Ubuntu Kernel Comparison Low-Latency Kernel

AMD EPYC 8534P 64-Core testing with a AMD Cinnabar (RCB1009C BIOS) and ASPEED 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 2401290-NE-UBUNTUKER76
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:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 16 Tests
Creator Workloads 12 Tests
Cryptography 2 Tests
Encoding 5 Tests
Game Development 2 Tests
HPC - High Performance Computing 6 Tests
Imaging 3 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 2 Tests
Molecular Dynamics 3 Tests
Multi-Core 14 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 4 Tests
Renderers 2 Tests
Scientific Computing 3 Tests
Server 3 Tests
Server CPU Tests 13 Tests
Video Encoding 5 Tests
Common Workstation Benchmarks 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
6.5.0-15-lowlatency
January 29
  8 Hours, 38 Minutes
6.5.0-15-generic
January 29
  8 Hours
Invert Hiding All Results Option
  8 Hours, 19 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

6.5.0-15-lowlatency

Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.5.0-15-lowlatency (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, 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-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-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/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
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)
Python Notes: Python 3.11.5
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 + 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 + srbds: Not affected + tsx_async_abort: Not affected

6.5.0-15-generic

OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Ubuntu Kernel Comparison Low-Latency KernelOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a46 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.5.0-15-lowlatency (x86_64)6.5.0-15-generic (x86_64)GNOME ShellX Server 1.21.1.7GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelsDesktopDisplay ServerCompilerFile-SystemScreen ResolutionUbuntu Kernel Comparison Low-Latency Kernel 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-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/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 performance (Boost: Enabled) - CPU Microcode: 0xaa00212 - OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)- Python 3.11.5- 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 + 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 + srbds: Not affected + tsx_async_abort: Not affected

6.5.0-15-lowlatency vs. 6.5.0-15-generic ComparisonPhoronix Test SuiteBaseline+30.2%+30.2%+60.4%+60.4%+90.6%+90.6%120.6%10.3%10.1%8.6%6%4.1%4%4%3.5%3.3%3.3%3.2%2.7%2.7%2.6%2.6%2.6%2.2%2.2%2.1%2%2%2%Socket ActivityPipeNUMAIO_uring9.7%d.S.M.S - Mesh TimeForking8.3%1000 - 1000 - Read Write - Average Latency6.4%1000 - 1000 - Read Write6.4%S.V.M.PPthread4.8%Tradebeans4.6%SemaphoresFutexBosphorus 4K - Ultra FastMixed Scheduler3.9%Apache Tomcat10 - Bosphorus 4KR.O.R.S.IApache Xalan XSLT3.2%CPU CacheG.C.S.F2.9%allmodconfig16 - ThreadSENDFILEGraphChiMutex100 - 1000 - Read Only - Average Latency100 - 1000 - Read OnlyPreset 12 - Bosphorus 4KZ.1.2.B.I.P2.1%defconfig7 - Bosphorus 1080pCPU - 1 - ResNet-50Stress-NGStress-NGStress-NGStress-NGOpenFOAMStress-NGPostgreSQLPostgreSQLStress-NGStress-NGDaCapo BenchmarkStress-NGStress-NGuvg266Stress-NGDaCapo BenchmarkSVT-HEVCOpenRadiossDaCapo BenchmarkStress-NGStress-NGTimed Linux Kernel CompilationHackbenchStress-NGDaCapo BenchmarkStress-NGPostgreSQLPostgreSQLSVT-AV1DaCapo BenchmarkTimed Linux Kernel CompilationSVT-HEVCPyTorch6.5.0-15-lowlatency6.5.0-15-generic

Ubuntu Kernel Comparison Low-Latency Kernelstress-ng: Socket Activitystress-ng: Pipestress-ng: NUMAopenfoam: drivaerFastback, Small Mesh Size - Mesh Timestress-ng: Forkingpgbench: 1000 - 1000 - Read Write - Average Latencypgbench: 1000 - 1000 - Read Writestress-ng: System V Message Passingstress-ng: Pthreadstress-ng: Semaphoresstress-ng: Futexuvg266: Bosphorus 4K - Ultra Faststress-ng: Mixed Schedulerdacapobench: Apache Tomcatsvt-hevc: 10 - Bosphorus 4Kopenradioss: Rubber O-Ring Seal Installationdacapobench: Apache Xalan XSLTstress-ng: Glibc C String Functionsbuild-linux-kernel: allmodconfighackbench: 16 - Threadstress-ng: SENDFILEdacapobench: GraphChistress-ng: Mutexpgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlysvt-av1: Preset 12 - Bosphorus 4Kdacapobench: Zxing 1D/2D Barcode Image Processingbuild-linux-kernel: defconfigsvt-hevc: 7 - Bosphorus 1080ppytorch: CPU - 1 - ResNet-50rawtherapee: Total Benchmark Timesvt-av1: Preset 13 - Bosphorus 4Kdacapobench: BioJava Biological Data Frameworkdarktable: Masskrug - CPU-onlystress-ng: MEMFDstress-ng: MMAPsvt-hevc: 7 - Bosphorus 4Kstress-ng: Cloningopenradioss: Cell Phone Drop Testpytorch: CPU - 16 - ResNet-50dacapobench: PMD Source Code Analyzersvt-av1: Preset 4 - Bosphorus 4Ktensorflow: CPU - 1 - ResNet-50pytorch: CPU - 32 - ResNet-50stress-ng: Context Switchingsvt-hevc: 1 - Bosphorus 1080pbuild-llvm: Unix Makefilesstress-ng: Pollxmrig: Wownero - 1Mopenfoam: drivaerFastback, Small Mesh Size - Execution Timeembree: Pathtracer ISPC - Asian Dragondacapobench: FOP Print Formatterincompact3d: input.i3d 129 Cells Per Directionbuild-godot: Time To Compilebuild-llvm: Ninjadacapobench: Apache Lucene Search Engineopenfoam: drivaerFastback, Medium Mesh Size - Execution Timehackbench: 32 - Processdarktable: Server Rack - CPU-onlydacapobench: Apache Cassandrastress-ng: Cryptoblender: BMW27 - CPU-Onlyxmrig: Monero - 1Mgimp: rotatestress-ng: Vector Floating Pointdacapobench: Jythonembree: Pathtracer ISPC - Asian Dragon Objcompress-7zip: Compression Ratingquicksilver: CTS2dacapobench: Spring Bootembree: Pathtracer ISPC - Crownblender: Barbershop - CPU-Onlysvt-hevc: 1 - Bosphorus 4Khackbench: 16 - Processdarktable: Boat - CPU-onlyvvenc: Bosphorus 4K - Fasterstress-ng: AVL Treeblender: Classroom - CPU-Onlyospray-studio: 3 - 4K - 32 - Path Tracer - CPUospray-studio: 2 - 4K - 1 - Path Tracer - CPUstress-ng: Floating Pointospray-studio: 1 - 4K - 32 - Path Tracer - CPUquicksilver: CORAL2 P1gimp: resizeospray-studio: 2 - 4K - 32 - Path Tracer - CPUquicksilver: CORAL2 P2ospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUdacapobench: Avrora AVR Simulation Frameworkopenssl: AES-128-GCMstress-ng: Glibc Qsort Data Sortingstress-ng: Matrix Mathstress-ng: CPU Stressopenssl: ChaCha20-Poly1305dacapobench: Apache Kafkaopenssl: RSA4096vvenc: Bosphorus 1080p - Fastnginx: 500openssl: SHA256dacapobench: Tradesoapstress-ng: Zlibdacapobench: Eclipseopenssl: SHA512vvenc: Bosphorus 1080p - Fasterstress-ng: Vector Mathstress-ng: Wide Vector Mathopenradioss: Bird Strike on Windshieldvvenc: Bosphorus 4K - Fastnamd: ATPase Simulation - 327,506 Atomsstress-ng: Vector Shuffleopenssl: RSA4096ospray-studio: 2 - 4K - 16 - Path Tracer - CPUstress-ng: x86_64 RdRandx265: Bosphorus 4Kstress-ng: Memory Copyingcompress-7zip: Decompression Ratingnginx: 1000openssl: ChaCha20ospray-studio: 1 - 4K - 16 - Path Tracer - CPUpgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencystress-ng: AVX-512 VNNIstress-ng: Hashtensorflow: CPU - 256 - ResNet-50dacapobench: H2 Database Engineopenssl: AES-256-GCMstress-ng: Atomicpgbench: 1000 - 1000 - Read Only - Average Latencystress-ng: Matrix 3D Mathstress-ng: Mallocdacapobench: Apache Lucene Search Indexgimp: auto-levelsstress-ng: Fused Multiply-Addsvt-av1: Preset 8 - Bosphorus 4Kdacapobench: Batik SVG Toolkitsvt-hevc: 10 - Bosphorus 1080ppgbench: 1000 - 1000 - Read Onlystress-ng: Function Callgimp: unsharp-maskdacapobench: jMonkeyEnginedacapobench: H2O In-Memory Platform For Machine Learningincompact3d: input.i3d 193 Cells Per Directionopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeospray-studio: 3 - 4K - 16 - Path Tracer - CPUdarktable: Server Room - CPU-onlystress-ng: CPU Cachestress-ng: IO_uringdacapobench: Tradebeans6.5.0-15-lowlatency6.5.0-15-generic13469.9818643347.91636.5332.02919559764.2727.6803612919340813.3296546.5375089447.323327937.3853.0632486.751672187.3077.3993556978621.35326.00314.149521912.25341014551312.180.3672721155191.89665943.712373.6044.6858.425191.27478051.553404.61704.82157.559370.0133.1636.1517876.6715.8336.0411475558.3643.04269.0645648980.4939311.855.78964979.41617354.60799265137.833180.0881656678.4633524.9220.1025870136909.8026.6620615.418.244133716.35664868.146835208116226667234865.5550238.8611.7113.5412.39411.480468.9666.3479528193718558.55680162126666724.34368417161900002276191969095551737735031275.99264943.59132403.752185888965505195923491.517.349164282.907850152467357437378.54123272546381491030.742370337.001662923.70146.266.2700.3832139928.7527452.43737520511068.6927.4716427.96385445161643.39317443372413372535956116.7905486245.6112090785.3099.662560478096851310159.480.7036040.8867596590.54452021.170123555973.6467.3931688605.07142311944601.6026.6266904403720.5615164168.85476427371.8501032723.133442148.86882329718.9420557017.78700.5129.5011855199.9329.4423396720507819.8592150.1178155878.193462526.4155.1831279.371616193.4874.9296555365663.36317.42913.779535491.60332414926322.790.3592780491196.01667342.840381.0445.5657.330194.79479461.526397.78716.72160.189216.1732.6236.7117616.7655.9136.5211325453.1543.61265.6045722201.3639793.855.1391980.33247274.55911493136.408178.2311673685.3806124.6760.1035815138204.0326.4220800.818.084134898.53659168.729535498916360000236766.0812236.9911.8013.6452.41211.562472.2865.8878986192418675.28675992139333324.21168047162766672264190969445577642159701281.79266118.69132983.372195366817335173927407.617.419164926.617879702195757647405.07122832555125446330.844371488.551668092.45146.716.2520.3821240037.3827526.13727520563515.7727.5416467.86386375161255.10318200857393371675969016.7545497771.7312115726.5199.862555478996153957159.740.7026049.3467506235.12452621.142123709386.4367.3131690605.78142453444557.5926.6466907403620.5665773168.82037427361.8501065746.513138743.689231OpenBenchmarking.org

