Linux 6.10 Benchmarks AMD Threadripper

Benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2405281-NE-LINUX610B68
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

Limit displaying results to tests within:

C/C++ Compiler Tests 7 Tests
CPU Massive 11 Tests
Creator Workloads 8 Tests
Database Test Suite 2 Tests
Disk Test Suite 2 Tests
Encoding 4 Tests
HPC - High Performance Computing 3 Tests
Imaging 2 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 2 Tests
Multi-Core 11 Tests
OpenMPI Tests 2 Tests
Python Tests 3 Tests
Server 3 Tests
Server CPU Tests 8 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 3 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
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 6.9
May 26
  9 Hours, 28 Minutes
Linux 6.10-rc1
May 27
  10 Hours, 32 Minutes
Invert Hiding All Results Option
  10 Hours
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):

Linux 6.9

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 5.37GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Ubuntu 24.04, Kernel: 6.9.0-060900-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5-1ubuntu1 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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
Disk Notes: NONE / relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB
Java Notes: OpenJDK Runtime Environment (build 11.0.23+9-post-Ubuntu-1ubuntu1)
Python Notes: Python 3.12.3
Security Notes: 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: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Linux 6.10-rc1

OS: Ubuntu 24.04, Kernel: 6.10.0-061000rc1-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5-1ubuntu1 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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
Disk Notes: NONE / relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB
Python Notes: Python 3.12.3
Security Notes: 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: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Linux 6.10 Benchmarks AMD ThreadripperOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 7980X 64-Cores @ 5.37GHz (64 Cores / 128 Threads)System76 Thelio Major (FA Z5 BIOS)AMD Device 14a44 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA21000GB CT1000T700SSD5AMD Radeon Pro W7900 45GBAMD Device 14ccDELL P2415QAquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6EUbuntu 24.046.9.0-060900-generic (x86_64)6.10.0-061000rc1-generic (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.0.5-1ubuntu1 (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelsDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionLinux 6.10 Benchmarks AMD Threadripper PerformanceSystem Logs- Transparent Huge Pages: madvise- --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 - NONE / relatime,rw / Block Size: 4096- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- BAR1 / Visible vRAM Size: 46064 MB- Linux 6.9: OpenJDK Runtime Environment (build 11.0.23+9-post-Ubuntu-1ubuntu1)- Python 3.12.3- 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: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Linux 6.9 vs. Linux 6.10-rc1 ComparisonPhoronix Test SuiteBaseline+31.6%+31.6%+63.2%+63.2%+94.8%+94.8%126.3%126.3%119.9%115.4%107.4%8.7%5.4%4%2.9%2.8%2.4%2.4%2.4%2.4%2%100 - 1000 - Read Write - Average Latency100 - 1000 - Read WriteSocket Activityoltp_update_non_index - 128oltp_update_index - 128Rand Write - IO_uring - Yes - 4KB - 1616.6%Rand Write - IO_uring - Yes - 4KB - 1616.6%S.V.M.P13.7%NUMA9.5%Chrysler Neon 1MP.P.B.T.T8.5%N.S.P.L.F - CPU7%N.S.P.L.F - CPU7%Preset 12 - Bosphorus 4K6.2%Tomographic ModelRand Write - IO_uring - Yes - 4KB - 324.8%Rand Write - IO_uring - Yes - 4KB - 324.8%Semaphores4.6%Bosphorus 4K - Very Fast4.2%Mutex4%Read While WritingR.R.W.R3.7%CPU - 32 - ResNet-503.7%R.S.A.F.I - CPU3.6%R.S.A.F.I - CPU3.5%Bosphorus 4K - Super Fast3.2%Update Rand3%1920 x 1200 - F.K.O - OffBosphorus 4K - Ultra Fast2.9%Context Switchingoltp_write_only - 1282.8%Futex2.8%P.D.F - CPU2.5%HWB Color Space1920 x 1200 - FurMark OpenGL - Off32 - ProcessP.D.F - CPU2.4%Chess Benchmark1920 x 1200 - Fullscreen - Low - OpenGLPostgreSQLPostgreSQLStress-NGMariaDBMariaDBFlexible IO TesterFlexible IO TesterStress-NGStress-NGOpenRadiosssrsRAN ProjectOpenVINOOpenVINOSVT-AV1SPECFEM3DFlexible IO TesterFlexible IO TesterStress-NGuvg266Stress-NGRocksDBRocksDBTensorFlowOpenVINOOpenVINOuvg266RocksDBFurMarkuvg266Stress-NGMariaDBStress-NGOpenVINOGraphicsMagickFurMarkHackbenchOpenVINOStockfishUnigine SuperpositionLinux 6.9Linux 6.10-rc1

