AMD INVLPGB Linux Patch Performance

Benchmarks for a future article looking at AMD broadcast TLB invalidation Linux kernel patches with the INVLPGB instruction on newer AMD Zen 3 processors.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2412250-NE-AMDINVLPG56
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 6.13 Git
December 25 2024
  5 Hours, 46 Minutes
INVLPGB Patched
December 24 2024
  5 Hours, 41 Minutes
Invert Behavior (Only Show Selected Data)
  5 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):


AMD INVLPGB Linux Patch PerformanceOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads)Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS)AMD 1Ah12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF3201GB Micron_7450_MTFDKCB3T2TFS + 257GB Flash DriveASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 24.106.13.0-rc4-phx-stock (x86_64)6.13.0-rc4-phx-broadcast-tlb (x86_64)GNOME Shell 47.0X ServerGCC 14.2.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelsDesktopDisplay ServerCompilerFile-SystemScreen ResolutionAMD INVLPGB Linux Patch Performance BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 - NONE / relatime,rw,stripe=64 / Block Size: 4096- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116 - OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)- Python 3.12.7- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Linux 6.13 Git vs. INVLPGB Patched ComparisonPhoronix Test SuiteBaseline+4.3%+4.3%+8.6%+8.6%+12.9%+12.9%17.2%4.7%3.9%3.5%3.4%3.1%3.1%2.7%2.7%2.5%2.4%2.1%GhostRider - 1MZ.1.2.B.I.PJythonoltp_update_index - 256d.M.M.S - Mesh TimeWrites800 - 100 - 800 - 400500CORAL2 P1ggml-small.en - 2.S.o.t.UEP.C800 - 100 - 800 - 4001.R.H.D.S.R2%XmrigDaCapo BenchmarkDaCapo BenchmarkMariaDBOpenFOAMApache CassandraApache IoTDBnginxQuicksilverWhisper.cppNAS Parallel BenchmarksApache IoTDBClickHouseLinux 6.13 GitINVLPGB Patched

AMD INVLPGB Linux Patch Performancenpb: BT.Cnpb: EP.Cnpb: IS.Dnpb: LU.Cnpb: MG.Cnpb: SP.Cquicksilver: CORAL2 P1quicksilver: CORAL2 P2rodinia: OpenMP Leukocytenamd: ATPase with 327,506 Atomsnamd: STMV with 1,066,628 Atomsopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timerelion: Basic - CPUxmrig: GhostRider - 1Mdacapobench: Jythondacapobench: GraphChidacapobench: Apache Kafkadacapobench: jMonkeyEnginedacapobench: Apache Xalan XSLTdacapobench: Avrora AVR Simulation Frameworkdacapobench: BioJava Biological Data Frameworkdacapobench: Zxing 1D/2D Barcode Image Processingrenaissance: ALS Movie Lensrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: In-Memory Database Shootoutbuild-godot: Time To Compilebuild-llvm: Ninjabuild-llvm: Unix Makefilesbuild-python: Defaultbuild-python: Released Build, PGO + LTO Optimizedclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, Third Runapache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 500 - 100 - 800 - 100apache-iotdb: 500 - 100 - 800 - 100apache-iotdb: 500 - 100 - 800 - 400apache-iotdb: 500 - 100 - 800 - 400apache-iotdb: 800 - 100 - 500 - 100apache-iotdb: 800 - 100 - 500 - 100apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 800 - 400memcached: 1:5mariadb: oltp_read_only - 256mariadb: oltp_read_write - 256mariadb: oltp_update_index - 256blender: Barbershop - CPU-Onlycassandra: Writesrocksdb: Read While Writingspeedb: Rand Readspeedb: Update Randspeedb: Read Rand Write Randnginx: 500whisper-cpp: ggml-small.en - 2016 State of the Unionwhisper-cpp: ggml-medium.en - 2016 State of the UnionLinux 6.13 GitINVLPGB Patched353192.1611180.117001.42312554.83145177.79154232.79340866672205666731.67412.224434.21510109.86392214.44213706.943202363504668088162585451964818214.8180.15722.92261.34511.680.68790.415160.66613.067190.912738.99764.71751.849680680947.8599520170168.3612073844961.49125423055211.8111788721040.40121237884141171394212.983569817.6637688172615113658124.03438419146418896220840835198673054826503771.76225.41952460.62129356244.9111450.176984.65311722.61147724.66155286.47349966672205666731.29812.221254.20973106.20884211.38016061.441582323505068068122556454761918368.8181.75651.42283.34512.980.83190.775161.06012.984191.972735.32749.62759.449775137747.03100250585167.9512168195360.93124631354214.4811889017040.04120726010144092202206.653583145.4637868173765117679124.48452025147375506272869395222383106319517615.54219.87375453.06996OpenBenchmarking.org

