TR 3990X Linux 6.0 Dummy Wait WA

Tests for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2209270-PTS-TR399XLI31
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:

AV1 2 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 10 Tests
C/C++ Compiler Tests 12 Tests
CPU Massive 15 Tests
Creator Workloads 13 Tests
Database Test Suite 7 Tests
Desktop Graphics 2 Tests
Encoding 5 Tests
Game Development 3 Tests
Go Language Tests 3 Tests
HPC - High Performance Computing 2 Tests
Imaging 3 Tests
Common Kernel Benchmarks 2 Tests
Multi-Core 20 Tests
Intel oneAPI 2 Tests
Programmer / Developer System Benchmarks 11 Tests
Python Tests 6 Tests
Renderers 2 Tests
Server 10 Tests
Server CPU Tests 10 Tests
Single-Threaded 2 Tests
Video Encoding 5 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Pre
September 26 2022
  21 Hours, 9 Minutes
Post
September 27 2022
  20 Hours, 17 Minutes
Invert Hiding All Results Option
  20 Hours, 43 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):

Pre

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc7daily20220926-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.1.7 (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055
Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Post

OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc7daily20220927-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.1.7 (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

TR 3990X Linux 6.0 Dummy Wait WAOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS)AMD Starship/Matisse128GBSamsung SSD 970 EVO Plus 500GBAMD Radeon RX 5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.106.0.0-060000rc7daily20220926-generic (x86_64)6.0.0-060000rc7daily20220927-generic (x86_64)GNOME ShellX Server 1.21.1.3 + Wayland4.6 Mesa 22.1.7 (LLVM 14.0.6 DRM 3.48)1.3.211GCC 12.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelsDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionTR 3990X Linux 6.0 Dummy Wait WA BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055- GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101- OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)- Python 3.10.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Pre vs. Post ComparisonPhoronix Test SuiteBaseline+16.7%+16.7%+33.4%+33.4%+50.1%+50.1%6.2%3.6%3.5%3.3%3.3%3.1%3.1%2.8%2.4%2.2%2%PUT - 500 - 100 - Average Latency66.7%PUT - 500 - 10063.8%PUT - 100 - 10060.8%PUT - 50 - 10060.6%PUT - 100 - 100 - Average Latency60%PUT - 50 - 100 - Average Latency60%50019.3%GET - 5017.2%PUT - 50 - 100015.2%PUT - 50 - 1000 - Average Latency14.7%PUT - 100 - 1000 - Average Latency11.1%PUT - 100 - 100010.7%16.2%10000000 - 100 - I.J.T.T1000000 - 100 - B.I.J.T.T5%Q.9.C.E.74.3%Q.7.C.E.74.3%1000000 - 2000 - S.5.B.T3.9%PUT - 500 - 10003.7%40000000 - 100 - C.P.B.U.DPUT - 500 - 1000 - Average Latency3.5%10000000 - 100 - B.I.J.T.T40000000 - 2000 - Group By Test TimeV.P.MOpenGL 3.x - On - On - 1920 x 10803.2%GET - 5001000000 - 2000 - R.T.TQ.1.C.E.5100 - 250 - Read Write2.7%1000000 - 2000 - C.P.B2.7%100 - 250 - Read Write - Average Latency2.7%A.G.R.R.0.F - CPU2.6%Exhaustive2.4%SET - 1000BMW27 - CPU-Only2.4%10000000 - 100 - R.T.T2.3%10000000 - 100 - Group By Test Time2.3%10000000 - 2000 - C.P.B2.2%10000000 - 100 - C.P.B.U.DA.G.R.R.0.F - CPU2.1%1000000 - 100 - R.T.T2%40000000 - 2000 - R.T.TetcdetcdetcdetcdetcdetcdApache HTTP ServerRedisetcdetcdetcdetcdApache HTTP ServerApache SparkApache SparkWebP2 Image EncodeWebP2 Image EncodeApache SparketcdApache SparketcdApache SparkApache SparkBRL-CADyquake2RedisApache SparkWebP2 Image EncodePostgreSQL pgbenchApache SparkPostgreSQL pgbenchOpenVINOASTC EncoderRedisBlenderApache SparkApache SparkApache SparkApache SparkOpenVINOApache SparkApache SparkPrePost

TR 3990X Linux 6.0 Dummy Wait WAetcd: PUT - 500 - 100 - Average Latencyetcd: PUT - 500 - 100etcd: PUT - 100 - 100etcd: PUT - 50 - 100etcd: PUT - 100 - 100 - Average Latencyetcd: PUT - 50 - 100 - Average Latencyapache: 500redis: GET - 50etcd: PUT - 50 - 1000etcd: PUT - 50 - 1000 - Average Latencyetcd: PUT - 100 - 1000 - Average Latencyetcd: PUT - 100 - 1000apache: 1spark: 10000000 - 100 - Inner Join Test Timewebp2: Quality 95, Compression Effort 7webp2: Quality 75, Compression Effort 7spark: 1000000 - 2000 - SHA-512 Benchmark Timeetcd: PUT - 500 - 1000spark: 40000000 - 100 - Calculate Pi Benchmark Using Dataframeetcd: PUT - 500 - 1000 - Average Latencyspark: 10000000 - 100 - Broadcast Inner Join Test Timebrl-cad: VGR Performance Metricyquake2: OpenGL 3.x - On - On - 1920 x 1080redis: GET - 500webp2: Quality 100, Compression Effort 5pgbench: 100 - 250 - Read Writespark: 1000000 - 2000 - Calculate Pi Benchmarkpgbench: 100 - 250 - Read Write - Average Latencyopenvino: Age Gender Recognition Retail 0013 FP16 - CPUastcenc: Exhaustiveredis: SET - 1000blender: BMW27 - CPU-Onlyspark: 10000000 - 100 - Repartition Test Timespark: 10000000 - 100 - Group By Test Timespark: 10000000 - 2000 - Calculate Pi Benchmarkopenvino: Age Gender Recognition Retail 0013 FP16 - CPUspark: 40000000 - 2000 - Repartition Test Timespark: 1000000 - 2000 - Broadcast Inner Join Test Timespark: 10000000 - 2000 - Inner Join Test Timenode-web-tooling: dragonflydb: 50 - 1:1spark: 40000000 - 2000 - SHA-512 Benchmark Timespark: 10000000 - 2000 - Broadcast Inner Join Test Timespark: 40000000 - 100 - SHA-512 Benchmark Timedragonflydb: 50 - 1:5memtier-benchmark: Redis - 50 - 5:1spark: 1000000 - 100 - SHA-512 Benchmark Timeopenfoam: drivaerFastback, Small Mesh Size - Execution Timememtier-benchmark: Redis - 50 - 1:10ddnet: 1920 x 1080 - Fullscreen - Vulkan - Default - RaiNyMore2nginx: 1webp2: Defaultspark: 40000000 - 2000 - Inner Join Test Timeapache: 200webp: Quality 100, Losslesssvt-hevc: 7 - Bosphorus 1080pspark: 40000000 - 100 - Group By Test Timespark: 40000000 - 2000 - Calculate Pi Benchmarkdragonflydb: 50 - 5:1clickhouse: 100M Rows Web Analytics Dataset, Third Runavifenc: 6, Losslessopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUsvt-vp9: VMAF Optimized - Bosphorus 1080predis: SET - 50apache: 20spark: 40000000 - 100 - Broadcast Inner Join Test Timepgbench: 100 - 500 - Read Writespark: 40000000 - 100 - Calculate Pi Benchmarkastcenc: Fastsrsran: OFDM_Testapache: 1000pgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 100 - Read Only - Average Latencyxonotic: 1920 x 1080 - Lowsvt-hevc: 10 - Bosphorus 4Kopenvino: Weld Porosity Detection FP16 - CPUsvt-av1: Preset 8 - Bosphorus 1080popenvino: Face Detection FP16-INT8 - CPUblender: Classroom - CPU-Onlysvt-vp9: Visual Quality Optimized - Bosphorus 4Kopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUbuild-llvm: Unix Makefilessrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMopenvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUetcd: RANGE - 500 - 100openfoam: drivaerFastback, Small Mesh Size - Mesh Timeunvanquished: 1920 x 1080 - Highopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUbuild-godot: Time To Compilespark: 10000000 - 2000 - Group By Test Timesvt-av1: Preset 8 - Bosphorus 4Kpgbench: 100 - 500 - Read Onlypgbench: 100 - 500 - Read Only - Average Latencycompress-7zip: Compression Ratingspark: 40000000 - 100 - Inner Join Test Timeddnet: 1920 x 1080 - Fullscreen - Vulkan - Default - Multeasymapspark: 10000000 - 2000 - Calculate Pi Benchmark Using Dataframeetcd: RANGE - 100 - 100tesseract: 1920 x 1080openvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUblender: Barbershop - CPU-Onlyopenvino: Person Vehicle Bike Detection FP16 - CPUpgbench: 100 - 250 - Read Onlyastcenc: Thoroughetcd: RANGE - 50 - 100spark: 10000000 - 100 - SHA-512 Benchmark Timepgbench: 100 - 100 - Read Onlyspark: 10000000 - 100 - Calculate Pi Benchmarksvt-av1: Preset 10 - Bosphorus 1080pavifenc: 0spark: 1000000 - 100 - Calculate Pi Benchmarkavifenc: 2pgbench: 100 - 250 - Read Only - Average Latencyapache: 100xonotic: 1920 x 1080 - Ultimatesvt-av1: Preset 12 - Bosphorus 1080psrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMnginx: 200redis: SET - 500xonotic: 1920 x 1080 - Highx265: Bosphorus 1080pnginx: 500srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMx265: Bosphorus 4Kspark: 40000000 - 2000 - Broadcast Inner Join Test Timespark: 10000000 - 2000 - SHA-512 Benchmark Timespark: 1000000 - 100 - Group By Test Timeopenvino: Person Detection FP16 - CPUastcenc: Mediumavifenc: 10, Losslesssrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMwebp: Quality 100, Highest Compressionsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMspark: 40000000 - 100 - Repartition Test Timesvt-vp9: Visual Quality Optimized - Bosphorus 1080pbuild-wasmer: Time To Compilenginx: 20redis: GET - 1000spark: 1000000 - 2000 - Inner Join Test Timespark: 10000000 - 2000 - Repartition Test Timeavifenc: 6build-mplayer: Time To Compilesrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMnginx: 1000svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080punvanquished: 1920 x 1080 - Ultraxonotic: 1920 x 1080 - Ultrabuild-nodejs: Time To Compilesrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMopenvino: Person Detection FP16 - CPUopenvino: Face Detection FP16 - CPUcompress-7zip: Decompression Ratingetcd: RANGE - 100 - 1000openvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUbuild-php: Time To Compilesvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Kopenvino: Face Detection FP16 - CPUbuild-ffmpeg: Time To Compileetcd: RANGE - 500 - 1000openvino: Person Detection FP32 - CPUclickhouse: 100M Rows Web Analytics Dataset, Second Runsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMbuild-linux-kernel: defconfignginx: 100webp: Defaultospray-studio: 1 - 4K - 32 - Path Tracergravitymark: 1920 x 1080 - Vulkanwebp: Quality 100svt-av1: Preset 12 - Bosphorus 4Kbuild-apache: Time To Compilebuild-llvm: Ninjasvt-hevc: 7 - Bosphorus 4Ketcd: RANGE - 50 - 1000svt-av1: Preset 10 - Bosphorus 4Kospray-studio: 3 - 4K - 32 - Path Tracerpgbench: 100 - 100 - Read Write - Average Latencyyquake2: Vulkan - On - On - 1920 x 1080unvanquished: 1920 x 1080 - Mediumopenvino: Person Detection FP32 - CPUospray-studio: 3 - 4K - 1 - Path Tracerbuild-mesa: Time To Compilepgbench: 100 - 100 - Read Writesrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMbuild-linux-kernel: allmodconfigsvt-hevc: 10 - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 4Kspark: 1000000 - 100 - Inner Join Test Timeetcd: RANGE - 500 - 1000 - Average Latencyetcd: RANGE - 100 - 1000 - Average Latencyetcd: RANGE - 500 - 100 - Average Latencyetcd: RANGE - 50 - 1000 - Average Latencyetcd: RANGE - 100 - 100 - Average Latencyetcd: RANGE - 50 - 100 - Average Latencyospray-studio: 1 - 4K - 1 - Path Tracerwebp2: Quality 100, Lossless Compressionwebp: Quality 100, Lossless, Highest Compressionspark: 40000000 - 2000 - Group By Test Timespark: 40000000 - 2000 - Calculate Pi Benchmark Using Dataframespark: 10000000 - 100 - Calculate Pi Benchmark Using Dataframespark: 1000000 - 2000 - Repartition Test Timespark: 1000000 - 2000 - Group By Test Timespark: 1000000 - 2000 - Calculate Pi Benchmark Using Dataframespark: 1000000 - 100 - Broadcast Inner Join Test Timespark: 1000000 - 100 - Repartition Test Timespark: 1000000 - 100 - Calculate Pi Benchmark Using Dataframeclickhouse: 100M Rows Web Analytics Dataset, First Run / Cold CachePrePost3.329891.759428656.834028857.43063.53.583302.362506805.0054313.390618.418.055325.42118494.507.370.240.494.8258432.42812.8517.16.267305461347.51726980.019.97909838.1327.48633749.443.15111317540.7528.696.429.2539.201.8922.332.618.5110.333375321.4737.057.6535.503601723.811317722.394.4372.7282691527667.861959.0150377.649.3425.9099437.501.52250.7523.4039.883198167.19256.337.16951216.45342.561722230.4651978.9821.59939239.47662.901214066666781918.4653.2980.098537.8789870153.651067.93101.39516.5679.19106.0229.9439.25247.427158.01922.041629.74328.6897.1318549.764834.442847257.31.2448.00510.5955.72212341570.40519139623.211695.622.7718229.7707491.95161329.1024.0621.22317.241506.32123787028.972218289.611711.69101471939.157614970225.06377.06538.5341.0890.20283161.49293.9428972343.463147.6159203.981318362.39438.894798847.27159778.8360.021.1024.4012.546.316.50231.92405.300166.53.32103.520.68259.9549.093167443.621724111.213.647.473.84012.718156.0158800.01334.46253.4403.6260256195.313361.0387.64808.0910.1536518351027.327860.02532.4450.612109.593106.8719.02656371.60286.44255.09387.034.069158355.4617.1091009100.710.70137.11324.053183.918118.7050651.438394.08210734413.9941057.5257.84830.95316227.7537148362.7295.069450.56104.432.5917.719.55.419.75.55.526390.050.6032.012.802.853.707.392.761.792.942.68245.165.518248.726517821.774517968.76285.65.669805.042138166.747154.980721.120.049967.95627996.466.940.230.475.0156337.50912.7517.76.057545001306.01781139.1810.25885839.1628.22432889.793.07641349145.8829.376.579.4640.051.9321.892.668.6710.523316852.0836.427.5236.113542376.961338961.024.3673.8868711551616.451929.3149665.879.2125.5498072.971.50254.0323.1040.383159076.72259.387.25250633.80338.681741763.9652567.9821.35928839.91655.781513916666781049.6853.8660.099543.2503116152.211058.05102.32616.4179.91105.0730.2139.60249.621159.41939.071615.46331.5796.2918392.185034.151439259.41.2548.38910.5156.14412249620.40819280523.381707.882.7918101.1885495.36651320.2324.2221.36319.301496.69123004228.793418176.782711.62100875239.38226.31877.47438.7341.2950.20383564.68295.3523866344.995147.0158586.331323405.12440.562525547.10159244.1959.821.1724.3212.586.336.48231.22355.316166.03.33103.220.74259.2148.956167908.471719383.043.657.493.85012.685156.4158395.16333.61254.0402.7044946194.879360.2386.84817.7610.1336448051122.703660.13531.4750.700109.783111.8618.99656459.84576.45254.73387.534.113158154.4617.1290904100.810.69137.22224.034184.031118.6350622.757294.13310739813.9871058.0257.94829.13316127.7617150362.8294.999450.46104.442.5917.719.55.419.75.55.526390.050.6030.982.842.793.597.332.721.883.002.66244.82OpenBenchmarking.org

