ddddx

AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 23.10 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 2403218-NE-DDDDX513530
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

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 8 Tests
Creator Workloads 12 Tests
Encoding 3 Tests
HPC - High Performance Computing 3 Tests
Imaging 2 Tests
Machine Learning 3 Tests
Multi-Core 11 Tests
Intel oneAPI 4 Tests
Python Tests 2 Tests
Raytracing 2 Tests
Renderers 3 Tests
Server CPU Tests 4 Tests
Video Encoding 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 20
  2 Hours, 33 Minutes
b
March 20
  2 Hours, 33 Minutes
c
March 21
  7 Hours, 54 Minutes
d
March 21
  2 Hours, 37 Minutes
Invert Hiding All Results Option
  3 Hours, 54 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):


ddddxOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads)ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS)AMD Starship/Matisse8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C162048GB SOLIDIGM SSDPFKKW020X7ASUS NVIDIA NV106 2GBAMD Starship/MatisseVA24312 x Intel X550 + Intel Wi-Fi 6 AX200Ubuntu 23.106.5.0-15-generic (x86_64)GNOME Shell 45.0X Server + Waylandnouveau4.3 Mesa 23.2.1-1ubuntu3GCC 13.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionDdddx BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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-build-config=bootstrap-lto-lean --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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa008205- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + 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

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 80abcd1020304050SE +/- 0.29, N = 344.7543.2539.9042.181. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90abcd918273645SE +/- 0.27, N = 1539.4037.4438.5138.271. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 80abcd1122334455SE +/- 0.32, N = 346.5842.6642.3543.501. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90abcd1020304050SE +/- 0.39, N = 1542.5039.8940.7639.601. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100abcd714212835SE +/- 0.01, N = 327.6527.5727.4927.341. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100abcd612182430SE +/- 0.03, N = 327.5327.3227.3227.321. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

JPEG-XL Decoding libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: 1abcd1428425670SE +/- 0.12, N = 364.0363.3063.0462.82

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: Allabcd100200300400500SE +/- 1.28, N = 3483.42482.58470.16439.61

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PDSCH Processor Benchmark, Throughput Totalabcd3K6K9K12K15KSE +/- 27.21, N = 311710.312063.411723.511654.91. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PUSCH Processor Benchmark, Throughput Totalabcd400800120016002000SE +/- 1.62, N = 31888.21889.21886.91857.0MIN: 1136.3MIN: 1137.6MIN: 1135 / MAX: 1889.2MIN: 1145.41. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PDSCH Processor Benchmark, Throughput Threadabcd130260390520650SE +/- 1.71, N = 3603.7600.2605.5607.81. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PUSCH Processor Benchmark, Throughput Threadabcd4080120160200SE +/- 0.70, N = 3177.6178.7178.6177.9MIN: 113.3MIN: 112.2MIN: 112.6 / MAX: 179.4MIN: 110.91. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kabcd246810SE +/- 0.005, N = 36.6476.7876.7116.6601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kabcd1428425670SE +/- 0.26, N = 362.9563.8962.5062.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kabcd306090120150SE +/- 0.99, N = 3154.17150.81150.13151.641. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kabcd306090120150SE +/- 1.34, N = 3151.96145.97150.52152.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pabcd510152025SE +/- 0.04, N = 319.2118.9219.1719.321. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pabcd306090120150SE +/- 0.72, N = 3131.72131.93133.27133.781. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pabcd110220330440550SE +/- 6.37, N = 3489.43499.14487.66488.521. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pabcd130260390520650SE +/- 4.87, N = 3587.48602.97606.36587.971. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: Fastabcd246810SE +/- 0.031, N = 37.0607.0757.0667.0621. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: Fasterabcd48121620SE +/- 0.03, N = 314.5714.8214.7814.861. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: Fastabcd510152025SE +/- 0.03, N = 319.6219.4919.4619.531. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: Fasterabcd918273645SE +/- 0.15, N = 341.2840.4640.9241.001. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeabcd3691215SE +/- 0.01, N = 310.2810.2510.2810.30