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Socket Activity6.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KSE +/- 103.72, N = 3SE +/- 106.01, N = 313469.9829718.941. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Socket Activity6.5.0-15-lowlatency6.5.0-15-generic5K10K15K20K25KMin: 13332.5 / Avg: 13469.98 / Max: 13673.26Min: 29511.17 / Avg: 29718.94 / Max: 29859.451. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pipe6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MSE +/- 240322.92, N = 3SE +/- 54256.67, N = 318643347.9120557017.781. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pipe6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MMin: 18272158.42 / Avg: 18643347.91 / Max: 19093383.74Min: 20458609.41 / Avg: 20557017.78 / Max: 20645822.51. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: NUMA6.5.0-15-lowlatency6.5.0-15-generic150300450600750SE +/- 1.48, N = 3SE +/- 0.89, N = 3636.53700.511. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: NUMA6.5.0-15-lowlatency6.5.0-15-generic120240360480600Min: 634.4 / Avg: 636.53 / Max: 639.38Min: 698.82 / Avg: 700.51 / Max: 701.861. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh Time6.5.0-15-lowlatency6.5.0-15-generic71421283532.0329.501. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Forking6.5.0-15-lowlatency6.5.0-15-generic13K26K39K52K65KSE +/- 598.81, N = 3SE +/- 413.74, N = 359764.2755199.931. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Forking6.5.0-15-lowlatency6.5.0-15-generic10K20K30K40K50KMin: 58603.87 / Avg: 59764.27 / Max: 60601.02Min: 54517.1 / Avg: 55199.93 / Max: 55946.141. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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: 1000 - Clients: 1000 - Mode: Read Write - Average Latency6.5.0-15-lowlatency6.5.0-15-generic714212835SE +/- 0.13, N = 3SE +/- 0.14, N = 327.6829.441. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write - Average Latency6.5.0-15-lowlatency6.5.0-15-generic714212835Min: 27.49 / Avg: 27.68 / Max: 27.92Min: 29.19 / Avg: 29.44 / Max: 29.691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write6.5.0-15-lowlatency6.5.0-15-generic8K16K24K32K40KSE +/- 166.48, N = 3SE +/- 166.45, N = 336129339671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write6.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KMin: 35814.94 / Avg: 36129.36 / Max: 36381.46Min: 33683.52 / Avg: 33966.95 / Max: 34259.881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: System V Message Passing6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MSE +/- 26226.97, N = 3SE +/- 24607.27, N = 319340813.3220507819.851. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: System V Message Passing6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MMin: 19292324.55 / Avg: 19340813.32 / Max: 19382383.72Min: 20466517.79 / Avg: 20507819.85 / Max: 20551647.541. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pthread6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KSE +/- 107.61, N = 3SE +/- 18.69, N = 396546.5392150.111. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pthread6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KMin: 96337.74 / Avg: 96546.53 / Max: 96696.17Min: 92120.41 / Avg: 92150.11 / Max: 92184.611. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Semaphores6.5.0-15-lowlatency6.5.0-15-generic20M40M60M80M100MSE +/- 277504.14, N = 3SE +/- 613300.97, N = 375089447.3278155878.191. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Semaphores6.5.0-15-lowlatency6.5.0-15-generic14M28M42M56M70MMin: 74782346.1 / Avg: 75089447.32 / Max: 75643363.1Min: 76929446.06 / Avg: 78155878.19 / Max: 78786769.61. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Futex6.5.0-15-lowlatency6.5.0-15-generic700K1400K2100K2800K3500KSE +/- 41561.40, N = 12SE +/- 27733.99, N = 153327937.383462526.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Futex6.5.0-15-lowlatency6.5.0-15-generic600K1200K1800K2400K3000KMin: 3106809.52 / Avg: 3327937.38 / Max: 3518680.67Min: 3265826.2 / Avg: 3462526.41 / Max: 3599105.991. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fast6.5.0-15-lowlatency6.5.0-15-generic1224364860SE +/- 0.08, N = 3SE +/- 0.20, N = 353.0655.18
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fast6.5.0-15-lowlatency6.5.0-15-generic1122334455Min: 52.92 / Avg: 53.06 / Max: 53.2Min: 54.81 / Avg: 55.18 / Max: 55.48

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mixed Scheduler6.5.0-15-lowlatency6.5.0-15-generic7K14K21K28K35KSE +/- 34.60, N = 3SE +/- 167.10, N = 332486.7531279.371. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mixed Scheduler6.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KMin: 32434.54 / Avg: 32486.75 / Max: 32552.18Min: 31025.47 / Avg: 31279.37 / Max: 31594.531. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Tomcat6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 16.05, N = 3SE +/- 15.93, N = 316721616
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Tomcat6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1652 / Avg: 1672.33 / Max: 1704Min: 1585 / Avg: 1616.33 / Max: 1637

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 1.29, N = 13SE +/- 2.64, N = 3187.30193.481. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200Min: 178.04 / Avg: 187.3 / Max: 192.55Min: 189.16 / Avg: 193.48 / Max: 198.281. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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: Rubber O-Ring Seal Installation6.5.0-15-lowlatency6.5.0-15-generic20406080100SE +/- 0.94, N = 15SE +/- 0.57, N = 377.3974.92
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal Installation6.5.0-15-lowlatency6.5.0-15-generic1530456075Min: 75.12 / Avg: 77.39 / Max: 86.36Min: 74.17 / Avg: 74.92 / Max: 76.04

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLT6.5.0-15-lowlatency6.5.0-15-generic2004006008001000SE +/- 6.84, N = 3SE +/- 3.48, N = 3935965
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLT6.5.0-15-lowlatency6.5.0-15-generic2004006008001000Min: 928 / Avg: 935.33 / Max: 949Min: 959 / Avg: 964.67 / Max: 971

