kvm-8vcpu-16gb-reference-08-06-2023

KVM testing on Debian 12 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2308093-SAMU-KVM8VCP35
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
kvm-8vcpu-16gb-reference-08-06-2023
August 06 2023
  2 Days, 1 Hour, 45 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


kvm-8vcpu-16gb-reference-08-06-2023OpenBenchmarking.orgPhoronix Test SuiteIntel Xeon Gold 6212U (8 Cores)QEMU Standard PC (Q35 + ICH9 2009) (rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org BIOS)Intel 82G33/G31/P35/P31 + ICH916GB275GB QEMU HDDbochs-drmdrmfbIntel 82801IRed Hat Virtio deviceDebian 126.1.0-10-amd64 (x86_64)GCC 12.2.0ext41024x768KVMProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelCompilerFile-SystemScreen ResolutionSystem LayerKvm-8vcpu-16gb-reference-08-06-2023 BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-bTRWOB/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-bTRWOB/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096- CPU Microcode: 0x5003302- Python 3.11.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

kvm-8vcpu-16gb-reference-08-06-2023fs-mark: 5000 Files, 1MB Size, 4 Threadsbuild-nodejs: Time To Compilepgbench: 1000 - 50 - Read Write - Average Latencypgbench: 1000 - 50 - Read Writepgbench: 1000 - 500 - Read Only - Average Latencypgbench: 1000 - 500 - Read Onlyopencv: Graph APIpgbench: 1000 - 1 - Read Only - Average Latencypgbench: 1000 - 1 - Read Onlynumenta-nab: KNN CADblender: Classroom - CPU-Onlytensorflow: CPU - 64 - VGG-16influxdb: 4 - 10000 - 2,5000,1 - 10000fio: Rand Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directorytensorflow: CPU - 512 - GoogLeNetopencv: Image Processingpgbench: 1000 - 500 - Read Write - Average Latencypgbench: 1000 - 500 - Read Writepgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writefio: Rand Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizesqlite: 1pgbench: 1 - 1 - Read Write - Average Latencypgbench: 1 - 1 - Read Writeopencv: Corefio: Seq Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directorystockfish: Total Timeopencv: Features 2Dinfluxdb: 64 - 10000 - 2,5000,1 - 10000tensorflow: CPU - 64 - ResNet-50fio: Rand Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryinfluxdb: 1024 - 10000 - 2,5000,1 - 10000pgbench: 100 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Writefio: Rand Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryopencv: Stitchingsqlite: 8tensorflow: CPU - 256 - GoogLeNetffmpeg: libx264 - Uploadffmpeg: libx264 - Uploadfio: Seq Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directorytensorflow: CPU - 32 - VGG-16ramspeed: Scale - Integersqlite: 4sqlite: 2pgbench: 1000 - 50 - Read Only - Average Latencypgbench: 1000 - 50 - Read Onlypgbench: 1000 - 1 - Read Write - Average Latencypgbench: 1000 - 1 - Read Writetensorflow: CPU - 512 - AlexNetpgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlybuild-linux-kernel: defconfigffmpeg: libx265 - Video On Demandffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformffmpeg: libx265 - Platformffmpeg: libx264 - Video On Demandffmpeg: libx264 - Video On Demandffmpeg: libx264 - Platformffmpeg: libx264 - Platformffmpeg: libx265 - Uploadffmpeg: libx265 - Uploadfio: Rand Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directoryfs-mark: 1000 Files, 1MB Sizenumpy: pgbench: 100 - 1 - Read Write - Average Latencypgbench: 100 - 1 - Read Writeopencv: Object Detectiontensorflow: CPU - 16 - VGG-16openssl: SHA256openssl: ChaCha20-Poly1305openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: ChaCha20openssl: SHA512rbenchmark: pgbench: 1 - 50 - Read Write - Average Latencypgbench: 1 - 50 - Read Writenumenta-nab: Earthgecko Skylineopencv: Videotiobench: Rand Write - 32MB - 8tensorflow: CPU - 256 - AlexNettensorflow: CPU - 32 - ResNet-50fio: Seq Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directorypgbench: 100 - 50 - Read Only - Average Latencypgbench: 100 - 50 - Read Onlypgbench: 100 - 1 - Read Only - Average Latencypgbench: 100 - 1 - Read Onlytiobench: Read - 32MB - 8tiobench: Write - 32MB - 8ramspeed: Copy - Floating Pointtiobench: Rand Read - 32MB - 8numenta-nab: Relative Entropyramspeed: Average - Floating Pointpgbench: 1 - 500 - Read Write - Average Latencypgbench: 1 - 500 - Read Writepgbench: 1 - 1 - Read Only - Average Latencypgbench: 1 - 1 - Read Onlypgbench: 1 - 500 - Read Only - Average Latencypgbench: 1 - 500 - Read Onlypgbench: 1 - 50 - Read Only - Average Latencypgbench: 1 - 50 - Read Onlyopencv: DNN - Deep Neural Networkcachebench: Read / Modify / Writecachebench: Writecachebench: Readmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3mnn: nasnetc-ray: Total Time - 4K, 16 Rays Per Pixelleveldb: Rand Deleteopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUfio: Seq Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directorytensorflow: CPU - 64 - GoogLeNetfio: Rand Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directoryfio: Seq Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directorytensorflow-lite: Mobilenet Quantopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUfio: Rand Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryfio: Rand Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directoryapache: 500nginx: 500nginx: 100apache: 20apache: 100nginx: 20sysbench: CPUtensorflow: CPU - 16 - ResNet-50fio: Seq Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Seq Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryfio: Rand Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directoryonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUnode-web-tooling: ffmpeg: libx265 - Liveffmpeg: libx265 - Liveonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUsimdjson: PartialTweetssimdjson: DistinctUserIDsimdjson: TopTweetcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedramspeed: Add - Integerramspeed: Triad - Integerramspeed: Average - Integercompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedramspeed: Triad - Floating Pointramspeed: Scale - Floating Pointramspeed: Copy - Integerramspeed: Add - Floating Pointsysbench: RAM / Memoryopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUsimdjson: Kostyacompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 3 - Compression Speedcompress-zstd: 12 - Decompression Speedcompress-zstd: 12 - Compression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUfs-mark: 1000 Files, 1MB Size, No Sync/FSyncopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUtensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2tensorflow-lite: NASNet Mobileopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUtensorflow-lite: Mobilenet Floattensorflow-lite: SqueezeNetopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenssl: RSA4096openssl: RSA4096ffmpeg: libx264 - Liveffmpeg: libx264 - Livenumenta-nab: Bayesian Changepointsimdjson: LargeRandtensorflow: CPU - 32 - GoogLeNetnumenta-nab: Contextual Anomaly Detector OSEbuild-imagemagick: Time To Compileonednn: IP Shapes 3D - bf16bf16bf16 - CPUtensorflow: CPU - 64 - AlexNetcompress-gzip: Linux Source Tree Archiving To .tar.gzredis: LPUSH - 500redis: LPUSH - 50redis: SET - 50redis: SET - 500redis: SADD - 500redis: SADD - 50redis: GET - 500tensorflow: CPU - 16 - GoogLeNetleveldb: Rand Readcrafty: Elapsed Timephpbench: PHP Benchmark Suiteredis: LPOP - 50redis: GET - 50redis: LPOP - 500tensorflow: CPU - 32 - AlexNetcompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingnode-express-loadtest: pybench: Total For Average Test Timesleveldb: Overwriteleveldb: Overwriteleveldb: Seq Fillleveldb: Seq Fillleveldb: Hot Readonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUstream: Copytensorflow: CPU - 16 - AlexNetleveldb: Fill Syncleveldb: Fill Syncnumenta-nab: Windowed Gaussianonednn: IP Shapes 1D - bf16bf16bf16 - CPUleveldb: Seek Randleveldb: Rand Fillleveldb: Rand Fillonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUstream: Addstream: Triadstream: Scalekvm-8vcpu-16gb-reference-08-06-2023177.11316.97564.82978416.983295323252380.07513336282.704829.589.37589177.9408232551.4782.91171097279.9541788207.58624189557611667.433179203430.4699.2145.2864.495223172778731314919.5712066180986091084268.124.7933873387.081195455.927.57618391842114425.791836673462.8338223822.43420982631.1437873787.61431066409.42876.329.12276.8231150124601.979.9624254.25350.966320.8890.888563344.824207182.701.814275784198.00133.28227.5933.34227.18814142734.02222.6534.07222.3516.02157.6345664566.54106.0363.594.859206381009.6224164983231840542451731174839590420399376133546362283727360858900.7974226.926220172.1814209118.014181.4623.352115584619.940.1603120540.0392557113654.2211.78125078.4023004.58528.22825144.452657.8291880.036278621.7192909470.1453455283207341296.96707425320.0659403034.95461220.4932.3742.7874.17110.9852.2501.61210.627112.55243.9931248.853.1957765776.0156865685.80113055452220.0671.51207281295.49517333233.34598213738.80151608606433.31212081325.503901.767.281097.4328212112850.2049015.4234006.2834698.7734792.3148848.1833872.859437.6121.741897075878.611778871153.222882.3510.0288.2257.251498.843.203.663.58756.010.424656.0423172.4124842.21758.25.5624527.4025074.8926237.8924812.557483.242274.901.752256.111.76659.3012.071.97949.4309.6944.6327.3957.21343.0869.1113.3996.8775.6115.3234.661764.524.53325.3749228.346465.412723.615.42517.652191.452888.1022.94174.1425.99307.240.98792.811.027766.49134141.02060.7148.5833.9955.3550.7670.8750.83150.5156.16259161.2745.6951525722.921475450.171616870.331656869.421828605.081836281.792008282.4266.735.87967240466905682217153.832246792.082303036.0144.1629162430684140101246.35319.145.94919.25.94627.739187359.0109.880.116802.97017.41410.33587.90849.27317.918.517920.428368102.468357.159657.4OpenBenchmarking.org

