for CpuAcc so it will always copy, this will break whenever |
| 1001 | // reconfigure is implemented |
| 1002 | // We should get 0 SyncMemGeneric for the Output |
| 1003 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 1004 | CHECK(count == 0); |
| 1005 | // Should be 2 CopyMemGeneric as we copied the input |
| 1006 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 1007 | CHECK(count == 2); |
| 1008 | } |
| 1009 | else |
| 1010 | { |
| 1011 | // We should get 1 SyncMemGeneric for the Output |
| 1012 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 1013 | CHECK(count == 1); |
| 1014 | // Should only be 1 CopyMemGeneric as we copied the input |
| 1015 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 1016 | CHECK(count == 1); |
| 1017 | } |
| 1018 | } |
| 1019 | // Check the output is correct |
| 1020 | CHECK(std::equal(outputData.begin(), outputData.end(), expectedOutput.begin(), expectedOutput.end())); |
| 1021 | std::free(memPtr); |
| 1022 | } |
| 1023 | |
| 1024 | inline void ForceImportWithMisalignedOutputBuffersEndToEndTest(std::vector<BackendId> backends) |
| 1025 | { |
| 1026 | /** |
| 1027 | * This test is similar to the Import tests above, we create a network with a square function and pass in a vector |
| 1028 | * with 4 floats, square them. and validate the output. We then check the profiling logs to see if input/output |
| 1029 | * tensors are copied (CopyMemGeneric) or imported (SyncMemGeneric) |
| 1030 | * In this case all only the input should be imported |
| 1031 | */ |
| 1032 | using namespace armnn; |
| 1033 | |
| 1034 | IRuntime::CreationOptions options; |
| 1035 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 1036 | |
| 1037 | // Builds up the structure of the network. |
| 1038 | INetworkPtr net(INetwork::Create()); |
| 1039 | IConnectableLayer* input = net->AddInputLayer(0); |
| 1040 | |
| 1041 | ActivationDescriptor descriptor; |
| 1042 | descriptor.m_Function = ActivationFunction::Square; |
| 1043 | IConnectableLayer* activationLayer = net->AddActivationLayer(descriptor); |
| 1044 | |
| 1045 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 1046 | |
| 1047 | input->GetOutputSlot(0).Connect(activationLayer->GetInputSlot(0)); |
| 1048 | activationLayer->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 1049 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
| 1050 | activationLayer->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 1051 | |
| 1052 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 1053 | INFO("Load Network"); |
| 1054 | // Load it into the runtime. It should pass. |
| 1055 | NetworkId netId; |
| 1056 | std::string ignoredErrorMessage; |
| 1057 | INetworkProperties networkProperties(false, MemorySource::Undefined, MemorySource::Undefined); |
| 1058 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
| 1059 | == Status::Success); |
| 1060 | INFO("Generate Data"); |
| 1061 | |
| 1062 | // This code looks a little funky but the idea is to create a buffer of floats but offset by the size of a char |
| 1063 | // this will guarantee that the resultant buffer is misaligned and thus should always be copied. |
| 1064 | auto memPtr = std::malloc(4 * sizeof(float) + sizeof(char)); |
| 1065 | |
| 1066 | float* misalignedMemPtr = reinterpret_cast<float*>(reinterpret_cast<char*>(memPtr) + 1); |
| 1067 | |
| 1068 | // Check if our pointer is truly misaligned |
| 1069 | uintptr_t alignment = GetDataTypeSize(DataType::Float32); |
| 1070 | CHECK (reinterpret_cast<uintptr_t>(misalignedMemPtr) % alignment); |
| 1071 | |
| 1072 | // Creates structures for input & output |
| 1073 | std::vector<float> inputData |
| 1074 | { |
| 1075 | 1.0f, 2.0f, 3.0f, 4.0f |
| 1076 | }; |
| 1077 | |
| 1078 | // Check our input buffer is aligned |
| 1079 | CHECK(!(reinterpret_cast<uintptr_t>(inputData.data()) % alignment)); |
| 1080 | std::vector<float> expectedOutput |
| 1081 | { |
| 1082 | 1.0f, 4.0f, 9.0f, 16.0f |
| 1083 | }; |
| 1084 | |
| 1085 | INFO("Create Inference"); |
| 1086 | InputTensors inputTensors |
| 1087 | { |
