Xeon Cascade Lake R Intel FSGSBASE

Intel FSGSBASE benchmarking by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2006246-NE-XEONGOLD517&obr_sgm=y&obr_swl=y&grs&rdt.

Xeon Cascade Lake R Intel FSGSBASEProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionFSGSBASE Enablednofsgsbase2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)TYAN S7106 (V2.01.B40 BIOS)Intel Sky Lake-E DMI3 Registers94GB500GB Samsung SSD 860ASPEEDVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEUbuntu 20.045.8.0-rc1-phx-fsgsbase (x86_64) 20200620GNOME Shell 3.36.1X Server 1.20.8modesetting 1.20.8GCC 9.3.0ext41920x1080OpenBenchmarking.orgEnvironment Details- CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details- MQ-DEADLINE / errors=remount-ro,relatime,rwProcessor Details- FSGSBASE Enabled: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - nofsgsbase: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5002f01Java Details- FSGSBASE Enabled: OpenJDK Runtime Environment (build 11.0.7-ea+9-post-Ubuntu-1ubuntu1) - nofsgsbase: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Details- Python 3.8.2Security Details- itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Xeon Cascade Lake R Intel FSGSBASEpgbench: Buffer Test - Heavy Contention - Read Writepgbench: Buffer Test - Normal Load - Read Writeredis: LPOPfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 2MB - Default Test Directorystress-ng: Context Switchingmysqlslap: 512cp2k: Fayalite-FIST Dataredis: GEThbase: Increment - 1hbase: Increment - 1stress-ng: Atomicmysqlslap: 256java-gradle-perf: Reactorplaidml: No - Inference - VGG19 - CPUmysqlslap: 128leveldb: Seq Fillmysqlslap: 64aom-av1: Speed 6 Two-Passkeydb: leveldb: Seq Fillplaidml: No - Inference - IMDB LSTM - CPUleveldb: Rand Fillplaidml: No - Inference - NASNer Large - CPUleveldb: Rand Deletesvt-av1: Enc Mode 4 - 1080pbuild-gdb: Time To Compileleveldb: Rand Fillnumenta-nab: Earthgecko Skylinepmbench: 72 - 100% Writesbuild-apache: Time To Compiledav1d: Summer Nature 4Kleveldb: Rand Readplaidml: No - Inference - DenseNet 201 - CPUleveldb: Overwritevpxenc: Speed 5dav1d: Summer Nature 1080pplaidml: No - Inference - Inception V3 - CPUrocksdb: Seq Fillmlpack: scikit_svmleveldb: Overwritenumenta-nab: EXPoSEhimeno: Poisson Pressure Solverctx-clock: Context Switch Timeredis: SADDstress-ng: SENDFILErocksdb: Read While Writingaom-av1: Speed 6 Realtimestress-ng: CPU Stresssvt-av1: Enc Mode 8 - 1080pleveldb: Hot Readplaidml: No - Inference - VGG16 - CPUnumenta-nab: Relative Entropyplaidml: No - Inference - ResNet 50 - CPUbuild-linux-kernel: Time To Compilemlpack: scikit_icaleveldb: Fill Syncbuild-llvm: Time To Compilerocksdb: Rand Readaom-av1: Speed 4 Two-Passredis: SEThbase: Rand Read - 1aom-av1: Speed 8 Realtimenumenta-nab: Bayesian Changepointebizzy: dav1d: Chimera 1080phbase: Rand Read - 1leveldb: Seek Randvpxenc: Speed 0dav1d: Chimera 1080p 10-bitonednn: IP Batch 1D - bf16bf16bf16 - CPUgromacs: Water Benchmarkrocksdb: Rand Fillplaidml: No - Inference - Mobilenet - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUpgbench: Buffer Test - Normal Load - Read Onlyonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUapache-siege: 10mlpack: scikit_qdapgbench: Buffer Test - Heavy Contention - Read Onlyhmmer: Pfam Database Searchnamd: ATPase Simulation - 327,506 Atomsqmcpack: onednn: IP Batch All - bf16bf16bf16 - CPUapache-siege: 50onednn: Deconvolution Batch deconv_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch deconv_3d - bf16bf16bf16 - CPUleveldb: Fill Syncsvt-av1: Enc Mode 0 - 1080paom-av1: Speed 0 Two-Passpmbench: 1 - 80% Reads 20% Writespostmark: Disk Transaction Performancemlpack: scikit_linearridgeregressionapache-siege: 200hbase: Async Rand Read - 1hbase: Async Rand Read - 1hbase: Seq Read - 1hbase: Seq Read - 1rocksdb: Rand Fill Synccassandra: Writesmemtier-benchmark: Redisyafaray: Total Time For Sample Scenenode-express-loadtest: renaissance: Savina Reactors.IOrenaissance: Apache Spark ALSlammps: Rhodopsin Proteinmafft: Multiple Sequence Alignmentpmbench: 72 - 100% Readsblogbench: Writefio: Seq Write - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Seq Write - IO_uring - Yes - No - 2MB - Default Test DirectoryFSGSBASE Enablednofsgsbase4727.7137444908.5017042611119.75888001879410762.671612027.6932500801.50291341390016.18150276.58020.641599.62052.98428585.01826.268868.099.80.57774.3575.770137.398809.69590.7750.080225.764182.7893.9991.969.923.01338.365.5018795028.71799.3561513.7793932.7626151242087688.75447930.47535627210.8611896.4248.87492.27724.9814.8134.4537.43174.664485.350283.7371422056481.951918164.8321323.7432.7381087183329.394643113.5816.1487.205.695623.50618609310.621.44923593329.4276836.3972822712.0546.03618994.74271512.7190.611042687.651.096433173.457.391549.461581.80.1200.270.075657251.9648540.411895245189527065321470232859981.40108.818939521837.0032896.19117.9502.6600.0460242471893852634.2663192762.9022551707562.79634001357847877.591401886.2572340376.2308323185800.80143288.79321.391549.91992.91418712.10809.441850.6510.00.58761.4345.683135.384798.60189.6090.081225.474180.7793.0101.9810.023.24335.165.4518964328.46792.4391500.8473966.3559791252071005.92444432.10539641110.7811983.6649.21191.64625.1514.9134.4837.18175.124460.308285.3001414481981.941908415.4621423.8432.6011082650328.034625113.2036.1287.475.679103.51418645110.601.45193594395.9066916.3873522746.8846.09619694.85563712.7270.610772688.551.113433180.667.390639.461631.80.120.270.075657252.0143531.701935137195509056811342852635763.82113.629934224407.0832985.59617.1412.6650.045120455170346OpenBenchmarking.org