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc C String Functions6.5.0-15-lowlatency6.5.0-15-generic12M24M36M48M60MSE +/- 450311.20, N = 15SE +/- 790042.39, N = 356978621.3555365663.361. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc C String Functions6.5.0-15-lowlatency6.5.0-15-generic10M20M30M40M50MMin: 54293868.63 / Avg: 56978621.35 / Max: 59751313.46Min: 53823662.8 / Avg: 55365663.36 / Max: 56435288.231. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -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 6.1Build: allmodconfig6.5.0-15-lowlatency6.5.0-15-generic70140210280350SE +/- 0.73, N = 3SE +/- 0.85, N = 3326.00317.43
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfig6.5.0-15-lowlatency6.5.0-15-generic60120180240300Min: 325.14 / Avg: 326 / Max: 327.45Min: 316.33 / Avg: 317.43 / Max: 319.11

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: 16 - Type: Thread6.5.0-15-lowlatency6.5.0-15-generic48121620SE +/- 0.02, N = 3SE +/- 0.10, N = 314.1513.781. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Thread6.5.0-15-lowlatency6.5.0-15-generic48121620Min: 14.12 / Avg: 14.15 / Max: 14.18Min: 13.66 / Avg: 13.78 / Max: 13.981. (CC) gcc options: -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: SENDFILE6.5.0-15-lowlatency6.5.0-15-generic110K220K330K440K550KSE +/- 4199.63, N = 15SE +/- 6422.27, N = 4521912.25535491.601. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: SENDFILE6.5.0-15-lowlatency6.5.0-15-generic90K180K270K360K450KMin: 508267.89 / Avg: 521912.25 / Max: 564218.41Min: 526265.5 / Avg: 535491.6 / Max: 554033.871. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChi6.5.0-15-lowlatency6.5.0-15-generic7001400210028003500SE +/- 37.74, N = 4SE +/- 11.59, N = 334103324
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChi6.5.0-15-lowlatency6.5.0-15-generic6001200180024003000Min: 3301 / Avg: 3410 / Max: 3475Min: 3310 / Avg: 3324 / Max: 3347

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mutex6.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MSE +/- 52786.16, N = 3SE +/- 98927.59, N = 314551312.1814926322.791. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mutex6.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MMin: 14452248.01 / Avg: 14551312.18 / Max: 14632448.91Min: 14733521.93 / Avg: 14926322.79 / Max: 15061205.361. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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 Latency6.5.0-15-lowlatency6.5.0-15-generic0.08260.16520.24780.33040.413SE +/- 0.002, N = 3SE +/- 0.001, N = 30.3670.3591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency6.5.0-15-lowlatency6.5.0-15-generic12345Min: 0.36 / Avg: 0.37 / Max: 0.37Min: 0.36 / Avg: 0.36 / Max: 0.361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only6.5.0-15-lowlatency6.5.0-15-generic600K1200K1800K2400K3000KSE +/- 11767.66, N = 3SE +/- 9375.92, N = 3272115527804911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only6.5.0-15-lowlatency6.5.0-15-generic500K1000K1500K2000K2500KMin: 2704016.98 / Avg: 2721154.79 / Max: 2743693.48Min: 2767930.74 / Avg: 2780490.81 / Max: 2798829.341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 0.85, N = 3SE +/- 1.30, N = 3191.90196.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200Min: 190.67 / Avg: 191.9 / Max: 193.52Min: 193.59 / Avg: 196.02 / Max: 198.051. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image Processing6.5.0-15-lowlatency6.5.0-15-generic150300450600750SE +/- 6.74, N = 3SE +/- 6.36, N = 3659673
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image Processing6.5.0-15-lowlatency6.5.0-15-generic120240360480600Min: 649 / Avg: 659.33 / Max: 672Min: 666 / Avg: 673.33 / Max: 686

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfig6.5.0-15-lowlatency6.5.0-15-generic1020304050SE +/- 0.54, N = 4SE +/- 0.52, N = 443.7142.84
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfig6.5.0-15-lowlatency6.5.0-15-generic918273645Min: 43.13 / Avg: 43.71 / Max: 45.35Min: 42.3 / Avg: 42.84 / Max: 44.39

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic80160240320400SE +/- 0.36, N = 3SE +/- 1.09, N = 3373.60381.041. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic70140210280350Min: 373.13 / Avg: 373.6 / Max: 374.3Min: 379.51 / Avg: 381.04 / Max: 383.141. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic1020304050SE +/- 0.12, N = 3SE +/- 0.11, N = 344.6845.56MIN: 20.29 / MAX: 45.41MIN: 14.65 / MAX: 46.41
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic918273645Min: 44.45 / Avg: 44.68 / Max: 44.8Min: 45.34 / Avg: 45.56 / Max: 45.73

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time6.5.0-15-lowlatency6.5.0-15-generic1326395265SE +/- 0.02, N = 3SE +/- 0.02, N = 358.4357.331. RawTherapee, version 5.9, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time6.5.0-15-lowlatency6.5.0-15-generic1224364860Min: 58.39 / Avg: 58.43 / Max: 58.46Min: 57.3 / Avg: 57.33 / Max: 57.371. RawTherapee, version 5.9, command line.

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 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 1.84, N = 3SE +/- 0.65, N = 3191.27194.791. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200Min: 187.7 / Avg: 191.27 / Max: 193.79Min: 193.84 / Avg: 194.79 / Max: 196.041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data Framework6.5.0-15-lowlatency6.5.0-15-generic2K4K6K8K10KSE +/- 106.52, N = 3SE +/- 82.32, N = 378057946
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data Framework6.5.0-15-lowlatency6.5.0-15-generic14002800420056007000Min: 7688 / Avg: 7805.33 / Max: 8018Min: 7825 / Avg: 7945.67 / Max: 8103

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Masskrug - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic0.34940.69881.04821.39761.747SE +/- 0.007, N = 3SE +/- 0.005, N = 31.5531.526
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Masskrug - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic246810Min: 1.54 / Avg: 1.55 / Max: 1.56Min: 1.52 / Avg: 1.53 / Max: 1.53

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MEMFD6.5.0-15-lowlatency6.5.0-15-generic90180270360450SE +/- 0.36, N = 3SE +/- 0.62, N = 3404.61397.781. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MEMFD6.5.0-15-lowlatency6.5.0-15-generic70140210280350Min: 403.9 / Avg: 404.61 / Max: 405.1Min: 396.81 / Avg: 397.78 / Max: 398.941. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MMAP6.5.0-15-lowlatency6.5.0-15-generic150300450600750SE +/- 0.98, N = 3SE +/- 0.69, N = 3704.82716.721. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MMAP6.5.0-15-lowlatency6.5.0-15-generic130260390520650Min: 703.13 / Avg: 704.82 / Max: 706.51Min: 715.5 / Avg: 716.72 / Max: 717.881. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 0.41, N = 3SE +/- 0.54, N = 3157.55160.181. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic306090120150Min: 157.03 / Avg: 157.55 / Max: 158.35Min: 159.11 / Avg: 160.18 / Max: 160.861. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloning6.5.0-15-lowlatency6.5.0-15-generic2K4K6K8K10KSE +/- 19.32, N = 3SE +/- 4.93, N = 39370.019216.171. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloning6.5.0-15-lowlatency6.5.0-15-generic16003200480064008000Min: 9338.08 / Avg: 9370.01 / Max: 9404.81Min: 9208.54 / Avg: 9216.17 / Max: 9225.381. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -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: Cell Phone Drop Test6.5.0-15-lowlatency6.5.0-15-generic816243240SE +/- 0.14, N = 3SE +/- 0.05, N = 333.1632.62
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop Test6.5.0-15-lowlatency6.5.0-15-generic714212835Min: 32.95 / Avg: 33.16 / Max: 33.44Min: 32.56 / Avg: 32.62 / Max: 32.73

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic816243240SE +/- 0.13, N = 3SE +/- 0.22, N = 336.1536.71MIN: 35.07 / MAX: 36.69MIN: 35.15 / MAX: 37.53
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic816243240Min: 35.91 / Avg: 36.15 / Max: 36.34Min: 36.43 / Avg: 36.71 / Max: 37.14

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code Analyzer6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 20.47, N = 15SE +/- 17.05, N = 317871761
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code Analyzer6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1682 / Avg: 1787.27 / Max: 1938Min: 1731 / Avg: 1761.33 / Max: 1790