| 1088 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), inputData.data())}, |
| 1089 | }; |
| 1090 | OutputTensors outputTensors |
| 1091 | { |
| 1092 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), misalignedMemPtr)} |
| 1093 | }; |
| 1094 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 1095 | std::vector<ImportedInputId> importedInputIds = |
| 1096 | runtime->ImportInputs(netId, inputTensors, MemorySource::Malloc); |
| 1097 | std::vector<ImportedOutputId> importedOutputIds = |
| 1098 | runtime->ImportOutputs(netId, outputTensors, MemorySource::Malloc); |
| 1099 | |
| 1100 | // Do the inference and force the import as the memory is misaligned. |
| 1101 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors, importedInputIds, importedOutputIds); |
| 1102 | |
| 1103 | // Retrieve the Profiler.Print() output to get the workload execution |
| 1104 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 1105 | std::stringstream ss; |
| 1106 | profilerManager.GetProfiler()->Print(ss);; |
| 1107 | std::string dump = ss.str(); |
| 1108 | |
| 1109 | // GpuAcc is a different case to CpuRef and CpuAcc, it doesn't use the buffer directly but instead maps it to a |
| 1110 | // new set of addresses within Gpu Memory. This will almost always be auto-aligned, so we don't need to check |
| 1111 | // for imports/copies. Only that the output is correct. |
| 1112 | if (backends[0] != Compute::GpuAcc) |
| 1113 | { |
| 1114 | // Even though we Imported the Input we still shouldn't have a SyncMemGeneric |
| 1115 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 1116 | CHECK(count == 0); |
| 1117 | // Should only be 1 CopyMemGeneric as we copied the input |
| 1118 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 1119 | if (backends[0] == Compute::CpuAcc) |
| 1120 | { |
| 1121 | // Reconfigure has not been implemented for CpuAcc so it will always copy, this will break whenever |
| 1122 | // reconfigure is implemented |
| 1123 | CHECK(count == 2); |
| 1124 | } |
| 1125 | else |
| 1126 | { |
| 1127 | CHECK(count == 1); |
| 1128 | } |
| 1129 | // Check the output is correct |
| 1130 | } |
| 1131 | unsigned int index = 0; |
| 1132 | for (auto outputValue : expectedOutput) |
| 1133 | { |
| 1134 | CHECK(outputValue == reinterpret_cast<float*>(misalignedMemPtr)[index]); |
| 1135 | ++index; |
| 1136 | } |
| 1137 | std::free(memPtr); |
| 1138 | } |
| 1139 | |
| 1140 | inline void ForceImportWithMisalignedInputAndOutputBuffersEndToEndTest(std::vector<BackendId> backends) |
| 1141 | { |
| 1142 | /** |
| 1143 | * This test is similar to the Import tests above, we create a network with a square function and pass in a vector |
| 1144 | * with 4 floats, square them. and validate the output. We then check the profiling logs to see if input/output |
| 1145 | * tensors are copied (CopyMemGeneric) or imported (SyncMemGeneric) |
| 1146 | * In this case all inputs and outputs should be copied |
| 1147 | */ |
| 1148 | using namespace armnn; |
| 1149 | |
| 1150 | IRuntime::CreationOptions options; |
| 1151 | IRuntimePtr runtime(IRuntime::Create(options)); |
| 1152 | |
| 1153 | // Builds up the structure of the network. |
| 1154 | INetworkPtr net(INetwork::Create()); |
| 1155 | IConnectableLayer* input = net->AddInputLayer(0); |
| 1156 | |
| 1157 | ActivationDescriptor descriptor; |
| 1158 | descriptor.m_Function = ActivationFunction::Square; |
| 1159 | IConnectableLayer* activationLayer = net->AddActivationLayer(descriptor); |
| 1160 | |
| 1161 | IConnectableLayer* output = net->AddOutputLayer(0); |
| 1162 | |
| 1163 | input->GetOutputSlot(0).Connect(activationLayer->GetInputSlot(0)); |
| 1164 | activationLayer->GetOutputSlot(0).Connect(output->GetInputSlot(0)); |
| 1165 | input->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32, 0.0f, 0, true)); |
| 1166 | activationLayer->GetOutputSlot(0).SetTensorInfo(TensorInfo({ 1, 1, 1, 4 }, DataType::Float32)); |
| 1167 | |
| 1168 | IOptimizedNetworkPtr optNet = Optimize(*net, backends, runtime->GetDeviceSpec()); |
| 1169 | INFO("Load Network"); |
| 1170 | // Load it into the runtime. It should pass. |