DDraceNetwork

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: RaiNyMore2 - Total Frame TimePrePost246810Min: 0.11 / Avg: 0.52 / Max: 3.41Min: 0.11 / Avg: 0.52 / Max: 2.961. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: Multeasymap - Total Frame TimePrePost246810Min: 0.24 / Avg: 0.6 / Max: 2.44Min: 0.25 / Avg: 0.6 / Max: 2.231. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 100 - Average LatencyPrePost1.23752.4753.71254.956.1875SE +/- 0.00, N = 3SE +/- 0.00, N = 33.35.5
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 100 - Average LatencyPrePost246810Min: 3.3 / Avg: 3.3 / Max: 3.3Min: 5.5 / Avg: 5.5 / Max: 5.5

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 100PrePost6K12K18K24K30KSE +/- 5.42, N = 3SE +/- 31.68, N = 329891.7618248.73
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 100PrePost5K10K15K20K25KMin: 29883.71 / Avg: 29891.76 / Max: 29902.08Min: 18185.53 / Avg: 18248.73 / Max: 18284.35

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 100PrePost6K12K18K24K30KSE +/- 94.55, N = 3SE +/- 31.85, N = 328656.8317821.77
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 100PrePost5K10K15K20K25KMin: 28510.43 / Avg: 28656.83 / Max: 28833.69Min: 17768.76 / Avg: 17821.77 / Max: 17878.87

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 100PrePost6K12K18K24K30KSE +/- 60.77, N = 3SE +/- 44.79, N = 328857.4317968.76
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 100PrePost5K10K15K20K25KMin: 28736.7 / Avg: 28857.43 / Max: 28929.98Min: 17911.31 / Avg: 17968.76 / Max: 18057.02

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 100 - Average LatencyPrePost1.262.523.785.046.3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.55.6
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 100 - Average LatencyPrePost246810Min: 3.5 / Avg: 3.5 / Max: 3.5Min: 5.6 / Avg: 5.6 / Max: 5.6

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 100 - Average LatencyPrePost1.262.523.785.046.3SE +/- 0.00, N = 3SE +/- 0.03, N = 33.55.6
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 100 - Average LatencyPrePost246810Min: 3.5 / Avg: 3.5 / Max: 3.5Min: 5.5 / Avg: 5.57 / Max: 5.6

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500PrePost20K40K60K80K100KSE +/- 170.94, N = 3SE +/- 417.00, N = 383302.3669805.041. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500PrePost14K28K42K56K70KMin: 82992.27 / Avg: 83302.36 / Max: 83582.1Min: 68975.99 / Avg: 69805.04 / Max: 70298.081. (CC) gcc options: -shared -fPIC -O2

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50PrePost500K1000K1500K2000K2500KSE +/- 6511.85, N = 3SE +/- 21888.93, N = 32506805.002138166.701. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50PrePost400K800K1200K1600K2000KMin: 2500044.75 / Avg: 2506805 / Max: 2519825.5Min: 2113543.5 / Avg: 2138166.67 / Max: 2181825.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 1000PrePost12K24K36K48K60KSE +/- 489.52, N = 7SE +/- 125.47, N = 354313.3947154.98
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 1000PrePost9K18K27K36K45KMin: 51393.4 / Avg: 54313.39 / Max: 54985.96Min: 46906.56 / Avg: 47154.98 / Max: 47309.94

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 1000 - Average LatencyPrePost510152025SE +/- 0.18, N = 7SE +/- 0.03, N = 318.421.1
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 50 - Clients: 1000 - Average LatencyPrePost510152025Min: 18.1 / Avg: 18.36 / Max: 19.4Min: 21.1 / Avg: 21.13 / Max: 21.2

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 1000 - Average LatencyPrePost510152025SE +/- 0.03, N = 3SE +/- 0.20, N = 618.020.0
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 1000 - Average LatencyPrePost510152025Min: 18 / Avg: 18.03 / Max: 18.1Min: 19.6 / Avg: 19.97 / Max: 20.7

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 1000PrePost12K24K36K48K60KSE +/- 100.85, N = 3SE +/- 507.20, N = 655325.4249967.96
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 100 - Clients: 1000PrePost10K20K30K40K50KMin: 55195.35 / Avg: 55325.42 / Max: 55523.96Min: 48164.85 / Avg: 49967.96 / Max: 50944.79

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1PrePost2K4K6K8K10KSE +/- 94.95, N = 4SE +/- 74.29, N = 78494.507996.461. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1PrePost15003000450060007500Min: 8243.41 / Avg: 8494.5 / Max: 8684.96Min: 7718.5 / Avg: 7996.46 / Max: 8292.071. (CC) gcc options: -shared -fPIC -O2

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Inner Join Test TimePrePost246810SE +/- 0.23, N = 3SE +/- 0.20, N = 37.376.94
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Inner Join Test TimePrePost3691215Min: 7.07 / Avg: 7.37 / Max: 7.83Min: 6.62 / Avg: 6.94 / Max: 7.3

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 95, Compression Effort 7PrePost0.0540.1080.1620.2160.27SE +/- 0.00, N = 3SE +/- 0.00, N = 30.240.231. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 95, Compression Effort 7PrePost12345Min: 0.24 / Avg: 0.24 / Max: 0.24Min: 0.23 / Avg: 0.23 / Max: 0.231. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 75, Compression Effort 7PrePost0.11030.22060.33090.44120.5515SE +/- 0.00, N = 3SE +/- 0.00, N = 150.490.471. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 75, Compression Effort 7PrePost246810Min: 0.48 / Avg: 0.49 / Max: 0.5Min: 0.45 / Avg: 0.47 / Max: 0.51. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost1.12732.25463.38194.50925.6365SE +/- 0.03, N = 3SE +/- 0.00, N = 34.825.01
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost246810Min: 4.75 / Avg: 4.82 / Max: 4.85Min: 5 / Avg: 5.01 / Max: 5.02