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 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic246810SE +/- 0.029, N = 3SE +/- 0.022, N = 36.6716.7651. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic3691215Min: 6.62 / Avg: 6.67 / Max: 6.72Min: 6.72 / Avg: 6.77 / Max: 6.791. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic1.32982.65963.98945.31926.649SE +/- 0.01, N = 3SE +/- 0.01, N = 35.835.91
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic246810Min: 5.82 / Avg: 5.83 / Max: 5.84Min: 5.9 / Avg: 5.91 / Max: 5.92

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic816243240SE +/- 0.05, N = 3SE +/- 0.06, N = 336.0436.52MIN: 21.12 / MAX: 36.53MIN: 14.8 / MAX: 37.07
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic816243240Min: 35.94 / Avg: 36.04 / Max: 36.09Min: 36.4 / Avg: 36.52 / Max: 36.6

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Context Switching6.5.0-15-lowlatency6.5.0-15-generic2M4M6M8M10MSE +/- 26060.73, N = 3SE +/- 13763.06, N = 311475558.3611325453.151. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Context Switching6.5.0-15-lowlatency6.5.0-15-generic2M4M6M8M10MMin: 11436842.7 / Avg: 11475558.36 / Max: 11525137.18Min: 11301495.94 / Avg: 11325453.15 / Max: 11349170.771. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic1020304050SE +/- 0.06, N = 3SE +/- 0.06, N = 343.0443.611. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic918273645Min: 42.93 / Avg: 43.04 / Max: 43.14Min: 43.49 / Avg: 43.61 / Max: 43.711. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix Makefiles6.5.0-15-lowlatency6.5.0-15-generic60120180240300SE +/- 0.79, N = 3SE +/- 0.71, N = 3269.06265.60
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix Makefiles6.5.0-15-lowlatency6.5.0-15-generic50100150200250Min: 267.9 / Avg: 269.06 / Max: 270.58Min: 264.49 / Avg: 265.6 / Max: 266.91

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Poll6.5.0-15-lowlatency6.5.0-15-generic1.2M2.4M3.6M4.8M6MSE +/- 1984.30, N = 3SE +/- 3278.55, N = 35648980.495722201.361. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Poll6.5.0-15-lowlatency6.5.0-15-generic1000K2000K3000K4000K5000KMin: 5645415.59 / Avg: 5648980.49 / Max: 5652273.24Min: 5718760.11 / Avg: 5722201.36 / Max: 5728755.721. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1M6.5.0-15-lowlatency6.5.0-15-generic9K18K27K36K45KSE +/- 37.63, N = 3SE +/- 57.20, N = 339311.839793.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1M6.5.0-15-lowlatency6.5.0-15-generic7K14K21K28K35KMin: 39274.2 / Avg: 39311.83 / Max: 39387.1Min: 39692 / Avg: 39793.77 / Max: 39889.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution Time6.5.0-15-lowlatency6.5.0-15-generic132639526555.7955.141. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon6.5.0-15-lowlatency6.5.0-15-generic20406080100SE +/- 0.06, N = 3SE +/- 0.11, N = 379.4280.33MIN: 78.74 / MAX: 80.49MIN: 79.52 / MAX: 81.9
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon6.5.0-15-lowlatency6.5.0-15-generic1530456075Min: 79.32 / Avg: 79.42 / Max: 79.52Min: 80.13 / Avg: 80.33 / Max: 80.5

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: FOP Print Formatter6.5.0-15-lowlatency6.5.0-15-generic160320480640800SE +/- 7.10, N = 12SE +/- 5.69, N = 10735727
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: FOP Print Formatter6.5.0-15-lowlatency6.5.0-15-generic130260390520650Min: 659 / Avg: 734.83 / Max: 749Min: 681 / Avg: 727.2 / Max: 742

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction6.5.0-15-lowlatency6.5.0-15-generic1.03682.07363.11044.14725.184SE +/- 0.04467137, N = 3SE +/- 0.01890146, N = 34.607992654.559114931. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction6.5.0-15-lowlatency6.5.0-15-generic246810Min: 4.52 / Avg: 4.61 / Max: 4.67Min: 4.53 / Avg: 4.56 / Max: 4.591. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To Compile6.5.0-15-lowlatency6.5.0-15-generic306090120150SE +/- 0.10, N = 3SE +/- 0.33, N = 3137.83136.41
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To Compile6.5.0-15-lowlatency6.5.0-15-generic306090120150Min: 137.64 / Avg: 137.83 / Max: 137.94Min: 136.02 / Avg: 136.41 / Max: 137.06

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninja6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 0.11, N = 3SE +/- 0.14, N = 3180.09178.23
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninja6.5.0-15-lowlatency6.5.0-15-generic306090120150Min: 179.97 / Avg: 180.09 / Max: 180.3Min: 178 / Avg: 178.23 / Max: 178.48

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Engine6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 8.72, N = 3SE +/- 6.57, N = 316561673
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Engine6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1640 / Avg: 1656 / Max: 1670Min: 1660 / Avg: 1672.67 / Max: 1682

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Time6.5.0-15-lowlatency6.5.0-15-generic150300450600750678.46685.381. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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: Process6.5.0-15-lowlatency6.5.0-15-generic612182430SE +/- 0.05, N = 3SE +/- 0.04, N = 324.9224.681. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: Process6.5.0-15-lowlatency6.5.0-15-generic612182430Min: 24.87 / Avg: 24.92 / Max: 25.02Min: 24.63 / Avg: 24.68 / Max: 24.751. (CC) gcc options: -lpthread

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Rack - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic0.02320.04640.06960.09280.116SE +/- 0.001, N = 3SE +/- 0.001, N = 40.1020.103
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Rack - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic12345Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.11

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Cassandra6.5.0-15-lowlatency6.5.0-15-generic13002600390052006500SE +/- 54.23, N = 3SE +/- 5.51, N = 358705815
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Cassandra6.5.0-15-lowlatency6.5.0-15-generic10002000300040005000Min: 5798 / Avg: 5869.67 / Max: 5976Min: 5804 / Avg: 5815 / Max: 5821

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Crypto6.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KSE +/- 1011.54, N = 3SE +/- 71.78, N = 3136909.80138204.031. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Crypto6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KMin: 134935.2 / Avg: 136909.8 / Max: 138278.33Min: 138080.8 / Avg: 138204.03 / Max: 138329.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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 4.0Blend File: BMW27 - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic612182430SE +/- 0.17, N = 3SE +/- 0.04, N = 326.6626.42
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic612182430Min: 26.45 / Avg: 26.66 / Max: 27.01Min: 26.37 / Avg: 26.42 / Max: 26.5

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1M6.5.0-15-lowlatency6.5.0-15-generic4K8K12K16K20KSE +/- 12.05, N = 3SE +/- 11.59, N = 320615.420800.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1M6.5.0-15-lowlatency6.5.0-15-generic4K8K12K16K20KMin: 20591.8 / Avg: 20615.43 / Max: 20631.3Min: 20782.2 / Avg: 20800.83 / Max: 20822.11. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: rotate6.5.0-15-lowlatency6.5.0-15-generic48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 318.2418.08
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: rotate6.5.0-15-lowlatency6.5.0-15-generic510152025Min: 18.23 / Avg: 18.24 / Max: 18.27Min: 18.08 / Avg: 18.08 / Max: 18.09

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating Point6.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KSE +/- 193.55, N = 3SE +/- 255.73, N = 3133716.35134898.531. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating Point6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KMin: 133435.87 / Avg: 133716.35 / Max: 134087.64Min: 134629.34 / Avg: 134898.53 / Max: 135409.751. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Jython6.5.0-15-lowlatency6.5.0-15-generic14002800420056007000SE +/- 31.18, N = 3SE +/- 40.48, N = 366486591
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Jython6.5.0-15-lowlatency6.5.0-15-generic12002400360048006000Min: 6593 / Avg: 6647.67 / Max: 6701Min: 6537 / Avg: 6590.67 / Max: 6670

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon Obj6.5.0-15-lowlatency6.5.0-15-generic1530456075SE +/- 0.02, N = 3SE +/- 0.02, N = 368.1568.73MIN: 67.57 / MAX: 69MIN: 68.21 / MAX: 69.63
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon Obj6.5.0-15-lowlatency6.5.0-15-generic1326395265Min: 68.11 / Avg: 68.15 / Max: 68.17Min: 68.69 / Avg: 68.73 / Max: 68.76