| 1171 | NetworkId netId; |
| 1172 | std::string ignoredErrorMessage; |
| 1173 | INetworkProperties networkProperties(false, MemorySource::Undefined, MemorySource::Undefined); |
| 1174 | CHECK(runtime->LoadNetwork(netId, std::move(optNet),ignoredErrorMessage, networkProperties) |
| 1175 | == Status::Success); |
| 1176 | INFO("Generate Data"); |
| 1177 | |
| 1178 | // This code looks a little funky but the idea is to create a buffer of floats but offset by the size of a char |
| 1179 | // this will guarantee that the resultant buffer is misaligned and thus should always be copied. |
| 1180 | auto inputMemPtr = std::malloc(4 * sizeof(float) + sizeof(char)); |
| 1181 | float* misalignedInputPtr = reinterpret_cast<float*>(reinterpret_cast<char*>(inputMemPtr) + 1); |
| 1182 | |
| 1183 | // Check if our pointer is truly misaligned |
| 1184 | uintptr_t alignment = GetDataTypeSize(DataType::Float32); |
| 1185 | CHECK (reinterpret_cast<uintptr_t>(misalignedInputPtr) % alignment); |
| 1186 | auto inputBuffer = reinterpret_cast<float*>(misalignedInputPtr); |
| 1187 | for (int i = 0; i < 4; i++) |
| 1188 | { |
| 1189 | inputBuffer[i] = 1.0f + static_cast<float>(i); |
| 1190 | } |
| 1191 | |
| 1192 | auto outputMemPtr = std::malloc(4 * sizeof(float) + sizeof(char)); |
| 1193 | float* misalignedOutputPtr = reinterpret_cast<float*>(reinterpret_cast<char*>(outputMemPtr) + 1); |
| 1194 | |
| 1195 | // Check if our pointer is truly misaligned |
| 1196 | CHECK (reinterpret_cast<uintptr_t>(misalignedOutputPtr) % alignment); |
| 1197 | |
| 1198 | std::vector<float> expectedOutput |
| 1199 | { |
| 1200 | 1.0f, 4.0f, 9.0f, 16.0f |
| 1201 | }; |
| 1202 | |
| 1203 | INFO("Create Inference"); |
| 1204 | InputTensors inputTensors |
| 1205 | { |
| 1206 | {0,armnn::ConstTensor(runtime->GetInputTensorInfo(netId, 0), misalignedInputPtr)}, |
| 1207 | }; |
| 1208 | OutputTensors outputTensors |
| 1209 | { |
| 1210 | {0,armnn::Tensor(runtime->GetOutputTensorInfo(netId, 0), misalignedOutputPtr)} |
| 1211 | }; |
| 1212 | runtime->GetProfiler(netId)->EnableProfiling(true); |
| 1213 | std::vector<ImportedInputId> importedInputIds = |
| 1214 | runtime->ImportInputs(netId, inputTensors, MemorySource::Malloc); |
| 1215 | std::vector<ImportedOutputId> importedOutputIds = |
| 1216 | runtime->ImportOutputs(netId, outputTensors, MemorySource::Malloc); |
| 1217 | |
| 1218 | // Do the inference and force the import as the memory is misaligned. |
| 1219 | runtime->EnqueueWorkload(netId, inputTensors, outputTensors, importedInputIds, importedOutputIds); |
| 1220 | |
| 1221 | // Retrieve the Profiler.Print() output to get the workload execution |
| 1222 | ProfilerManager& profilerManager = armnn::ProfilerManager::GetInstance(); |
| 1223 | std::stringstream ss; |
| 1224 | profilerManager.GetProfiler()->Print(ss);; |
| 1225 | std::string dump = ss.str(); |
| 1226 | |
| 1227 | // GpuAcc is a different case to CpuRef and CpuAcc, it doesn't use the buffer directly but instead maps it to a |
| 1228 | // new set of addresses within Gpu Memory. This will almost always be auto-aligned, so we don't need to check |
| 1229 | // for imports/copies. Only that the output is correct. |
| 1230 | if (backends[0] != Compute::GpuAcc) |
| 1231 | { |
| 1232 | // We can only copy so there should be no SyncMemGeneric |
| 1233 | int count = SubStringCounter(dump, "SyncMemGeneric"); |
| 1234 | CHECK(count == 0); |
| 1235 | // Should only be CopyMemGeneric workloads as we copied all buffers |
| 1236 | count = SubStringCounter(dump, "CopyMemGeneric"); |
| 1237 | CHECK(count == 2); |
| 1238 | } |
| 1239 | // Check the output is correct |
| 1240 | unsigned int index = 0; |
| 1241 | for (auto outputValue : expectedOutput) |
| 1242 | { |
| 1243 | CHECK(outputValue == reinterpret_cast<float*>(misalignedOutputPtr)[index]); |
| 1244 | ++index; |
| 1245 | } |
| 1246 | std::free(inputMemPtr); |
| 1247 | std::free(outputMemPtr); |
| 1248 | } |
| 1249 | |
Nattapat Chaimanowong | 1fcb4ff | 2019-01-24 15:25:26 +0000 | [diff] [blame] | 1250 | } // anonymous namespace |