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeabcd3691215SE +/- 0.01, N = 310.1410.1410.1510.18

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeabcd306090120150SE +/- 0.22, N = 3156.40155.37155.83155.05

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeabcd1.10312.20623.30934.41245.5155SE +/- 0.01074, N = 34.902574.880534.886084.89928

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeabcd1.03472.06943.10414.13885.1735SE +/- 0.00963, N = 34.598824.577064.592664.58081

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeabcd246810SE +/- 0.00473, N = 37.466147.448377.438217.45220

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess Benchmarkabcd13M26M39M52M65MSE +/- 1129127.95, N = 15526075286100827055237573530824521. (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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigabcd1224364860SE +/- 0.59, N = 354.1354.2152.8154.16

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigabcd130260390520650SE +/- 0.92, N = 3597.03597.90596.51597.83

Parallel BZIP2 Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionabcd0.74581.49162.23742.98323.729SE +/- 0.043942, N = 123.2303053.3147493.2850823.2219931. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12abcd246810SE +/- 0.056, N = 36.2446.0816.1136.1231. (CXX) g++ options: -O3

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13abcd20406080100SE +/- 0.05, N = 377.1576.9277.2177.061. (CXX) g++ options: -O3

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUabcd0.29870.59740.89611.19481.4935SE +/- 0.00673, N = 31.314741.311011.327431.31333MIN: 1.27MIN: 1.27MIN: 1.26MIN: 1.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUabcd0.79621.59242.38863.18483.981SE +/- 0.00386, N = 33.525693.525843.533233.53851MIN: 3.48MIN: 3.48MIN: 3.47MIN: 3.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUabcd0.61611.23221.84832.46443.0805SE +/- 0.00421, N = 32.738042.711352.731922.73352MIN: 2.66MIN: 2.65MIN: 2.66MIN: 2.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUabcd1.23992.47983.71974.95966.1995SE +/- 0.03672, N = 35.510825.339295.373675.03641MIN: 3.9MIN: 3.86MIN: 3.84MIN: 3.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUabcd0.53211.06421.59632.12842.6605SE +/- 0.00819, N = 32.365112.346022.361382.34346MIN: 2.28MIN: 2.28MIN: 2.25MIN: 2.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUabcd30060090012001500SE +/- 0.77, N = 31254.681255.671256.431254.43MIN: 1250.31MIN: 1250.99MIN: 1249.44MIN: 1249.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUabcd140280420560700SE +/- 0.39, N = 3638.13636.77637.17642.19MIN: 634.67MIN: 632.58MIN: 632.47MIN: 633.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd10002000300040005000SE +/- 4.41, N = 34528452145354528

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd10002000300040005000SE +/- 7.22, N = 34616460946154618

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd11002200330044005500SE +/- 4.04, N = 35330534253415331

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100KSE +/- 155.86, N = 378061769957751177073

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd30K60K90K120K150KSE +/- 64.70, N = 3150375150040150381150694

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100KSE +/- 110.73, N = 378788783047891978354

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd30K60K90K120K150KSE +/- 88.33, N = 3152653153552152510151620

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100KSE +/- 228.07, N = 390362901319008390380

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd40K80K120K160K200KSE +/- 268.88, N = 3177445175496175767175129

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd2004006008001000SE +/- 1.00, N = 31138113811381134

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd2004006008001000SE +/- 0.67, N = 31158115011521153

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd30060090012001500SE +/- 4.41, N = 31336133813331330

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd4K8K12K16K20KSE +/- 39.50, N = 318203181811822918177

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd9K18K27K36K45KSE +/- 58.89, N = 341167411254118941111

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd4K8K12K16K20KSE +/- 16.33, N = 318543184711857918488

