Linux 5.18 sched-core AMD NUMA Change

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2203068-PTS-LINUX51857&grs.

Linux 5.18 sched-core AMD NUMA ChangeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolutionsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3904 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 PlusAMD Radeon RX 6800 (2475/1000MHz)AMD Navi 21 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.045.17.0-rc1-sched-core-phx (x86_64)GNOME Shell 41.3X Server 1.20.144.6 Mesa 22.1.0-devel (git-9da3d71 2022-02-05 jammy-oibaf-ppa) (LLVM 13.0.0 DRM 3.44)1.3.204GCC 11.2.0ext43840x21605.17.0-051700rc4daily20220218-generic (x86_64)5.17.0-rc1-sched-core-phx (x86_64)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-O5cEXJ/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-O5cEXJ/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016Graphics Details- BAR1 / Visible vRAM Size: 16368 MBSecurity Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.18 sched-core AMD NUMA Changepgbench: 100 - 100 - Read Only - Average Latencypgbench: 100 - 100 - Read Onlybasemark: OpenGL - 1920 x 1080 - Highaskap: tConvolve MPI - Griddingmrbayes: Primate Phylogeny Analysisluxcorerender: Danish Mood - CPUaom-av1: Speed 8 Realtime - Bosphorus 4Kpgbench: 100 - 100 - Read Write - Average Latencypgbench: 100 - 100 - Read Writepgbench: 100 - 50 - Read Onlyunvanquished: 3840 x 2160 - Mediumpgbench: 100 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Writeinfluxdb: 64 - 10000 - 2,5000,1 - 10000pgbench: 100 - 50 - Read Only - Average Latencyaskap: tConvolve MPI - Degriddingrocksdb: Read While Writingbuild-linux-kernel: defconfiggravitymark: 1920 x 1080 - Vulkangromacs: MPI CPU - water_GMX50_bareluxcorerender: DLSC - CPUpgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writeunvanquished: 3840 x 2160 - Highsqlite-speedtest: Timed Time - Size 1,000askap: tConvolve OpenMP - Griddingkeydb: pgbench: 100 - 250 - Read Onlyaskap: tConvolve OpenMP - Degriddinginfluxdb: 4 - 10000 - 2,5000,1 - 10000rocksdb: Rand Readpgbench: 100 - 250 - Read Only - Average Latencygravitymark: 1920 x 1080 - OpenGLrocksdb: Rand Fillnamd: ATPase Simulation - 327,506 Atomsaskap: tConvolve MT - Griddingbasemark: Vulkan - 1920 x 1080 - Highaskap: tConvolve MT - Degriddingrocksdb: Update Randbasemark: Vulkan - 1920 x 1080 - Mediumbasemark: OpenGL - 1920 x 1080 - Mediummysqlslap: 64mysqlslap: 32mysqlslap: 16mysqlslap: 8aom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kunvanquished: 3840 x 2160 - Ultrasched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.178562617166.806559.8989.4052.9945.936.91514481546830413.93.884128782429787.80.0916505.90399748948.826190.21.2583.5615.53216096395.342.3022699.34817041.545928613247.021991313.41161781590.422188.713641311.09599786.822339.111355.867932141750.95441.5175014231583214058.8558.84385.10.167597703164.976642.9392.7042.9345.186.67414986563727401.73.856129722419457.10.0896480.86401437548.479187.01.2793.5915.46316175390.841.8172680.49813258.375913583273.751982541.31160515240.423188.613596351.09861784.192338.971352.927927271751.28390.6279013141629164064.4658.08387.90.170589486163.476728.0993.5812.9344.296.75114813554267404.53.968126252367595.50.0906615.25394020648.389189.91.2753.5415.67115966395.842.3122698.97809585.045875463260.381997610.41153284220.425188.313672211.09677787.667338.891354.287917631749.00418.9583314981623213858.8156.38391.00.177566101172.276400.5389.1093.0445.506.72814888548919410.43.909127890.0916506.5647.924190.31.2753.5415.57316053394.142.0602707.75815619.455913763260.380.423189.61.09376786.020339.891353.7880013181529181860.8058.55396.2OpenBenchmarking.org

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.04010.08020.12030.16040.2005SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1780.1670.1700.1771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Onlysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4130K260K390K520K650KSE +/- 498.19, N = 3SE +/- 2821.67, N = 3SE +/- 5225.26, N = 3SE +/- 3066.01, N = 35626175977035894865661011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Basemark GPU

Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: High

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: Highsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP44080120160200SE +/- 2.00, N = 3SE +/- 1.21, N = 15SE +/- 1.92, N = 3SE +/- 1.94, N = 3166.80164.97163.47172.27MIN: 98.55 / MAX: 537.96MIN: 95.95 / MAX: 538.6MIN: 98.53 / MAX: 545.89MIN: 103.04 / MAX: 536