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 1000PrePost13K26K39K52K65KSE +/- 833.66, N = 3SE +/- 45.44, N = 358432.4356337.51
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 1000PrePost10K20K30K40K50KMin: 56994.24 / Avg: 58432.43 / Max: 59882.06Min: 56256.93 / Avg: 56337.51 / Max: 56414.19

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost0.64131.28261.92392.56523.2065SE +/- 0.04, N = 3SE +/- 0.05, N = 32.852.75
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.77 / Avg: 2.85 / Max: 2.89Min: 2.66 / Avg: 2.75 / Max: 2.84

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 1000 - Average LatencyPrePost48121620SE +/- 0.23, N = 3SE +/- 0.00, N = 317.117.7
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: PUT - Connections: 500 - Clients: 1000 - Average LatencyPrePost48121620Min: 16.7 / Avg: 17.1 / Max: 17.5Min: 17.7 / Avg: 17.7 / Max: 17.7

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost246810SE +/- 0.15, N = 3SE +/- 0.08, N = 36.266.05
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost3691215Min: 6.05 / Avg: 6.26 / Max: 6.55Min: 5.89 / Avg: 6.05 / Max: 6.16

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.6VGR Performance MetricPrePost160K320K480K640K800K7305467545001. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080PrePost30060090012001500SE +/- 13.51, N = 5SE +/- 12.08, N = 31347.51306.01. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080PrePost2004006008001000Min: 1311.2 / Avg: 1347.48 / Max: 1395.1Min: 1281.9 / Avg: 1306 / Max: 1319.41. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500PrePost400K800K1200K1600K2000KSE +/- 24650.52, N = 15SE +/- 23854.62, N = 151726980.011781139.181. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500PrePost300K600K900K1200K1500KMin: 1576118.5 / Avg: 1726980.01 / Max: 1895409.25Min: 1592486.62 / Avg: 1781139.18 / Max: 1926074.621. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Compression Effort 5PrePost3691215SE +/- 0.10, N = 3SE +/- 0.06, N = 159.9710.251. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Compression Effort 5PrePost3691215Min: 9.78 / Avg: 9.97 / Max: 10.14Min: 9.5 / Avg: 10.25 / Max: 10.51. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WritePrePost2K4K6K8K10KSE +/- 109.92, N = 3SE +/- 41.19, N = 3909888581. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WritePrePost16003200480064008000Min: 8987.89 / Avg: 9098.11 / Max: 9317.96Min: 8802.21 / Avg: 8858.22 / Max: 8938.541. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.58, N = 3SE +/- 0.11, N = 338.1339.16
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost816243240Min: 37.24 / Avg: 38.13 / Max: 39.21Min: 38.94 / Avg: 39.16 / Max: 39.29

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyPrePost714212835SE +/- 0.33, N = 3SE +/- 0.13, N = 327.4928.221. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyPrePost612182430Min: 26.83 / Avg: 27.49 / Max: 27.82Min: 27.97 / Avg: 28.22 / Max: 28.41. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUPrePost7K14K21K28K35KSE +/- 346.01, N = 3SE +/- 401.40, N = 333749.4432889.791. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUPrePost6K12K18K24K30KMin: 33279.95 / Avg: 33749.44 / Max: 34424.47Min: 32398.67 / Avg: 32889.79 / Max: 33685.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustivePrePost0.7091.4182.1272.8363.545SE +/- 0.0195, N = 3SE +/- 0.0203, N = 33.15113.07641. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustivePrePost246810Min: 3.12 / Avg: 3.15 / Max: 3.19Min: 3.05 / Avg: 3.08 / Max: 3.121. (CXX) g++ options: -O3 -flto -pthread

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 1000PrePost300K600K900K1200K1500KSE +/- 7044.05, N = 3SE +/- 2383.81, N = 31317540.751349145.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 1000PrePost200K400K600K800K1000KMin: 1306799.25 / Avg: 1317540.75 / Max: 1330805.88Min: 1345206.88 / Avg: 1349145.88 / Max: 1353441.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: BMW27 - Compute: CPU-OnlyPrePost714212835SE +/- 0.17, N = 3SE +/- 0.05, N = 328.6929.37
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: BMW27 - Compute: CPU-OnlyPrePost714212835Min: 28.42 / Avg: 28.69 / Max: 29.01Min: 29.28 / Avg: 29.37 / Max: 29.44

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Repartition Test TimePrePost246810SE +/- 0.09, N = 3SE +/- 0.17, N = 36.426.57
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Repartition Test TimePrePost3691215Min: 6.33 / Avg: 6.42 / Max: 6.6Min: 6.34 / Avg: 6.57 / Max: 6.9

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Group By Test TimePrePost3691215SE +/- 0.14, N = 3SE +/- 0.11, N = 39.259.46
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Group By Test TimePrePost3691215Min: 9.04 / Avg: 9.25 / Max: 9.53Min: 9.25 / Avg: 9.46 / Max: 9.62

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.18, N = 14SE +/- 0.12, N = 1539.2040.05
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost816243240Min: 38.06 / Avg: 39.2 / Max: 40.29Min: 39.24 / Avg: 40.05 / Max: 40.69

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUPrePost0.43430.86861.30291.73722.1715SE +/- 0.02, N = 3SE +/- 0.02, N = 31.891.93MIN: 0.99 / MAX: 23.11MIN: 0.98 / MAX: 18.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUPrePost246810Min: 1.85 / Avg: 1.89 / Max: 1.91Min: 1.89 / Avg: 1.93 / Max: 1.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Repartition Test TimePrePost510152025SE +/- 0.22, N = 3SE +/- 0.50, N = 322.3321.89
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Repartition Test TimePrePost510152025Min: 22.07 / Avg: 22.33 / Max: 22.77Min: 20.89 / Avg: 21.89 / Max: 22.44

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost0.59851.1971.79552.3942.9925SE +/- 0.04, N = 3SE +/- 0.07, N = 32.612.66
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost246810Min: 2.54 / Avg: 2.61 / Max: 2.66Min: 2.58 / Avg: 2.66 / Max: 2.81

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Inner Join Test TimePrePost246810SE +/- 0.10, N = 14SE +/- 0.12, N = 158.518.67
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Inner Join Test TimePrePost3691215Min: 8.07 / Avg: 8.51 / Max: 9.49Min: 8.15 / Avg: 8.67 / Max: 9.42

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkPrePost3691215SE +/- 0.04, N = 3SE +/- 0.04, N = 310.3310.52
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkPrePost3691215Min: 10.28 / Avg: 10.33 / Max: 10.4Min: 10.48 / Avg: 10.52 / Max: 10.59

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 1:1PrePost700K1400K2100K2800K3500KSE +/- 666.50, N = 3SE +/- 29614.50, N = 33375321.473316852.081. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 1:1PrePost600K1200K1800K2400K3000KMin: 3374443.55 / Avg: 3375321.47 / Max: 3376629.12Min: 3263850.31 / Avg: 3316852.08 / Max: 3366247.611. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost918273645SE +/- 0.38, N = 3SE +/- 0.11, N = 337.0536.42
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost816243240Min: 36.32 / Avg: 37.05 / Max: 37.59Min: 36.26 / Avg: 36.42 / Max: 36.63

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost246810SE +/- 0.07, N = 14SE +/- 0.06, N = 157.657.52
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost3691215Min: 7.38 / Avg: 7.65 / Max: 8.36Min: 7.15 / Avg: 7.52 / Max: 7.85

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost816243240SE +/- 0.21, N = 3SE +/- 0.35, N = 335.5036.11
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost816243240Min: 35.08 / Avg: 35.5 / Max: 35.74Min: 35.5 / Avg: 36.11 / Max: 36.7

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 1:5PrePost800K1600K2400K3200K4000KSE +/- 4565.80, N = 3SE +/- 15513.58, N = 33601723.813542376.961. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 1:5PrePost600K1200K1800K2400K3000KMin: 3596145.3 / Avg: 3601723.81 / Max: 3610774.04Min: 3513538.46 / Avg: 3542376.96 / Max: 3566709.31. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is Bettermemtier_benchmark 1.4Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1PrePost300K600K900K1200K1500KSE +/- 3267.03, N = 3SE +/- 10324.88, N = 31317722.391338961.021. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is Bettermemtier_benchmark 1.4Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1PrePost200K400K600K800K1000KMin: 1313807.66 / Avg: 1317722.39 / Max: 1324210.38Min: 1324806.3 / Avg: 1338961.02 / Max: 1359059.231. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost0.99681.99362.99043.98724.984SE +/- 0.04, N = 15SE +/- 0.03, N = 34.434.36
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost246810Min: 4.1 / Avg: 4.43 / Max: 4.68Min: 4.32 / Avg: 4.36 / Max: 4.41

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 TimePrePost163248648072.7373.891. (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

memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is Bettermemtier_benchmark 1.4Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10PrePost300K600K900K1200K1500KSE +/- 3584.04, N = 3SE +/- 18012.05, N = 41527667.861551616.451. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is Bettermemtier_benchmark 1.4Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10PrePost300K600K900K1200K1500KMin: 1520569.27 / Avg: 1527667.86 / Max: 1532079.49Min: 1526336.52 / Avg: 1551616.45 / Max: 1603193.211. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

DDraceNetwork

This is a test of DDraceNetwork, an open-source cooperative platformer. Vulkan or OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: RaiNyMore2PrePost400800120016002000SE +/- 18.83, N = 15SE +/- 2.05, N = 31959.011929.311. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: RaiNyMore2PrePost30060090012001500Min: 1929.13 / Avg: 1959.01 / Max: 2168.27Min: 1926.61 / Avg: 1929.31 / Max: 1933.331. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1PrePost11K22K33K44K55KSE +/- 131.25, N = 3SE +/- 496.78, N = 1550377.6449665.871. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1PrePost9K18K27K36K45KMin: 50124.2 / Avg: 50377.64 / Max: 50563.55Min: 47042.35 / Avg: 49665.87 / Max: 535001. (CC) gcc options: -lcrypt -lz -O3 -march=native

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: DefaultPrePost3691215SE +/- 0.11, N = 4SE +/- 0.09, N = 39.349.211. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: DefaultPrePost3691215Min: 9.07 / Avg: 9.34 / Max: 9.61Min: 9.03 / Avg: 9.21 / Max: 9.341. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Inner Join Test TimePrePost612182430SE +/- 0.46, N = 3SE +/- 0.30, N = 325.9025.54
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Inner Join Test TimePrePost612182430Min: 25.21 / Avg: 25.9 / Max: 26.78Min: 25.23 / Avg: 25.54 / Max: 26.14

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200PrePost20K40K60K80K100KSE +/- 169.93, N = 3SE +/- 171.76, N = 399437.5098072.971. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200PrePost20K40K60K80K100KMin: 99125.45 / Avg: 99437.5 / Max: 99710.12Min: 97746.26 / Avg: 98072.97 / Max: 98328.221. (CC) gcc options: -shared -fPIC -O2

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessPrePost0.3420.6841.0261.3681.71SE +/- 0.00, N = 3SE +/- 0.00, N = 31.521.501. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessPrePost246810Min: 1.51 / Avg: 1.52 / Max: 1.53Min: 1.5 / Avg: 1.5 / Max: 1.511. (CC) gcc options: -fvisibility=hidden -O2 -lm

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 1080pPrePost60120180240300SE +/- 1.38, N = 3SE +/- 2.39, N = 3250.75254.031. (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 1080pPrePost50100150200250Min: 248.14 / Avg: 250.75 / Max: 252.84Min: 249.27 / Avg: 254.03 / Max: 256.741. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Group By Test TimePrePost612182430SE +/- 0.20, N = 3SE +/- 0.34, N = 323.4023.10
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Group By Test TimePrePost510152025Min: 23.13 / Avg: 23.4 / Max: 23.79Min: 22.57 / Avg: 23.1 / Max: 23.72

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.55, N = 3SE +/- 0.21, N = 339.8840.38
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Calculate Pi BenchmarkPrePost816243240Min: 38.84 / Avg: 39.88 / Max: 40.71Min: 40 / Avg: 40.38 / Max: 40.72

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 5:1PrePost700K1400K2100K2800K3500KSE +/- 22283.21, N = 3SE +/- 10865.55, N = 33198167.193159076.721. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 5:1PrePost600K1200K1800K2400K3000KMin: 3169763.65 / Avg: 3198167.19 / Max: 3242110.4Min: 3138122.98 / Avg: 3159076.72 / Max: 3174542.211. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Third RunPrePost60120180240300SE +/- 1.82, N = 13SE +/- 2.23, N = 12256.33259.38MIN: 18.48 / MAX: 20000MIN: 18.74 / MAX: 200001. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Third RunPrePost50100150200250Min: 244.12 / Avg: 256.33 / Max: 267.36Min: 245.53 / Avg: 259.38 / Max: 275.11. ClickHouse server version 22.5.4.19 (official build).