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threadskvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 11.85, N = 9177.1

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To Compilekvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 2.62, N = 31316.98

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 50 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-20231428425670SE +/- 2.83, N = 964.831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 50 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 37.71, N = 97841. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.34, N = 916.981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 500 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-20236K12K18K24K30KSE +/- 578.09, N = 9295321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Graph APIkvm-8vcpu-16gb-reference-08-06-202370K140K210K280K350KSE +/- 7476.40, N = 93252381. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.01690.03380.05070.06760.0845SE +/- 0.002, N = 90.0751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-20233K6K9K12K15KSE +/- 273.19, N = 9133361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADkvm-8vcpu-16gb-reference-08-06-202360120180240300SE +/- 2.52, N = 9282.70

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlykvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 1.65, N = 3829.58

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16kvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.01, N = 39.37

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000kvm-8vcpu-16gb-reference-08-06-2023130K260K390K520K650KSE +/- 11629.19, N = 12589177.9

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20239K18K27K36K45KSE +/- 1704.32, N = 1240823MIN: 29080.6 / MAX: 49142.021. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20235001000150020002500SE +/- 106.52, N = 122551.47MIN: 1817.56 / MAX: 3071.381. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetkvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 0.27, N = 382.91

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Image Processingkvm-8vcpu-16gb-reference-08-06-202340K80K120K160K200KSE +/- 1963.15, N = 121710971. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-202360120180240300SE +/- 4.43, N = 6279.951. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 500 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-2023400800120016002000SE +/- 28.48, N = 617881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 3.86, N = 12207.591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-20235001000150020002500SE +/- 48.20, N = 1224181. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20232K4K6K8K10KSE +/- 745.99, N = 129557MIN: 5271.86 / MAX: 12040.961. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-2023130K260K390K520K650KSE +/- 47743.46, N = 12611667.43MIN: 337404.05 / MAX: 770629.621. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20237001400210028003500SE +/- 191.99, N = 153179MIN: 2035.73 / MAX: 5289.671. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202340K80K120K160K200KSE +/- 12287.08, N = 15203430.46MIN: 130289.83 / MAX: 338541.721. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Sizekvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 1.08, N = 499.2