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Griddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP414002800420056007000SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 45.07, N = 36559.896642.936728.096400.531. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysissched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP420406080100SE +/- 1.12, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 389.4192.7093.5889.111. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.6841.3682.0522.7363.42SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 32.992.932.933.04MIN: 1.07 / MAX: 3.48MIN: 1.08 / MAX: 3.42MIN: 1.05 / MAX: 3.43MIN: 1.06 / MAX: 3.51

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4Ksched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP41020304050SE +/- 0.40, N = 3SE +/- 0.36, N = 15SE +/- 0.68, N = 15SE +/- 0.10, N = 345.9345.1844.2945.501. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4246810SE +/- 0.080, N = 12SE +/- 0.064, N = 3SE +/- 0.039, N = 3SE +/- 0.077, N = 126.9156.6746.7516.7281. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 100 - Mode: Read Writesched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP43K6K9K12K15KSE +/- 153.57, N = 12SE +/- 143.94, N = 3SE +/- 85.89, N = 3SE +/- 187.85, N = 12144811498614813148881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 50 - Mode: Read Onlysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4120K240K360K480K600KSE +/- 1603.02, N = 3SE +/- 5681.00, N = 3SE +/- 2596.28, N = 3SE +/- 2157.07, N = 35468305637275542675489191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Mediumsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP490180270360450SE +/- 1.88, N = 3SE +/- 0.84, N = 3SE +/- 1.07, N = 3SE +/- 4.98, N = 3413.9401.7404.5410.4

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.89281.78562.67843.57124.464SE +/- 0.049, N = 3SE +/- 0.043, N = 3SE +/- 0.055, N = 12SE +/- 0.005, N = 33.8843.8563.9683.9091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 50 - Mode: Read Writesched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP43K6K9K12K15KSE +/- 163.39, N = 3SE +/- 145.76, N = 3SE +/- 156.04, N = 12SE +/- 15.15, N = 3128781297212625127891. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

InfluxDB

Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000sched-core GitLinux 5.17 GitLinux 5.17 Git NP4500K1000K1500K2000K2500KSE +/- 9654.38, N = 3SE +/- 6832.85, N = 3SE +/- 991.45, N = 32429787.82419457.12367595.5

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.02050.0410.06150.0820.1025SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.0910.0890.0900.0911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Degriddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP414002800420056007000SE +/- 27.00, N = 3SE +/- 79.03, N = 3SE +/- 27.68, N = 3SE +/- 53.33, N = 36505.906480.866615.256506.561. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read While Writingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4900K1800K2700K3600K4500KSE +/- 14310.78, N = 3SE +/- 14332.52, N = 3SE +/- 8901.28, N = 33997489401437539402061. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.16Build: defconfigsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP41122334455SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 348.8348.4848.3947.92

GravityMark

Resolution: 1920 x 1080 - Renderer: Vulkan

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.44Resolution: 1920 x 1080 - Renderer: Vulkansched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP44080120160200SE +/- 0.03, N = 3SE +/- 0.41, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3190.2187.0189.9190.3

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_baresched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.28780.57560.86341.15121.439SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 31.2581.2791.2751.2751. (CXX) g++ options: -O3

LuxCoreRender

Scene: DLSC - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.80781.61562.42343.23124.039SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.563.593.543.54MIN: 3.46 / MAX: 3.75MIN: 3.47 / MAX: 3.83MIN: 3.45 / MAX: 3.72MIN: 3.42 / MAX: 3.73

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP448121620SE +/- 0.06, N = 3SE +/- 0.22, N = 3SE +/- 0.14, N = 12SE +/- 0.04, N = 315.5315.4615.6715.571. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Writesched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP43K6K9K12K15KSE +/- 64.59, N = 3SE +/- 229.63, N = 3SE +/- 136.84, N = 12SE +/- 42.89, N = 3160961617515966160531. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Highsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP490180270360450SE +/- 4.76, N = 4SE +/- 4.11, N = 3SE +/- 4.79, N = 3SE +/- 3.85, N = 3395.3390.8395.8394.1

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP41020304050SE +/- 0.08, N = 3SE +/- 0.26, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 342.3041.8242.3142.061. (CC) gcc options: -O2 -lz

ASKAP

Test: tConvolve OpenMP - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Griddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP46001200180024003000SE +/- 32.59, N = 3SE +/- 8.96, N = 3SE +/- 24.24, N = 3SE +/- 9.15, N = 32699.342680.492698.972707.751. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.2.0sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4200K400K600K800K1000KSE +/- 4317.28, N = 3SE +/- 2415.23, N = 3SE +/- 890.13, N = 3SE +/- 8487.07, N = 3817041.54813258.37809585.04815619.451. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Onlysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP4130K260K390K520K650KSE +/- 2509.74, N = 3SE +/- 1730.43, N = 3SE +/- 2439.90, N = 3SE +/- 2074.95, N = 35928615913585875465913761. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ASKAP

Test: tConvolve OpenMP - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Degriddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP47001400210028003500SE +/- 0.00, N = 3SE +/- 13.36, N = 3SE +/- 13.36, N = 3SE +/- 13.36, N = 33247.023273.753260.383260.381. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