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd9K18K27K36K45KSE +/- 250.02, N = 341839415984205041959

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd5K10K15K20K25KSE +/- 35.14, N = 321449213982140921385

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd10K20K30K40K50KSE +/- 129.36, N = 347495478274768647597

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd612182430SE +/- 0.04, N = 326.6926.6026.6226.69

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd100200300400500SE +/- 0.38, N = 3448.71447.65449.12448.93

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.02, N = 318.3718.5118.4018.40

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd1224364860SE +/- 0.05, N = 354.4254.0154.3354.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd150300450600750SE +/- 0.35, N = 3684.57685.45684.02685.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd48121620SE +/- 0.01, N = 317.5117.4917.5217.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 0.92, N = 3194.29191.76192.98194.38

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd1.17262.34523.51784.69045.863SE +/- 0.0247, N = 35.14355.21155.17875.1408

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd70140210280350SE +/- 0.00, N = 3307.00307.02306.92306.94

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd918273645SE +/- 0.00, N = 339.0539.0539.0739.06

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd306090120150SE +/- 0.37, N = 3156.21155.34155.68156.04

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd246810SE +/- 0.0148, N = 36.39276.42866.41556.4001

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd400800120016002000SE +/- 6.40, N = 31994.392032.961998.612014.58

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd246810SE +/- 0.0186, N = 36.00305.88985.98885.9417

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd2004006008001000SE +/- 1.90, N = 3798.47800.05799.42794.39

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.28260.56520.84781.13041.413SE +/- 0.0030, N = 31.24911.24681.24781.2559

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabcd0.42240.84481.26721.68962.112SE +/- 0.0031, N = 31.87721.86771.87051.8701

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabcd13002600390052006500SE +/- 9.69, N = 35873.275904.285896.595897.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabcd246810SE +/- 0.0038, N = 36.04486.03936.04256.0373

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 0.11, N = 3165.40165.55165.47165.61

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd70140210280350SE +/- 0.03, N = 3306.97307.09306.95306.90

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd918273645SE +/- 0.00, N = 339.0539.0339.0639.07

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd306090120150SE +/- 0.15, N = 3156.43155.31155.79155.90

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd246810SE +/- 0.0061, N = 36.38466.42936.41036.4059

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.31, N = 3150.83151.98151.26150.73

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.16, N = 379.4578.8279.2579.51

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.05, N = 399.3399.2298.8099.05

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.01, N = 310.0610.0710.1210.09

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd50100150200250SE +/- 0.20, N = 3224.16224.20223.00223.55

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd1224364860SE +/- 0.05, N = 353.4853.4753.7653.63

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd306090120150SE +/- 0.07, N = 3112.33111.84112.00111.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.0057, N = 38.89218.93178.91898.9625

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd714212835SE +/- 0.09, N = 330.4730.4930.3930.49

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd90180270360450SE +/- 0.32, N = 3393.66393.08393.82393.39

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.01, N = 321.7021.7521.6921.72

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd1020304050SE +/- 0.03, N = 346.0645.9646.0846.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd70140210280350SE +/- 0.53, N = 3334.39337.45334.75334.72

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd816243240SE +/- 0.06, N = 335.8535.5435.8135.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.14, N = 375.8876.1276.0675.70

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.02, N = 313.1713.1313.1413.20

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd612182430SE +/- 0.03, N = 326.7426.8626.7026.81

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd100200300400500SE +/- 0.66, N = 3446.84446.24447.58447.17

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.01, N = 318.4918.5218.4918.48

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd1224364860SE +/- 0.02, N = 354.0753.9754.0854.10

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Lionabcd12002400360048006000SE +/- 15.72, N = 353285365536353471. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church Facadeabcd15003000450060007500SE +/- 9.91, N = 370237034709270961. (CXX) g++ options: -O3