Linux 6.10 Benchmarks AMD Threadripperpgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writestress-ng: Socket Activitymariadb: oltp_update_non_index - 128stress-ng: System V Message Passingstress-ng: NUMAsrsran: PDSCH Processor Benchmark, Throughput Totalopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUsvt-av1: Preset 12 - Bosphorus 4Kspecfem3d: Tomographic Modelfio: Rand Write - IO_uring - Yes - 4KB - 32 - Default Test Directoryfio: Rand Write - IO_uring - Yes - 4KB - 32 - Default Test Directorystress-ng: Semaphoresuvg266: Bosphorus 4K - Very Faststress-ng: Mutexrocksdb: Read While Writingrocksdb: Read Rand Write Randtensorflow: CPU - 32 - ResNet-50openvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUuvg266: Bosphorus 4K - Super Fastrocksdb: Update Randfurmark: 1920 x 1200 - FurMark Knot OpenGL - Offuvg266: Bosphorus 4K - Ultra Faststress-ng: Context Switchingmariadb: oltp_write_only - 128stress-ng: Futexgraphics-magick: HWB Color Spacefurmark: 1920 x 1200 - FurMark OpenGL - Offhackbench: 32 - Processunigine-super: 1920 x 1200 - Fullscreen - Low - OpenGLmariadb: oltp_read_write - 128furmark: 1920 x 1200 - Furmark Knot Vulkan - Offgraphics-magick: Noise-Gaussianspecfem3d: Water-layered Halfspaceopenradioss: Bumper Beamsrsran: PUSCH Processor Benchmark, Throughput Totalkvazaar: Bosphorus 4K - Super Fastgraphics-magick: Rotatewebp: Quality 100, Lossless, Highest Compressionfurmark: 1920 x 1200 - FurMark Vulkan - Offfio: Rand Read - IO_uring - Yes - 4KB - 16 - Default Test Directoryfio: Rand Read - IO_uring - Yes - 4KB - 32 - Default Test Directoryfio: Rand Read - IO_uring - Yes - 4KB - 32 - Default Test Directoryfio: Rand Read - IO_uring - Yes - 4KB - 16 - Default Test Directorymariadb: oltp_point_select - 128pgbench: 100 - 1000 - Read Only - Average Latencyparaview: Wavelet Volume - 1920 x 1200specfem3d: Mount St. Helensx265: Bosphorus 1080ppgbench: 100 - 1000 - Read Onlyrocksdb: Rand Readgraphics-magick: Resizinggraphics-magick: Sharpencompress-7zip: Decompression Ratinggraphics-magick: Swirlcompress-7zip: Compression Ratingsvt-av1: Preset 8 - Bosphorus 4Kblender: Junkshop - CPU-Onlywebp: Quality 100, Losslesswebp: Quality 100kvazaar: Bosphorus 4K - Very Fastparaview: Many Spheres - 1920 x 1200specfem3d: Layered Halfspacekvazaar: Bosphorus 4K - Ultra Fastparaview: Wavelet Contour - 1920 x 1200x265: Bosphorus 4Kopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUkvazaar: Bosphorus 4K - Mediumopenvino: Person Re-Identification Retail FP16 - CPUopenradioss: Cell Phone Drop Testopenradioss: INIVOL and Fluid Structure Interaction Drop Containeropenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Person Re-Identification Retail FP16 - CPUkvazaar: Bosphorus 4K - Slowblender: BMW27 - CPU-Onlyopenvino: Handwritten English Recognition FP16-INT8 - CPUstress-ng: Vector Mathunigine-super: 1920 x 1200 - Fullscreen - High - OpenGLsvt-av1: Preset 4 - Bosphorus 4K3dmark: 1920 x 1200webp: Quality 100, Highest Compressionuvg266: Bosphorus 4K - Mediummariadb: oltp_read_only - 128uvg266: Bosphorus 4K - Slowbuild-linux-kernel: defconfigspecfem3d: Homogeneous Halfspacebuild-linux-kernel: allmodconfigunigine-super: 1920 x 1200 - Fullscreen - Medium - OpenGLstress-ng: Memory Copyingopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUgraphics-magick: Enhancedfs-mark: 1000 Files, 1MB Sizeopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUmariadb: oltp_update_index - 128stockfish: Chess Benchmarkopenradioss: Chrysler Neon 1Mparaview: Wavelet Contour - 1920 x 1200paraview: Wavelet Volume - 1920 x 1200paraview: Many Spheres - 1920 x 1200fs-mark: 5000 Files, 1MB Size, 4 Threadsfio: Rand Write - IO_uring - Yes - 4KB - 16 - Default Test Directoryfio: Rand Write - IO_uring - Yes - 4KB - 16 - Default Test DirectoryLinux 6.9Linux 6.10-rc163.3251583411324.962333230153119.99991.7716468.818.183381.03203.0458.836709905916234333112151434.8463.9719512992.5111321860367551271.3924.551298.1862.70535052116.47391864.2114981469.06636633347537.05245252.10158818.984242.7137600132.20568917522.43653234373.094738.695.771620.81217.01904335533335533313871389515350.259697.217.795535516106.903858087425897202174175569666544356663101.16223.822.0514.5379.72171.2025.62834802897.93795.3536.46379.3184.1237.005.4322.03120.072306.425811.0936.2617.0327.64559407.57201.810.059579.214.9226.983623824.3628.91010.077647718275.830219.523493.08127138.440.37262394.1177.16180.7925623152557938454.878288.47311155.36517163.552599.423433391527.9863582524901.865025626517976.37905.6015174.619.463161.12191.1158.385808611874223667107201868.6961.4018755558.8211774985354327968.8625.431253.9260.76519583119.85255262.4215405579.69619433257261.44251258.26438418.533247.5135048134.65737917822.79661192974.144676.094.541640.82214.75358135900035866714001402511040.261702.397.741159029106.223835067423427483175176566510547358561100.64423.942.0614.6079.34172.0025.51121106998.37791.9136.31380.8783.7837.155.4521.95120.462299.065792.9736.3717.0827.72557814.45202.310.035580.514.9326.933617124.3328.87910.067154160276.095219.723478.63127111.920.37262181.57176.5753152156193576418.458252.66711238.27717244.121201000785OpenBenchmarking.org