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CLinux 6.13 GitINVLPGB Patched80K160K240K320K400KSE +/- 3855.67, N = 3SE +/- 3962.64, N = 5353192.16356244.911. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CLinux 6.13 GitINVLPGB Patched2K4K6K8K10KSE +/- 27.23, N = 3SE +/- 98.82, N = 1511180.1111450.171. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DLinux 6.13 GitINVLPGB Patched15003000450060007500SE +/- 60.97, N = 3SE +/- 68.35, N = 57001.426984.651. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CLinux 6.13 GitINVLPGB Patched70K140K210K280K350KSE +/- 2270.42, N = 15SE +/- 2363.19, N = 10312554.83311722.611. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CLinux 6.13 GitINVLPGB Patched30K60K90K120K150KSE +/- 2956.05, N = 15SE +/- 1764.21, N = 3145177.79147724.661. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CLinux 6.13 GitINVLPGB Patched30K60K90K120K150KSE +/- 1469.84, N = 3SE +/- 279.05, N = 3154232.79155286.471. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

Quicksilver

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

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1Linux 6.13 GitINVLPGB Patched7M14M21M28M35MSE +/- 46666.67, N = 3SE +/- 98713.95, N = 334086667349966671. (CXX) g++ options: -fopenmp -O3 -march=native

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2Linux 6.13 GitINVLPGB Patched5M10M15M20M25MSE +/- 12018.50, N = 3SE +/- 18559.21, N = 322056667220566671. (CXX) g++ options: -fopenmp -O3 -march=native

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteLinux 6.13 GitINVLPGB Patched714212835SE +/- 0.33, N = 3SE +/- 0.16, N = 331.6731.301. (CXX) g++ options: -O2 -lOpenCL

NAMD

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: ATPase with 327,506 AtomsLinux 6.13 GitINVLPGB Patched3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 312.2212.22

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 AtomsLinux 6.13 GitINVLPGB Patched0.94841.89682.84523.79364.742SE +/- 0.00531, N = 3SE +/- 0.00334, N = 34.215104.20973

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeLinux 6.13 GitINVLPGB Patched20406080100109.86106.211. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

RELION

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 5.0Test: Basic - Device: CPULinux 6.13 GitINVLPGB Patched50100150200250SE +/- 3.72, N = 12SE +/- 4.55, N = 12214.44211.381. (CXX) g++ options: -fPIC -std=c++14 -fopenmp -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MLinux 6.13 GitINVLPGB Patched3K6K9K12K15KSE +/- 668.22, N = 15SE +/- 32.37, N = 313706.916061.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: JythonLinux 6.13 GitINVLPGB Patched9001800270036004500SE +/- 37.01, N = 15SE +/- 10.53, N = 343204158

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChiLinux 6.13 GitINVLPGB Patched5001000150020002500SE +/- 8.96, N = 3SE +/- 15.84, N = 323632323

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache KafkaLinux 6.13 GitINVLPGB Patched11002200330044005500SE +/- 4.26, N = 3SE +/- 6.08, N = 350465050

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngineLinux 6.13 GitINVLPGB Patched15003000450060007500SE +/- 1.67, N = 3SE +/- 1.67, N = 368086806

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLTLinux 6.13 GitINVLPGB Patched2004006008001000SE +/- 7.60, N = 6SE +/- 2.00, N = 3816812

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation FrameworkLinux 6.13 GitINVLPGB Patched6001200180024003000SE +/- 8.50, N = 3SE +/- 19.37, N = 325852556

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data FrameworkLinux 6.13 GitINVLPGB Patched10002000300040005000SE +/- 20.17, N = 3SE +/- 17.52, N = 345194547

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image ProcessingLinux 6.13 GitINVLPGB Patched140280420560700SE +/- 4.04, N = 3SE +/- 6.43, N = 3648619

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: ALS Movie LensLinux 6.13 GitINVLPGB Patched4K8K12K16K20KSE +/- 45.86, N = 3SE +/- 114.89, N = 318214.818368.8MIN: 17691.46 / MAX: 18303.77MIN: 17674.24 / MAX: 18580.57

