Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Timed Linux Kernel Compilation
7-Zip Compression
Blender
SVT-AV1
FFmpeg
Hashcat
Newest Tests
XNNPACK
GROMACS
Stockfish
POV-Ray
GraphicsMagick
7-Zip Compression
Recently Updated Tests
simdjson
LeelaChessZero
Mobile Neural Network
Y-Cruncher
Etcpak
Unigine Heaven
New & Recently Updated Tests
Recently Updated Suites
Machine Learning
Database Test Suite
Steam
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>