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyLinux 6.9Linux 6.10-rc11428425670SE +/- 0.99, N = 12SE +/- 0.41, N = 1263.3327.991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteLinux 6.9Linux 6.10-rc18K16K24K32K40KSE +/- 244.52, N = 12SE +/- 567.51, N = 1215834358251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Socket ActivityLinux 6.9Linux 6.10-rc15K10K15K20K25KSE +/- 113.43, N = 5SE +/- 173.55, N = 311324.9624901.861. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 128Linux 6.9Linux 6.10-rc111K22K33K44K55KSE +/- 122.62, N = 3SE +/- 363.44, N = 323332502561. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: System V Message PassingLinux 6.9Linux 6.10-rc16M12M18M24M30MSE +/- 61321.57, N = 3SE +/- 7126.61, N = 330153119.9926517976.371. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: NUMALinux 6.9Linux 6.10-rc12004006008001000SE +/- 1.92, N = 3SE +/- 1.07, N = 3991.77905.601. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalLinux 6.9Linux 6.10-rc14K8K12K16K20KSE +/- 191.94, N = 3SE +/- 146.37, N = 316468.815174.61. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPULinux 6.9Linux 6.10-rc1510152025SE +/- 0.12, N = 15SE +/- 0.14, N = 1518.1819.46MIN: 7.58 / MAX: 80.87MIN: 7.28 / MAX: 85.951. (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: CPULinux 6.9Linux 6.10-rc17001400210028003500SE +/- 23.76, N = 15SE +/- 24.30, N = 153381.033161.121. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KLinux 6.9Linux 6.10-rc14080120160200SE +/- 1.10, N = 3SE +/- 0.65, N = 3203.05191.121. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Tomographic ModelLinux 6.9Linux 6.10-rc1246810SE +/- 0.123053751, N = 3SE +/- 0.099060131, N = 158.8367099058.3858086111. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.36Type: Random Write - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 32 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc12004006008001000SE +/- 4.84, N = 3SE +/- 5.37, N = 159168741. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.36Type: Random Write - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 32 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc150K100K150K200K250KSE +/- 1201.85, N = 3SE +/- 1396.14, N = 152343332236671. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: SemaphoresLinux 6.9Linux 6.10-rc120M40M60M80M100MSE +/- 818877.00, N = 3SE +/- 214521.77, N = 3112151434.84107201868.691. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