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 1kvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 3.74, N = 11145.291. (CC) gcc options: -O2 -lz -lm

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-20231.01142.02283.03424.04565.057SE +/- 0.034, N = 124.4951. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 1 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 1.60, N = 122231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Corekvm-8vcpu-16gb-reference-08-06-202340K80K120K160K200KSE +/- 4138.18, N = 91727781. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-2023160320480640800SE +/- 273.76, N = 12731MIN: 196.32 / MAX: 3478.921. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202370K140K210K280K350KSE +/- 61676.44, N = 12314919.57MIN: 1609.68 / MAX: 703568.591. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total Timekvm-8vcpu-16gb-reference-08-06-20233M6M9M12M15MSE +/- 134605.03, N = 12120661801. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Features 2Dkvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 1626.64, N = 15986091. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000kvm-8vcpu-16gb-reference-08-06-2023200K400K600K800K1000KSE +/- 9736.12, N = 151084268.1

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50kvm-8vcpu-16gb-reference-08-06-2023612182430SE +/- 0.27, N = 524.79

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20237001400210028003500SE +/- 288.31, N = 93387MIN: 1920.63 / MAX: 4194.511. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20237001400210028003500SE +/- 288.35, N = 93387.08MIN: 1920.96 / MAX: 4194.761. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000kvm-8vcpu-16gb-reference-08-06-2023300K600K900K1200K1500KSE +/- 11564.55, N = 151195455.9

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-2023612182430SE +/- 1.31, N = 927.581. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-2023400800120016002000SE +/- 69.84, N = 918391. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-2023400800120016002000SE +/- 209.49, N = 91842MIN: 990.4 / MAX: 2723.181. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 112477.03, N = 9114425.79MIN: 1143.05 / MAX: 1014240.871. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20234K8K12K16K20KSE +/- 226.88, N = 1518366MIN: 16840.55 / MAX: 19532.481. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202316K32K48K64K80KSE +/- 907.54, N = 1573462.83MIN: 67362.35 / MAX: 78130.121. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 52.87, N = 143822MIN: 3198.06 / MAX: 3984.491. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 52.87, N = 143822.43MIN: 3198.15 / MAX: 3984.641. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20239K18K27K36K45KSE +/- 1332.09, N = 1042098MIN: 35978.71 / MAX: 50985.111. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20236001200180024003000SE +/- 83.25, N = 102631.14MIN: 2248.69 / MAX: 3186.581. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 396.19, N = 93787MIN: 1303.93 / MAX: 5298.761. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 396.21, N = 93787.61MIN: 1304.17 / MAX: 5298.871. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Stitchingkvm-8vcpu-16gb-reference-08-06-202390K180K270K360K450KSE +/- 4772.38, N = 34310661. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 8kvm-8vcpu-16gb-reference-08-06-202390180270360450SE +/- 1.31, N = 3409.431. (CC) gcc options: -O2 -lz -lm

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetkvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 0.26, N = 376.32

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Uploadkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.02, N = 39.121. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Uploadkvm-8vcpu-16gb-reference-08-06-202360120180240300SE +/- 0.49, N = 3276.821. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 225.18, N = 1131150MIN: 30267.43 / MAX: 32788.581. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202330K60K90K120K150KSE +/- 900.73, N = 11124601.97MIN: 121070.02 / MAX: 131154.531. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16kvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.07, N = 39.96

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integerkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 236.84, N = 1524254.251. (CC) gcc options: -O3 -march=native

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 4kvm-8vcpu-16gb-reference-08-06-202380160240320400SE +/- 0.69, N = 3350.971. (CC) gcc options: -O2 -lz -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 2kvm-8vcpu-16gb-reference-08-06-202370140210280350SE +/- 3.47, N = 3320.891. (CC) gcc options: -O2 -lz -lm

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 50 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.19980.39960.59940.79920.999SE +/- 0.009, N = 30.8881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 50 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-202312K24K36K48K60KSE +/- 550.87, N = 3563341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-20231.08542.17083.25624.34165.427SE +/- 0.041, N = 34.8241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 1.75, N = 32071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetkvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 1.46, N = 3182.70

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.40820.81641.22461.63282.041SE +/- 0.018, N = 61.8141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-202360K120K180K240K300KSE +/- 2707.55, N = 62757841. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigkvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 2.39, N = 4198.00

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandkvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.03, N = 333.281. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandkvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 0.22, N = 3227.591. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Platformkvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.11, N = 333.341. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Platformkvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 0.75, N = 3227.191. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On Demandkvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.01, N = 334.021. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On Demandkvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 0.06, N = 3222.651. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformkvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.10, N = 334.071. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformkvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 0.65, N = 3222.351. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Uploadkvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.03, N = 316.021. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Uploadkvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.34, N = 3157.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202310002000300040005000SE +/- 43.89, N = 64566MIN: 4375.08 / MAX: 4683.211. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202310002000300040005000SE +/- 43.88, N = 64566.54MIN: 4375.23 / MAX: 4683.281. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Sizekvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 0.54, N = 3106.0

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkkvm-8vcpu-16gb-reference-08-06-202380160240320400SE +/- 0.67, N = 3363.59

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-20231.09332.18663.27994.37325.4665SE +/- 0.052, N = 44.8591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 2.16, N = 42061. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Object Detectionkvm-8vcpu-16gb-reference-08-06-20238K16K24K32K40KSE +/- 804.71, N = 15381001. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: VGG-16kvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.04, N = 39.62