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Rating6.5.0-15-lowlatency6.5.0-15-generic80K160K240K320K400KSE +/- 164.55, N = 3SE +/- 229.06, N = 33520813549891. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Rating6.5.0-15-lowlatency6.5.0-15-generic60K120K180K240K300KMin: 351891 / Avg: 352081.33 / Max: 352409Min: 354558 / Avg: 354989 / Max: 3553391. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS26.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MSE +/- 8819.17, N = 3SE +/- 11547.01, N = 316226667163600001. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS26.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MMin: 16210000 / Avg: 16226666.67 / Max: 16240000Min: 16340000 / Avg: 16360000 / Max: 163800001. (CXX) g++ options: -fopenmp -O3 -march=native

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring Boot6.5.0-15-lowlatency6.5.0-15-generic5001000150020002500SE +/- 24.10, N = 3SE +/- 21.57, N = 323482367
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring Boot6.5.0-15-lowlatency6.5.0-15-generic400800120016002000Min: 2302 / Avg: 2348.33 / Max: 2383Min: 2333 / Avg: 2367 / Max: 2407

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Crown6.5.0-15-lowlatency6.5.0-15-generic1530456075SE +/- 0.11, N = 3SE +/- 0.08, N = 365.5666.08MIN: 64.4 / MAX: 67.95MIN: 64.99 / MAX: 68.67
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Crown6.5.0-15-lowlatency6.5.0-15-generic1326395265Min: 65.36 / Avg: 65.56 / Max: 65.76Min: 65.96 / Avg: 66.08 / Max: 66.24

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 4.0Blend File: Barbershop - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic50100150200250SE +/- 0.10, N = 3SE +/- 0.07, N = 3238.86236.99
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic4080120160200Min: 238.69 / Avg: 238.86 / Max: 239.03Min: 236.87 / Avg: 236.99 / Max: 237.11

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic3691215SE +/- 0.02, N = 3SE +/- 0.03, N = 311.7111.801. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic3691215Min: 11.66 / Avg: 11.71 / Max: 11.74Min: 11.77 / Avg: 11.8 / Max: 11.851. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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: 16 - Type: Process6.5.0-15-lowlatency6.5.0-15-generic48121620SE +/- 0.05, N = 3SE +/- 0.09, N = 313.5413.651. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Process6.5.0-15-lowlatency6.5.0-15-generic48121620Min: 13.44 / Avg: 13.54 / Max: 13.6Min: 13.46 / Avg: 13.64 / Max: 13.741. (CC) gcc options: -lpthread

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Boat - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic0.54271.08541.62812.17082.7135SE +/- 0.012, N = 3SE +/- 0.014, N = 32.3942.412
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Boat - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic246810Min: 2.37 / Avg: 2.39 / Max: 2.41Min: 2.4 / Avg: 2.41 / Max: 2.44

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Faster6.5.0-15-lowlatency6.5.0-15-generic3691215SE +/- 0.03, N = 3SE +/- 0.01, N = 311.4811.561. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Faster6.5.0-15-lowlatency6.5.0-15-generic3691215Min: 11.44 / Avg: 11.48 / Max: 11.54Min: 11.55 / Avg: 11.56 / Max: 11.581. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVL Tree6.5.0-15-lowlatency6.5.0-15-generic100200300400500SE +/- 0.35, N = 3SE +/- 0.14, N = 3468.96472.281. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVL Tree6.5.0-15-lowlatency6.5.0-15-generic80160240320400Min: 468.35 / Avg: 468.96 / Max: 469.56Min: 472.11 / Avg: 472.28 / Max: 472.551. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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 4.0Blend File: Classroom - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic1530456075SE +/- 0.09, N = 3SE +/- 0.04, N = 366.3465.88
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-Only6.5.0-15-lowlatency6.5.0-15-generic1326395265Min: 66.21 / Avg: 66.34 / Max: 66.52Min: 65.81 / Avg: 65.88 / Max: 65.94

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KSE +/- 130.78, N = 3SE +/- 56.83, N = 37952878986
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic14K28K42K56K70KMin: 79336 / Avg: 79528.33 / Max: 79778Min: 78873 / Avg: 78985.67 / Max: 79055

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 0.33, N = 3SE +/- 1.86, N = 319371924
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1937 / Avg: 1937.33 / Max: 1938Min: 1922 / Avg: 1924.33 / Max: 1928

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating Point6.5.0-15-lowlatency6.5.0-15-generic4K8K12K16K20KSE +/- 28.95, N = 3SE +/- 1.33, N = 318558.5518675.281. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating Point6.5.0-15-lowlatency6.5.0-15-generic3K6K9K12K15KMin: 18525.36 / Avg: 18558.55 / Max: 18616.23Min: 18672.82 / Avg: 18675.28 / Max: 18677.41. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic15K30K45K60K75KSE +/- 79.50, N = 3SE +/- 177.83, N = 36801667599
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic12K24K36K48K60KMin: 67902 / Avg: 68016 / Max: 68169Min: 67289 / Avg: 67598.67 / Max: 67905

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P16.5.0-15-lowlatency6.5.0-15-generic5M10M15M20M25MSE +/- 8819.17, N = 3SE +/- 46308.15, N = 321266667213933331. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P16.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MMin: 21250000 / Avg: 21266666.67 / Max: 21280000Min: 21310000 / Avg: 21393333.33 / Max: 214700001. (CXX) g++ options: -fopenmp -O3 -march=native

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: resize6.5.0-15-lowlatency6.5.0-15-generic612182430SE +/- 0.12, N = 3SE +/- 0.03, N = 324.3424.21
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: resize6.5.0-15-lowlatency6.5.0-15-generic612182430Min: 24.1 / Avg: 24.34 / Max: 24.47Min: 24.18 / Avg: 24.21 / Max: 24.27

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic15K30K45K60K75KSE +/- 67.71, N = 3SE +/- 146.08, N = 36841768047
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic12K24K36K48K60KMin: 68345 / Avg: 68416.67 / Max: 68552Min: 67792 / Avg: 68047 / Max: 68298

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P26.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MSE +/- 15275.25, N = 3SE +/- 3333.33, N = 316190000162766671. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P26.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MMin: 16170000 / Avg: 16190000 / Max: 16220000Min: 16270000 / Avg: 16276666.67 / Max: 162800001. (CXX) g++ options: -fopenmp -O3 -march=native

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic5001000150020002500SE +/- 1.20, N = 3SE +/- 0.58, N = 322762264
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic400800120016002000Min: 2274 / Avg: 2276.33 / Max: 2278Min: 2263 / Avg: 2264 / Max: 2265

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 0.67, N = 3SE +/- 0.33, N = 319191909
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1918 / Avg: 1919.33 / Max: 1920Min: 1909 / Avg: 1909.33 / Max: 1910

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation Framework6.5.0-15-lowlatency6.5.0-15-generic15003000450060007500SE +/- 4.91, N = 3SE +/- 11.46, N = 369096944
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation Framework6.5.0-15-lowlatency6.5.0-15-generic12002400360048006000Min: 6899 / Avg: 6908.67 / Max: 6915Min: 6921 / Avg: 6943.67 / Max: 6958

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCM6.5.0-15-lowlatency6.5.0-15-generic120000M240000M360000M480000M600000MSE +/- 875380897.88, N = 3SE +/- 591990057.48, N = 35551737735035577642159701. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCM6.5.0-15-lowlatency6.5.0-15-generic100000M200000M300000M400000M500000MMin: 553785062470 / Avg: 555173773503.33 / Max: 556791430920Min: 556646425400 / Avg: 557764215970 / Max: 5586611421201. (CC) gcc options: -pthread -m64 -O3 -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc Qsort Data Sorting6.5.0-15-lowlatency6.5.0-15-generic30060090012001500SE +/- 1.18, N = 3SE +/- 0.29, N = 31275.991281.791. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc Qsort Data Sorting6.5.0-15-lowlatency6.5.0-15-generic2004006008001000Min: 1273.64 / Avg: 1275.99 / Max: 1277.4Min: 1281.32 / Avg: 1281.79 / Max: 1282.311. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix Math6.5.0-15-lowlatency6.5.0-15-generic60K120K180K240K300KSE +/- 606.41, N = 3SE +/- 1059.88, N = 3264943.59266118.691. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix Math6.5.0-15-lowlatency6.5.0-15-generic50K100K150K200K250KMin: 263740.47 / Avg: 264943.59 / Max: 265677.76Min: 264353.53 / Avg: 266118.69 / Max: 268017.721. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Stress6.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KSE +/- 26.52, N = 3SE +/- 26.95, N = 3132403.75132983.371. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Stress6.5.0-15-lowlatency6.5.0-15-generic20K40K60K80K100KMin: 132358.72 / Avg: 132403.75 / Max: 132450.55Min: 132935.55 / Avg: 132983.37 / Max: 133028.831. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly13056.5.0-15-lowlatency6.5.0-15-generic50000M100000M150000M200000M250000MSE +/- 47929208.90, N = 3SE +/- 42805654.09, N = 32185888965502195366817331. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly13056.5.0-15-lowlatency6.5.0-15-generic40000M80000M120000M160000M200000MMin: 218537508860 / Avg: 218588896550 / Max: 218684669680Min: 219451441150 / Avg: 219536681733.33 / Max: 2195861943601. (CC) gcc options: -pthread -m64 -O3 -ldl