uvg266

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.8.0Video Input: Bosphorus 4K - Video Preset: Very FastLinux 6.9Linux 6.10-rc11428425670SE +/- 0.10, N = 3SE +/- 0.26, N = 363.9761.40

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: MutexLinux 6.9Linux 6.10-rc14M8M12M16M20MSE +/- 112105.25, N = 3SE +/- 209986.02, N = 319512992.5118755558.821. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingLinux 6.9Linux 6.10-rc13M6M9M12M15MSE +/- 95160.29, N = 3SE +/- 97089.91, N = 911321860117749851. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomLinux 6.9Linux 6.10-rc1800K1600K2400K3200K4000KSE +/- 9898.77, N = 3SE +/- 13181.32, N = 3367551235432791. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50Linux 6.9Linux 6.10-rc11632486480SE +/- 0.07, N = 3SE +/- 0.15, N = 371.3968.86

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPULinux 6.9Linux 6.10-rc1612182430SE +/- 0.10, N = 3SE +/- 0.30, N = 324.5525.43MIN: 9.93 / MAX: 50.16MIN: 10.9 / MAX: 68.61. (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: CPULinux 6.9Linux 6.10-rc130060090012001500SE +/- 5.23, N = 3SE +/- 14.59, N = 31298.181253.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

uvg266

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.8.0Video Input: Bosphorus 4K - Video Preset: Super FastLinux 6.9Linux 6.10-rc11428425670SE +/- 0.07, N = 3SE +/- 0.08, N = 362.7060.76

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomLinux 6.9Linux 6.10-rc1110K220K330K440K550KSE +/- 606.77, N = 3SE +/- 319.69, N = 35350525195831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1200 - Demo: FurMark Knot OpenGL - MSAA: OffLinux 6.9Linux 6.10-rc1306090120150SE +/- 1.54, N = 3SE +/- 0.47, N = 3116.47119.85MIN: 113 / MAX: 122MIN: 118 / MAX: 125

uvg266

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.8.0Video Input: Bosphorus 4K - Video Preset: Ultra FastLinux 6.9Linux 6.10-rc11428425670SE +/- 0.03, N = 3SE +/- 0.15, N = 364.2162.42

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Context SwitchingLinux 6.9Linux 6.10-rc13M6M9M12M15MSE +/- 119455.25, N = 3SE +/- 207966.00, N = 314981469.0615405579.691. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 128Linux 6.9Linux 6.10-rc114K28K42K56K70KSE +/- 848.85, N = 3SE +/- 105.38, N = 363663619431. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: FutexLinux 6.9Linux 6.10-rc1700K1400K2100K2800K3500KSE +/- 18408.96, N = 3SE +/- 35268.90, N = 153347537.053257261.441. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceLinux 6.9Linux 6.10-rc150100150200250SE +/- 0.33, N = 3SE +/- 0.88, N = 32452511. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1200 - Demo: FurMark OpenGL - MSAA: OffLinux 6.9Linux 6.10-rc160120180240300SE +/- 3.01, N = 3SE +/- 0.37, N = 3252.10258.26MIN: 242 / MAX: 269MIN: 252 / MAX: 274

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessLinux 6.9Linux 6.10-rc1510152025SE +/- 0.10, N = 3SE +/- 0.07, N = 318.9818.531. (CC) gcc options: -lpthread

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLLinux 6.9Linux 6.10-rc150100150200250SE +/- 1.13, N = 3SE +/- 0.58, N = 3242.7247.5MAX: 360MAX: 361.6