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessPrePost246810SE +/- 0.041, N = 3SE +/- 0.024, N = 37.1697.2521. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessPrePost3691215Min: 7.12 / Avg: 7.17 / Max: 7.25Min: 7.21 / Avg: 7.25 / Max: 7.281. (CXX) g++ options: -O3 -fPIC -lm

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUPrePost11K22K33K44K55KSE +/- 121.05, N = 3SE +/- 140.50, N = 351216.4550633.801. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUPrePost9K18K27K36K45KMin: 51066.35 / Avg: 51216.45 / Max: 51456Min: 50406.58 / Avg: 50633.8 / Max: 50890.61. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pPrePost70140210280350SE +/- 1.20, N = 3SE +/- 4.61, N = 3342.56338.681. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pPrePost60120180240300Min: 340.29 / Avg: 342.56 / Max: 344.38Min: 330.52 / Avg: 338.68 / Max: 346.461. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50PrePost400K800K1200K1600K2000KSE +/- 22131.86, N = 3SE +/- 9233.17, N = 31722230.461741763.961. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50PrePost300K600K900K1200K1500KMin: 1678896.5 / Avg: 1722230.46 / Max: 1751713Min: 1723336.88 / Avg: 1741763.96 / Max: 1752019.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 20PrePost11K22K33K44K55KSE +/- 706.18, N = 3SE +/- 152.29, N = 351978.9852567.981. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 20PrePost9K18K27K36K45KMin: 50671.26 / Avg: 51978.98 / Max: 53094.88Min: 52264.99 / Avg: 52567.98 / Max: 52746.451. (CC) gcc options: -shared -fPIC -O2

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost510152025SE +/- 0.37, N = 3SE +/- 0.33, N = 321.5921.35
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost510152025Min: 20.88 / Avg: 21.59 / Max: 22.14Min: 20.7 / Avg: 21.35 / Max: 21.77

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WritePrePost2K4K6K8K10KSE +/- 93.83, N = 12SE +/- 68.61, N = 12939292881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WritePrePost16003200480064008000Min: 8702 / Avg: 9391.85 / Max: 9818.46Min: 8933.01 / Avg: 9287.79 / Max: 9618.351. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.37, N = 3SE +/- 0.25, N = 339.4739.91
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost816243240Min: 38.76 / Avg: 39.47 / Max: 39.98Min: 39.4 / Avg: 39.91 / Max: 40.2

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: FastPrePost140280420560700SE +/- 4.16, N = 3SE +/- 7.30, N = 3662.90655.781. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: FastPrePost120240360480600Min: 654.61 / Avg: 662.9 / Max: 667.59Min: 642.8 / Avg: 655.78 / Max: 668.041. (CXX) g++ options: -O3 -flto -pthread

srsRAN

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

OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 22.04.1Test: OFDM_TestPrePost30M60M90M120M150MSE +/- 437162.57, N = 3SE +/- 1169520.32, N = 31406666671391666671. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 22.04.1Test: OFDM_TestPrePost20M40M60M80M100MMin: 139800000 / Avg: 140666666.67 / Max: 141200000Min: 136900000 / Avg: 139166666.67 / Max: 1408000001. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000PrePost20K40K60K80K100KSE +/- 219.45, N = 3SE +/- 142.73, N = 381918.4681049.681. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000PrePost14K28K42K56K70KMin: 81484.05 / Avg: 81918.46 / Max: 82189.86Min: 80768.23 / Avg: 81049.68 / Max: 81231.741. (CC) gcc options: -shared -fPIC -O2

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyPrePost1224364860SE +/- 0.55, N = 12SE +/- 0.40, N = 1253.3053.871. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyPrePost1122334455Min: 50.92 / Avg: 53.3 / Max: 57.46Min: 51.98 / Avg: 53.87 / Max: 55.971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average LatencyPrePost0.02230.04460.06690.08920.1115SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0980.0991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average LatencyPrePost12345Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.11. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: LowPrePost120240360480600SE +/- 4.08, N = 3SE +/- 1.03, N = 3537.88543.25MIN: 336 / MAX: 1018MIN: 364 / MAX: 1020
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: LowPrePost100200300400500Min: 529.88 / Avg: 537.88 / Max: 543.23Min: 541.28 / Avg: 543.25 / Max: 544.75

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 4KPrePost306090120150SE +/- 1.73, N = 3SE +/- 1.02, N = 3153.65152.211. (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 4KPrePost306090120150Min: 150.6 / Avg: 153.65 / Max: 156.58Min: 151.17 / Avg: 152.21 / Max: 154.241. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUPrePost2004006008001000SE +/- 9.33, N = 3SE +/- 4.30, N = 31067.931058.051. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUPrePost2004006008001000Min: 1049.27 / Avg: 1067.93 / Max: 1077.63Min: 1053.03 / Avg: 1058.05 / Max: 1066.61. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pPrePost20406080100SE +/- 0.95, N = 3SE +/- 0.25, N = 3101.40102.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pPrePost20406080100Min: 99.51 / Avg: 101.4 / Max: 102.62Min: 102.02 / Avg: 102.33 / Max: 102.821. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUPrePost48121620SE +/- 0.17, N = 3SE +/- 0.15, N = 316.5616.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUPrePost48121620Min: 16.34 / Avg: 16.56 / Max: 16.89Min: 16.22 / Avg: 16.41 / Max: 16.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Classroom - Compute: CPU-OnlyPrePost20406080100SE +/- 0.41, N = 3SE +/- 0.19, N = 379.1979.91
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Classroom - Compute: CPU-OnlyPrePost1530456075Min: 78.5 / Avg: 79.19 / Max: 79.91Min: 79.53 / Avg: 79.91 / Max: 80.13

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KPrePost20406080100SE +/- 0.55, N = 3SE +/- 0.19, N = 3106.02105.071. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KPrePost20406080100Min: 105.33 / Avg: 106.02 / Max: 107.11Min: 104.8 / Avg: 105.07 / Max: 105.441. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUPrePost714212835SE +/- 0.27, N = 3SE +/- 0.12, N = 329.9430.21MIN: 14.7 / MAX: 78.06MIN: 15.49 / MAX: 58.31. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUPrePost714212835Min: 29.66 / Avg: 29.94 / Max: 30.47Min: 29.97 / Avg: 30.21 / Max: 30.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUPrePost918273645SE +/- 0.31, N = 3SE +/- 0.32, N = 339.2539.60MIN: 21.13 / MAX: 66.14MIN: 20.81 / MAX: 70.881. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUPrePost816243240Min: 38.64 / Avg: 39.25 / Max: 39.61Min: 38.97 / Avg: 39.6 / Max: 40.011. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesPrePost50100150200250SE +/- 0.76, N = 3SE +/- 0.74, N = 3247.43249.62
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesPrePost50100150200250Min: 246.38 / Avg: 247.43 / Max: 248.9Min: 248.2 / Avg: 249.62 / Max: 250.68

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMPrePost4080120160200SE +/- 1.13, N = 3SE +/- 0.22, N = 3158.0159.41. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMPrePost306090120150Min: 156 / Avg: 157.97 / Max: 159.9Min: 159.1 / Avg: 159.37 / Max: 159.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUPrePost400800120016002000SE +/- 20.49, N = 3SE +/- 18.88, N = 31922.041939.07MIN: 1758.65 / MAX: 1999.58MIN: 1756.19 / MAX: 2015.081. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUPrePost30060090012001500Min: 1881.58 / Avg: 1922.04 / Max: 1947.95Min: 1901.71 / Avg: 1939.07 / Max: 1962.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUPrePost400800120016002000SE +/- 12.88, N = 3SE +/- 13.14, N = 31629.741615.461. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUPrePost30060090012001500Min: 1614.94 / Avg: 1629.74 / Max: 1655.4Min: 1598.69 / Avg: 1615.46 / Max: 1641.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUPrePost70140210280350SE +/- 1.86, N = 3SE +/- 0.72, N = 3328.68331.57MIN: 154.69 / MAX: 404.67MIN: 155.06 / MAX: 402.931. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUPrePost60120180240300Min: 325.01 / Avg: 328.68 / Max: 331.03Min: 330.14 / Avg: 331.57 / Max: 332.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUPrePost20406080100SE +/- 0.56, N = 3SE +/- 0.20, N = 397.1396.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUPrePost20406080100Min: 96.4 / Avg: 97.13 / Max: 98.24Min: 96.05 / Avg: 96.29 / Max: 96.71. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 100PrePost4K8K12K16K20KSE +/- 40.42, N = 3SE +/- 19.23, N = 318549.7618392.19
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 100PrePost3K6K9K12K15KMin: 18493.83 / Avg: 18549.76 / Max: 18628.27Min: 18356.25 / Avg: 18392.18 / Max: 18422.03

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 TimePrePost81624324034.4434.151. (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

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: HighPrePost60120180240300SE +/- 0.84, N = 3SE +/- 2.21, N = 3257.3259.4
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: HighPrePost50100150200250Min: 255.8 / Avg: 257.3 / Max: 258.7Min: 255.2 / Avg: 259.4 / Max: 262.7

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUPrePost0.28130.56260.84391.12521.4065SE +/- 0.00, N = 3SE +/- 0.00, N = 31.241.25MIN: 0.74 / MAX: 14.13MIN: 0.73 / MAX: 13.061. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUPrePost246810Min: 1.23 / Avg: 1.24 / Max: 1.24Min: 1.25 / Avg: 1.25 / Max: 1.261. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