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256kvm-8vcpu-16gb-reference-08-06-2023500M1000M1500M2000M2500MSE +/- 18310345.44, N = 324164983231. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305kvm-8vcpu-16gb-reference-08-06-20234000M8000M12000M16000M20000MSE +/- 175951826.95, N = 3184054245171. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMkvm-8vcpu-16gb-reference-08-06-20237000M14000M21000M28000M35000MSE +/- 38177192.52, N = 3311748395901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMkvm-8vcpu-16gb-reference-08-06-20239000M18000M27000M36000M45000MSE +/- 85148856.84, N = 3420399376131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20kvm-8vcpu-16gb-reference-08-06-20238000M16000M24000M32000M40000MSE +/- 11846878.68, N = 3354636228371. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512kvm-8vcpu-16gb-reference-08-06-2023600M1200M1800M2400M3000MSE +/- 4931629.06, N = 327360858901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterR Benchmarkkvm-8vcpu-16gb-reference-08-06-20230.17940.35880.53820.71760.897SE +/- 0.0017, N = 30.7974

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 2.70, N = 4226.931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-202350100150200250SE +/- 2.56, N = 42201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinekvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 0.66, N = 3172.18

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Videokvm-8vcpu-16gb-reference-08-06-20239K18K27K36K45KSE +/- 2951.87, N = 12420911. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 32MB - Thread Count: 8kvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.18, N = 318.011. (CC) gcc options: -O2

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetkvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 0.71, N = 3181.46

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50kvm-8vcpu-16gb-reference-08-06-2023612182430SE +/- 0.10, N = 323.35

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 233.17, N = 521155MIN: 20342.39 / MAX: 21714.111. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 932.68, N = 584619.94MIN: 81369.69 / MAX: 86856.581. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.0360.0720.1080.1440.18SE +/- 0.001, N = 30.1601. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-202370K140K210K280K350KSE +/- 2846.34, N = 33120541. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.00880.01760.02640.03520.044SE +/- 0.000, N = 30.0391. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 62.77, N = 3255711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 32MB - Thread Count: 8kvm-8vcpu-16gb-reference-08-06-20233K6K9K12K15KSE +/- 105.32, N = 313654.221. (CC) gcc options: -O2

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 8kvm-8vcpu-16gb-reference-08-06-20230.40070.80141.20211.60282.0035SE +/- 0.023, N = 31.7811. (CC) gcc options: -O2

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Pointkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 240.47, N = 625078.401. (CC) gcc options: -O3 -march=native

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 32MB - Thread Count: 8kvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 103.44, N = 323004.591. (CC) gcc options: -O2

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropykvm-8vcpu-16gb-reference-08-06-2023714212835SE +/- 0.18, N = 1528.23

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Pointkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 248.67, N = 625144.451. (CC) gcc options: -O3 -march=native

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latencykvm-8vcpu-16gb-reference-08-06-20236001200180024003000SE +/- 10.15, N = 32657.831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Writekvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 0.72, N = 31881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.00810.01620.02430.03240.0405SE +/- 0.000, N = 30.0361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 1 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-20236K12K18K24K30KSE +/- 175.40, N = 3278621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.38680.77361.16041.54721.934SE +/- 0.019, N = 31.7191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-202360K120K180K240K300KSE +/- 3122.52, N = 32909471. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latencykvm-8vcpu-16gb-reference-08-06-20230.03260.06520.09780.13040.163SE +/- 0.001, N = 30.1451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Onlykvm-8vcpu-16gb-reference-08-06-202370K140K210K280K350KSE +/- 3063.92, N = 33455281. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural Networkkvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 1592.63, N = 12320731. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Writekvm-8vcpu-16gb-reference-08-06-20239K18K27K36K45KSE +/- 59.86, N = 341296.97MIN: 37557.36 / MAX: 43626.391. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Writekvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 10.42, N = 325320.07MIN: 22490.82 / MAX: 27186.391. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Readkvm-8vcpu-16gb-reference-08-06-20237001400210028003500SE +/- 1.52, N = 33034.95MIN: 3008.2 / MAX: 3049.711. (CC) gcc options: -lrt

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3kvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.07, N = 320.49MIN: 18.58 / MAX: 28.121. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0kvm-8vcpu-16gb-reference-08-06-20230.53421.06841.60262.13682.671SE +/- 0.022, N = 32.374MIN: 1.99 / MAX: 3.441. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224kvm-8vcpu-16gb-reference-08-06-20230.62711.25421.88132.50843.1355SE +/- 0.011, N = 32.787MIN: 2.37 / MAX: 5.191. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0kvm-8vcpu-16gb-reference-08-06-20230.93851.8772.81553.7544.6925SE +/- 0.019, N = 34.171MIN: 3.71 / MAX: 8.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50kvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.04, N = 310.99MIN: 9.92 / MAX: 14.881. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1kvm-8vcpu-16gb-reference-08-06-20230.50631.01261.51892.02522.5315SE +/- 0.007, N = 32.250MIN: 1.95 / MAX: 3.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3kvm-8vcpu-16gb-reference-08-06-20230.36270.72541.08811.45081.8135SE +/- 0.006, N = 31.612MIN: 1.37 / MAX: 2.241. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.03, N = 310.63MIN: 9.65 / MAX: 15.091. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixelkvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.72, N = 3112.551. (CC) gcc options: -lm -lpthread -O3

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Random Deletekvm-8vcpu-16gb-reference-08-06-20231020304050SE +/- 0.44, N = 1543.991. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 13.25, N = 51248.85MIN: 1087.22 / MAX: 1452.061. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20230.71781.43562.15342.87123.589SE +/- 0.03, N = 53.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202312002400360048006000SE +/- 78.28, N = 35776MIN: 5657.18 / MAX: 5923.641. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202312002400360048006000SE +/- 78.27, N = 35776.01MIN: 5657.3 / MAX: 5923.751. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202312002400360048006000SE +/- 43.96, N = 35686MIN: 5613.34 / MAX: 5765.121. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 1MB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202312002400360048006000SE +/- 43.97, N = 35685.80MIN: 5613.47 / MAX: 5765.291. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 1200.99, N = 3113055MIN: 110666.74 / MAX: 114472.131. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-2023100K200K300K400K500KSE +/- 4804.15, N = 3452220.06MIN: 442667.25 / MAX: 457889.511. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetkvm-8vcpu-16gb-reference-08-06-20231632486480SE +/- 0.36, N = 371.51