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 128Linux 6.9Linux 6.10-rc130K60K90K120K150KSE +/- 772.42, N = 3SE +/- 714.82, N = 31376001350481. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1200 - Demo: Furmark Knot Vulkan - MSAA: OffLinux 6.9Linux 6.10-rc1306090120150SE +/- 1.12, N = 3SE +/- 0.34, N = 3132.21134.66MIN: 128 / MAX: 140MIN: 132 / MAX: 142

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianLinux 6.9Linux 6.10-rc14080120160200SE +/- 0.58, N = 3SE +/- 0.33, N = 31751781. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Water-layered HalfspaceLinux 6.9Linux 6.10-rc1510152025SE +/- 0.20, N = 3SE +/- 0.32, N = 322.4422.801. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamLinux 6.9Linux 6.10-rc11632486480SE +/- 0.15, N = 3SE +/- 0.44, N = 373.0974.14

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalLinux 6.9Linux 6.10-rc110002000300040005000SE +/- 62.43, N = 3SE +/- 62.95, N = 34738.64676.0MIN: 3135.1 / MAX: 4801.1MIN: 3134.3 / MAX: 4801.91. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastLinux 6.9Linux 6.10-rc120406080100SE +/- 0.08, N = 3SE +/- 0.14, N = 395.7794.541. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: RotateLinux 6.9Linux 6.10-rc14080120160200SE +/- 0.58, N = 3SE +/- 0.33, N = 31621641. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.4Encode Settings: Quality 100, Lossless, Highest CompressionLinux 6.9Linux 6.10-rc10.18450.3690.55350.7380.9225SE +/- 0.00, N = 3SE +/- 0.01, N = 30.810.821. (CC) gcc options: -fvisibility=hidden -O2 -lm

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1200 - Demo: FurMark Vulkan - MSAA: OffLinux 6.9Linux 6.10-rc150100150200250SE +/- 0.43, N = 3SE +/- 2.64, N = 3217.02214.75MIN: 211 / MAX: 232MIN: 205 / MAX: 231

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.36Type: Random Read - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 16 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc180K160K240K320K400KSE +/- 881.92, N = 3SE +/- 2000.00, N = 33553333590001. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.36Type: Random Read - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 32 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc180K160K240K320K400KSE +/- 2185.81, N = 3SE +/- 4977.73, N = 33553333586671. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.36Type: Random Read - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 32 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc130060090012001500SE +/- 8.84, N = 3SE +/- 19.09, N = 3138714001. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.36Type: Random Read - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 16 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc130060090012001500SE +/- 4.06, N = 3SE +/- 7.69, N = 3138914021. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_point_select - Threads: 128Linux 6.9Linux 6.10-rc111K22K33K44K55KSE +/- 53.08, N = 3SE +/- 39.24, N = 351535511041. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyLinux 6.9Linux 6.10-rc10.05870.11740.17610.23480.2935SE +/- 0.002, N = 3SE +/- 0.001, N = 30.2590.2611. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc1150300450600750SE +/- 7.01, N = 5SE +/- 7.60, N = 5697.21702.39
OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc12K4K6K8K10KSE +/- 112.24, N = 5SE +/- 121.54, N = 511155.3711238.28

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Mount St. HelensLinux 6.9Linux 6.10-rc1246810SE +/- 0.089058717, N = 4SE +/- 0.055723910, N = 37.7955355167.7411590291. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.6Video Input: Bosphorus 1080pLinux 6.9Linux 6.10-rc120406080100SE +/- 0.25, N = 3SE +/- 0.19, N = 3106.90106.221. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyLinux 6.9Linux 6.10-rc1800K1600K2400K3200K4000KSE +/- 28604.29, N = 3SE +/- 7103.88, N = 3385808738350671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadLinux 6.9Linux 6.10-rc190M180M270M360M450MSE +/- 306191.38, N = 3SE +/- 386132.71, N = 34258972024234274831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingLinux 6.9Linux 6.10-rc14080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 31741751. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenLinux 6.9Linux 6.10-rc14080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 31751761. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Decompression RatingLinux 6.9Linux 6.10-rc1120K240K360K480K600KSE +/- 1101.28, N = 3SE +/- 1934.83, N = 35696665665101. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlLinux 6.9Linux 6.10-rc1120240360480600SE +/- 0.88, N = 3SE +/- 0.67, N = 35445471. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Compression RatingLinux 6.9Linux 6.10-rc180K160K240K320K400KSE +/- 1578.73, N = 3SE +/- 2255.65, N = 33566633585611. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KLinux 6.9Linux 6.10-rc120406080100SE +/- 0.71, N = 3SE +/- 0.34, N = 3101.16100.641. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlyLinux 6.9Linux 6.10-rc1612182430SE +/- 0.10, N = 3SE +/- 0.04, N = 323.8223.94