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark BayesLinux 6.13 GitINVLPGB Patched4080120160200SE +/- 0.85, N = 3SE +/- 1.59, N = 3180.1181.7MIN: 160.23 / MAX: 297.68MIN: 164.62 / MAX: 284.35

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Savina Reactors.IOLinux 6.13 GitINVLPGB Patched12002400360048006000SE +/- 75.13, N = 3SE +/- 52.24, N = 75722.95651.4MIN: 5596.11 / MAX: 9196.98MIN: 5405.73 / MAX: 9193.8

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark PageRankLinux 6.13 GitINVLPGB Patched5001000150020002500SE +/- 9.21, N = 3SE +/- 22.38, N = 32261.32283.3MIN: 1572.27 / MAX: 2279.05MIN: 1561.41 / MAX: 2328.07

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: In-Memory Database ShootoutLinux 6.13 GitINVLPGB Patched10002000300040005000SE +/- 55.34, N = 4SE +/- 34.36, N = 34511.64512.9MIN: 4295.26 / MAX: 5024.51MIN: 4347.69 / MAX: 5072.64

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileLinux 6.13 GitINVLPGB Patched20406080100SE +/- 0.05, N = 3SE +/- 0.16, N = 380.6980.83

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaLinux 6.13 GitINVLPGB Patched20406080100SE +/- 0.24, N = 3SE +/- 0.11, N = 390.4290.78

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesLinux 6.13 GitINVLPGB Patched4080120160200SE +/- 0.32, N = 3SE +/- 0.59, N = 3160.67161.06

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: DefaultLinux 6.13 GitINVLPGB Patched369121513.0712.98

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedLinux 6.13 GitINVLPGB Patched4080120160200190.91191.97

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/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheLinux 6.13 GitINVLPGB Patched160320480640800SE +/- 6.88, N = 3SE +/- 4.99, N = 3738.99735.32MIN: 69.85 / MAX: 7500MIN: 68.03 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunLinux 6.13 GitINVLPGB Patched160320480640800SE +/- 4.01, N = 3SE +/- 1.96, N = 3764.71749.62MIN: 69.85 / MAX: 8571.43MIN: 69.28 / MAX: 6666.67

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunLinux 6.13 GitINVLPGB Patched160320480640800SE +/- 0.95, N = 3SE +/- 3.07, N = 3751.84759.44MIN: 70.34 / MAX: 6666.67MIN: 69.04 / MAX: 8571.43

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Linux 6.13 GitINVLPGB Patched20M40M60M80M100MSE +/- 1081476.60, N = 3SE +/- 291260.63, N = 39680680997751377

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Linux 6.13 GitINVLPGB Patched1122334455SE +/- 0.55, N = 3SE +/- 0.36, N = 347.8547.03MAX: 12576.32MAX: 12578.34

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Linux 6.13 GitINVLPGB Patched20M40M60M80M100MSE +/- 603733.82, N = 3SE +/- 97805.09, N = 399520170100250585

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Linux 6.13 GitINVLPGB Patched4080120160200SE +/- 0.88, N = 3SE +/- 0.71, N = 3168.36167.95MAX: 26450.24MAX: 26468.05

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Linux 6.13 GitINVLPGB Patched30M60M90M120M150MSE +/- 58310.64, N = 3SE +/- 67599.70, N = 3120738449121681953

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Linux 6.13 GitINVLPGB Patched1428425670SE +/- 0.36, N = 3SE +/- 0.25, N = 361.4960.93MAX: 11313.55MAX: 11306.84

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Linux 6.13 GitINVLPGB Patched30M60M90M120M150MSE +/- 352556.17, N = 3SE +/- 332877.17, N = 3125423055124631354

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Linux 6.13 GitINVLPGB Patched50100150200250SE +/- 2.05, N = 3SE +/- 0.65, N = 3211.81214.48MAX: 26536.58MAX: 26489.9

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Linux 6.13 GitINVLPGB Patched30M60M90M120M150MSE +/- 1087988.19, N = 3SE +/- 226557.07, N = 3117887210118890170

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Linux 6.13 GitINVLPGB Patched918273645SE +/- 0.37, N = 3SE +/- 0.04, N = 340.4040.04MAX: 23837.32MAX: 23821.12

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Linux 6.13 GitINVLPGB Patched30M60M90M120M150MSE +/- 875042.28, N = 3SE +/- 1093112.93, N = 3121237884120726010

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Linux 6.13 GitINVLPGB Patched30M60M90M120M150MSE +/- 870384.94, N = 3SE +/- 1488492.23, N = 3141171394144092202