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabcd246810SE +/- 0.01, N = 37.607.687.597.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabcd30060090012001500SE +/- 0.80, N = 31558.811547.311563.151553.54MIN: 1416.22 / MAX: 1644.19MIN: 1403.59 / MAX: 1636.72MIN: 1369.79 / MAX: 1663.37MIN: 1365.71 / MAX: 1635.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabcd1632486480SE +/- 0.04, N = 370.0169.9569.8369.611. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabcd4080120160200SE +/- 0.11, N = 3171.22171.43171.67172.18MIN: 130.32 / MAX: 233.99MIN: 140.26 / MAX: 224.54MIN: 132.19 / MAX: 231.16MIN: 138.53 / MAX: 224.81. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabcd1632486480SE +/- 0.06, N = 369.7370.0169.9969.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabcd4080120160200SE +/- 0.12, N = 3171.92171.16171.29171.54MIN: 129.51 / MAX: 227.57MIN: 129.54 / MAX: 225.82MIN: 134.25 / MAX: 225.4MIN: 135.7 / MAX: 226.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabcd130260390520650SE +/- 0.39, N = 3600.94598.03592.96603.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabcd510152025SE +/- 0.01, N = 319.9420.0420.2119.84MIN: 8.87 / MAX: 42.42MIN: 12.81 / MAX: 37.51MIN: 9.28 / MAX: 49.09MIN: 11.38 / MAX: 34.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabcd48121620SE +/- 0.01, N = 316.6616.7316.6616.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabcd150300450600750SE +/- 0.26, N = 3715.22713.72716.16713.64MIN: 664.62 / MAX: 729.04MIN: 658.61 / MAX: 738.08MIN: 661.6 / MAX: 732.11MIN: 667.56 / MAX: 731.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabcd5001000150020002500SE +/- 4.26, N = 32192.092197.502197.982198.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabcd1.22852.4573.68554.9146.1425SE +/- 0.01, N = 35.465.455.455.45MIN: 2.82 / MAX: 21.64MIN: 2.89 / MAX: 21.85MIN: 2.8 / MAX: 22.36MIN: 2.8 / MAX: 28.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabcd4080120160200SE +/- 0.04, N = 3170.10170.68169.65169.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabcd1632486480SE +/- 0.02, N = 370.4870.2370.6670.76MIN: 43.7 / MAX: 128.66MIN: 43.23 / MAX: 122.75MIN: 24.84 / MAX: 127.05MIN: 41.53 / MAX: 122.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabcd2004006008001000SE +/- 1.89, N = 31104.031106.441107.641103.601. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabcd3691215SE +/- 0.02, N = 310.8610.8310.8210.86MIN: 7.32 / MAX: 25.15MIN: 6.67 / MAX: 24.71MIN: 5.79 / MAX: 27.55MIN: 6.39 / MAX: 25.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabcd160320480640800SE +/- 0.61, N = 3718.20719.93715.28716.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabcd48121620SE +/- 0.01, N = 316.6916.6516.7616.72MIN: 13.14 / MAX: 33.56MIN: 10 / MAX: 33.75MIN: 8.74 / MAX: 34.17MIN: 9.04 / MAX: 25.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabcd7001400210028003500SE +/- 3.42, N = 33224.643241.353228.193230.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabcd0.83481.66962.50443.33924.174SE +/- 0.01, N = 33.713.693.713.71MIN: 2.14 / MAX: 26.73MIN: 2.28 / MAX: 15.95MIN: 2.23 / MAX: 18MIN: 2.38 / MAX: 15.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd90180270360450SE +/- 0.36, N = 3428.43428.18427.02428.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd714212835SE +/- 0.02, N = 327.9928.0028.0827.98MIN: 18.95 / MAX: 38.76MIN: 18.81 / MAX: 38.86MIN: 14.29 / MAX: 41.57MIN: 14.99 / MAX: 46.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabcd20406080100SE +/- 0.03, N = 388.1388.3388.0588.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabcd306090120150SE +/- 0.06, N = 3136.00135.70136.15135.96MIN: 118.61 / MAX: 153.61MIN: 109.99 / MAX: 155.71MIN: 73.11 / MAX: 161.85MIN: 110.6 / MAX: 155.