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.4Encode Settings: Quality 100, LosslessLinux 6.9Linux 6.10-rc10.46350.9271.39051.8542.3175SE +/- 0.01, N = 3SE +/- 0.02, N = 32.052.061. (CC) gcc options: -fvisibility=hidden -O2 -lm

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.4Encode Settings: Quality 100Linux 6.9Linux 6.10-rc148121620SE +/- 0.03, N = 3SE +/- 0.02, N = 314.5314.601. (CC) gcc options: -fvisibility=hidden -O2 -lm

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastLinux 6.9Linux 6.10-rc120406080100SE +/- 0.13, N = 3SE +/- 0.08, N = 379.7279.341. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc14080120160200SE +/- 1.31, N = 3SE +/- 1.47, N = 3171.20172.00
OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc14K8K12K16K20KSE +/- 131.62, N = 3SE +/- 147.91, N = 317163.5517244.12

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Layered HalfspaceLinux 6.9Linux 6.10-rc1612182430SE +/- 0.28, N = 3SE +/- 0.13, N = 325.6325.511. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastLinux 6.9Linux 6.10-rc120406080100SE +/- 0.19, N = 3SE +/- 0.08, N = 397.9398.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc12004006008001000SE +/- 1.60, N = 3SE +/- 0.24, N = 3795.35791.91
OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc12K4K6K8K10KSE +/- 16.67, N = 3SE +/- 2.51, N = 38288.478252.67

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.6Video Input: Bosphorus 4KLinux 6.9Linux 6.10-rc1816243240SE +/- 0.06, N = 3SE +/- 0.09, N = 336.4636.311. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPULinux 6.9Linux 6.10-rc180160240320400SE +/- 0.24, N = 3SE +/- 0.24, N = 3379.31380.87MIN: 195.85 / MAX: 399.4MIN: 325.27 / MAX: 401.531. (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: CPULinux 6.9Linux 6.10-rc120406080100SE +/- 0.09, N = 3SE +/- 0.06, N = 384.1283.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumLinux 6.9Linux 6.10-rc1918273645SE +/- 0.03, N = 3SE +/- 0.05, N = 337.0037.151. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPULinux 6.9Linux 6.10-rc11.22632.45263.67894.90526.1315SE +/- 0.01, N = 3SE +/- 0.00, N = 35.435.45MIN: 3.12 / MAX: 33.49MIN: 3.09 / MAX: 19.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestLinux 6.9Linux 6.10-rc1510152025SE +/- 0.08, N = 3SE +/- 0.07, N = 322.0321.95

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerLinux 6.9Linux 6.10-rc1306090120150SE +/- 0.48, N = 3SE +/- 0.19, N = 3120.07120.46

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPULinux 6.9Linux 6.10-rc15001000150020002500SE +/- 1.38, N = 3SE +/- 1.46, N = 32306.422299.061. (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: CPULinux 6.9Linux 6.10-rc112002400360048006000SE +/- 8.59, N = 3SE +/- 2.56, N = 35811.095792.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowLinux 6.9Linux 6.10-rc1816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 336.2636.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-OnlyLinux 6.9Linux 6.10-rc148121620SE +/- 0.09, N = 3SE +/- 0.08, N = 317.0317.08

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPULinux 6.9Linux 6.10-rc1714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 327.6427.72MIN: 16.34 / MAX: 57MIN: 16.96 / MAX: 51.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Vector MathLinux 6.9Linux 6.10-rc1120K240K360K480K600KSE +/- 303.88, N = 3SE +/- 360.27, N = 3559407.57557814.451. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: High - Renderer: OpenGLLinux 6.9Linux 6.10-rc14080120160200SE +/- 0.94, N = 3SE +/- 0.85, N = 3201.8202.3MAX: 267.2MAX: 269.8