InfluxDB

Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000sched-core GitLinux 5.17 GitLinux 5.17 Git NP4400K800K1200K1600K2000KSE +/- 9604.17, N = 3SE +/- 20306.63, N = 3SE +/- 7435.43, N = 31991313.41982541.31997610.4

Facebook RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random Readsched-core GitLinux 5.17 GitLinux 5.17 Git NP420M40M60M80M100MSE +/- 146743.57, N = 3SE +/- 448554.59, N = 3SE +/- 134782.96, N = 31161781591160515241153284221. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latencysched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.09560.19120.28680.38240.478SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 30.4220.4230.4250.4231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

GravityMark

Resolution: 1920 x 1080 - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.44Resolution: 1920 x 1080 - Renderer: OpenGLsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP44080120160200SE +/- 0.07, N = 3SE +/- 1.42, N = 12SE +/- 0.03, N = 3SE +/- 0.18, N = 3188.7188.6188.3189.6

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random Fillsched-core GitLinux 5.17 GitLinux 5.17 Git NP4300K600K900K1200K1500KSE +/- 4975.99, N = 3SE +/- 6801.67, N = 3SE +/- 1236.00, N = 31364131135963513672211. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomssched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP40.24720.49440.74160.98881.236SE +/- 0.00753, N = 3SE +/- 0.00218, N = 3SE +/- 0.00294, N = 3SE +/- 0.00721, N = 31.095991.098611.096771.09376

ASKAP

Test: tConvolve MT - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Griddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP42004006008001000SE +/- 1.18, N = 3SE +/- 1.36, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3786.82784.19787.67786.021. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Basemark GPU

Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: High

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Highsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP470140210280350SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.47, N = 3SE +/- 0.32, N = 3339.11338.97338.89339.89MIN: 263.97 / MAX: 698.32MIN: 266.21 / MAX: 570.25MIN: 265.55 / MAX: 662.31MIN: 264.64 / MAX: 643.06

ASKAP

Test: tConvolve MT - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Degriddingsched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP430060090012001500SE +/- 2.05, N = 3SE +/- 0.52, N = 3SE +/- 1.65, N = 3SE +/- 2.31, N = 31355.861352.921354.281353.781. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Facebook RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Update Randomsched-core GitLinux 5.17 GitLinux 5.17 Git NP4200K400K600K800K1000KSE +/- 4547.26, N = 3SE +/- 4621.86, N = 3SE +/- 234.25, N = 37932147927277917631. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Basemark GPU

Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Mediumsched-core GitLinux 5.17 GitLinux 5.17 Git NP4400800120016002000SE +/- 0.24, N = 3SE +/- 0.27, N = 3SE +/- 0.38, N = 31750.951751.281749.00MIN: 685.3 / MAX: 2794.85MIN: 757.55 / MAX: 2768.58MIN: 745.65 / MAX: 2628.98

Basemark GPU

Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: Medium

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: Mediumsched-core GitLinux 5.17 GitLinux 5.17 Git NP4100200300400500SE +/- 14.52, N = 15SE +/- 6.42, N = 15SE +/- 9.04, N = 15441.51390.62418.95MIN: 32.24 / MAX: 1296.98MIN: 31.49 / MAX: 1286.57MIN: 30.44 / MAX: 1264.48

MariaDB

Clients: 64

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 64sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP42004006008001000SE +/- 40.66, N = 9SE +/- 9.06, N = 3SE +/- 38.43, N = 9SE +/- 37.88, N = 97507908338001. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

MariaDB

Clients: 32

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 32sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP430060090012001500SE +/- 81.73, N = 12SE +/- 83.34, N = 9SE +/- 70.80, N = 12SE +/- 94.02, N = 914231314149813181. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

MariaDB

Clients: 16

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 16sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP430060090012001500SE +/- 51.95, N = 12SE +/- 51.80, N = 12SE +/- 53.99, N = 12SE +/- 71.17, N = 915831629162315291. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

MariaDB

Clients: 8

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 8sched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP45001000150020002500SE +/- 7.66, N = 3SE +/- 65.96, N = 10SE +/- 9.28, N = 3SE +/- 80.26, N = 921401640213818181. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4Ksched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP41428425670SE +/- 1.19, N = 15SE +/- 0.73, N = 3SE +/- 1.33, N = 12SE +/- 1.25, N = 1558.8564.4658.8160.801. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Ksched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP41326395265SE +/- 0.55, N = 3SE +/- 0.71, N = 4SE +/- 1.42, N = 12SE +/- 0.79, N = 1558.8458.0856.3858.551. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Ultrasched-core GitLinux 5.17 GitLinux 5.17 Git NP4sched-core Git NP490180270360450SE +/- 4.12, N = 15SE +/- 4.80, N = 4SE +/- 8.80, N = 12SE +/- 5.98, N = 12385.1387.9391.0396.2

Phoronix Test Suite v10.8.4