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 3.2.3Time To CompilePrePost1122334455SE +/- 0.17, N = 3SE +/- 0.25, N = 348.0148.39
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompilePrePost1020304050Min: 47.67 / Avg: 48.01 / Max: 48.21Min: 47.99 / Avg: 48.39 / Max: 48.86

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Group By Test TimePrePost3691215SE +/- 0.07, N = 14SE +/- 0.06, N = 1510.5910.51
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Group By Test TimePrePost3691215Min: 10.14 / Avg: 10.59 / Max: 11.12Min: 10.12 / Avg: 10.51 / Max: 10.86

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 4KPrePost1326395265SE +/- 0.36, N = 3SE +/- 0.39, N = 355.7256.141. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 4KPrePost1122334455Min: 54.99 / Avg: 55.72 / Max: 56.09Min: 55.44 / Avg: 56.14 / Max: 56.771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyPrePost300K600K900K1200K1500KSE +/- 8036.60, N = 3SE +/- 5587.45, N = 3123415712249621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyPrePost200K400K600K800K1000KMin: 1221288.6 / Avg: 1234156.58 / Max: 1248931.57Min: 1218792.6 / Avg: 1224962.43 / Max: 1236116.351. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyPrePost0.09180.18360.27540.36720.459SE +/- 0.003, N = 3SE +/- 0.002, N = 30.4050.4081. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyPrePost12345Min: 0.4 / Avg: 0.41 / Max: 0.41Min: 0.4 / Avg: 0.41 / Max: 0.411. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 RatingPrePost40K80K120K160K200KSE +/- 496.53, N = 3SE +/- 255.25, N = 31913961928051. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingPrePost30K60K90K120K150KMin: 190476 / Avg: 191395.67 / Max: 192180Min: 192315 / Avg: 192805 / Max: 1931741. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Inner Join Test TimePrePost612182430SE +/- 0.44, N = 3SE +/- 0.42, N = 323.2123.38
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Inner Join Test TimePrePost510152025Min: 22.43 / Avg: 23.21 / Max: 23.95Min: 22.55 / Avg: 23.38 / Max: 23.85

DDraceNetwork

This is a test of DDraceNetwork, an open-source cooperative platformer. Vulkan or OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: MulteasymapPrePost400800120016002000SE +/- 6.46, N = 3SE +/- 18.94, N = 31695.621707.881. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 16.3.2Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: MulteasymapPrePost30060090012001500Min: 1686.36 / Avg: 1695.62 / Max: 1708.05Min: 1670.88 / Avg: 1707.88 / Max: 1733.381. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost0.62781.25561.88342.51123.139SE +/- 0.04, N = 14SE +/- 0.04, N = 152.772.79
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.56 / Avg: 2.77 / Max: 3.06Min: 2.63 / Avg: 2.79 / Max: 3.05

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 100PrePost4K8K12K16K20KSE +/- 22.26, N = 3SE +/- 21.78, N = 318229.7718101.19
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 100PrePost3K6K9K12K15KMin: 18191.62 / Avg: 18229.77 / Max: 18268.71Min: 18057.86 / Avg: 18101.19 / Max: 18126.83

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080PrePost110220330440550SE +/- 4.20, N = 3SE +/- 3.95, N = 3491.95495.37
OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080PrePost90180270360450Min: 486.12 / Avg: 491.95 / Max: 500.11Min: 487.47 / Avg: 495.37 / Max: 499.64

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUPrePost30060090012001500SE +/- 4.82, N = 3SE +/- 6.51, N = 31329.101320.231. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUPrePost2004006008001000Min: 1323.61 / Avg: 1329.1 / Max: 1338.7Min: 1308.06 / Avg: 1320.23 / Max: 1330.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUPrePost612182430SE +/- 0.09, N = 3SE +/- 0.12, N = 324.0624.22MIN: 13.86 / MAX: 52.93MIN: 13.8 / MAX: 55.221. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUPrePost612182430Min: 23.89 / Avg: 24.06 / Max: 24.16Min: 24.04 / Avg: 24.22 / Max: 24.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUPrePost510152025SE +/- 0.04, N = 3SE +/- 0.04, N = 321.2221.36MIN: 12.11 / MAX: 49.33MIN: 12.28 / MAX: 49.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUPrePost510152025Min: 21.14 / Avg: 21.22 / Max: 21.26Min: 21.27 / Avg: 21.36 / Max: 21.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Barbershop - Compute: CPU-OnlyPrePost70140210280350SE +/- 1.70, N = 3SE +/- 1.98, N = 3317.24319.30
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Barbershop - Compute: CPU-OnlyPrePost60120180240300Min: 314.19 / Avg: 317.24 / Max: 320.06Min: 315.78 / Avg: 319.3 / Max: 322.62

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUPrePost30060090012001500SE +/- 2.70, N = 3SE +/- 3.03, N = 31506.321496.691. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUPrePost30060090012001500Min: 1503.52 / Avg: 1506.32 / Max: 1511.72Min: 1492.92 / Avg: 1496.69 / Max: 1502.691. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyPrePost300K600K900K1200K1500KSE +/- 1633.26, N = 3SE +/- 4381.86, N = 3123787012300421. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyPrePost200K400K600K800K1000KMin: 1235708.26 / Avg: 1237870.48 / Max: 1241072.02Min: 1223755.87 / Avg: 1230042.12 / Max: 1238473.381. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughPrePost714212835SE +/- 0.08, N = 3SE +/- 0.06, N = 328.9728.791. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughPrePost612182430Min: 28.84 / Avg: 28.97 / Max: 29.12Min: 28.71 / Avg: 28.79 / Max: 28.911. (CXX) g++ options: -O3 -flto -pthread

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 100PrePost4K8K12K16K20KSE +/- 53.95, N = 3SE +/- 30.58, N = 318289.6118176.78
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 100PrePost3K6K9K12K15KMin: 18196.89 / Avg: 18289.61 / Max: 18383.76Min: 18121.68 / Avg: 18176.78 / Max: 18227.31

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost3691215SE +/- 0.12, N = 3SE +/- 0.02, N = 311.6911.62
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - SHA-512 Benchmark TimePrePost3691215Min: 11.54 / Avg: 11.69 / Max: 11.92Min: 11.58 / Avg: 11.62 / Max: 11.66

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read OnlyPrePost200K400K600K800K1000KSE +/- 5107.95, N = 3SE +/- 795.23, N = 3101471910087521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read OnlyPrePost200K400K600K800K1000KMin: 1005377.04 / Avg: 1014718.94 / Max: 1022970.4Min: 1007517.97 / Avg: 1008752.13 / Max: 1010238.011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.21, N = 3SE +/- 0.12, N = 339.1639.38
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost816243240Min: 38.87 / Avg: 39.16 / Max: 39.57Min: 39.18 / Avg: 39.38 / Max: 39.59

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 1080pPrePost50100150200250SE +/- 2.44, N = 3SE +/- 2.05, N = 3225.06226.321. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 1080pPrePost4080120160200Min: 221.26 / Avg: 225.06 / Max: 229.61Min: 222.89 / Avg: 226.32 / Max: 229.991. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0PrePost20406080100SE +/- 0.40, N = 3SE +/- 0.43, N = 377.0777.471. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0PrePost1530456075Min: 76.4 / Avg: 77.07 / Max: 77.79Min: 76.93 / Avg: 77.47 / Max: 78.321. (CXX) g++ options: -O3 -fPIC -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost918273645SE +/- 0.23, N = 15SE +/- 0.09, N = 338.5338.73
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi BenchmarkPrePost816243240Min: 36.92 / Avg: 38.53 / Max: 39.54Min: 38.55 / Avg: 38.73 / Max: 38.85

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2PrePost918273645SE +/- 0.07, N = 3SE +/- 0.19, N = 341.0941.301. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2PrePost918273645Min: 40.97 / Avg: 41.09 / Max: 41.2Min: 40.97 / Avg: 41.3 / Max: 41.611. (CXX) g++ options: -O3 -fPIC -lm

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyPrePost0.04570.09140.13710.18280.2285SE +/- 0.000, N = 3SE +/- 0.001, N = 30.2020.2031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyPrePost12345Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.2 / Avg: 0.2 / Max: 0.21. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100PrePost20K40K60K80K100KSE +/- 62.36, N = 3SE +/- 137.89, N = 383161.4983564.681. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100PrePost14K28K42K56K70KMin: 83079.61 / Avg: 83161.49 / Max: 83283.9Min: 83364.18 / Avg: 83564.68 / Max: 83828.911. (CC) gcc options: -shared -fPIC -O2

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: UltimatePrePost60120180240300SE +/- 2.83, N = 3SE +/- 2.95, N = 3293.94295.35MIN: 68 / MAX: 674MIN: 73 / MAX: 675
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: UltimatePrePost50100150200250Min: 290.47 / Avg: 293.94 / Max: 299.55Min: 291.73 / Avg: 295.35 / Max: 301.21

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 1080pPrePost70140210280350SE +/- 1.61, N = 3SE +/- 1.46, N = 3343.46345.001. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 1080pPrePost60120180240300Min: 341.15 / Avg: 343.46 / Max: 346.57Min: 342.08 / Avg: 345 / Max: 346.491. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMPrePost306090120150SE +/- 0.26, N = 3SE +/- 0.47, N = 3147.6147.01. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMPrePost306090120150Min: 147.1 / Avg: 147.6 / Max: 148Min: 146.1 / Avg: 147.03 / Max: 147.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200PrePost30K60K90K120K150KSE +/- 244.05, N = 3SE +/- 92.30, N = 3159203.98158586.331. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200PrePost30K60K90K120K150KMin: 158794.54 / Avg: 159203.98 / Max: 159638.81Min: 158492.34 / Avg: 158586.33 / Max: 158770.931. (CC) gcc options: -lcrypt -lz -O3 -march=native

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500PrePost300K600K900K1200K1500KSE +/- 13352.50, N = 15SE +/- 12400.64, N = 151318362.391323405.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500PrePost200K400K600K800K1000KMin: 1221112.62 / Avg: 1318362.39 / Max: 1425492.75Min: 1256461.88 / Avg: 1323405.12 / Max: 1435198.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: HighPrePost100200300400500SE +/- 0.74, N = 3SE +/- 1.56, N = 3438.89440.56MIN: 241 / MAX: 816MIN: 289 / MAX: 830
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: HighPrePost80160240320400Min: 437.67 / Avg: 438.89 / Max: 440.23Min: 437.82 / Avg: 440.56 / Max: 443.22

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 1080pPrePost1122334455SE +/- 0.03, N = 3SE +/- 0.15, N = 347.2747.101. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pPrePost1020304050Min: 47.23 / Avg: 47.27 / Max: 47.33Min: 46.93 / Avg: 47.1 / Max: 47.41. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500PrePost30K60K90K120K150KSE +/- 187.50, N = 3SE +/- 218.62, N = 3159778.83159244.191. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500PrePost30K60K90K120K150KMin: 159428.39 / Avg: 159778.83 / Max: 160069.63Min: 158896.97 / Avg: 159244.19 / Max: 159647.941. (CC) gcc options: -lcrypt -lz -O3 -march=native