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd400800120016002000SE +/- 0.87, N = 31652.051654.721647.131652.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd48121620SE +/- 0.01, N = 314.5214.4914.5614.51MIN: 8.14 / MAX: 28.07MIN: 8.36 / MAX: 28.02MIN: 8.28 / MAX: 27.62MIN: 8.58 / MAX: 29.81. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd2004006008001000SE +/- 3.73, N = 3895.25889.36894.57894.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd3691215SE +/- 0.05, N = 313.3813.4713.3913.40MIN: 7.23 / MAX: 35.43MIN: 7.33 / MAX: 31.02MIN: 7.1 / MAX: 31.9MIN: 8.15 / MAX: 34.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd2004006008001000SE +/- 3.03, N = 31033.671046.301041.671043.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd3691215SE +/- 0.03, N = 311.5411.4111.4611.44MIN: 6.61 / MAX: 30.79MIN: 7.86 / MAX: 31.96MIN: 6.19 / MAX: 32.08MIN: 9.06 / MAX: 31.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabcd80160240320400SE +/- 0.65, N = 3377.84380.22378.34377.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabcd1428425670SE +/- 0.11, N = 363.4663.0863.4063.54MIN: 45.07 / MAX: 85.2MIN: 42.84 / MAX: 83.6MIN: 37.56 / MAX: 90.19MIN: 41.89 / MAX: 89.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabcd30060090012001500SE +/- 0.87, N = 31198.641201.221202.091202.221. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabcd3691215SE +/- 0.01, N = 310.009.989.979.97MIN: 6.87 / MAX: 16.1MIN: 5.6 / MAX: 24.1MIN: 5.91 / MAX: 41.34MIN: 5.63 / MAX: 25.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd5K10K15K20K25KSE +/- 23.00, N = 324478.3124434.5124329.2124496.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd0.22050.4410.66150.8821.1025SE +/- 0.00, N = 30.970.970.980.97MIN: 0.66 / MAX: 15.15MIN: 0.57 / MAX: 14.08MIN: 0.53 / MAX: 16.95MIN: 0.55 / MAX: 13.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd90180270360450SE +/- 0.10, N = 3421.72426.03423.46421.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd1326395265SE +/- 0.01, N = 356.8756.3056.6456.90MIN: 35.77 / MAX: 72.74MIN: 52.17 / MAX: 69.13MIN: 36.21 / MAX: 73.18MIN: 51.72 / MAX: 72.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd10K20K30K40K50KSE +/- 27.92, N = 344518.2044461.0244306.1044596.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd0.11930.23860.35790.47720.5965SE +/- 0.00, N = 30.530.530.530.53MIN: 0.3 / MAX: 12.95MIN: 0.3 / MAX: 12.53MIN: 0.3 / MAX: 13.83MIN: 0.31 / MAX: 12.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Overwriteabcd200K400K600K800K1000KSE +/- 4178.44, N = 37811667792367778047621751. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fillabcd200K400K600K800K1000KSE +/- 1329.24, N = 37906037839677743847771151. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readabcd30M60M90M120M150MSE +/- 374266.35, N = 31459628911458937531449217631455168741. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randomabcd140K280K420K560K700KSE +/- 1458.06, N = 36711216667156609786585201. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Sequential Fillabcd200K400K600K800K1000KSE +/- 4090.17, N = 39204309081779088829191481. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill Syncabcd10K20K30K40K50KSE +/- 32.60, N = 3455284597446701462991. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingabcd1.2M2.4M3.6M4.8M6MSE +/- 38492.46, N = 355468015586539559276056336131. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomabcd600K1200K1800K2400K3000KSE +/- 5471.11, N = 328797872859339286868128145131. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