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KLinux 6.9Linux 6.10-rc13691215SE +/- 0.01, N = 3SE +/- 0.02, N = 310.0610.041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

3DMark Wild Life Extreme

This test profile only automates the vendor build of 3DMark with its command-line / JSON support. If you do not have a licensed copy of the necessary 3DMark binaries in your Phoronix Test Suite download cache on your system, this test profile will not do anything and simply fail. You must have already obtained the proper licensed binaries from UL for this test profile to work -- this test profile simply automates the firing of the 3DMark benchmark at your desired resolution and capturing the results within the Phoronix Test Suite while you must already have the necessary 3DMark files on your system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Better3DMark Wild Life Extreme 1.1.2.1Resolution: 1920 x 1200Linux 6.9Linux 6.10-rc1130260390520650SE +/- 0.34, N = 3SE +/- 1.28, N = 3579.21580.51

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.4Encode Settings: Quality 100, Highest CompressionLinux 6.9Linux 6.10-rc11.10932.21863.32794.43725.5465SE +/- 0.06, N = 4SE +/- 0.03, N = 34.924.931. (CC) gcc options: -fvisibility=hidden -O2 -lm

uvg266

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.8.0Video Input: Bosphorus 4K - Video Preset: MediumLinux 6.9Linux 6.10-rc1612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 326.9826.93

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_only - Threads: 128Linux 6.9Linux 6.10-rc18K16K24K32K40KSE +/- 7.32, N = 3SE +/- 38.27, N = 336238361711. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

uvg266

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.8.0Video Input: Bosphorus 4K - Video Preset: SlowLinux 6.9Linux 6.10-rc1612182430SE +/- 0.01, N = 3SE +/- 0.04, N = 324.3624.33

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigLinux 6.9Linux 6.10-rc1714212835SE +/- 0.26, N = 7SE +/- 0.36, N = 428.9128.88

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Homogeneous HalfspaceLinux 6.9Linux 6.10-rc13691215SE +/- 0.09, N = 3SE +/- 0.07, N = 310.0810.071. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigLinux 6.9Linux 6.10-rc160120180240300SE +/- 0.29, N = 3SE +/- 0.32, N = 3275.83276.10

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGLLinux 6.9Linux 6.10-rc150100150200250SE +/- 0.67, N = 3SE +/- 0.72, N = 3219.5219.7MAX: 331.2MAX: 301.5

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Memory CopyingLinux 6.9Linux 6.10-rc15K10K15K20K25KSE +/- 13.52, N = 3SE +/- 8.27, N = 323493.0823478.631. (CXX) g++ options: -O2 -std=gnu99 -lc -lm

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPULinux 6.9Linux 6.10-rc130K60K90K120K150KSE +/- 84.33, N = 3SE +/- 19.69, N = 3127138.44127111.921. (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: CPULinux 6.9Linux 6.10-rc10.08330.16660.24990.33320.4165SE +/- 0.00, N = 3SE +/- 0.00, N = 30.370.37MIN: 0.18 / MAX: 22.35MIN: 0.18 / MAX: 21.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedLinux 6.9Linux 6.10-rc160120180240300SE +/- 0.33, N = 3SE +/- 0.33, N = 32622621. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp

FS-Mark

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

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeLinux 6.990180270360450SE +/- 5.25, N = 3394.1

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPULinux 6.9Linux 6.10-rc14080120160200SE +/- 2.75, N = 12SE +/- 2.86, N = 15177.16181.57MIN: 55.49 / MAX: 381.02MIN: 49.05 / MAX: 395.831. (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: CPULinux 6.9Linux 6.10-rc14080120160200SE +/- 2.95, N = 12SE +/- 3.02, N = 15180.79176.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 128Linux 6.9Linux 6.10-rc111K22K33K44K55KSE +/- 202.47, N = 3SE +/- 5166.02, N = 925623531521. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

Count: 32 - Type: Thread

Linux 6.9: The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

Linux 6.10-rc1: The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkLinux 6.9Linux 6.10-rc130M60M90M120M150MSE +/- 2411327.27, N = 15SE +/- 3250185.42, N = 151525579381561935761. (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 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MLinux 6.9Linux 6.10-rc1100200300400500SE +/- 14.77, N = 9SE +/- 9.53, N = 9454.87418.45