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Kafka6.5.0-15-lowlatency6.5.0-15-generic11002200330044005500SE +/- 7.75, N = 3SE +/- 33.17, N = 351955173
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Kafka6.5.0-15-lowlatency6.5.0-15-generic9001800270036004500Min: 5180 / Avg: 5195.33 / Max: 5205Min: 5107 / Avg: 5173.33 / Max: 5207

OpenSSL

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

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA40966.5.0-15-lowlatency6.5.0-15-generic200K400K600K800K1000KSE +/- 75.90, N = 3SE +/- 118.84, N = 3923491.5927407.61. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA40966.5.0-15-lowlatency6.5.0-15-generic160K320K480K640K800KMin: 923381 / Avg: 923491.53 / Max: 923636.9Min: 927239.5 / Avg: 927407.63 / Max: 927637.21. (CC) gcc options: -pthread -m64 -O3 -ldl

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Fast6.5.0-15-lowlatency6.5.0-15-generic48121620SE +/- 0.02, N = 3SE +/- 0.08, N = 317.3517.421. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Fast6.5.0-15-lowlatency6.5.0-15-generic48121620Min: 17.33 / Avg: 17.35 / Max: 17.39Min: 17.28 / Avg: 17.42 / Max: 17.551. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

nginx

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

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 5006.5.0-15-lowlatency6.5.0-15-generic40K80K120K160K200KSE +/- 1947.02, N = 3SE +/- 1636.08, N = 3164282.90164926.611. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 5006.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KMin: 161506.63 / Avg: 164282.9 / Max: 168035.76Min: 162044.83 / Avg: 164926.61 / Max: 167709.811. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA2566.5.0-15-lowlatency6.5.0-15-generic20000M40000M60000M80000M100000MSE +/- 42796422.99, N = 3SE +/- 30370906.26, N = 378501524673787970219571. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA2566.5.0-15-lowlatency6.5.0-15-generic14000M28000M42000M56000M70000MMin: 78439230750 / Avg: 78501524673.33 / Max: 78583506680Min: 78737286070 / Avg: 78797021956.67 / Max: 788364237201. (CC) gcc options: -pthread -m64 -O3 -ldl

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradesoap6.5.0-15-lowlatency6.5.0-15-generic12002400360048006000SE +/- 2.03, N = 3SE +/- 65.05, N = 357435764
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradesoap6.5.0-15-lowlatency6.5.0-15-generic10002000300040005000Min: 5740 / Avg: 5743.33 / Max: 5747Min: 5636 / Avg: 5764.33 / Max: 5847

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Zlib6.5.0-15-lowlatency6.5.0-15-generic16003200480064008000SE +/- 2.46, N = 3SE +/- 10.81, N = 37378.547405.071. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Zlib6.5.0-15-lowlatency6.5.0-15-generic13002600390052006500Min: 7375.37 / Avg: 7378.54 / Max: 7383.38Min: 7384.22 / Avg: 7405.07 / Max: 7420.431. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Eclipse6.5.0-15-lowlatency6.5.0-15-generic3K6K9K12K15KSE +/- 58.89, N = 3SE +/- 45.35, N = 31232712283
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Eclipse6.5.0-15-lowlatency6.5.0-15-generic2K4K6K8K10KMin: 12213 / Avg: 12327.33 / Max: 12409Min: 12210 / Avg: 12282.67 / Max: 12366

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA5126.5.0-15-lowlatency6.5.0-15-generic5000M10000M15000M20000M25000MSE +/- 3067863.29, N = 3SE +/- 745050.04, N = 325463814910255512544631. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA5126.5.0-15-lowlatency6.5.0-15-generic4000M8000M12000M16000M20000MMin: 25459343270 / Avg: 25463814910 / Max: 25469689230Min: 25550213570 / Avg: 25551254463.33 / Max: 255526983301. (CC) gcc options: -pthread -m64 -O3 -ldl

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Faster6.5.0-15-lowlatency6.5.0-15-generic714212835SE +/- 0.07, N = 3SE +/- 0.03, N = 330.7430.841. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Faster6.5.0-15-lowlatency6.5.0-15-generic714212835Min: 30.66 / Avg: 30.74 / Max: 30.88Min: 30.79 / Avg: 30.84 / Max: 30.891. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Math6.5.0-15-lowlatency6.5.0-15-generic80K160K240K320K400KSE +/- 75.87, N = 3SE +/- 144.39, N = 3370337.00371488.551. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Math6.5.0-15-lowlatency6.5.0-15-generic60K120K180K240K300KMin: 370190.66 / Avg: 370337 / Max: 370444.92Min: 371200.23 / Avg: 371488.55 / Max: 371646.731. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Math6.5.0-15-lowlatency6.5.0-15-generic400K800K1200K1600K2000KSE +/- 364.98, N = 3SE +/- 151.71, N = 31662923.701668092.451. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Math6.5.0-15-lowlatency6.5.0-15-generic300K600K900K1200K1500KMin: 1662203.4 / Avg: 1662923.7 / Max: 1663386.38Min: 1667789.33 / Avg: 1668092.45 / Max: 1668255.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -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: Bird Strike on Windshield6.5.0-15-lowlatency6.5.0-15-generic306090120150SE +/- 0.59, N = 3SE +/- 1.10, N = 3146.26146.71
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on Windshield6.5.0-15-lowlatency6.5.0-15-generic306090120150Min: 145.32 / Avg: 146.26 / Max: 147.35Min: 145 / Avg: 146.71 / Max: 148.77

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Fast6.5.0-15-lowlatency6.5.0-15-generic246810SE +/- 0.009, N = 3SE +/- 0.036, N = 36.2706.2521. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Fast6.5.0-15-lowlatency6.5.0-15-generic3691215Min: 6.25 / Avg: 6.27 / Max: 6.28Min: 6.18 / Avg: 6.25 / Max: 6.31. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms6.5.0-15-lowlatency6.5.0-15-generic0.08620.17240.25860.34480.431SE +/- 0.00028, N = 3SE +/- 0.00139, N = 30.383210.38212
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms6.5.0-15-lowlatency6.5.0-15-generic12345Min: 0.38 / Avg: 0.38 / Max: 0.38Min: 0.38 / Avg: 0.38 / Max: 0.38

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shuffle6.5.0-15-lowlatency6.5.0-15-generic9K18K27K36K45KSE +/- 1.05, N = 3SE +/- 0.49, N = 339928.7540037.381. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shuffle6.5.0-15-lowlatency6.5.0-15-generic7K14K21K28K35KMin: 39927.03 / Avg: 39928.75 / Max: 39930.64Min: 40036.42 / Avg: 40037.38 / Max: 40038.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenSSL

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

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA40966.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KSE +/- 12.12, N = 3SE +/- 11.43, N = 327452.427526.11. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA40966.5.0-15-lowlatency6.5.0-15-generic5K10K15K20K25KMin: 27430.4 / Avg: 27452.4 / Max: 27472.2Min: 27509.8 / Avg: 27526.07 / Max: 27548.11. (CC) gcc options: -pthread -m64 -O3 -ldl

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic8K16K24K32K40KSE +/- 91.85, N = 3SE +/- 250.73, N = 33737537275
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KMin: 37192 / Avg: 37375.33 / Max: 37477Min: 36832 / Avg: 37275 / Max: 37700