PostgreSQL pgbench

Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read WriteFSGSBASE Enablednofsgsbase10002000300040005000SE +/- 59.91, N = 3SE +/- 25.55, N = 94727.712634.271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteFSGSBASE Enablednofsgsbase11002200330044005500SE +/- 59.24, N = 6SE +/- 34.32, N = 34908.502762.901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPFSGSBASE Enablednofsgsbase600K1200K1800K2400K3000KSE +/- 14141.11, N = 3SE +/- 9534.81, N = 32611119.751707562.791. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryFSGSBASE Enablednofsgsbase20K40K60K80K100KSE +/- 251.66, N = 3SE +/- 100.00, N = 388800634001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryFSGSBASE Enablednofsgsbase4080120160200SE +/- 0.33, N = 3SE +/- 0.88, N = 31871351. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingFSGSBASE Enablednofsgsbase2M4M6M8M10MSE +/- 154150.18, N = 3SE +/- 27584.57, N = 39410762.677847877.591. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

MariaDB

Clients: 512

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512FSGSBASE Enablednofsgsbase4080120160200SE +/- 2.84, N = 9SE +/- 0.52, N = 31611401. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST DataFSGSBASE Enablednofsgsbase4008001200160020002027.691886.26

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETFSGSBASE Enablednofsgsbase500K1000K1500K2000K2500KSE +/- 31845.75, N = 3SE +/- 18114.33, N = 32500801.502340376.201. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Apache HBase

Test: Increment - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Increment - Clients: 1FSGSBASE Enablednofsgsbase70140210280350SE +/- 2.52, N = 11SE +/- 2.70, N = 15291308

Apache HBase

Test: Increment - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Increment - Clients: 1FSGSBASE Enablednofsgsbase7001400210028003500SE +/- 30.10, N = 11SE +/- 28.49, N = 1534133231

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicFSGSBASE Enablednofsgsbase20K40K60K80K100KSE +/- 1267.27, N = 3SE +/- 1320.48, N = 390016.1885800.801. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

MariaDB

Clients: 256

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256FSGSBASE Enablednofsgsbase306090120150SE +/- 0.58, N = 3SE +/- 0.32, N = 31501431. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Java Gradle Build

Gradle Build: Reactor

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorFSGSBASE Enablednofsgsbase60120180240300SE +/- 3.18, N = 3SE +/- 2.12, N = 3276.58288.79

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUFSGSBASE Enablednofsgsbase510152025SE +/- 0.18, N = 3SE +/- 0.12, N = 320.6421.39

MariaDB

Clients: 128

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128FSGSBASE Enablednofsgsbase4080120160200SE +/- 0.48, N = 3SE +/- 0.65, N = 31591541. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillFSGSBASE Enablednofsgsbase3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 39.69.91. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

MariaDB

Clients: 64

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64FSGSBASE Enablednofsgsbase4080120160200SE +/- 2.42, N = 6SE +/- 2.50, N = 52051991. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

AOM AV1

Encoder Mode: Speed 6 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-PassFSGSBASE Enablednofsgsbase0.67051.3412.01152.6823.3525SE +/- 0.00, N = 3SE +/- 0.02, N = 32.982.911. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.1FSGSBASE Enablednofsgsbase90K180K270K360K450KSE +/- 4575.82, N = 3SE +/- 5862.96, N = 3428585.01418712.101. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillFSGSBASE Enablednofsgsbase2004006008001000SE +/- 3.79, N = 3SE +/- 3.18, N = 3826.27809.441. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUFSGSBASE Enablednofsgsbase2004006008001000SE +/- 11.90, N = 4SE +/- 3.24, N = 3868.09850.65