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20234K8K12K16K20KSE +/- 208.68, N = 320728MIN: 20413.33 / MAX: 21122.621. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 13.04, N = 31295.49MIN: 1275.84 / MAX: 1320.171. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202311K22K33K44K55KSE +/- 505.16, N = 351733MIN: 50992.77 / MAX: 52698.821. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20237001400210028003500SE +/- 31.58, N = 33233.34MIN: 3187.05 / MAX: 3293.691. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202313K26K39K52K65KSE +/- 706.55, N = 359821MIN: 58557.4 / MAX: 61000.71. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 44.16, N = 33738.80MIN: 3659.84 / MAX: 3812.551. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202330K60K90K120K150KSE +/- 364.86, N = 3151608MIN: 151126.51 / MAX: 152323.751. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-2023130K260K390K520K650KSE +/- 1459.37, N = 3606433.31MIN: 604506.89 / MAX: 609295.451. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 147.26, N = 321208MIN: 20925.72 / MAX: 21421.951. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 64KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 9.21, N = 31325.50MIN: 1307.86 / MAX: 1338.881. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantkvm-8vcpu-16gb-reference-08-06-20238001600240032004000SE +/- 43.05, N = 53901.76

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023246810SE +/- 0.08, N = 57.28MIN: 5.75 / MAX: 24.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 12.16, N = 51097.431. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20236K12K18K24K30KSE +/- 292.38, N = 328212MIN: 27771.13 / MAX: 28765.361. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Read - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 1 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 1169.52, N = 3112850.20MIN: 111084.77 / MAX: 115061.741. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500kvm-8vcpu-16gb-reference-08-06-202310K20K30K40K50KSE +/- 185.87, N = 349015.421. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500kvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 97.71, N = 334006.281. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 100kvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 129.09, N = 334698.771. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 20kvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 117.04, N = 334792.311. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 100kvm-8vcpu-16gb-reference-08-06-202310K20K30K40K50KSE +/- 492.44, N = 348848.181. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 20kvm-8vcpu-16gb-reference-08-06-20237K14K21K28K35KSE +/- 28.11, N = 333872.851. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUkvm-8vcpu-16gb-reference-08-06-20232K4K6K8K10KSE +/- 6.38, N = 39437.611. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50kvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.08, N = 321.74

Flexible IO Tester

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20234K8K12K16K20KSE +/- 212.19, N = 318970MIN: 18611.15 / MAX: 19345.551. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Sequential Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202316K32K48K64K80KSE +/- 848.75, N = 375878.61MIN: 74445.07 / MAX: 77382.691. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-20234K8K12K16K20KSE +/- 167.76, N = 317788MIN: 17508.38 / MAX: 18088.441. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMiB/s, More Is BetterFlexible IO Tester 3.35Type: Random Write - Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directorykvm-8vcpu-16gb-reference-08-06-202315K30K45K60K75KSE +/- 671.05, N = 371153.22MIN: 70033.87 / MAX: 72354.141. (CC) gcc options: -rdynamic -ll -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-20236001200180024003000SE +/- 10.41, N = 32882.35MIN: 2726.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling Benchmarkkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.05, N = 310.02

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Livekvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 0.51, N = 388.221. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Livekvm-8vcpu-16gb-reference-08-06-20231326395265SE +/- 0.33, N = 357.251. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 6.20, N = 31498.84MIN: 1388.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetskvm-8vcpu-16gb-reference-08-06-20230.721.442.162.883.6SE +/- 0.00, N = 33.201. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDkvm-8vcpu-16gb-reference-08-06-20230.82351.6472.47053.2944.1175SE +/- 0.00, N = 33.661. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetkvm-8vcpu-16gb-reference-08-06-20230.80551.6112.41653.2224.0275SE +/- 0.00, N = 33.581. (CXX) g++ options: -O3

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression Speedkvm-8vcpu-16gb-reference-08-06-2023160320480640800SE +/- 4.59, N = 3756.01. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.09, N = 310.41. (CC) gcc options: -O3 -pthread -lz -llzma

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Integerkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 314.15, N = 324656.041. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integerkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 74.40, N = 323172.411. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integerkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 290.28, N = 324842.211. (CC) gcc options: -O3 -march=native

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression Speedkvm-8vcpu-16gb-reference-08-06-2023160320480640800SE +/- 2.31, N = 3758.21. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedkvm-8vcpu-16gb-reference-08-06-20231.2512.5023.7535.0046.255SE +/- 0.07, N = 35.561. (CC) gcc options: -O3 -pthread -lz -llzma

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Pointkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 258.56, N = 324527.401. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Pointkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 38.08, N = 325074.891. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integerkvm-8vcpu-16gb-reference-08-06-20236K12K18K24K30KSE +/- 355.23, N = 326237.891. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating Pointkvm-8vcpu-16gb-reference-08-06-20235K10K15K20K25KSE +/- 294.63, N = 324812.551. (CC) gcc options: -O3 -march=native

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memorykvm-8vcpu-16gb-reference-08-06-202316003200480064008000SE +/- 52.69, N = 157483.241. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20235001000150020002500SE +/- 11.59, N = 32274.90MIN: 2163.44 / MAX: 2447.011. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20230.39380.78761.18141.57521.969SE +/- 0.01, N = 31.751. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20235001000150020002500SE +/- 3.87, N = 32256.11MIN: 2133.47 / MAX: 2541.81. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20230.3960.7921.1881.5841.98SE +/- 0.01, N = 31.761. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023140280420560700SE +/- 1.32, N = 3659.30MIN: 560.67 / MAX: 830.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.03, N = 312.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: Kostyakvm-8vcpu-16gb-reference-08-06-20230.44330.88661.32991.77322.2165SE +/- 0.01, N = 31.971. (CXX) g++ options: -O3

