Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Flexible IO Tester
Timed Linux Kernel Compilation
Llama.cpp
Blender
Hashcat
PostgreSQL
Newest Tests
OpenVINO GenAI
Rustls
Recently Updated Tests
Basis Universal
NeatBench
OpenRadioss
QuantLib
GROMACS
AOM AV1
New & Recently Updated Tests
Recently Updated Suites
Machine Learning
Server Motherboard
HPC - High Performance Computing
New & Recently Updated Suites
Component Benchmarks
CPUs / Processors
GPUs / Graphics
OpenGL
Disks / Storage
Motherboards
File-Systems
Operating Systems
OpenBenchmarking.org
Corporate / Organization Info
Bug Reports / Feature Requests
NCNN 1.0.0
pts/ncnn-1.0.0
- 18 September 2020 -
Initial commit of Tencent NCNN.
downloads.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.0.0m2--> <PhoronixTestSuite> <Downloads> <Package> <URL>https://github.com/Tencent/ncnn/archive/20200916.tar.gz</URL> <MD5>d93c0b057066540f52bae858701f8ee0</MD5> <SHA256>a7abc03c9acdaa1b4f85ce3f80722822f9eacc0efefc9dfef1e253fdb23d0f80</SHA256> <FileName>ncnn-20200916.tar.gz</FileName> <FileSize>11121685</FileSize> </Package> </Downloads> </PhoronixTestSuite>
install.sh
#!/bin/sh tar -xf ncnn-20200916.tar.gz cd ncnn-20200916 # Workaround for build issues with current release echo "cmake_minimum_required(VERSION 3.1) # for CMAKE_CXX_STANDARD set(CMAKE_CXX_STANDARD 11) add_subdirectory(caffe) add_subdirectory(mxnet) add_subdirectory(onnx) add_subdirectory(darknet) add_subdirectory(quantize) " > tools/CMakeLists.txt echo "" > tools/caffe/CMakeLists.txt echo "" > tools/onnx/CMakeLists.txt mkdir build cd build # Vulkan build currently not enabled due to hitting seg fault... cmake .. make -j $NUM_CPU_CORES # sometimes parallel build seems to fail, so do another make in case make echo $? > ~/install-exit-status cp ../benchmark/*.param benchmark/ cd ~/ cat>ncnn<<EOT #!/bin/sh cd ncnn-20200916/build/benchmark ./benchncnn 150 \$NUM_CPU_CORES 0 \$@ 0 > \$LOG_FILE 2>&1 echo \$? > ~/test-exit-status EOT chmod +x ncnn
results-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.0.0m2--> <PhoronixTestSuite> <ResultsParser> <OutputTemplate> squeezenet_int8 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>squeezenet_int8</LineHint> <AppendToArgumentsDescription>Model: squeezenet_int8</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> mobilenet_v3 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>mobilenet_v3</LineHint> <AppendToArgumentsDescription>Model: mobilenet_v3</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> shufflenet_v2 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>shufflenet_v2</LineHint> <AppendToArgumentsDescription>Model: squeezenet</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> mnasnet min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>mnasnet</LineHint> <AppendToArgumentsDescription>Model: mnasnet</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> blazeface min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>blazeface</LineHint> <AppendToArgumentsDescription>Model: blazeface</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> googlenet_int8 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>googlenet_int8</LineHint> <AppendToArgumentsDescription>Model: googlenet_int8</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> vgg16_int8 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>vgg16_int8</LineHint> <AppendToArgumentsDescription>Model: vgg16_int8</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> resnet18_int8 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>resnet18_int8</LineHint> <AppendToArgumentsDescription>Model: resnet18_int8</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> alexnet min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>alexnet</LineHint> <AppendToArgumentsDescription>Model: alexnet</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> resnet50_int8 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>resnet50_int8</LineHint> <AppendToArgumentsDescription>Model: resnet50_int8</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate> mobilenetv2_yolov3 min = #_MIN_RESULT_# max = #_MAX_RESULT_# avg = #_RESULT_#</OutputTemplate> <LineHint>mobilenetv2_yolov3</LineHint> <AppendToArgumentsDescription>Model: mobilenetv2_yolov3</AppendToArgumentsDescription> </ResultsParser> </PhoronixTestSuite>
test-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.0.0m2--> <PhoronixTestSuite> <TestInformation> <Title>NCNN</Title> <AppVersion>20200916</AppVersion> <Description>NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent.</Description> <ResultScale>ms</ResultScale> <Proportion>LIB</Proportion> <TimesToRun>3</TimesToRun> </TestInformation> <TestProfile> <Version>1.0.0</Version> <SupportedPlatforms>Linux</SupportedPlatforms> <SoftwareType>Scientific</SoftwareType> <TestType>System</TestType> <License>Free</License> <Status>Verified</Status> <ExternalDependencies>cmake, build-utilities, protobuf, opencv</ExternalDependencies> <EnvironmentSize>2700</EnvironmentSize> <ProjectURL>https://github.com/Tencent/ncnn</ProjectURL> <Maintainer>Michael Larabel</Maintainer> </TestProfile> <TestSettings> <Option> <DisplayName>Target</DisplayName> <Identifier>target</Identifier> <Menu> <Entry> <Name>CPU</Name> <Value>-1</Value> </Entry> </Menu> </Option> </TestSettings> </PhoronixTestSuite>