core-i5-12500

Intel Core i5-12500 testing with a ASUS PRIME Z690M-HZ (9023 BIOS) and ASUS Intel Alder Lake-S GT1 [UHD 770] on Debian 12 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2407248-NE-COREI512555.

core-i5-12500ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemIntel Core i5-12500Intel Core i5-12500 @ 5.90GHz (6 Cores / 12 Threads)ASUS PRIME Z690M-HZ (9023 BIOS)Intel Alder Lake-S PCH2 x 32 GB DDR4-3200MT/s Samsung M378A4G43AB2-CWE2 x 512GB SAMSUNG MZVL2512HCJQ-00B00ASUS Intel Alder Lake-S GT1 [UHD 770] (1450MHz)IntelDebian 126.1.0-21-amd64 (x86_64)GCC 12.2.0ext4OpenBenchmarking.org- 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 - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x32 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Vulnerable: No microcode + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected

core-i5-12500cachebench: Readcachebench: Writecachebench: Read / Modify / Writecrafty: Elapsed Timex264: Bosphorus 4Kx264: Bosphorus 1080px265: Bosphorus 4Kx265: Bosphorus 1080pstockfish: Total Timestockfish: Chess Benchmarkbuild-linux-kernel: defconfigbuild-mplayer: Time To Compilec-ray: Total Time - 4K, 16 Rays Per Pixelcompress-gzip: Linux Source Tree Archiving To .tar.gzencode-mp3: WAV To MP3m-queens: Time To Solvesystem-decompress-gzip: namd: ATPase with 327,506 Atomsnamd: STMV with 1,066,628 Atomsquicksilver: CTS2quicksilver: CORAL2 P1quicksilver: CORAL2 P2minibude: OpenMP - BM1minibude: OpenMP - BM1minibude: OpenMP - BM2minibude: OpenMP - BM2fftw: Stock - 1D FFT Size 32fftw: Stock - 2D FFT Size 32fftw: Stock - 1D FFT Size 4096fftw: Stock - 2D FFT Size 4096fftw: Float + SSE - 1D FFT Size 32fftw: Float + SSE - 2D FFT Size 32fftw: Float + SSE - 1D FFT Size 4096fftw: Float + SSE - 2D FFT Size 4096mafft: Multiple Sequence Alignment - LSU RNAeasywave: e2Asean Grid + BengkuluSept2007 Source - 240easywave: e2Asean Grid + BengkuluSept2007 Source - 1200easywave: e2Asean Grid + BengkuluSept2007 Source - 2400mt-dgemm: Sustained Floating-Point Ratehimeno: Poisson Pressure Solveronednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUdeepspeech: CPUtensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2mnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3tnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUIntel Core i5-1250017523.88046088020.585425101918.3513381138925022.90104.5215.3965.531878776910955091134.47345.68872.82630.7445.872107.4472.6320.472330.145999110000963066715476667249.0379.962248.6299.9451636916491130779137.9273857387875226315688.24710.188219.426551.0532.3145658475.4418953.5860311.904711.27588.300827.534004229.082170.4051.479233334.9346719.58699.212329.054661.7443588.48.7811.1012.39021.4353.7722.2002.77724.5522041.587200.51545.410155.261OpenBenchmarking.org

CacheBench

Test: Read

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadIntel Core i5-125004K8K12K16K20KSE +/- 0.06, N = 317523.88MIN: 17523.21 / MAX: 17524.671. (CC) gcc options: -O3 -lrt

CacheBench

Test: Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteIntel Core i5-1250020K40K60K80K100KSE +/- 22.01, N = 388020.59MIN: 51205.56 / MAX: 120821.351. (CC) gcc options: -O3 -lrt

CacheBench

Test: Read / Modify / Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteIntel Core i5-1250020K40K60K80K100KSE +/- 1556.30, N = 3101918.35MIN: 80191.55 / MAX: 122700.51. (CC) gcc options: -O3 -lrt