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: x86_64 RdRand6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MSE +/- 529.91, N = 3SE +/- 779.64, N = 320511068.6920563515.771. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: x86_64 RdRand6.5.0-15-lowlatency6.5.0-15-generic4M8M12M16M20MMin: 20510262.25 / Avg: 20511068.69 / Max: 20512067.43Min: 20561959.27 / Avg: 20563515.77 / Max: 20564374.651. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -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 3.4Video Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic612182430SE +/- 0.07, N = 3SE +/- 0.11, N = 327.4727.541. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic612182430Min: 27.33 / Avg: 27.47 / Max: 27.57Min: 27.34 / Avg: 27.54 / Max: 27.731. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Memory Copying6.5.0-15-lowlatency6.5.0-15-generic4K8K12K16K20KSE +/- 0.69, N = 3SE +/- 5.49, N = 316427.9616467.861. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Memory Copying6.5.0-15-lowlatency6.5.0-15-generic3K6K9K12K15KMin: 16426.79 / Avg: 16427.96 / Max: 16429.18Min: 16457.22 / Avg: 16467.86 / Max: 16475.51. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Rating6.5.0-15-lowlatency6.5.0-15-generic80K160K240K320K400KSE +/- 71.67, N = 3SE +/- 213.86, N = 33854453863751. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Rating6.5.0-15-lowlatency6.5.0-15-generic70K140K210K280K350KMin: 385365 / Avg: 385445 / Max: 385588Min: 386096 / Avg: 386374.67 / Max: 3867951. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

nginx

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

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 10006.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KSE +/- 2020.85, N = 3SE +/- 562.98, N = 3161643.39161255.101. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 10006.5.0-15-lowlatency6.5.0-15-generic30K60K90K120K150KMin: 158158.07 / Avg: 161643.39 / Max: 165158.31Min: 160155.47 / Avg: 161255.1 / Max: 162014.571. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha206.5.0-15-lowlatency6.5.0-15-generic70000M140000M210000M280000M350000MSE +/- 25916007.30, N = 3SE +/- 6879596.46, N = 33174433724133182008573931. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha206.5.0-15-lowlatency6.5.0-15-generic60000M120000M180000M240000M300000MMin: 317393686710 / Avg: 317443372413.33 / Max: 317480998710Min: 318187099200 / Avg: 318200857393.33 / Max: 3182078801201. (CC) gcc options: -pthread -m64 -O3 -ldl

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic8K16K24K32K40KSE +/- 165.13, N = 3SE +/- 73.06, N = 33725337167
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic6K12K18K24K30KMin: 36996 / Avg: 37252.67 / Max: 37561Min: 37021 / Avg: 37167 / Max: 37245

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 Write6.5.0-15-lowlatency6.5.0-15-generic13K26K39K52K65KSE +/- 161.98, N = 3SE +/- 139.98, N = 359561596901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write6.5.0-15-lowlatency6.5.0-15-generic10K20K30K40K50KMin: 59254.92 / Avg: 59560.72 / Max: 59806.23Min: 59454.59 / Avg: 59689.99 / Max: 59938.941. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency6.5.0-15-lowlatency6.5.0-15-generic48121620SE +/- 0.05, N = 3SE +/- 0.04, N = 316.7916.751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency6.5.0-15-lowlatency6.5.0-15-generic48121620Min: 16.72 / Avg: 16.79 / Max: 16.88Min: 16.68 / Avg: 16.75 / Max: 16.821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNI6.5.0-15-lowlatency6.5.0-15-generic1.2M2.4M3.6M4.8M6MSE +/- 671.99, N = 3SE +/- 3126.14, N = 35486245.615497771.731. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNI6.5.0-15-lowlatency6.5.0-15-generic1000K2000K3000K4000K5000KMin: 5484962.32 / Avg: 5486245.61 / Max: 5487233.07Min: 5491521.6 / Avg: 5497771.73 / Max: 5501039.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Hash6.5.0-15-lowlatency6.5.0-15-generic3M6M9M12M15MSE +/- 1010.49, N = 3SE +/- 2649.18, N = 312090785.3012115726.511. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Hash6.5.0-15-lowlatency6.5.0-15-generic2M4M6M8M10MMin: 12088991.25 / Avg: 12090785.3 / Max: 12092488.11Min: 12110563.68 / Avg: 12115726.51 / Max: 12119339.091. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic20406080100SE +/- 0.02, N = 3SE +/- 0.02, N = 399.6699.86
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-506.5.0-15-lowlatency6.5.0-15-generic20406080100Min: 99.63 / Avg: 99.66 / Max: 99.7Min: 99.84 / Avg: 99.86 / Max: 99.9

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database Engine6.5.0-15-lowlatency6.5.0-15-generic5001000150020002500SE +/- 6.81, N = 3SE +/- 20.81, N = 325602555
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database Engine6.5.0-15-lowlatency6.5.0-15-generic400800120016002000Min: 2550 / Avg: 2560 / Max: 2573Min: 2520 / Avg: 2555 / Max: 2592

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCM6.5.0-15-lowlatency6.5.0-15-generic100000M200000M300000M400000M500000MSE +/- 183215368.38, N = 3SE +/- 708194585.39, N = 34780968513104789961539571. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCM6.5.0-15-lowlatency6.5.0-15-generic80000M160000M240000M320000M400000MMin: 477857163950 / Avg: 478096851310 / Max: 478456728510Min: 477636768560 / Avg: 478996153956.67 / Max: 4800203350001. (CC) gcc options: -pthread -m64 -O3 -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Atomic6.5.0-15-lowlatency6.5.0-15-generic4080120160200SE +/- 0.32, N = 3SE +/- 0.17, N = 3159.48159.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Atomic6.5.0-15-lowlatency6.5.0-15-generic306090120150Min: 158.84 / Avg: 159.48 / Max: 159.87Min: 159.47 / Avg: 159.74 / Max: 160.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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: 1000 - Clients: 1000 - Mode: Read Only - Average Latency6.5.0-15-lowlatency6.5.0-15-generic0.15820.31640.47460.63280.791SE +/- 0.003, N = 3SE +/- 0.003, N = 30.7030.7021. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average Latency6.5.0-15-lowlatency6.5.0-15-generic246810Min: 0.7 / Avg: 0.7 / Max: 0.71Min: 0.7 / Avg: 0.7 / Max: 0.711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D Math6.5.0-15-lowlatency6.5.0-15-generic13002600390052006500SE +/- 4.25, N = 3SE +/- 4.59, N = 36040.886049.341. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D Math6.5.0-15-lowlatency6.5.0-15-generic11002200330044005500Min: 6032.39 / Avg: 6040.88 / Max: 6045.3Min: 6043.54 / Avg: 6049.34 / Max: 6058.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Malloc6.5.0-15-lowlatency6.5.0-15-generic14M28M42M56M70MSE +/- 184967.23, N = 3SE +/- 55877.51, N = 367596590.5467506235.121. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Malloc6.5.0-15-lowlatency6.5.0-15-generic12M24M36M48M60MMin: 67226999.75 / Avg: 67596590.54 / Max: 67795192.38Min: 67412509.48 / Avg: 67506235.12 / Max: 67605809.581. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Index6.5.0-15-lowlatency6.5.0-15-generic10002000300040005000SE +/- 19.43, N = 3SE +/- 49.74, N = 445204526
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Index6.5.0-15-lowlatency6.5.0-15-generic8001600240032004000Min: 4495 / Avg: 4519.67 / Max: 4558Min: 4458 / Avg: 4525.5 / Max: 4671

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: auto-levels6.5.0-15-lowlatency6.5.0-15-generic510152025SE +/- 0.08, N = 3SE +/- 0.07, N = 321.1721.14
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: auto-levels6.5.0-15-lowlatency6.5.0-15-generic510152025Min: 21 / Avg: 21.17 / Max: 21.27Min: 21.03 / Avg: 21.14 / Max: 21.27

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-Add6.5.0-15-lowlatency6.5.0-15-generic30M60M90M120M150MSE +/- 236978.02, N = 3SE +/- 720348.50, N = 3123555973.64123709386.431. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-Add6.5.0-15-lowlatency6.5.0-15-generic20M40M60M80M100MMin: 123082122.83 / Avg: 123555973.64 / Max: 123801547.82Min: 122285322.23 / Avg: 123709386.43 / Max: 124610460.171. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic1530456075SE +/- 0.25, N = 3SE +/- 0.04, N = 367.3967.311. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4K6.5.0-15-lowlatency6.5.0-15-generic1326395265Min: 66.95 / Avg: 67.39 / Max: 67.8Min: 67.27 / Avg: 67.31 / Max: 67.41. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Batik SVG Toolkit6.5.0-15-lowlatency6.5.0-15-generic400800120016002000SE +/- 6.96, N = 3SE +/- 19.19, N = 316881690
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Batik SVG Toolkit6.5.0-15-lowlatency6.5.0-15-generic30060090012001500Min: 1675 / Avg: 1687.67 / Max: 1699Min: 1669 / Avg: 1689.67 / Max: 1728