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 1.27, N = 3949.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression Speedkvm-8vcpu-16gb-reference-08-06-202370140210280350SE +/- 0.09, N = 3309.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 3.61, N = 3944.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression Speedkvm-8vcpu-16gb-reference-08-06-202370140210280350SE +/- 2.58, N = 3327.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Decompression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 1.05, N = 3957.21. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Compression Speedkvm-8vcpu-16gb-reference-08-06-202330060090012001500SE +/- 2.51, N = 31343.01. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 0.75, N = 3869.11. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression Speedkvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.62, N = 3113.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Decompression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 1.68, N = 3996.81. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Compression Speedkvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 2.66, N = 3775.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.47, N = 3115.32MIN: 107.12 / MAX: 187.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.14, N = 334.661. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSynckvm-8vcpu-16gb-reference-08-06-2023400800120016002000SE +/- 5.13, N = 31764.5

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023612182430SE +/- 0.24, N = 324.53MIN: 20.65 / MAX: 45.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-202370140210280350SE +/- 3.20, N = 3325.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4kvm-8vcpu-16gb-reference-08-06-202311K22K33K44K55KSE +/- 513.12, N = 349228.3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2kvm-8vcpu-16gb-reference-08-06-202310K20K30K40K50KSE +/- 519.06, N = 346465.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilekvm-8vcpu-16gb-reference-08-06-20233K6K9K12K15KSE +/- 18.18, N = 312723.6

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.06, N = 315.42MIN: 13.19 / MAX: 30.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023110220330440550SE +/- 1.86, N = 3517.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatkvm-8vcpu-16gb-reference-08-06-20235001000150020002500SE +/- 16.28, N = 32191.45

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetkvm-8vcpu-16gb-reference-08-06-20236001200180024003000SE +/- 5.42, N = 32888.10

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.33, N = 322.94MIN: 20.02 / MAX: 40.991. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 2.44, N = 3174.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-2023612182430SE +/- 0.13, N = 325.99MIN: 21.18 / MAX: 50.11. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-202370140210280350SE +/- 1.47, N = 3307.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20230.20250.4050.60750.811.0125SE +/- 0.00, N = 30.9MIN: 0.7 / MAX: 5.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20232K4K6K8K10KSE +/- 9.59, N = 38792.811. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-20230.22950.4590.68850.9181.1475SE +/- 0.01, N = 31.02MIN: 0.78 / MAX: 5.171. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUkvm-8vcpu-16gb-reference-08-06-202317003400510068008500SE +/- 100.43, N = 37766.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096kvm-8vcpu-16gb-reference-08-06-202330K60K90K120K150KSE +/- 128.65, N = 3134141.01. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096kvm-8vcpu-16gb-reference-08-06-2023400800120016002000SE +/- 2.03, N = 32060.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Livekvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.80, N = 3148.581. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Livekvm-8vcpu-16gb-reference-08-06-2023816243240SE +/- 0.18, N = 333.991. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointkvm-8vcpu-16gb-reference-08-06-20231224364860SE +/- 0.01, N = 355.36

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomkvm-8vcpu-16gb-reference-08-06-20230.1710.3420.5130.6840.855SE +/- 0.00, N = 30.761. (CXX) g++ options: -O3

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetkvm-8vcpu-16gb-reference-08-06-20231632486480SE +/- 0.17, N = 370.87

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEkvm-8vcpu-16gb-reference-08-06-20231122334455SE +/- 0.38, N = 350.83

Timed ImageMagick Compilation

This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compilekvm-8vcpu-16gb-reference-08-06-20231122334455SE +/- 0.41, N = 350.52

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-2023246810SE +/- 0.05781, N = 156.16259MIN: 5.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetkvm-8vcpu-16gb-reference-08-06-20234080120160200SE +/- 0.53, N = 3161.27

Gzip Compression

This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using Gzip compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gzkvm-8vcpu-16gb-reference-08-06-20231020304050SE +/- 0.31, N = 345.70

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPUSH - Parallel Connections: 500kvm-8vcpu-16gb-reference-08-06-2023300K600K900K1200K1500KSE +/- 20735.71, N = 31525722.921. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPUSH - Parallel Connections: 50kvm-8vcpu-16gb-reference-08-06-2023300K600K900K1200K1500KSE +/- 20366.22, N = 31475450.171. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50kvm-8vcpu-16gb-reference-08-06-2023300K600K900K1200K1500KSE +/- 4632.17, N = 31616870.331. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500kvm-8vcpu-16gb-reference-08-06-2023400K800K1200K1600K2000KSE +/- 13596.93, N = 31656869.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SADD - Parallel Connections: 500kvm-8vcpu-16gb-reference-08-06-2023400K800K1200K1600K2000KSE +/- 4732.32, N = 31828605.081. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 256 - Model: VGG-16

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SADD - Parallel Connections: 50kvm-8vcpu-16gb-reference-08-06-2023400K800K1200K1600K2000KSE +/- 12660.09, N = 31836281.791. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500kvm-8vcpu-16gb-reference-08-06-2023400K800K1200K1600K2000KSE +/- 11618.24, N = 32008282.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetkvm-8vcpu-16gb-reference-08-06-20231530456075SE +/- 0.21, N = 366.73

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Random Readkvm-8vcpu-16gb-reference-08-06-20231.32282.64563.96845.29126.614SE +/- 0.040, N = 155.8791. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

Crafty

This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Timekvm-8vcpu-16gb-reference-08-06-20231.4M2.8M4.2M5.6M7MSE +/- 19479.74, N = 367240461. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suitekvm-8vcpu-16gb-reference-08-06-2023150K300K450K600K750KSE +/- 1355.11, N = 3690568