Crafty

Elapsed Time

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeIntel Core i5-125002M4M6M8M10MSE +/- 15171.52, N = 3113892501. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

x264

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KIntel Core i5-12500510152025SE +/- 0.14, N = 322.901. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto

x264

Video Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 1080pIntel Core i5-1250020406080100SE +/- 0.10, N = 3104.521. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto

x265

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KIntel Core i5-1250048121620SE +/- 0.16, N = 315.391. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

x265

Video Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pIntel Core i5-125001530456075SE +/- 0.22, N = 365.531. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeIntel Core i5-125004M8M12M16M20MSE +/- 269522.89, N = 3187877691. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkIntel Core i5-125002M4M6M8M10MSE +/- 91350.69, N = 3109550911. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigIntel Core i5-12500306090120150SE +/- 0.77, N = 3134.47

Timed MPlayer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileIntel Core i5-125001020304050SE +/- 0.13, N = 345.69

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelIntel Core i5-125001632486480SE +/- 0.01, N = 372.831. (CC) gcc options: -lm -lpthread -O3

Gzip Compression

Linux Source Tree Archiving To .tar.gz

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gzIntel Core i5-12500714212835SE +/- 0.01, N = 330.74

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Intel Core i5-125001.32122.64243.96365.28486.606SE +/- 0.000, N = 35.8721. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveIntel Core i5-1250020406080100SE +/- 0.01, N = 3107.451. (CXX) g++ options: -fopenmp -O2 -march=native

System GZIP Decompression

OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP DecompressionIntel Core i5-125000.59221.18441.77662.36882.961SE +/- 0.002, N = 32.632

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsIntel Core i5-125000.10630.21260.31890.42520.5315SE +/- 0.00149, N = 30.47233

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsIntel Core i5-125000.03280.06560.09840.13120.164SE +/- 0.00065, N = 30.14599

Quicksilver

Input: CTS2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2Intel Core i5-125002M4M6M8M10MSE +/- 6658.33, N = 391100001. (CXX) g++ options: -fopenmp -O3 -march=native

Quicksilver

Input: CORAL2 P1

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1Intel Core i5-125002M4M6M8M10MSE +/- 6565.91, N = 396306671. (CXX) g++ options: -fopenmp -O3 -march=native

Quicksilver

Input: CORAL2 P2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2Intel Core i5-125003M6M9M12M15MSE +/- 49103.07, N = 3154766671. (CXX) g++ options: -fopenmp -O3 -march=native

miniBUDE

Implementation: OpenMP - Input Deck: BM1

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Intel Core i5-1250050100150200250SE +/- 0.24, N = 3249.041. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM1

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Intel Core i5-125003691215SE +/- 0.010, N = 39.9621. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Intel Core i5-1250050100150200250SE +/- 0.01, N = 3248.631. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Intel Core i5-125003691215SE +/- 0.000, N = 39.9451. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

FFTW

Build: Stock - Size: 1D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 32Intel Core i5-125004K8K12K16K20KSE +/- 0.88, N = 3163691. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 2D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 32Intel Core i5-125004K8K12K16K20KSE +/- 27.00, N = 3164911. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096Intel Core i5-125003K6K9K12K15KSE +/- 25.46, N = 3130771. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096Intel Core i5-125002K4K6K8K10KSE +/- 8.83, N = 39137.91. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Float + SSE - Size: 1D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 32Intel Core i5-125006K12K18K24K30KSE +/- 34.11, N = 3273851. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Float + SSE - Size: 2D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 32Intel Core i5-1250016K32K48K64K80KSE +/- 57.76, N = 3738781. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Float + SSE - Size: 1D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 4096Intel Core i5-1250016K32K48K64K80KSE +/- 848.34, N = 3752261. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Float + SSE - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096Intel Core i5-125007K14K21K28K35KSE +/- 129.62, N = 3315681. (CC) gcc options: -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAIntel Core i5-12500246810SE +/- 0.024, N = 38.2471. (CC) gcc options: -std=c99 -O3 -lm -lpthread

