epyc last

AMD EPYC 7343 16-Core testing with a Supermicro H12SSL-i v1.02 (2.4 BIOS) and astdrmfb on AlmaLinux 9.1 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 2304307-NE-EPYCLAST283
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
April 30 2023
  7 Hours, 46 Minutes
b
April 30 2023
  2 Hours, 34 Minutes
c
April 30 2023
  2 Hours, 34 Minutes
d
April 30 2023
  2 Hours, 34 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 52 Minutes

Only show results where is faster than
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):


epyc lastOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7343 16-Core @ 3.20GHz (16 Cores / 32 Threads)Supermicro H12SSL-i v1.02 (2.4 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07astdrmfbDELL E207WFPAlmaLinux 9.15.14.0-162.12.1.el9_1.x86_64 (x86_64)GCC 11.3.1 20220421ext41680x1050ProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelCompilerFile-SystemScreen ResolutionEpyc Last BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - NONE / relatime,rw,stripe=32 / raid1 nvme1n1p3[0] nvme0n1p3[1] Block Size: 4096 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173 - Python 3.9.14- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%104%109%113%118%SQLiteInfluxDBQuantLibIntel TensorFlowSVT-AV1

epyc lastsqlite: 8sqlite: 4sqlite: 2sqlite: 32intel-tensorflow: inceptionv4_fp32_pretrained_model - 1intel-tensorflow: mobilenetv1_int8_pretrained_model - 256intel-tensorflow: mobilenetv1_int8_pretrained_model - 32svt-av1: Preset 4 - Bosphorus 1080pintel-tensorflow: mobilenetv1_int8_pretrained_model - 64intel-tensorflow: resnet50_int8_pretrained_model - 1intel-tensorflow: resnet50_int8_pretrained_model - 1svt-av1: Preset 12 - Bosphorus 1080pintel-tensorflow: inceptionv4_int8_pretrained_model - 64intel-tensorflow: inceptionv4_int8_pretrained_model - 16svt-av1: Preset 12 - Bosphorus 4Kintel-tensorflow: resnet50_fp32_pretrained_model - 16intel-tensorflow: resnet50_int8_pretrained_model - 32intel-tensorflow: inceptionv4_fp32_pretrained_model - 64intel-tensorflow: inceptionv4_int8_pretrained_model - 96intel-tensorflow: resnet50_fp32_pretrained_model - 32intel-tensorflow: resnet50_fp32_pretrained_model - 1intel-tensorflow: resnet50_fp32_pretrained_model - 1svt-av1: Preset 8 - Bosphorus 4Kintel-tensorflow: inceptionv4_fp32_pretrained_model - 1intel-tensorflow: resnet50_int8_pretrained_model - 16svt-av1: Preset 13 - Bosphorus 1080pinfluxdb: 4 - 10000 - 2,5000,1 - 10000intel-tensorflow: mobilenetv1_int8_pretrained_model - 16intel-tensorflow: inceptionv4_fp32_pretrained_model - 16intel-tensorflow: inceptionv4_int8_pretrained_model - 32intel-tensorflow: resnet50_fp32_pretrained_model - 960intel-tensorflow: inceptionv4_int8_pretrained_model - 512intel-tensorflow: mobilenetv1_int8_pretrained_model - 512intel-tensorflow: mobilenetv1_int8_pretrained_model - 96svt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 1080pintel-tensorflow: inceptionv4_fp32_pretrained_model - 32svt-av1: Preset 4 - Bosphorus 4Kintel-tensorflow: resnet50_int8_pretrained_model - 256intel-tensorflow: inceptionv4_fp32_pretrained_model - 96influxdb: 64 - 10000 - 2,5000,1 - 10000intel-tensorflow: resnet50_int8_pretrained_model - 512intel-tensorflow: mobilenetv1_fp32_pretrained_model - 16intel-tensorflow: mobilenetv1_int8_pretrained_model - 960quantlib: intel-tensorflow: inceptionv4_int8_pretrained_model - 1intel-tensorflow: resnet50_fp32_pretrained_model - 96intel-tensorflow: inceptionv4_fp32_pretrained_model - 960intel-tensorflow: mobilenetv1_fp32_pretrained_model - 96intel-tensorflow: resnet50_int8_pretrained_model - 64intel-tensorflow: mobilenetv1_fp32_pretrained_model - 32intel-tensorflow: inceptionv4_int8_pretrained_model - 960intel-tensorflow: inceptionv4_fp32_pretrained_model - 256intel-tensorflow: resnet50_int8_pretrained_model - 960intel-tensorflow: resnet50_fp32_pretrained_model - 512intel-tensorflow: mobilenetv1_fp32_pretrained_model - 1intel-tensorflow: inceptionv4_int8_pretrained_model - 256intel-tensorflow: mobilenetv1_fp32_pretrained_model - 64intel-tensorflow: inceptionv4_int8_pretrained_model - 1intel-tensorflow: resnet50_int8_pretrained_model - 96intel-tensorflow: inceptionv4_fp32_pretrained_model - 512intel-tensorflow: resnet50_fp32_pretrained_model - 64intel-tensorflow: mobilenetv1_fp32_pretrained_model - 512intel-tensorflow: mobilenetv1_fp32_pretrained_model - 960intel-tensorflow: mobilenetv1_fp32_pretrained_model - 256intel-tensorflow: resnet50_fp32_pretrained_model - 256intel-tensorflow: mobilenetv1_int8_pretrained_model - 1sqlite: 16sqlite: 1abcd5.0653.1782.15011.32132.232090.972056.189.0272112.33221.8554.508547.498118.48113.31174.519168.744356.31752.44118.25174.04079.28312.61352.58230.817346.017548.0071547894.42003.4953.20117.00168.721119.902170.092083.55160.50195.92553.103.766382.09351.831602099.9383.615932.192133.183202.114.436169.72651.76990.35365.095981.32120.7451.92391.680168.3711045.59119.18998.4369.04373.12651.76170.509976.58983.761001.61167.9681933.378.4763.8562.9382.04111.81133.162106.542110.199.0642120.77221.7694.509542.028118.93111.63175.683171.632361.36252.40119.097759734174.30379.77612.53551.98230.475347.926542.6251545780.82002.0953.47117.81169.729119.612179.092081.87160.66495.70752.913.782380.65251.721593776.4385.546929.582128.13206.114.415169.64951.78986.72364.043984.41120.9452.07392.07168.6411048.2119.18997.7369.16373.72351.87170.516974.84982.711000.28167.9981932.476.2093.9662.9042.10611.74332.062028.822037.869.1212063.78216.3694.622535.678117.61113.63172.696171.049357.71451.72119.82174.25579.98812.50252.52330.647348.365545.8641552035.6198952.99116.93170.093119.912161.982087.39160.13996.32953.113.791381.06451.901599391.9385.5933.762137.23200.714.426169.97151.59988.15365.003982.66120.7452.06392.383168.7881046.79119.33999.9369.01372.93351.77170.603976.22982.461001.43168.0551933.587.1983.7612.7122.03911.59831.862091.62033.579.282091.66217.5934.596539.588119.83113.36174.836169.333357.03551.97118.23172.26980.21812.46652.57230.723344.868547.43215607581984.3853.22117.89169.338120.562171.792071.18159.52195.64853.273.784380.01552.001600346.9384.26931.222132.293192.714.377169.3151.62988.72365.305981.61120.5752.04391.383168.3651046.4119.45999.9269.07372.92851.76170.261974.69984.361001.3168.161934.326.075OpenBenchmarking.org