FS-Mark

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

Test: 4000 Files, 32 Sub Dirs, 1MB Size

Linux 6.9: The test run did not produce a result. E: sh: 1: exec: ./fs-mark: not found

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 ThreadsLinux 6.9130260390520650SE +/- 80.52, N = 11599.4

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.36Type: Random Write - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 16 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc150K100K150K200K250KSE +/- 1452.97, N = 3SE +/- 10237.65, N = 152343332010001. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.36Type: Random Write - Engine: IO_uring - Direct: Yes - Block Size: 4KB - Job Count: 16 - Disk Target: Default Test DirectoryLinux 6.9Linux 6.10-rc12004006008001000SE +/- 5.86, N = 3SE +/- 40.09, N = 159157851. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -std=gnu99 -ffast-math -include -O3 -fcommon -march=native

104 Results Shown

PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
Stress-NG
MariaDB
Stress-NG:
  System V Message Passing
  NUMA
srsRAN Project
OpenVINO:
  Noise Suppression Poconet-Like FP16 - CPU:
    ms
    FPS
SVT-AV1
SPECFEM3D
Flexible IO Tester:
  Rand Write - IO_uring - Yes - 4KB - 32 - Default Test Directory:
    MB/s
    IOPS
Stress-NG
uvg266
Stress-NG
RocksDB:
  Read While Writing
  Read Rand Write Rand
TensorFlow
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
uvg266
RocksDB
FurMark
uvg266
Stress-NG
MariaDB
Stress-NG
GraphicsMagick
FurMark
Hackbench
Unigine Superposition
MariaDB
FurMark
GraphicsMagick
SPECFEM3D
OpenRadioss
srsRAN Project
Kvazaar
GraphicsMagick
WebP Image Encode
FurMark
Flexible IO Tester:
  Rand Read - IO_uring - Yes - 4KB - 16 - Default Test Directory
  Rand Read - IO_uring - Yes - 4KB - 32 - Default Test Directory
  Rand Read - IO_uring - Yes - 4KB - 32 - Default Test Directory
  Rand Read - IO_uring - Yes - 4KB - 16 - Default Test Directory
MariaDB
PostgreSQL
ParaView
SPECFEM3D
x265
PostgreSQL
RocksDB
GraphicsMagick:
  Resizing
  Sharpen
7-Zip Compression
GraphicsMagick
7-Zip Compression
SVT-AV1
Blender
WebP Image Encode:
  Quality 100, Lossless
  Quality 100
Kvazaar
ParaView
SPECFEM3D
Kvazaar
ParaView
x265
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
Kvazaar
OpenVINO
OpenRadioss:
  Cell Phone Drop Test
  INIVOL and Fluid Structure Interaction Drop Container
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU
  Person Re-Identification Retail FP16 - CPU
Kvazaar
Blender
OpenVINO
Stress-NG
Unigine Superposition
SVT-AV1
3DMark Wild Life Extreme
WebP Image Encode
uvg266
MariaDB
uvg266
Timed Linux Kernel Compilation
SPECFEM3D
Timed Linux Kernel Compilation
Unigine Superposition
Stress-NG
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
GraphicsMagick
FS-Mark
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
MariaDB
Stockfish
OpenRadioss
FS-Mark
Flexible IO Tester:
  Rand Write - IO_uring - Yes - 4KB - 16 - Default Test Directory:
    IOPS
    MB/s

Linux 6.9

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 5.37GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Ubuntu 24.04, Kernel: 6.9.0-060900-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5-1ubuntu1 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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
Disk Notes: NONE / relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB
Java Notes: OpenJDK Runtime Environment (build 11.0.23+9-post-Ubuntu-1ubuntu1)
Python Notes: Python 3.12.3
Security Notes: 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: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 May 2024 14:37 by user phoronix.

Linux 6.10-rc1

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 5.37GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Ubuntu 24.04, Kernel: 6.10.0-061000rc1-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5-1ubuntu1 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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
Disk Notes: NONE / relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB
Python Notes: Python 3.12.3
Security Notes: 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: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 27 May 2024 00:11 by user phoronix.