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMPrePost1326395265SE +/- 0.06, N = 3SE +/- 0.03, N = 360.059.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMPrePost1224364860Min: 59.9 / Avg: 60 / Max: 60.1Min: 59.7 / Avg: 59.77 / Max: 59.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

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 4KPrePost510152025SE +/- 0.04, N = 3SE +/- 0.08, N = 321.1021.171. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KPrePost510152025Min: 21.04 / Avg: 21.1 / Max: 21.19Min: 21.08 / Avg: 21.17 / Max: 21.331. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost612182430SE +/- 0.19, N = 3SE +/- 0.22, N = 324.4024.32
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Broadcast Inner Join Test TimePrePost612182430Min: 24.06 / Avg: 24.4 / Max: 24.7Min: 23.94 / Avg: 24.32 / Max: 24.71

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost3691215SE +/- 0.10, N = 14SE +/- 0.10, N = 1512.5412.58
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - SHA-512 Benchmark TimePrePost48121620Min: 12.11 / Avg: 12.54 / Max: 13.62Min: 11.9 / Avg: 12.58 / Max: 13.3

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Group By Test TimePrePost246810SE +/- 0.04, N = 15SE +/- 0.06, N = 36.316.33
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Group By Test TimePrePost3691215Min: 6.03 / Avg: 6.31 / Max: 6.59Min: 6.22 / Avg: 6.33 / Max: 6.41

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUPrePost246810SE +/- 0.03, N = 3SE +/- 0.04, N = 36.506.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUPrePost3691215Min: 6.45 / Avg: 6.5 / Max: 6.56Min: 6.41 / Avg: 6.48 / Max: 6.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumPrePost50100150200250SE +/- 0.35, N = 3SE +/- 0.15, N = 3231.92231.221. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumPrePost4080120160200Min: 231.38 / Avg: 231.92 / Max: 232.57Min: 230.93 / Avg: 231.22 / Max: 231.451. (CXX) g++ options: -O3 -flto -pthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessPrePost1.19612.39223.58834.78445.9805SE +/- 0.007, N = 3SE +/- 0.026, N = 35.3005.3161. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessPrePost246810Min: 5.29 / Avg: 5.3 / Max: 5.31Min: 5.28 / Avg: 5.32 / Max: 5.371. (CXX) g++ options: -O3 -fPIC -lm

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMPrePost4080120160200SE +/- 0.00, N = 3SE +/- 0.09, N = 3166.5166.01. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMPrePost306090120150Min: 166.5 / Avg: 166.5 / Max: 166.5Min: 165.9 / Avg: 166.03 / Max: 166.21. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionPrePost0.74931.49862.24792.99723.7465SE +/- 0.01, N = 3SE +/- 0.00, N = 33.323.331. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionPrePost246810Min: 3.31 / Avg: 3.32 / Max: 3.34Min: 3.33 / Avg: 3.33 / Max: 3.331. (CC) gcc options: -fvisibility=hidden -O2 -lm

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMPrePost20406080100SE +/- 0.00, N = 3SE +/- 0.10, N = 3103.5103.21. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMPrePost20406080100Min: 103.5 / Avg: 103.5 / Max: 103.5Min: 103.1 / Avg: 103.2 / Max: 103.41. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Repartition Test TimePrePost510152025SE +/- 0.41, N = 3SE +/- 0.33, N = 320.6820.74
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 100 - Repartition Test TimePrePost510152025Min: 19.86 / Avg: 20.68 / Max: 21.16Min: 20.08 / Avg: 20.74 / Max: 21.19

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pPrePost60120180240300SE +/- 2.98, N = 3SE +/- 2.42, N = 3259.95259.211. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pPrePost50100150200250Min: 255.13 / Avg: 259.95 / Max: 265.39Min: 254.37 / Avg: 259.21 / Max: 261.771. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 2.3Time To CompilePrePost1122334455SE +/- 0.15, N = 3SE +/- 0.07, N = 349.0948.961. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 2.3Time To CompilePrePost1020304050Min: 48.89 / Avg: 49.09 / Max: 49.4Min: 48.84 / Avg: 48.96 / Max: 49.11. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 20PrePost40K80K120K160K200KSE +/- 211.96, N = 3SE +/- 205.09, N = 3167443.62167908.471. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 20PrePost30K60K90K120K150KMin: 167116.95 / Avg: 167443.62 / Max: 167840.93Min: 167559.66 / Avg: 167908.47 / Max: 168269.791. (CC) gcc options: -lcrypt -lz -O3 -march=native

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 1000PrePost400K800K1200K1600K2000KSE +/- 5666.30, N = 3SE +/- 15686.73, N = 71724111.211719383.041. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 1000PrePost300K600K900K1200K1500KMin: 1714440.38 / Avg: 1724111.21 / Max: 1734063Min: 1630938.75 / Avg: 1719383.04 / Max: 1754573.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Inner Join Test TimePrePost0.82131.64262.46393.28524.1065SE +/- 0.03, N = 3SE +/- 0.06, N = 33.643.65
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Inner Join Test TimePrePost246810Min: 3.57 / Avg: 3.64 / Max: 3.68Min: 3.59 / Avg: 3.65 / Max: 3.78

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Repartition Test TimePrePost246810SE +/- 0.07, N = 14SE +/- 0.08, N = 157.477.49
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 2000 - Repartition Test TimePrePost3691215Min: 7.09 / Avg: 7.47 / Max: 7.88Min: 7.2 / Avg: 7.49 / Max: 8.15

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6PrePost0.86631.73262.59893.46524.3315SE +/- 0.012, N = 3SE +/- 0.014, N = 33.8403.8501. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6PrePost246810Min: 3.82 / Avg: 3.84 / Max: 3.86Min: 3.83 / Avg: 3.85 / Max: 3.881. (CXX) g++ options: -O3 -fPIC -lm

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompilePrePost3691215SE +/- 0.02, N = 3SE +/- 0.05, N = 312.7212.69
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompilePrePost48121620Min: 12.67 / Avg: 12.72 / Max: 12.75Min: 12.6 / Avg: 12.69 / Max: 12.76

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMPrePost306090120150SE +/- 0.83, N = 3SE +/- 0.32, N = 3156.0156.41. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMPrePost306090120150Min: 154.3 / Avg: 155.97 / Max: 156.8Min: 156 / Avg: 156.37 / Max: 1571. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000PrePost30K60K90K120K150KSE +/- 30.13, N = 3SE +/- 109.81, N = 3158800.01158395.161. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000PrePost30K60K90K120K150KMin: 158764.27 / Avg: 158800.01 / Max: 158859.9Min: 158275.5 / Avg: 158395.16 / Max: 158614.481. (CC) gcc options: -lcrypt -lz -O3 -march=native

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pPrePost70140210280350SE +/- 2.12, N = 3SE +/- 0.47, N = 3334.46333.611. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pPrePost60120180240300Min: 331.55 / Avg: 334.46 / Max: 338.59Min: 332.68 / Avg: 333.61 / Max: 334.21. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: UltraPrePost60120180240300SE +/- 2.90, N = 3SE +/- 0.47, N = 3253.4254.0
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: UltraPrePost50100150200250Min: 248.7 / Avg: 253.4 / Max: 258.7Min: 253.3 / Avg: 254.03 / Max: 254.9

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: UltraPrePost90180270360450SE +/- 2.19, N = 3SE +/- 1.50, N = 3403.63402.70MIN: 209 / MAX: 723MIN: 249 / MAX: 713
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 1920 x 1080 - Effects Quality: UltraPrePost70140210280350Min: 399.84 / Avg: 403.63 / Max: 407.43Min: 400.6 / Avg: 402.7 / Max: 405.62

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To CompilePrePost4080120160200SE +/- 0.71, N = 3SE +/- 0.18, N = 3195.31194.88
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To CompilePrePost4080120160200Min: 194.27 / Avg: 195.31 / Max: 196.68Min: 194.52 / Avg: 194.88 / Max: 195.13

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMPrePost80160240320400SE +/- 0.64, N = 3SE +/- 0.18, N = 3361.0360.21. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMPrePost60120180240300Min: 359.7 / Avg: 360.97 / Max: 361.7Min: 359.9 / Avg: 360.23 / Max: 360.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMPrePost80160240320400SE +/- 0.74, N = 3SE +/- 0.64, N = 3387.6386.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMPrePost70140210280350Min: 386.1 / Avg: 387.57 / Max: 388.5Min: 385.7 / Avg: 386.8 / Max: 387.91. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUPrePost10002000300040005000SE +/- 24.52, N = 3SE +/- 29.58, N = 34808.094817.76MIN: 3351.25 / MAX: 5995.41MIN: 2234.82 / MAX: 5891.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUPrePost8001600240032004000Min: 4765.52 / Avg: 4808.09 / Max: 4850.47Min: 4769.34 / Avg: 4817.76 / Max: 4871.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUPrePost3691215SE +/- 0.03, N = 3SE +/- 0.04, N = 310.1510.131. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUPrePost3691215Min: 10.11 / Avg: 10.15 / Max: 10.2Min: 10.07 / Avg: 10.13 / Max: 10.21. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

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 RatingPrePost80K160K240K320K400KSE +/- 1775.17, N = 3SE +/- 1936.05, N = 33651833644801. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingPrePost60K120K180K240K300KMin: 362278 / Avg: 365182.67 / Max: 368403Min: 361572 / Avg: 364479.67 / Max: 3681481. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 1000PrePost11K22K33K44K55KSE +/- 64.10, N = 3SE +/- 74.50, N = 351027.3351122.70
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 1000PrePost9K18K27K36K45KMin: 50915.32 / Avg: 51027.33 / Max: 51137.34Min: 51045.82 / Avg: 51122.7 / Max: 51271.69

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUPrePost1326395265SE +/- 0.09, N = 3SE +/- 0.04, N = 360.0260.13MIN: 19.69 / MAX: 106.62MIN: 17.74 / MAX: 105.551. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUPrePost1224364860Min: 59.87 / Avg: 60.02 / Max: 60.18Min: 60.05 / Avg: 60.13 / Max: 60.181. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUPrePost120240360480600SE +/- 0.76, N = 3SE +/- 0.35, N = 3532.44531.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUPrePost90180270360450Min: 531.09 / Avg: 532.44 / Max: 533.71Min: 530.98 / Avg: 531.47 / Max: 532.151. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Timed PHP Compilation

This test times how long it takes to build PHP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompilePrePost1122334455SE +/- 0.01, N = 3SE +/- 0.08, N = 350.6150.70
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompilePrePost1020304050Min: 50.59 / Avg: 50.61 / Max: 50.63Min: 50.55 / Avg: 50.7 / Max: 50.8

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KPrePost20406080100SE +/- 0.54, N = 3SE +/- 0.42, N = 3109.59109.781. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KPrePost20406080100Min: 108.76 / Avg: 109.59 / Max: 110.59Min: 109.23 / Avg: 109.78 / Max: 110.611. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUPrePost7001400210028003500SE +/- 10.50, N = 3SE +/- 10.14, N = 33106.873111.86MIN: 1660.75 / MAX: 3844.98MIN: 1704.05 / MAX: 3875.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUPrePost5001000150020002500Min: 3089.09 / Avg: 3106.87 / Max: 3125.43Min: 3093.65 / Avg: 3111.86 / Max: 3128.691. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompilePrePost510152025SE +/- 0.05, N = 3SE +/- 0.03, N = 319.0319.00
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompilePrePost510152025Min: 18.93 / Avg: 19.03 / Max: 19.08Min: 18.94 / Avg: 19 / Max: 19.04

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 1000PrePost12K24K36K48K60KSE +/- 110.49, N = 3SE +/- 27.51, N = 356371.6056459.85
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 1000PrePost10K20K30K40K50KMin: 56190.01 / Avg: 56371.6 / Max: 56571.45Min: 56415.43 / Avg: 56459.85 / Max: 56510.16

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUPrePost246810SE +/- 0.02, N = 3SE +/- 0.04, N = 36.446.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUPrePost3691215Min: 6.41 / Avg: 6.44 / Max: 6.46Min: 6.37 / Avg: 6.45 / Max: 6.51. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Second RunPrePost60120180240300SE +/- 1.65, N = 13SE +/- 1.67, N = 12255.09254.73MIN: 18.52 / MAX: 20000MIN: 18.43 / MAX: 200001. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Second RunPrePost50100150200250Min: 244.33 / Avg: 255.09 / Max: 267.53Min: 245.71 / Avg: 254.73 / Max: 265.741. ClickHouse server version 22.5.4.19 (official build).