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: 8acbd1.13962.27923.41884.55845.698SE +/- 0.038, N = 35.0653.9663.8563.7611. (CC) gcc options: -O2 -lz -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 4abcd0.71511.43022.14532.86043.5755SE +/- 0.030, N = 153.1782.9382.9042.7121. (CC) gcc options: -O2 -lz -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 2acbd0.48380.96761.45141.93522.419SE +/- 0.004, N = 32.1502.1062.0412.0391. (CC) gcc options: -O2 -lz -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 32bcda3691215SE +/- 0.05, N = 311.8111.7411.6011.321. (CC) gcc options: -O2 -lz -lm

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 1dcab816243240SE +/- 0.26, N = 331.8632.0632.2333.16

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 256cadb5001000150020002500SE +/- 14.60, N = 32028.822090.972091.602106.54

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 32dcab5001000150020002500SE +/- 19.33, N = 72033.572037.862056.182110.19

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 4 - Input: Bosphorus 1080pabcd3691215SE +/- 0.031, N = 39.0279.0649.1219.2801. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 64cdab5001000150020002500SE +/- 10.67, N = 32063.782091.662112.332120.77

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 1cdba50100150200250SE +/- 1.58, N = 3216.37217.59221.77221.86

OpenBenchmarking.orgms, Fewer Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 1cdba1.042.083.124.165.2SE +/- 0.032, N = 34.6224.5964.5094.508

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 12 - Input: Bosphorus 1080pcdba120240360480600SE +/- 0.64, N = 3535.68539.59542.03547.501. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 64cabd306090120150SE +/- 0.54, N = 3117.61118.48118.93119.83

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 16badc306090120150SE +/- 0.30, N = 3111.63113.31113.36113.63