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic130260390520650SE +/- 3.00, N = 3SE +/- 4.86, N = 15605.07605.781. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p6.5.0-15-lowlatency6.5.0-15-generic110220330440550Min: 600 / Avg: 605.07 / Max: 610.38Min: 583.66 / Avg: 605.78 / Max: 643.091. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only6.5.0-15-lowlatency6.5.0-15-generic300K600K900K1200K1500KSE +/- 6639.24, N = 3SE +/- 6376.04, N = 3142311914245341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only6.5.0-15-lowlatency6.5.0-15-generic200K400K600K800K1000KMin: 1410726.43 / Avg: 1423119.02 / Max: 1433445.23Min: 1414549.91 / Avg: 1424534.25 / Max: 1436396.371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Function Call6.5.0-15-lowlatency6.5.0-15-generic10K20K30K40K50KSE +/- 14.17, N = 3SE +/- 201.97, N = 344601.6044557.591. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Function Call6.5.0-15-lowlatency6.5.0-15-generic8K16K24K32K40KMin: 44577.09 / Avg: 44601.6 / Max: 44626.16Min: 44154.52 / Avg: 44557.59 / Max: 44782.021. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: unsharp-mask6.5.0-15-lowlatency6.5.0-15-generic612182430SE +/- 0.11, N = 3SE +/- 0.10, N = 326.6326.65
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: unsharp-mask6.5.0-15-lowlatency6.5.0-15-generic612182430Min: 26.43 / Avg: 26.63 / Max: 26.79Min: 26.46 / Avg: 26.65 / Max: 26.8

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngine6.5.0-15-lowlatency6.5.0-15-generic15003000450060007500SE +/- 1.20, N = 3SE +/- 1.86, N = 369046907
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngine6.5.0-15-lowlatency6.5.0-15-generic12002400360048006000Min: 6902 / Avg: 6903.67 / Max: 6906Min: 6903 / Avg: 6906.67 / Max: 6909

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2O In-Memory Platform For Machine Learning6.5.0-15-lowlatency6.5.0-15-generic9001800270036004500SE +/- 37.89, N = 3SE +/- 38.17, N = 340374036
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2O In-Memory Platform For Machine Learning6.5.0-15-lowlatency6.5.0-15-generic7001400210028003500Min: 3961 / Avg: 4036.67 / Max: 4078Min: 3960 / Avg: 4036.33 / Max: 4075

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction6.5.0-15-lowlatency6.5.0-15-generic510152025SE +/- 0.01, N = 3SE +/- 0.10, N = 320.5620.571. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction6.5.0-15-lowlatency6.5.0-15-generic510152025Min: 20.54 / Avg: 20.56 / Max: 20.58Min: 20.44 / Avg: 20.57 / Max: 20.761. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Time6.5.0-15-lowlatency6.5.0-15-generic4080120160200168.85168.821. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic9K18K27K36K45KSE +/- 168.90, N = 3SE +/- 298.50, N = 34273742736
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU6.5.0-15-lowlatency6.5.0-15-generic7K14K21K28K35KMin: 42405 / Avg: 42737 / Max: 42957Min: 42139 / Avg: 42736 / Max: 43035

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Room - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic0.41630.83261.24891.66522.0815SE +/- 0.007, N = 3SE +/- 0.002, N = 31.8501.850
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Room - Acceleration: CPU-only6.5.0-15-lowlatency6.5.0-15-generic246810Min: 1.84 / Avg: 1.85 / Max: 1.86Min: 1.85 / Avg: 1.85 / Max: 1.86

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Cache6.5.0-15-lowlatency6.5.0-15-generic200K400K600K800K1000KSE +/- 21496.63, N = 15SE +/- 18757.84, N = 151032723.131065746.511. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Cache6.5.0-15-lowlatency6.5.0-15-generic200K400K600K800K1000KMin: 851294.71 / Avg: 1032723.13 / Max: 1200681.11Min: 941185.93 / Avg: 1065746.51 / Max: 1163193.811. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: IO_uring6.5.0-15-lowlatency6.5.0-15-generic700K1400K2100K2800K3500KSE +/- 51499.17, N = 15SE +/- 198534.21, N = 123442148.863138743.681. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: IO_uring6.5.0-15-lowlatency6.5.0-15-generic600K1200K1800K2400K3000KMin: 2795705.7 / Avg: 3442148.86 / Max: 3530317.17Min: 1045122.79 / Avg: 3138743.68 / Max: 3465237.391. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz

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

6.5.0-15-lowlatency: The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

6.5.0-15-generic: The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradebeans6.5.0-15-lowlatency6.5.0-15-generic2K4K6K8K10KSE +/- 165.10, N = 12SE +/- 19.60, N = 388239231
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradebeans6.5.0-15-lowlatency6.5.0-15-generic16003200480064008000Min: 7803 / Avg: 8823.17 / Max: 10009Min: 9201 / Avg: 9231.33 / Max: 9268

148 Results Shown

Stress-NG:
  Socket Activity
  Pipe
  NUMA
OpenFOAM
Stress-NG
PostgreSQL:
  1000 - 1000 - Read Write - Average Latency
  1000 - 1000 - Read Write
Stress-NG:
  System V Message Passing
  Pthread
  Semaphores
  Futex
uvg266
Stress-NG
DaCapo Benchmark
SVT-HEVC
OpenRadioss
DaCapo Benchmark
Stress-NG
Timed Linux Kernel Compilation
Hackbench
Stress-NG
DaCapo Benchmark
Stress-NG
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
SVT-AV1
DaCapo Benchmark
Timed Linux Kernel Compilation
SVT-HEVC
PyTorch
RawTherapee
SVT-AV1
DaCapo Benchmark
Darktable
Stress-NG:
  MEMFD
  MMAP
SVT-HEVC
Stress-NG
OpenRadioss
PyTorch
DaCapo Benchmark
SVT-AV1
TensorFlow
PyTorch
Stress-NG
SVT-HEVC
Timed LLVM Compilation
Stress-NG
Xmrig
OpenFOAM
Embree
DaCapo Benchmark
Xcompact3d Incompact3d
Timed Godot Game Engine Compilation
Timed LLVM Compilation
DaCapo Benchmark
OpenFOAM
Hackbench
Darktable
DaCapo Benchmark
Stress-NG
Blender
Xmrig
GIMP
Stress-NG
DaCapo Benchmark
Embree
7-Zip Compression
Quicksilver
DaCapo Benchmark
Embree
Blender
SVT-HEVC
Hackbench
Darktable
VVenC
Stress-NG
Blender
OSPRay Studio:
  3 - 4K - 32 - Path Tracer - CPU
  2 - 4K - 1 - Path Tracer - CPU
Stress-NG
OSPRay Studio
Quicksilver
GIMP
OSPRay Studio
Quicksilver
OSPRay Studio:
  3 - 4K - 1 - Path Tracer - CPU
  1 - 4K - 1 - Path Tracer - CPU
DaCapo Benchmark
OpenSSL
Stress-NG:
  Glibc Qsort Data Sorting
  Matrix Math
  CPU Stress
OpenSSL
DaCapo Benchmark
OpenSSL
VVenC
nginx
OpenSSL
DaCapo Benchmark
Stress-NG
DaCapo Benchmark
OpenSSL
VVenC
Stress-NG:
  Vector Math
  Wide Vector Math
OpenRadioss
VVenC
NAMD
Stress-NG
OpenSSL
OSPRay Studio
Stress-NG
x265
Stress-NG
7-Zip Compression
nginx
OpenSSL
OSPRay Studio
PostgreSQL:
  100 - 1000 - Read Write
  100 - 1000 - Read Write - Average Latency
Stress-NG:
  AVX-512 VNNI
  Hash
TensorFlow
DaCapo Benchmark
OpenSSL
Stress-NG
PostgreSQL
Stress-NG:
  Matrix 3D Math
  Malloc
DaCapo Benchmark
GIMP
Stress-NG
SVT-AV1
DaCapo Benchmark
SVT-HEVC
PostgreSQL
Stress-NG
GIMP
DaCapo Benchmark:
  jMonkeyEngine
  H2O In-Memory Platform For Machine Learning
Xcompact3d Incompact3d
OpenFOAM
OSPRay Studio
Darktable
Stress-NG:
  CPU Cache
  IO_uring
DaCapo Benchmark

6.5.0-15-lowlatency

Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.5.0-15-lowlatency (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, 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-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-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/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
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)
Python Notes: Python 3.11.5
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 + 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 29 January 2024 02:38 by user phoronix.

6.5.0-15-generic

Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, 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-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-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/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
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)
Python Notes: Python 3.11.5
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 + 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 29 January 2024 11:19 by user phoronix.