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPOP - Parallel Connections: 50kvm-8vcpu-16gb-reference-08-06-2023500K1000K1500K2000K2500KSE +/- 16523.46, N = 32217153.831. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50kvm-8vcpu-16gb-reference-08-06-2023500K1000K1500K2000K2500KSE +/- 19320.60, N = 32246792.081. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPOP - Parallel Connections: 500kvm-8vcpu-16gb-reference-08-06-2023500K1000K1500K2000K2500KSE +/- 13581.79, N = 32303036.01. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetkvm-8vcpu-16gb-reference-08-06-2023306090120150SE +/- 0.30, N = 3144.16

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingkvm-8vcpu-16gb-reference-08-06-20236K12K18K24K30KSE +/- 65.10, N = 3291621. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingkvm-8vcpu-16gb-reference-08-06-20239K18K27K36K45KSE +/- 144.04, N = 3430681. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Node.js Express HTTP Load Test

A Node.js Express server with a Node-based loadtest client for facilitating HTTP benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load Testkvm-8vcpu-16gb-reference-08-06-20239001800270036004500SE +/- 8.35, N = 34140

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timeskvm-8vcpu-16gb-reference-08-06-20232004006008001000SE +/- 4.04, N = 31012

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Overwritekvm-8vcpu-16gb-reference-08-06-20231122334455SE +/- 0.78, N = 1546.351. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.23Benchmark: Overwritekvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.30, N = 1519.11. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Sequential Fillkvm-8vcpu-16gb-reference-08-06-20231020304050SE +/- 0.29, N = 345.951. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.23Benchmark: Sequential Fillkvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.12, N = 319.21. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 256 - Model: ResNet-50

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Hot Readkvm-8vcpu-16gb-reference-08-06-20231.33792.67584.01375.35166.6895SE +/- 0.045, N = 115.9461. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-2023714212835SE +/- 0.09, N = 327.74MIN: 25.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copykvm-8vcpu-16gb-reference-08-06-202320K40K60K80K100KSE +/- 315.46, N = 587359.01. (CC) gcc options: -O3 -march=native -fopenmp

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetkvm-8vcpu-16gb-reference-08-06-202320406080100SE +/- 1.11, N = 3109.88

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.23Benchmark: Fill Synckvm-8vcpu-16gb-reference-08-06-20230.02250.0450.06750.090.11250.11. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Fill Synckvm-8vcpu-16gb-reference-08-06-20234K8K12K16K20KSE +/- 144.57, N = 316802.971. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 512 - Model: ResNet-50

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussiankvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.12, N = 317.41

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-20233691215SE +/- 0.04, N = 310.34MIN: 8.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 512 - Model: VGG-16

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Seek Randomkvm-8vcpu-16gb-reference-08-06-2023246810SE +/- 0.088, N = 37.9081. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.23Benchmark: Random Fillkvm-8vcpu-16gb-reference-08-06-20231122334455SE +/- 0.54, N = 449.271. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.23Benchmark: Random Fillkvm-8vcpu-16gb-reference-08-06-202348121620SE +/- 0.19, N = 417.91. (CXX) g++ options: -fno-exceptions -fno-rtti -O3 -lgmock -lgtest -lsnappy

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.09, N = 318.52MIN: 17.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUkvm-8vcpu-16gb-reference-08-06-2023510152025SE +/- 0.05, N = 320.43MIN: 19.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Loopback TCP Network Performance

This test measures the loopback network adapter performance using a micro-benchmark to measure the TCP performance. Learn more via the OpenBenchmarking.org test page.

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: localhost [127.0.0.1] 9999 (?) : Connection refused

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

Concurrent Requests: 4

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

Connections: 1

kvm-8vcpu-16gb-reference-08-06-2023: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Addkvm-8vcpu-16gb-reference-08-06-202315K30K45K60K75KSE +/- 323.86, N = 568102.41. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triadkvm-8vcpu-16gb-reference-08-06-202315K30K45K60K75KSE +/- 331.87, N = 568357.11. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scalekvm-8vcpu-16gb-reference-08-06-202313K26K39K52K65KSE +/- 242.71, N = 559657.41. (CC) gcc options: -O3 -march=native -fopenmp

