Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Flexible IO Tester
Timed Linux Kernel Compilation
Blender
SVT-AV1
7-Zip Compression
FFmpeg
Newest Tests
OpenVINO GenAI
Rustls
LiteRT
WarpX
Epoch
Valkey
Recently Updated Tests
srsRAN Project
VVenC
x265
RELION
Llamafile
Llama.cpp
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
XNNPACK 1.1.0
pts/xnnpack-1.1.0
- 15 October 2024 -
Update against XNNPACK upstream, switch to new benchmark.
downloads.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.5--> <PhoronixTestSuite> <Downloads> <Package> <URL>https://github.com/google/XNNPACK/archive/b7b0486488393c645cefd464648da85c664380e3.zip</URL> <MD5>4f6d9dbe8bd2832fc86744c46b8d2d05</MD5> <SHA256>0c6a84ace20c47b0ea9b0acac3d7b7c820933d946ce4f8819f84bdc5ec8689b9</SHA256> <FileName>XNNPACK-b7b0486488393c645cefd464648da85c664380e3.zip</FileName> <FileSize>24385687</FileSize> </Package> </Downloads> </PhoronixTestSuite>
install.sh
#!/bin/bash rm -rf XNNPACK-b7b0486488393c645cefd464648da85c664380e3 unzip -o XNNPACK-b7b0486488393c645cefd464648da85c664380e3.zip cd XNNPACK-b7b0486488393c645cefd464648da85c664380e3 mkdir build cd build cmake .. -DCMAKE_BUILD_TYPE=Release make -j $NUM_CPU_CORES echo $? > ~/install-exit-status cd ~/ cat>xnnpack<<EOT #!/bin/sh cd XNNPACK-b7b0486488393c645cefd464648da85c664380e3/build ./bench-models --num_threads=\$NUM_CPU_CORES --benchmark_min_time=10 --benchmark_min_warmup_time=2 --benchmark_filter="MobileNet" > \$LOG_FILE 2>&1 echo \$? > ~/test-exit-status EOT chmod +x xnnpack
results-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.5--> <PhoronixTestSuite> <ResultsParser> <OutputTemplate>FP32MobileNetV1/real_time #_RESULT_# us 1422 us 7966 cpufreq=5.46597G</OutputTemplate> <LineHint>FP32MobileNetV1</LineHint> <ArgumentsDescription>Model: FP32MobileNetV1</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP32MobileNetV2/real_time #_RESULT_# us 1694 us 6390 cpufreq=5.48528G</OutputTemplate> <LineHint>FP32MobileNetV2</LineHint> <ArgumentsDescription>Model: FP32MobileNetV2</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP32MobileNetV3Large/real_time #_RESULT_# us 867 us 12836 cpufreq=5.52173G</OutputTemplate> <LineHint>FP32MobileNetV3Large</LineHint> <ArgumentsDescription>Model: FP32MobileNetV3Large</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP32MobileNetV3Small/real_time #_RESULT_# us 1422 us 7966 cpufreq=5.46597G</OutputTemplate> <LineHint>FP32MobileNetV3Small</LineHint> <ArgumentsDescription>Model: FP32MobileNetV3Small</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP16MobileNetV1/real_time #_RESULT_# us 1694 us 6390 cpufreq=5.48528G</OutputTemplate> <LineHint>FP16MobileNetV1</LineHint> <ArgumentsDescription>Model: FP16MobileNetV1</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP16MobileNetV2/real_time #_RESULT_# us 867 us 12836 cpufreq=5.52173G</OutputTemplate> <LineHint>FP16MobileNetV2</LineHint> <ArgumentsDescription>Model: FP16MobileNetV2</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP16MobileNetV3Large/real_time #_RESULT_# us 1422 us 7966 cpufreq=5.46597G</OutputTemplate> <LineHint>FP16MobileNetV3Large</LineHint> <ArgumentsDescription>Model: FP16MobileNetV3Large</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>FP16MobileNetV3Small/real_time #_RESULT_# us 1694 us 6390 cpufreq=5.48528G</OutputTemplate> <LineHint>FP16MobileNetV3Small</LineHint> <ArgumentsDescription>Model: FP16MobileNetV3Small</ArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>QS8MobileNetV2/real_time #_RESULT_# us 867 us 12836 cpufreq=5.52173G</OutputTemplate> <LineHint>QS8MobileNetV2</LineHint> <ArgumentsDescription>Model: QS8MobileNetV2</ArgumentsDescription> </ResultsParser> </PhoronixTestSuite>
test-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.5--> <PhoronixTestSuite> <TestInformation> <Title>XNNPACK</Title> <AppVersion>b7b048</AppVersion> <Description>XNNPACK is a Google library for high efficiency floating-point neural network inference operators across mobile / server / web use. XNNPACK is used by machine learning frameworks like TensorFlow, PyTorch, ONNX Runtime, MediaPipe, and others. This test profile uses XNNPACK with its bench-models benchmark and testing all available CPU threads.</Description> <ResultScale>us</ResultScale> <Proportion>LIB</Proportion> <TimesToRun>3</TimesToRun> </TestInformation> <TestProfile> <Version>1.1.0</Version> <SupportedPlatforms>Linux</SupportedPlatforms> <SoftwareType>Scientific</SoftwareType> <TestType>System</TestType> <License>Free</License> <Status>Verified</Status> <ExternalDependencies>cmake, build-utilities</ExternalDependencies> <EnvironmentSize>6200</EnvironmentSize> <ProjectURL>https://github.com/google/XNNPACK/</ProjectURL> <RepositoryURL>https://github.com/google/XNNPACK</RepositoryURL> <Maintainer>Michael Larabel</Maintainer> </TestProfile> </PhoronixTestSuite>