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 12 - Input: Bosphorus 4Kcadb4080120160200SE +/- 0.56, N = 3172.70174.52174.84175.681. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 16adcb4080120160200SE +/- 0.83, N = 3168.74169.33171.05171.63

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 32adcb80160240320400SE +/- 0.47, N = 3356.32357.04357.71361.36

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 64cdba1224364860SE +/- 0.12, N = 351.7251.9752.4052.44

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 96dabc306090120150SE +/- 0.42, N = 3118.23118.25119.10119.82

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 32dacb4080120160200SE +/- 0.31, N = 3172.27174.04174.26174.30

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 1abcd20406080100SE +/- 0.09, N = 379.2879.7879.9980.22

OpenBenchmarking.orgms, Fewer Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 1abcd3691215SE +/- 0.01, N = 312.6112.5412.5012.47

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 8 - Input: Bosphorus 4Kbcda1224364860SE +/- 0.19, N = 351.9852.5252.5752.581. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 1adcb714212835SE +/- 0.10, N = 330.8230.7230.6530.48

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 16dabc80160240320400SE +/- 1.45, N = 3344.87346.02347.93348.37

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 13 - Input: Bosphorus 1080pbcda120240360480600SE +/- 0.34, N = 3542.63545.86547.43548.011. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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: 10000bacd300K600K900K1200K1500KSE +/- 5338.36, N = 31545780.81547894.41552035.61560758.0

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 16dcba400800120016002000SE +/- 14.27, N = 31984.381989.002002.092003.49

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 16cadb1224364860SE +/- 0.07, N = 352.9953.2053.2253.47

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 32cabd306090120150SE +/- 0.81, N = 3116.93117.00117.81117.89

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 960adbc4080120160200SE +/- 0.30, N = 3168.72169.34169.73170.09

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 512bacd306090120150SE +/- 0.14, N = 3119.61119.90119.91120.56

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 512cadb5001000150020002500SE +/- 2.76, N = 32161.982170.092171.792179.09

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 96dbac400800120016002000SE +/- 2.02, N = 32071.182081.872083.552087.39

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 13 - Input: Bosphorus 4Kdcab4080120160200SE +/- 0.85, N = 3159.52160.14160.50160.661. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 8 - Input: Bosphorus 1080pdbac20406080100SE +/- 0.42, N = 395.6595.7195.9396.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 32bacd1224364860SE +/- 0.09, N = 352.9153.1053.1153.27

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.5Encoder Mode: Preset 4 - Input: Bosphorus 4Kabdc0.8531.7062.5593.4124.265SE +/- 0.019, N = 33.7663.7823.7843.7911. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 256dbca80160240320400SE +/- 0.54, N = 3380.02380.65381.06382.09

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 96bacd1224364860SE +/- 0.07, N = 351.7251.8351.9052.00

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: 10000bcda300K600K900K1200K1500KSE +/- 3918.66, N = 31593776.41599391.91600346.91602099.9

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 512adcb80160240320400SE +/- 0.21, N = 3383.62384.26385.50385.55

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 16bdac2004006008001000SE +/- 0.39, N = 3929.58931.22932.19933.76

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 960bdac5001000150020002500SE +/- 2.58, N = 32128.102132.292133.182137.20

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.30dcab7001400210028003500SE +/- 1.35, N = 33192.73200.73202.13206.11. (CXX) g++ options: -O3 -march=native -fPIE -pie

Intel TensorFlow

Intel optimized version of TensorFlow with benchmarks of Intel AI models and configurable batch sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 1acbd48121620SE +/- 0.03, N = 314.4414.4314.4214.38

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 96dbac4080120160200SE +/- 0.11, N = 3169.31169.65169.73169.97

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 960cdab1224364860SE +/- 0.11, N = 351.5951.6251.7651.78

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 96bcda2004006008001000SE +/- 1.26, N = 3986.72988.15988.72990.35

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 64bcad80160240320400SE +/- 0.43, N = 3364.04365.00365.10365.31

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 32adcb2004006008001000SE +/- 1.14, N = 3981.32981.61982.66984.41

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 960dacb306090120150SE +/- 0.16, N = 3120.57120.74120.74120.94

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 256adcb1224364860SE +/- 0.02, N = 351.9252.0452.0652.07

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 960dabc90180270360450SE +/- 0.57, N = 3391.38391.68392.07392.38

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 512dabc4080120160200SE +/- 0.21, N = 3168.37168.37168.64168.79

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 1adcb2004006008001000SE +/- 0.98, N = 31045.591046.401046.791048.20

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 256abcd306090120150SE +/- 0.27, N = 3119.18119.18119.33119.45

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 64badc2004006008001000SE +/- 0.55, N = 3997.73998.43999.92999.93

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_int8_pretrained_model - Batch Size: 1cadb1530456075SE +/- 0.07, N = 369.0169.0469.0769.16

