Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Timed Linux Kernel Compilation
SVT-AV1
7-Zip Compression
Stockfish
x265
FFmpeg
Newest Tests
LiteRT
WarpX
Epoch
Valkey
Whisperfile
XNNPACK
Recently Updated Tests
ASTC Encoder
SVT-AV1
Unvanquished
Primesieve
XNNPACK
oneDNN
New & Recently Updated Tests
Recently Updated Suites
Database Test Suite
Machine Learning
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
Faiss 1.0.0
pts/faiss-1.0.0
- 28 April 2023 -
Initial commit of FAISS
downloads.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.4--> <PhoronixTestSuite> <Downloads> <Package> <URL>https://github.com/xianyi/OpenBLAS/archive/437c0bf2b4697339d96c7bd0bb0bcdac09eccba1.zip</URL> <MD5>622ddcb999fe99aec08f350eac316ffd</MD5> <SHA256>48261b648e3c726e1689e89fc8f2440a00624f35b07b4a0134f1a97fd4eddc30</SHA256> <FileName>OpenBLAS-437c0bf2b4697339d96c7bd0bb0bcdac09eccba1.zip</FileName> <FileSize>42119973</FileSize> </Package> <Package> <URL>https://github.com/facebookresearch/faiss/archive/refs/tags/v1.7.4.tar.gz</URL> <MD5>e1f96b228ec6a0819bc65efb9d196ec6</MD5> <SHA256>d9a7b31bf7fd6eb32c10b7ea7ff918160eed5be04fe63bb7b4b4b5f2bbde01ad</SHA256> <FileName>faiss-1.7.4.tar.gz</FileName> <FileSize>909408</FileSize> </Package> <Package> <URL>ftp://ftp.irisa.fr/local/texmex/corpus/sift.tar.gz</URL> <MD5>b23d1b3b2ee8469d819b61ca900ef0ed</MD5> <SHA256>92f1270c5e3a0cb46b89983e72b0511e4df065c31a9fa0276d8c9b1fca5bc81a</SHA256> <FileName>sift.tar.gz</FileName> <FileSize>168280445</FileSize> </Package> </Downloads> </PhoronixTestSuite>
install.sh
#!/bin/sh # Build our own BLAS to deal with NUM_THREADS limits with default Ubuntu packages on high core count systems.... mkdir ~/blas-install unzip -o OpenBLAS-437c0bf2b4697339d96c7bd0bb0bcdac09eccba1.zip cd OpenBLAS-437c0bf2b4697339d96c7bd0bb0bcdac09eccba1 make NUM_THREADS=512 USE_OPENMP=1 make PREFIX=$HOME/blas-install/ install cd ~ pip3 install --user swig faiss-cpu==1.7.4 tar -xf faiss-1.7.4.tar.gz cd faiss-1.7.4 chmod +x benchs/bench_polysemous_sift1m.py LD_LIBRARY_PATH=$HOME/blas-install/lib/:$LD_LIBRARY_PATH PATH=$HOME/blas-install/bin/:$PATH cmake -B build -DFAISS_ENABLE_GPU=OFF -DBUILD_TESTING=OFF -DCMAKE_BUILD_TYPE=Release -DFAISS_OPT_LEVEL=avx2 -DFAISS_ENABLE_PYTHON=ON -DBLAS_LIBDIR=$HOME/blas-install/lib/ -DBLA_VENDOR=OpenBLAS -DBLAS_INCDIR=$HOME/blas-install/include/ . cd build make -j faiss make demo_sift1M echo $? > ~/install-exit-status tar -xf ../../sift.tar.gz mv sift sift1M cd ~ echo "#!/bin/bash cd faiss-1.7.4/build ./\$1 > \$LOG_FILE 2>&1 echo \$? > ~/test-exit-status" > faiss chmod +x faiss
results-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.4--> <PhoronixTestSuite> <ResultsParser> <OutputTemplate>#_RESULT_# s] Compute recalls </OutputTemplate> <LineHint>Compute recalls</LineHint> <StripFromResult>[</StripFromResult> </ResultsParser> <ResultsParser> <OutputTemplate>PQ baseline #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>PQ baseline</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>PQ baseline</AppendToArgumentsDescription> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 64 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 64</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 64</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 62 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 62</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 62</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 58 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 58</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 58</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 54 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 54</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 54</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 50 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 50</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 50</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 46 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 46</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 46</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 42 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 42</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 42</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 38 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 38</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 38</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 34 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 34</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 34</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> <ResultsParser> <OutputTemplate>Polysemous 30 #_RESULT_# ms per query, R@1 0.4462</OutputTemplate> <LineHint>Polysemous 30</LineHint> <ResultScale>ms per query</ResultScale> <ResultProportion>LIB</ResultProportion> <AppendToArgumentsDescription>Polysemous 30</AppendToArgumentsDescription> <Importance>Secondary</Importance> </ResultsParser> </PhoronixTestSuite>
test-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.4--> <PhoronixTestSuite> <TestInformation> <Title>Faiss</Title> <AppVersion>1.7.4</AppVersion> <Description>Faiss is developed by Meta/Facebook. Faiss is a library for efficient similarity search and clustering of dense vectors.</Description> <ResultScale>Seconds</ResultScale> <Proportion>LIB</Proportion> <TimesToRun>3</TimesToRun> </TestInformation> <TestProfile> <Version>1.0.0</Version> <SupportedPlatforms>Linux</SupportedPlatforms> <SoftwareType>Utility</SoftwareType> <TestType>System</TestType> <License>Free</License> <Status>Verified</Status> <ExternalDependencies>python, build-utilities, fortran-compiler</ExternalDependencies> <RequiresInternet>TRUE</RequiresInternet> <EnvironmentSize>1100</EnvironmentSize> <ProjectURL>https://faiss.ai/</ProjectURL> <RepositoryURL>https://github.com/facebookresearch/faiss</RepositoryURL> <Maintainer>Michael Larabel</Maintainer> </TestProfile> <TestSettings> <Option> <DisplayName>Test</DisplayName> <Identifier>test</Identifier> <Menu> <Entry> <Name>demo_sift1M</Name> <Value>demos/demo_sift1M</Value> </Entry> <Entry> <Name>bench_polysemous_sift1m</Name> <Value>../benchs/bench_polysemous_sift1m.py</Value> </Entry> </Menu> </Option> </TestSettings> </PhoronixTestSuite>