280 Results Shown

FS-Mark
Timed Node.js Compilation
PostgreSQL:
  1000 - 50 - Read Write - Average Latency
  1000 - 50 - Read Write
  1000 - 500 - Read Only - Average Latency
  1000 - 500 - Read Only
OpenCV
PostgreSQL:
  1000 - 1 - Read Only - Average Latency
  1000 - 1 - Read Only
Numenta Anomaly Benchmark
Blender
TensorFlow
InfluxDB
Flexible IO Tester:
  Rand Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directory:
    IOPS
    MiB/s
TensorFlow
OpenCV
PostgreSQL:
  1000 - 500 - Read Write - Average Latency
  1000 - 500 - Read Write
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
Flexible IO Tester:
  Rand Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directory:
    IOPS
    MiB/s
  Seq Write - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directory:
    IOPS
    MiB/s
FS-Mark
SQLite
PostgreSQL:
  1 - 1 - Read Write - Average Latency
  1 - 1 - Read Write
OpenCV
Flexible IO Tester:
  Seq Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directory:
    IOPS
    MiB/s
Stockfish
OpenCV
InfluxDB
TensorFlow
Flexible IO Tester:
  Rand Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directory:
    IOPS
    MiB/s
InfluxDB
PostgreSQL:
  100 - 50 - Read Write - Average Latency
  100 - 50 - Read Write
Flexible IO Tester:
  Rand Write - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directory:
    IOPS
    MiB/s
  Rand Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directory:
    IOPS
    MiB/s
  Seq Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directory:
    IOPS
    MiB/s
  Seq Write - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Seq Write - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directory:
    IOPS
    MiB/s
OpenCV
SQLite
TensorFlow
FFmpeg:
  libx264 - Upload:
    FPS
    Seconds
Flexible IO Tester:
  Seq Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directory:
    IOPS
    MiB/s
TensorFlow
RAMspeed SMP
SQLite:
  4
  2
PostgreSQL:
  1000 - 50 - Read Only - Average Latency
  1000 - 50 - Read Only
  1000 - 1 - Read Write - Average Latency
  1000 - 1 - Read Write
TensorFlow
PostgreSQL:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
Timed Linux Kernel Compilation
FFmpeg:
  libx265 - Video On Demand:
    FPS
    Seconds
  libx265 - Platform:
    FPS
    Seconds
  libx264 - Video On Demand:
    FPS
    Seconds
  libx264 - Platform:
    FPS
    Seconds
  libx265 - Upload:
    FPS
    Seconds
Flexible IO Tester:
  Rand Read - POSIX AIO - No - Yes - 1MB - 1 - Default Test Directory:
    IOPS
    MiB/s
FS-Mark
Numpy Benchmark
PostgreSQL:
  100 - 1 - Read Write - Average Latency
  100 - 1 - Read Write
OpenCV
TensorFlow
OpenSSL:
  SHA256
  ChaCha20-Poly1305
  AES-256-GCM
  AES-128-GCM
  ChaCha20
  SHA512
R Benchmark
PostgreSQL:
  1 - 50 - Read Write - Average Latency
  1 - 50 - Read Write
Numenta Anomaly Benchmark
OpenCV
Threaded I/O Tester
TensorFlow:
  CPU - 256 - AlexNet
  CPU - 32 - ResNet-50
Flexible IO Tester:
  Seq Write - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directory:
    IOPS
    MiB/s
PostgreSQL:
  100 - 50 - Read Only - Average Latency
  100 - 50 - Read Only
  100 - 1 - Read Only - Average Latency
  100 - 1 - Read Only
Threaded I/O Tester:
  Read - 32MB - 8
  Write - 32MB - 8
RAMspeed SMP
Threaded I/O Tester
Numenta Anomaly Benchmark
RAMspeed SMP
PostgreSQL:
  1 - 500 - Read Write - Average Latency
  1 - 500 - Read Write
  1 - 1 - Read Only - Average Latency
  1 - 1 - Read Only
  1 - 500 - Read Only - Average Latency
  1 - 500 - Read Only
  1 - 50 - Read Only - Average Latency
  1 - 50 - Read Only
OpenCV
CacheBench:
  Read / Modify / Write
  Write
  Read
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
  nasnet
C-Ray
LevelDB
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
Flexible IO Tester:
  Seq Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Rand Read - POSIX AIO - No - Yes - 1MB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Rand Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directory:
    IOPS
    MiB/s
TensorFlow
Flexible IO Tester:
  Rand Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directory:
    IOPS
    MiB/s
  Rand Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Seq Read - POSIX AIO - No - Yes - 64KB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Seq Read - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Seq Read - POSIX AIO - No - Yes - 64KB - 1 - Default Test Directory:
    IOPS
    MiB/s
TensorFlow Lite
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
Flexible IO Tester:
  Rand Read - POSIX AIO - No - Yes - 4KB - 1 - Default Test Directory:
    IOPS
    MiB/s
Apache HTTP Server
nginx:
  500
  100
Apache HTTP Server:
  20
  100
nginx
Sysbench
TensorFlow
Flexible IO Tester:
  Seq Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directory:
    IOPS
    MiB/s
  Rand Write - POSIX AIO - No - Yes - 4KB - 8 - Default Test Directory:
    IOPS
    MiB/s
oneDNN
Node.js V8 Web Tooling Benchmark
FFmpeg:
  libx265 - Live:
    FPS
    Seconds
oneDNN
simdjson:
  PartialTweets
  DistinctUserID
  TopTweet
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
RAMspeed SMP:
  Add - Integer
  Triad - Integer
  Average - Integer
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
RAMspeed SMP:
  Triad - Floating Point
  Scale - Floating Point
  Copy - Integer
  Add - Floating Point
Sysbench
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
    FPS
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
simdjson
Zstd Compression:
  8, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  8 - Decompression Speed
  8 - Compression Speed
  3 - Decompression Speed
  3 - Compression Speed
  12 - Decompression Speed
  12 - Compression Speed
  3, Long Mode - Decompression Speed
  3, Long Mode - Compression Speed
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
FS-Mark
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
TensorFlow Lite:
  Inception V4
  Inception ResNet V2
  NASNet Mobile
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
TensorFlow Lite:
  Mobilenet Float
  SqueezeNet
OpenVINO:
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
OpenSSL:
  RSA4096:
    verify/s
    sign/s
FFmpeg:
  libx264 - Live:
    FPS
    Seconds
Numenta Anomaly Benchmark
simdjson
TensorFlow
Numenta Anomaly Benchmark
Timed ImageMagick Compilation
oneDNN
TensorFlow
Gzip Compression
Redis:
  LPUSH - 500
  LPUSH - 50
  SET - 50
  SET - 500
  SADD - 500
  SADD - 50
  GET - 500
TensorFlow
LevelDB
Crafty
PHPBench
Redis:
  LPOP - 50
  GET - 50
  LPOP - 500
TensorFlow
7-Zip Compression:
  Decompression Rating
  Compression Rating
Node.js Express HTTP Load Test
PyBench
LevelDB:
  Overwrite:
    Microseconds Per Op
    MB/s
  Seq Fill:
    Microseconds Per Op
    MB/s
  Hot Read:
    Microseconds Per Op
oneDNN
Stream
TensorFlow
LevelDB:
  Fill Sync:
    MB/s
    Microseconds Per Op
Numenta Anomaly Benchmark
oneDNN
LevelDB:
  Seek Rand
  Rand Fill
  Rand Fill
oneDNN:
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
Stream:
  Add
  Triad
  Scale