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Linux 6.13 GitINVLPGB Patched50100150200250SE +/- 2.18, N = 3SE +/- 3.85, N = 3212.98206.65MAX: 26561.37MAX: 26883.6

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:5Linux 6.13 GitINVLPGB Patched800K1600K2400K3200K4000KSE +/- 2641.20, N = 3SE +/- 7706.14, N = 33569817.663583145.461. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_only - Threads: 256Linux 6.13 GitINVLPGB Patched8K16K24K32K40KSE +/- 17.06, N = 3SE +/- 112.63, N = 337688378681. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 256Linux 6.13 GitINVLPGB Patched40K80K120K160K200KSE +/- 73.62, N = 3SE +/- 93.11, N = 31726151737651. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 256Linux 6.13 GitINVLPGB Patched30K60K90K120K150KSE +/- 190.75, N = 3SE +/- 200.13, N = 31136581176791. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-OnlyLinux 6.13 GitINVLPGB Patched306090120150SE +/- 0.13, N = 3SE +/- 0.12, N = 3124.03124.48

Apache Cassandra

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: WritesLinux 6.13 GitINVLPGB Patched100K200K300K400K500KSE +/- 5248.18, N = 3SE +/- 2371.91, N = 3438419452025

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingLinux 6.13 GitINVLPGB Patched3M6M9M12M15MSE +/- 157207.18, N = 3SE +/- 155717.24, N = 1514641889147375501. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadLinux 6.13 GitINVLPGB Patched130M260M390M520M650MSE +/- 7230810.31, N = 3SE +/- 1540848.02, N = 36220840836272869391. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update RandomLinux 6.13 GitINVLPGB Patched110K220K330K440K550KSE +/- 210.08, N = 3SE +/- 726.96, N = 35198675222381. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomLinux 6.13 GitINVLPGB Patched700K1400K2100K2800K3500KSE +/- 5973.22, N = 3SE +/- 22974.88, N = 3305482631063191. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

nginx

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

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Linux 6.13 GitINVLPGB Patched110K220K330K440K550KSE +/- 1734.77, N = 3SE +/- 1146.82, N = 3503771.76517615.541. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-small.en - Input: 2016 State of the UnionLinux 6.13 GitINVLPGB Patched50100150200250SE +/- 0.39, N = 3SE +/- 1.60, N = 3225.42219.871. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-medium.en - Input: 2016 State of the UnionLinux 6.13 GitINVLPGB Patched100200300400500SE +/- 3.15, N = 3SE +/- 0.73, N = 3460.62453.071. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

61 Results Shown

NAS Parallel Benchmarks:
  BT.C
  EP.C
  IS.D
  LU.C
  MG.C
  SP.C
Quicksilver:
  CORAL2 P1
  CORAL2 P2
Rodinia
NAMD:
  ATPase with 327,506 Atoms
  STMV with 1,066,628 Atoms
OpenFOAM
RELION
Xmrig
DaCapo Benchmark:
  Jython
  GraphChi
  Apache Kafka
  jMonkeyEngine
  Apache Xalan XSLT
  Avrora AVR Simulation Framework
  BioJava Biological Data Framework
  Zxing 1D/2D Barcode Image Processing
Renaissance:
  ALS Movie Lens
  Apache Spark Bayes
  Savina Reactors.IO
  Apache Spark PageRank
  In-Memory Database Shootout
Timed Godot Game Engine Compilation
Timed LLVM Compilation:
  Ninja
  Unix Makefiles
Timed CPython Compilation:
  Default
  Released Build, PGO + LTO Optimized
ClickHouse:
  100M Rows Hits Dataset, First Run / Cold Cache
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, Third Run
Apache IoTDB:
  500 - 100 - 500 - 100:
    point/sec
    Average Latency
  500 - 100 - 500 - 400:
    point/sec
    Average Latency
  500 - 100 - 800 - 100:
    point/sec
    Average Latency
  500 - 100 - 800 - 400:
    point/sec
    Average Latency
  800 - 100 - 500 - 100:
    point/sec
    Average Latency
  800 - 100 - 500 - 400:
    point/sec
  800 - 100 - 800 - 400:
    point/sec
    Average Latency
Memcached
MariaDB:
  oltp_read_only - 256
  oltp_read_write - 256
  oltp_update_index - 256
Blender
Apache Cassandra
RocksDB
Speedb:
  Rand Read
  Update Rand
  Read Rand Write Rand
nginx
Whisper.cpp:
  ggml-small.en - 2016 State of the Union
  ggml-medium.en - 2016 State of the Union