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240Intel Core i5-125003691215SE +/- 0.00, N = 310.191. (CXX) g++ options: -O3 -fopenmp

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200Intel Core i5-1250050100150200250SE +/- 0.10, N = 3219.431. (CXX) g++ options: -O3 -fopenmp

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400Intel Core i5-12500120240360480600SE +/- 0.02, N = 3551.051. (CXX) g++ options: -O3 -fopenmp

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateIntel Core i5-125000.52081.04161.56242.08322.604SE +/- 0.074772, N = 32.3145651. (CC) gcc options: -O3 -march=native -fopenmp

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverIntel Core i5-125002K4K6K8K10KSE +/- 2.76, N = 38475.441. (CC) gcc options: -O3 -mavx2

oneDNN

Harness: IP Shapes 1D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUIntel Core i5-125000.80691.61382.42073.22764.0345SE +/- 0.00800, N = 33.58603MIN: 3.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 3D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUIntel Core i5-125003691215SE +/- 0.01, N = 311.90MIN: 11.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUIntel Core i5-125003691215SE +/- 0.00, N = 311.28MIN: 11.181. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUIntel Core i5-12500246810SE +/- 0.28052, N = 38.30082MIN: 5.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUIntel Core i5-12500246810SE +/- 0.10860, N = 37.53400MIN: 7.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUIntel Core i5-125009001800270036004500SE +/- 2.09, N = 34229.08MIN: 4213.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUIntel Core i5-125005001000150020002500SE +/- 0.80, N = 32170.40MIN: 2159.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUIntel Core i5-125001224364860SE +/- 0.03, N = 351.48

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetIntel Core i5-125007001400210028003500SE +/- 17.04, N = 33334.93

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4Intel Core i5-1250010K20K30K40K50KSE +/- 120.66, N = 346719.5

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileIntel Core i5-125002K4K6K8K10KSE +/- 16.76, N = 38699.21

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatIntel Core i5-125005001000150020002500SE +/- 5.03, N = 32329.05

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantIntel Core i5-1250010002000300040005000SE +/- 14.73, N = 34661.74

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Intel Core i5-125009K18K27K36K45KSE +/- 115.94, N = 343588.4

Mobile Neural Network

Model: nasnet

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetIntel Core i5-12500246810SE +/- 0.053, N = 38.781MIN: 8.6 / MAX: 12.781. (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

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3Intel Core i5-125000.24770.49540.74310.99081.2385SE +/- 0.006, N = 31.101MIN: 1.08 / MAX: 4.961. (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

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1Intel Core i5-125000.53781.07561.61342.15122.689SE +/- 0.003, N = 32.390MIN: 2.33 / MAX: 6.471. (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

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50Intel Core i5-12500510152025SE +/- 0.05, N = 321.44MIN: 19.33 / MAX: 29.491. (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

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0Intel Core i5-125000.84871.69742.54613.39484.2435SE +/- 0.010, N = 33.772MIN: 3.67 / MAX: 7.771. (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

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224Intel Core i5-125000.4950.991.4851.982.475SE +/- 0.011, N = 32.200MIN: 2.12 / MAX: 6.21. (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

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0Intel Core i5-125000.62481.24961.87442.49923.124SE +/- 0.003, N = 32.777MIN: 2.74 / MAX: 6.681. (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

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3Intel Core i5-12500612182430SE +/- 0.03, N = 324.55MIN: 24.31 / MAX: 34.381. (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

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetIntel Core i5-12500400800120016002000SE +/- 6.83, N = 32041.59MIN: 2003.66 / MAX: 2120.311. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Intel Core i5-125004080120160200SE +/- 0.29, N = 3200.52MIN: 198.67 / MAX: 204.681. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Intel Core i5-125001020304050SE +/- 0.01, N = 345.41MIN: 45.04 / MAX: 45.861. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Intel Core i5-12500306090120150SE +/- 0.11, N = 3155.26MIN: 154.47 / MAX: 155.91. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.5