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_int8_pretrained_model - Batch Size: 96dcab80160240320400SE +/- 0.27, N = 3372.93372.93373.13373.72

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: inceptionv4_fp32_pretrained_model - Batch Size: 512adcb1224364860SE +/- 0.05, N = 351.7651.7651.7751.87

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 64dabc4080120160200SE +/- 0.12, N = 3170.26170.51170.52170.60

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 512dbca2004006008001000SE +/- 0.75, N = 3974.69974.84976.22976.58

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 960cbad2004006008001000SE +/- 0.13, N = 3982.46982.71983.76984.36

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_fp32_pretrained_model - Batch Size: 256bdca2004006008001000SE +/- 0.11, N = 31000.281001.301001.431001.61

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: resnet50_fp32_pretrained_model - Batch Size: 256abcd4080120160200SE +/- 0.12, N = 3167.97168.00168.06168.16

OpenBenchmarking.orgimages/sec, More Is BetterIntel TensorFlow 2.12Model: mobilenetv1_int8_pretrained_model - Batch Size: 1bacd400800120016002000SE +/- 0.61, N = 31932.471933.371933.581934.32

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: 16acbd246810SE +/- 0.163, N = 138.4767.1986.2096.0751. (CC) gcc options: -O2 -lz -lm

Threads / Copies: 1

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

68 Results Shown

SQLite:
  8
  4
  2
  32
Intel TensorFlow:
  inceptionv4_fp32_pretrained_model - 1
  mobilenetv1_int8_pretrained_model - 256
  mobilenetv1_int8_pretrained_model - 32
SVT-AV1
Intel TensorFlow:
  mobilenetv1_int8_pretrained_model - 64
  resnet50_int8_pretrained_model - 1
  resnet50_int8_pretrained_model - 1
SVT-AV1
Intel TensorFlow:
  inceptionv4_int8_pretrained_model - 64
  inceptionv4_int8_pretrained_model - 16
SVT-AV1
Intel TensorFlow:
  resnet50_fp32_pretrained_model - 16
  resnet50_int8_pretrained_model - 32
  inceptionv4_fp32_pretrained_model - 64
  inceptionv4_int8_pretrained_model - 96
  resnet50_fp32_pretrained_model - 32
  resnet50_fp32_pretrained_model - 1
  resnet50_fp32_pretrained_model - 1
SVT-AV1
Intel TensorFlow:
  inceptionv4_fp32_pretrained_model - 1
  resnet50_int8_pretrained_model - 16
SVT-AV1
InfluxDB
Intel TensorFlow:
  mobilenetv1_int8_pretrained_model - 16
  inceptionv4_fp32_pretrained_model - 16
  inceptionv4_int8_pretrained_model - 32
  resnet50_fp32_pretrained_model - 960
  inceptionv4_int8_pretrained_model - 512
  mobilenetv1_int8_pretrained_model - 512
  mobilenetv1_int8_pretrained_model - 96
SVT-AV1:
  Preset 13 - Bosphorus 4K
  Preset 8 - Bosphorus 1080p
Intel TensorFlow
SVT-AV1
Intel TensorFlow:
  resnet50_int8_pretrained_model - 256
  inceptionv4_fp32_pretrained_model - 96
InfluxDB
Intel TensorFlow:
  resnet50_int8_pretrained_model - 512
  mobilenetv1_fp32_pretrained_model - 16
  mobilenetv1_int8_pretrained_model - 960
QuantLib
Intel TensorFlow:
  inceptionv4_int8_pretrained_model - 1
  resnet50_fp32_pretrained_model - 96
  inceptionv4_fp32_pretrained_model - 960
  mobilenetv1_fp32_pretrained_model - 96
  resnet50_int8_pretrained_model - 64
  mobilenetv1_fp32_pretrained_model - 32
  inceptionv4_int8_pretrained_model - 960
  inceptionv4_fp32_pretrained_model - 256
  resnet50_int8_pretrained_model - 960
  resnet50_fp32_pretrained_model - 512
  mobilenetv1_fp32_pretrained_model - 1
  inceptionv4_int8_pretrained_model - 256
  mobilenetv1_fp32_pretrained_model - 64
  inceptionv4_int8_pretrained_model - 1
  resnet50_int8_pretrained_model - 96
  inceptionv4_fp32_pretrained_model - 512
  resnet50_fp32_pretrained_model - 64
  mobilenetv1_fp32_pretrained_model - 512
  mobilenetv1_fp32_pretrained_model - 960
  mobilenetv1_fp32_pretrained_model - 256
  resnet50_fp32_pretrained_model - 256
  mobilenetv1_int8_pretrained_model - 1
SQLite