WavPack Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.7WAV To WavPackabcd0.99951.9992.99853.9984.9975SE +/- 0.000, N = 54.4334.4384.4354.442

BRL-CAD

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance Metricabcd90K180K270K360K450K4303874246414205284257781. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6

Chaos Group V-RAY

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUabcd10K20K30K40K50KSE +/- 195.74, N = 344287446344437544633

158 Results Shown

JPEG-XL libjxl:
  PNG - 80
  PNG - 90
  JPEG - 80
  JPEG - 90
  PNG - 100
  JPEG - 100
JPEG-XL Decoding libjxl:
  1
  All
srsRAN Project:
  PDSCH Processor Benchmark, Throughput Total
  PUSCH Processor Benchmark, Throughput Total
  PDSCH Processor Benchmark, Throughput Thread
  PUSCH Processor Benchmark, Throughput Thread
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
  Preset 4 - Bosphorus 1080p
  Preset 8 - Bosphorus 1080p
  Preset 12 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
VVenC:
  Bosphorus 4K - Fast
  Bosphorus 4K - Faster
  Bosphorus 1080p - Fast
  Bosphorus 1080p - Faster
OSPRay:
  particle_volume/ao/real_time
  particle_volume/scivis/real_time
  particle_volume/pathtracer/real_time
  gravity_spheres_volume/dim_512/ao/real_time
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/pathtracer/real_time
Stockfish
Timed Linux Kernel Compilation:
  defconfig
  allmodconfig
Parallel BZIP2 Compression
Primesieve:
  1e12
  1e13
oneDNN:
  IP Shapes 1D - CPU
  IP Shapes 3D - CPU
  Convolution Batch Shapes Auto - CPU
  Deconvolution Batch shapes_1d - CPU
  Deconvolution Batch shapes_3d - CPU
  Recurrent Neural Network Training - CPU
  Recurrent Neural Network Inference - CPU
OSPRay Studio:
  1 - 4K - 1 - Path Tracer - CPU
  2 - 4K - 1 - Path Tracer - CPU
  3 - 4K - 1 - Path Tracer - CPU
  1 - 4K - 16 - Path Tracer - CPU
  1 - 4K - 32 - Path Tracer - CPU
  2 - 4K - 16 - Path Tracer - CPU
  2 - 4K - 32 - Path Tracer - CPU
  3 - 4K - 16 - Path Tracer - CPU
  3 - 4K - 32 - Path Tracer - CPU
  1 - 1080p - 1 - Path Tracer - CPU
  2 - 1080p - 1 - Path Tracer - CPU
  3 - 1080p - 1 - Path Tracer - CPU
  1 - 1080p - 16 - Path Tracer - CPU
  1 - 1080p - 32 - Path Tracer - CPU
  2 - 1080p - 16 - Path Tracer - CPU
  2 - 1080p - 32 - Path Tracer - CPU
  3 - 1080p - 16 - Path Tracer - CPU
  3 - 1080p - 32 - Path Tracer - CPU
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  Llama2 Chat 7b Quantized - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  Llama2 Chat 7b Quantized - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch
Google Draco:
  Lion
  Church Facade
OpenVINO:
  Face Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP32 - CPU:
    FPS
    ms
  Vehicle Detection FP16 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Face Detection Retail FP16 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Face Detection Retail FP16-INT8 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16-INT8 - CPU:
    FPS
    ms
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
  Noise Suppression Poconet-Like FP16 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16 - CPU:
    FPS
    ms
  Person Re-Identification Retail FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16-INT8 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
RocksDB:
  Overwrite
  Rand Fill
  Rand Read
  Update Rand
  Seq Fill
  Rand Fill Sync
  Read While Writing
  Read Rand Write Rand
WavPack Audio Encoding
BRL-CAD
Chaos Group V-RAY