Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Timed Linux Kernel Compilation
Blender
7-Zip Compression
SVT-AV1
FFmpeg
Newest Tests
OpenVINO GenAI
Rustls
LiteRT
WarpX
Epoch
Valkey
Recently Updated Tests
RELION
Llama.cpp
OpenVINO
Renaissance
Blender
vkpeak
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
PyTorch 1.0.0
pts/pytorch-1.0.0
- 16 November 2023 -
Initial commit.
install.sh
#!/bin/sh pip install --user torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 pytorch-benchmark==0.3.6 echo $? > ~/install-exit-status echo "#!/bin/sh echo \"import torch import yaml from torchvision.models import \$3 from pytorch_benchmark import benchmark #print(torchvision.models.list_models()) num_threads = torch.get_num_threads() print(f'Benchmarking on {num_threads} threads') model = \$3().to(\\\"\$1\\\") sample = torch.randn(2, 3, 224, 224) # (B, C, H, W) results = benchmark(model, sample, num_runs=1000, print_details=True, batch_size=\$2) print(yaml.dump(results)) \" > pytorch-benchmark.py python3 pytorch-benchmark.py > \$LOG_FILE 2>&1 echo \$? > ~/test-exit-status" > pytorch chmod +x pytorch
results-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.4--> <PhoronixTestSuite> <ResultsParser> <OutputTemplate> batches_per_second_max: #_MAX_RESULT_# batches_per_second_mean: #_RESULT_# batches_per_second_min: #_MIN_RESULT_# batches_per_second_std: 0.2647488016338466</OutputTemplate> </ResultsParser> </PhoronixTestSuite>
test-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.4--> <PhoronixTestSuite> <TestInformation> <Title>PyTorch</Title> <AppVersion>2.1</AppVersion> <Description>This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing.</Description> <ResultScale>batches/sec</ResultScale> <Proportion>HIB</Proportion> <TimesToRun>3</TimesToRun> </TestInformation> <TestProfile> <Version>1.0.0</Version> <SupportedPlatforms>Linux</SupportedPlatforms> <SoftwareType>Benchmark</SoftwareType> <TestType>System</TestType> <License>Free</License> <Status>Verified</Status> <ExternalDependencies>python</ExternalDependencies> <EnvironmentSize>4800</EnvironmentSize> <ProjectURL>https://pytorch.org/</ProjectURL> <RepositoryURL>https://github.com/pytorch/pytorch</RepositoryURL> <InternalTags>SMP</InternalTags> <Maintainer>Michael Larabel</Maintainer> <SystemDependencies>pip3</SystemDependencies> </TestProfile> <TestSettings> <Option> <DisplayName>Device</DisplayName> <Identifier>device</Identifier> <Menu> <Entry> <Name>CPU</Name> <Value>cpu</Value> </Entry> </Menu> </Option> <Option> <DisplayName>Batch Size</DisplayName> <Identifier>batch-size</Identifier> <Menu> <Entry> <Name>1</Name> <Value>1</Value> </Entry> <Entry> <Name>16</Name> <Value>16</Value> </Entry> <Entry> <Name>32</Name> <Value>32</Value> </Entry> <Entry> <Name>64</Name> <Value>64</Value> </Entry> <Entry> <Name>256</Name> <Value>256</Value> </Entry> <Entry> <Name>512</Name> <Value>512</Value> </Entry> </Menu> </Option> <Option> <DisplayName>Model</DisplayName> <Identifier>Model</Identifier> <Menu> <Entry> <Name>ResNet-50</Name> <Value>resnet50</Value> </Entry> <Entry> <Name>ResNet-152</Name> <Value>resnet152</Value> </Entry> <Entry> <Name>Efficientnet_v2_l</Name> <Value>efficientnet_v2_l</Value> </Entry> </Menu> </Option> </TestSettings> </PhoronixTestSuite>