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMPrePost80160240320400SE +/- 1.08, N = 3SE +/- 1.10, N = 3387.0387.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMPrePost70140210280350Min: 384.9 / Avg: 387.03 / Max: 388.4Min: 385.7 / Avg: 387.53 / Max: 389.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

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 5.18Build: defconfigPrePost816243240SE +/- 0.32, N = 6SE +/- 0.38, N = 534.0734.11
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: defconfigPrePost714212835Min: 33.6 / Avg: 34.07 / Max: 35.66Min: 33.61 / Avg: 34.11 / Max: 35.63

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100PrePost30K60K90K120K150KSE +/- 504.73, N = 3SE +/- 411.18, N = 3158355.46158154.461. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100PrePost30K60K90K120K150KMin: 157704.35 / Avg: 158355.46 / Max: 159349.08Min: 157483.19 / Avg: 158154.46 / Max: 158901.491. (CC) gcc options: -lcrypt -lz -O3 -march=native

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultPrePost48121620SE +/- 0.03, N = 3SE +/- 0.08, N = 317.1017.121. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultPrePost48121620Min: 17.03 / Avg: 17.1 / Max: 17.13Min: 16.96 / Avg: 17.12 / Max: 17.21. (CC) gcc options: -fvisibility=hidden -O2 -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 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerPrePost20K40K60K80K100KSE +/- 82.46, N = 3SE +/- 6.69, N = 391009909041. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerPrePost16K32K48K64K80KMin: 90883 / Avg: 91008.67 / Max: 91164Min: 90893 / Avg: 90903.67 / Max: 909161. (CXX) g++ options: -O3 -lm -ldl

GravityMark

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.72Resolution: 1920 x 1080 - Renderer: VulkanPrePost20406080100SE +/- 0.00, N = 3SE +/- 0.15, N = 3100.7100.8
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.72Resolution: 1920 x 1080 - Renderer: VulkanPrePost20406080100Min: 100.7 / Avg: 100.7 / Max: 100.7Min: 100.6 / Avg: 100.8 / Max: 101.1

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100PrePost3691215SE +/- 0.00, N = 3SE +/- 0.03, N = 310.7010.691. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100PrePost3691215Min: 10.69 / Avg: 10.7 / Max: 10.7Min: 10.64 / Avg: 10.69 / Max: 10.751. (CC) gcc options: -fvisibility=hidden -O2 -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 4KPrePost306090120150SE +/- 0.88, N = 3SE +/- 0.25, N = 3137.11137.221. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 4KPrePost306090120150Min: 135.96 / Avg: 137.11 / Max: 138.85Min: 136.83 / Avg: 137.22 / Max: 137.691. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompilePrePost612182430SE +/- 0.10, N = 3SE +/- 0.02, N = 324.0524.03
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompilePrePost612182430Min: 23.85 / Avg: 24.05 / Max: 24.18Min: 24 / Avg: 24.03 / Max: 24.08

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaPrePost4080120160200SE +/- 0.66, N = 3SE +/- 0.16, N = 3183.92184.03
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaPrePost306090120150Min: 183.07 / Avg: 183.92 / Max: 185.22Min: 183.72 / Avg: 184.03 / Max: 184.27

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 4KPrePost306090120150SE +/- 0.89, N = 3SE +/- 1.13, N = 12118.70118.631. (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 4KPrePost20406080100Min: 117 / Avg: 118.7 / Max: 119.98Min: 106.33 / Avg: 118.63 / Max: 120.511. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 1000PrePost11K22K33K44K55KSE +/- 123.18, N = 3SE +/- 79.98, N = 350651.4450622.76
OpenBenchmarking.orgRequests/sec, More Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 1000PrePost9K18K27K36K45KMin: 50470.55 / Avg: 50651.44 / Max: 50886.72Min: 50466.47 / Avg: 50622.76 / Max: 50730.39

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 4KPrePost20406080100SE +/- 0.15, N = 3SE +/- 0.31, N = 394.0894.131. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 4KPrePost20406080100Min: 93.9 / Avg: 94.08 / Max: 94.38Min: 93.63 / Avg: 94.13 / Max: 94.71. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerPrePost20K40K60K80K100KSE +/- 137.05, N = 3SE +/- 229.06, N = 31073441073981. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerPrePost20K40K60K80K100KMin: 107090 / Avg: 107344.33 / Max: 107560Min: 107060 / Avg: 107398.33 / Max: 1078351. (CXX) g++ options: -O3 -lm -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average LatencyPrePost48121620SE +/- 0.18, N = 3SE +/- 0.01, N = 313.9913.991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average LatencyPrePost48121620Min: 13.67 / Avg: 13.99 / Max: 14.3Min: 13.98 / Avg: 13.99 / Max: 141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Vulkan - AF: On - MSAA: On - Resolution: 1920 x 1080PrePost2004006008001000SE +/- 0.57, N = 3SE +/- 1.56, N = 31057.51058.01. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Vulkan - AF: On - MSAA: On - Resolution: 1920 x 1080PrePost2004006008001000Min: 1056.9 / Avg: 1057.47 / Max: 1058.6Min: 1055.1 / Avg: 1058.03 / Max: 1060.41. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: MediumPrePost60120180240300SE +/- 1.47, N = 3SE +/- 0.48, N = 3257.8257.9
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.53Resolution: 1920 x 1080 - Effects Quality: MediumPrePost50100150200250Min: 254.9 / Avg: 257.83 / Max: 259.5Min: 257 / Avg: 257.93 / Max: 258.6

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUPrePost10002000300040005000SE +/- 7.06, N = 3SE +/- 32.71, N = 34830.954829.13MIN: 2043.69 / MAX: 6200.37MIN: 2119.17 / MAX: 5968.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUPrePost8001600240032004000Min: 4819.6 / Avg: 4830.95 / Max: 4843.91Min: 4795.13 / Avg: 4829.13 / Max: 4894.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerPrePost7001400210028003500SE +/- 2.85, N = 3SE +/- 1.00, N = 3316231611. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerPrePost5001000150020002500Min: 3159 / Avg: 3162.33 / Max: 3168Min: 3160 / Avg: 3161 / Max: 31631. (CXX) g++ options: -O3 -lm -ldl

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompilePrePost714212835SE +/- 0.06, N = 3SE +/- 0.04, N = 327.7527.76
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompilePrePost612182430Min: 27.66 / Avg: 27.75 / Max: 27.86Min: 27.71 / Avg: 27.76 / Max: 27.83

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read WritePrePost15003000450060007500SE +/- 93.93, N = 3SE +/- 3.12, N = 3714871501. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read WritePrePost12002400360048006000Min: 6991.47 / Avg: 7148.26 / Max: 7316.28Min: 7145.63 / Avg: 7149.55 / Max: 7155.711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMPrePost80160240320400SE +/- 0.37, N = 3SE +/- 0.64, N = 3362.7362.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMPrePost60120180240300Min: 362.3 / Avg: 362.67 / Max: 363.4Min: 361.8 / Avg: 362.8 / Max: 3641. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

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 5.18Build: allmodconfigPrePost60120180240300SE +/- 0.53, N = 3SE +/- 0.87, N = 3295.07295.00
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: allmodconfigPrePost50100150200250Min: 294.43 / Avg: 295.07 / Max: 296.11Min: 293.92 / Avg: 295 / Max: 296.71

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 1080pPrePost100200300400500SE +/- 0.30, N = 3SE +/- 1.02, N = 3450.56450.461. (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 1080pPrePost80160240320400Min: 450.11 / Avg: 450.56 / Max: 451.13Min: 449.44 / Avg: 450.46 / Max: 452.491. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KPrePost20406080100SE +/- 1.20, N = 3SE +/- 1.13, N = 15104.43104.441. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KPrePost20406080100Min: 102.29 / Avg: 104.43 / Max: 106.46Min: 89.15 / Avg: 104.44 / Max: 106.831. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Inner Join Test TimePrePost0.58281.16561.74842.33122.914SE +/- 0.04, N = 15SE +/- 0.04, N = 32.592.59
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Inner Join Test TimePrePost246810Min: 2.36 / Avg: 2.59 / Max: 2.9Min: 2.54 / Avg: 2.59 / Max: 2.67

etcd

Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 1000 - Average LatencyPrePost48121620SE +/- 0.03, N = 3SE +/- 0.00, N = 317.717.7
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 1000 - Average LatencyPrePost48121620Min: 17.7 / Avg: 17.73 / Max: 17.8Min: 17.7 / Avg: 17.7 / Max: 17.7

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 1000 - Average LatencyPrePost510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 319.519.5
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 1000 - Average LatencyPrePost510152025Min: 19.5 / Avg: 19.53 / Max: 19.6Min: 19.4 / Avg: 19.47 / Max: 19.5

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 100 - Average LatencyPrePost1.2152.433.6454.866.075SE +/- 0.00, N = 3SE +/- 0.00, N = 35.45.4
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 500 - Clients: 100 - Average LatencyPrePost246810Min: 5.4 / Avg: 5.4 / Max: 5.4Min: 5.4 / Avg: 5.4 / Max: 5.4

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 1000 - Average LatencyPrePost510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 319.719.7
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 1000 - Average LatencyPrePost510152025Min: 19.6 / Avg: 19.67 / Max: 19.7Min: 19.6 / Avg: 19.67 / Max: 19.7

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 100 - Average LatencyPrePost1.23752.4753.71254.956.1875SE +/- 0.00, N = 3SE +/- 0.00, N = 35.55.5
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 100 - Clients: 100 - Average LatencyPrePost246810Min: 5.5 / Avg: 5.5 / Max: 5.5Min: 5.5 / Avg: 5.5 / Max: 5.5

OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 100 - Average LatencyPrePost1.23752.4753.71254.956.1875SE +/- 0.03, N = 3SE +/- 0.00, N = 35.55.5
OpenBenchmarking.orgms, Fewer Is Betteretcd 3.5.4Test: RANGE - Connections: 50 - Clients: 100 - Average LatencyPrePost246810Min: 5.4 / Avg: 5.47 / Max: 5.5Min: 5.5 / Avg: 5.5 / Max: 5.5

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 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerPrePost6001200180024003000SE +/- 6.06, N = 3SE +/- 8.88, N = 3263926391. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerPrePost5001000150020002500Min: 2629 / Avg: 2639.33 / Max: 2650Min: 2621 / Avg: 2638.67 / Max: 26491. (CXX) g++ options: -O3 -lm -ldl

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Lossless CompressionPrePost0.01130.02260.03390.04520.0565SE +/- 0.00, N = 3SE +/- 0.00, N = 30.050.051. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Lossless CompressionPrePost12345Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.051. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionPrePost0.1350.270.4050.540.675SE +/- 0.00, N = 3SE +/- 0.00, N = 30.600.601. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionPrePost246810Min: 0.6 / Avg: 0.6 / Max: 0.6Min: 0.6 / Avg: 0.6 / Max: 0.61. (CC) gcc options: -fvisibility=hidden -O2 -lm

memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

Protocol: Redis - Clients: 100 - Set To Get Ratio: 5:1

Pre: The test run did not produce a result.

Post: The test run did not produce a result.

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

Clients: 200 - Set To Get Ratio: 5:1

Pre: The test run did not produce a result.

Post: The test run did not produce a result.

Clients: 200 - Set To Get Ratio: 1:5

Pre: The test run did not produce a result.

Post: The test run did not produce a result.

Clients: 200 - Set To Get Ratio: 1:1

Pre: The test run did not produce a result.

Post: The test run did not produce a result.

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Group By Test TimePrePost714212835SE +/- 0.89, N = 3SE +/- 1.38, N = 332.0130.98
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Group By Test TimePrePost714212835Min: 30.26 / Avg: 32.01 / Max: 33.16Min: 28.25 / Avg: 30.98 / Max: 32.59

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost0.6391.2781.9172.5563.195SE +/- 0.05, N = 3SE +/- 0.10, N = 32.802.84
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.73 / Avg: 2.8 / Max: 2.91Min: 2.68 / Avg: 2.84 / Max: 3.04

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost0.64131.28261.92392.56523.2065SE +/- 0.06, N = 3SE +/- 0.12, N = 32.852.79
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.74 / Avg: 2.85 / Max: 2.92Min: 2.66 / Avg: 2.79 / Max: 3.04

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Repartition Test TimePrePost0.83251.6652.49753.334.1625SE +/- 0.09, N = 3SE +/- 0.13, N = 33.703.59
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Repartition Test TimePrePost246810Min: 3.6 / Avg: 3.7 / Max: 3.89Min: 3.37 / Avg: 3.59 / Max: 3.82

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Group By Test TimePrePost246810SE +/- 0.26, N = 3SE +/- 0.09, N = 37.397.33
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Group By Test TimePrePost3691215Min: 6.99 / Avg: 7.39 / Max: 7.87Min: 7.18 / Avg: 7.33 / Max: 7.49

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost0.6211.2421.8632.4843.105SE +/- 0.06, N = 3SE +/- 0.12, N = 32.762.72
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.66 / Avg: 2.76 / Max: 2.88Min: 2.56 / Avg: 2.72 / Max: 2.97

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost0.4230.8461.2691.6922.115SE +/- 0.03, N = 15SE +/- 0.09, N = 31.791.88
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test TimePrePost246810Min: 1.59 / Avg: 1.79 / Max: 2.15Min: 1.76 / Avg: 1.88 / Max: 2.05

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Repartition Test TimePrePost0.6751.352.0252.73.375SE +/- 0.06, N = 15SE +/- 0.15, N = 32.943.00
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Repartition Test TimePrePost246810Min: 2.71 / Avg: 2.94 / Max: 3.62Min: 2.74 / Avg: 3 / Max: 3.25

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost0.6031.2061.8092.4123.015SE +/- 0.04, N = 15SE +/- 0.12, N = 32.682.66
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframePrePost246810Min: 2.5 / Avg: 2.68 / Max: 3Min: 2.51 / Avg: 2.66 / Max: 2.9

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, First Run / Cold CachePrePost50100150200250SE +/- 5.22, N = 13SE +/- 5.79, N = 12245.16244.82MIN: 18.55 / MAX: 20000MIN: 18.71 / MAX: 200001. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, First Run / Cold CachePrePost4080120160200Min: 185.51 / Avg: 245.16 / Max: 260.03Min: 183.43 / Avg: 244.82 / Max: 260.111. ClickHouse server version 22.5.4.19 (official build).

216 Results Shown

DDraceNetwork:
  1920 x 1080 - Fullscreen - Vulkan - Default - RaiNyMore2 - Total Frame Time
  1920 x 1080 - Fullscreen - Vulkan - Default - Multeasymap - Total Frame Time
etcd:
  PUT - 500 - 100 - Average Latency
  PUT - 500 - 100
  PUT - 100 - 100
  PUT - 50 - 100
  PUT - 100 - 100 - Average Latency
  PUT - 50 - 100 - Average Latency
Apache HTTP Server
Redis
etcd:
  PUT - 50 - 1000
  PUT - 50 - 1000 - Average Latency
  PUT - 100 - 1000 - Average Latency
  PUT - 100 - 1000
Apache HTTP Server
Apache Spark
WebP2 Image Encode:
  Quality 95, Compression Effort 7
  Quality 75, Compression Effort 7
Apache Spark
etcd
Apache Spark
etcd
Apache Spark
BRL-CAD
yquake2
Redis
WebP2 Image Encode
PostgreSQL pgbench
Apache Spark
PostgreSQL pgbench
OpenVINO
ASTC Encoder
Redis
Blender
Apache Spark:
  10000000 - 100 - Repartition Test Time
  10000000 - 100 - Group By Test Time
  10000000 - 2000 - Calculate Pi Benchmark
OpenVINO
Apache Spark:
  40000000 - 2000 - Repartition Test Time
  1000000 - 2000 - Broadcast Inner Join Test Time
  10000000 - 2000 - Inner Join Test Time
Node.js V8 Web Tooling Benchmark
Dragonflydb
Apache Spark:
  40000000 - 2000 - SHA-512 Benchmark Time
  10000000 - 2000 - Broadcast Inner Join Test Time
  40000000 - 100 - SHA-512 Benchmark Time
Dragonflydb
memtier_benchmark
Apache Spark
OpenFOAM
memtier_benchmark
DDraceNetwork
nginx
WebP2 Image Encode
Apache Spark
Apache HTTP Server
WebP Image Encode
SVT-HEVC
Apache Spark:
  40000000 - 100 - Group By Test Time
  40000000 - 2000 - Calculate Pi Benchmark
Dragonflydb
ClickHouse
libavif avifenc
OpenVINO
SVT-VP9
Redis
Apache HTTP Server
Apache Spark
PostgreSQL pgbench
Apache Spark
ASTC Encoder
srsRAN
Apache HTTP Server
PostgreSQL pgbench:
  100 - 500 - Read Write - Average Latency
  100 - 100 - Read Only - Average Latency
Xonotic
SVT-HEVC
OpenVINO
SVT-AV1
OpenVINO
Blender
SVT-VP9
OpenVINO:
  Weld Porosity Detection FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
Timed LLVM Compilation
srsRAN
OpenVINO:
  Face Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
etcd
OpenFOAM
Unvanquished
OpenVINO
Timed Godot Game Engine Compilation
Apache Spark
SVT-AV1
PostgreSQL pgbench:
  100 - 500 - Read Only
  100 - 500 - Read Only - Average Latency
7-Zip Compression
Apache Spark
DDraceNetwork
Apache Spark
etcd
Tesseract
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    ms
Blender
OpenVINO
PostgreSQL pgbench
ASTC Encoder
etcd
Apache Spark
PostgreSQL pgbench
Apache Spark
SVT-AV1
libavif avifenc
Apache Spark
libavif avifenc
PostgreSQL pgbench
Apache HTTP Server
Xonotic
SVT-AV1
srsRAN
nginx
Redis
Xonotic
x265
nginx
srsRAN
x265
Apache Spark:
  40000000 - 2000 - Broadcast Inner Join Test Time
  10000000 - 2000 - SHA-512 Benchmark Time
  1000000 - 100 - Group By Test Time
OpenVINO
ASTC Encoder
libavif avifenc
srsRAN
WebP Image Encode
srsRAN
Apache Spark
SVT-VP9
Timed Wasmer Compilation
nginx
Redis
Apache Spark:
  1000000 - 2000 - Inner Join Test Time
  10000000 - 2000 - Repartition Test Time
libavif avifenc
Timed MPlayer Compilation
srsRAN
nginx
SVT-VP9
Unvanquished
Xonotic
Timed Node.js Compilation
srsRAN:
  4G PHY_DL_Test 100 PRB MIMO 64-QAM
  4G PHY_DL_Test 100 PRB SISO 256-QAM
OpenVINO:
  Person Detection FP16 - CPU
  Face Detection FP16 - CPU
7-Zip Compression
etcd
OpenVINO:
  Vehicle Detection FP16 - CPU:
    ms
    FPS
Timed PHP Compilation
SVT-VP9
OpenVINO
Timed FFmpeg Compilation
etcd
OpenVINO
ClickHouse
srsRAN
Timed Linux Kernel Compilation
nginx
WebP Image Encode
OSPRay Studio
GravityMark
WebP Image Encode
SVT-AV1
Timed Apache Compilation
Timed LLVM Compilation
SVT-HEVC
etcd
SVT-AV1
OSPRay Studio
PostgreSQL pgbench
yquake2
Unvanquished
OpenVINO
OSPRay Studio
Timed Mesa Compilation
PostgreSQL pgbench
srsRAN
Timed Linux Kernel Compilation
SVT-HEVC
SVT-VP9
Apache Spark
etcd:
  RANGE - 500 - 1000 - Average Latency
  RANGE - 100 - 1000 - Average Latency
  RANGE - 500 - 100 - Average Latency
  RANGE - 50 - 1000 - Average Latency
  RANGE - 100 - 100 - Average Latency
  RANGE - 50 - 100 - Average Latency
OSPRay Studio
WebP2 Image Encode
WebP Image Encode
Apache Spark:
  40000000 - 2000 - Group By Test Time
  40000000 - 2000 - Calculate Pi Benchmark Using Dataframe
  10000000 - 100 - Calculate Pi Benchmark Using Dataframe
  1000000 - 2000 - Repartition Test Time
  1000000 - 2000 - Group By Test Time
  1000000 - 2000 - Calculate Pi Benchmark Using Dataframe
  1000000 - 100 - Broadcast Inner Join Test Time
  1000000 - 100 - Repartition Test Time
  1000000 - 100 - Calculate Pi Benchmark Using Dataframe
ClickHouse

Pre

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc7daily20220926-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.1.7 (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055
Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 September 2022 20:38 by user pts.

Post

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc7daily20220927-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.1.7 (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055
Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 27 September 2022 08:03 by user pts.