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillFSGSBASE Enablednofsgsbase3691215SE +/- 0.03, N = 3SE +/- 0.10, N = 39.810.01. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

PlaidML

FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: CPUFSGSBASE Enablednofsgsbase0.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 30.570.58

LevelDB

Benchmark: Random Delete

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteFSGSBASE Enablednofsgsbase170340510680850SE +/- 1.02, N = 3SE +/- 2.15, N = 3774.36761.431. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pFSGSBASE Enablednofsgsbase1.29832.59663.89495.19326.4915SE +/- 0.067, N = 3SE +/- 0.082, N = 35.7705.6831. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Timed GDB GNU Debugger Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileFSGSBASE Enablednofsgsbase306090120150SE +/- 0.07, N = 3SE +/- 0.05, N = 3137.40135.38

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillFSGSBASE Enablednofsgsbase2004006008001000SE +/- 3.59, N = 3SE +/- 8.40, N = 3809.70798.601. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineFSGSBASE Enablednofsgsbase20406080100SE +/- 0.50, N = 3SE +/- 0.29, N = 390.7889.61

pmbench

Concurrent Worker Threads: 72 - Read-Write Ratio: 100% Writes

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 72 - Read-Write Ratio: 100% WritesFSGSBASE Enablednofsgsbase0.01830.03660.05490.07320.0915SE +/- 0.0010, N = 5SE +/- 0.0009, N = 30.08020.08121. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileFSGSBASE Enablednofsgsbase612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 325.7625.47

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KFSGSBASE Enablednofsgsbase4080120160200SE +/- 2.74, N = 3SE +/- 0.93, N = 3182.78180.77MIN: 88.23 / MAX: 199.52MIN: 91.75 / MAX: 195.311. (CC) gcc options: -O3 -march=native -pthread

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadFSGSBASE Enablednofsgsbase20406080100SE +/- 0.05, N = 3SE +/- 0.66, N = 394.0093.011. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPUFSGSBASE Enablednofsgsbase0.44550.8911.33651.7822.2275SE +/- 0.01, N = 3SE +/- 0.01, N = 31.961.98

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteFSGSBASE Enablednofsgsbase3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 39.910.01. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

VP9 libvpx Encoding

Speed: Speed 5

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5FSGSBASE Enablednofsgsbase612182430SE +/- 0.09, N = 3SE +/- 0.08, N = 323.0123.241. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pFSGSBASE Enablednofsgsbase70140210280350SE +/- 1.19, N = 3SE +/- 1.40, N = 3338.36335.16MIN: 185.24 / MAX: 374.84MIN: 172.66 / MAX: 372.41. (CC) gcc options: -O3 -march=native -pthread

PlaidML

FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUFSGSBASE Enablednofsgsbase1.23752.4753.71254.956.1875SE +/- 0.03, N = 3SE +/- 0.02, N = 35.505.45

Facebook RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillFSGSBASE Enablednofsgsbase40K80K120K160K200KSE +/- 190.16, N = 3SE +/- 107.10, N = 31879501896431. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmFSGSBASE Enablednofsgsbase714212835SE +/- 0.14, N = 3SE +/- 0.02, N = 328.7128.46

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteFSGSBASE Enablednofsgsbase2004006008001000SE +/- 1.81, N = 3SE +/- 2.31, N = 3799.36792.441. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Numenta Anomaly Benchmark

Detector: EXPoSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: EXPoSEFSGSBASE Enablednofsgsbase30060090012001500SE +/- 15.42, N = 3SE +/- 5.29, N = 31513.781500.85

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverFSGSBASE Enablednofsgsbase9001800270036004500SE +/- 0.87, N = 3SE +/- 0.38, N = 33932.763966.361. (CC) gcc options: -O3 -march=native -mavx2

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeFSGSBASE Enablednofsgsbase306090120150SE +/- 0.67, N = 31241251. (CC) gcc options: -O3 -march=native

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDFSGSBASE Enablednofsgsbase400K800K1200K1600K2000KSE +/- 2516.35, N = 3SE +/- 30688.88, N = 152087688.752071005.921. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEFSGSBASE Enablednofsgsbase100K200K300K400K500KSE +/- 1247.48, N = 3SE +/- 104.27, N = 3447930.47444432.101. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingFSGSBASE Enablednofsgsbase1.2M2.4M3.6M4.8M6MSE +/- 27153.16, N = 3SE +/- 54477.77, N = 3535627253964111. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

AOM AV1

Encoder Mode: Speed 6 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 RealtimeFSGSBASE Enablednofsgsbase3691215SE +/- 0.08, N = 3SE +/- 0.09, N = 310.8610.781. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressFSGSBASE Enablednofsgsbase3K6K9K12K15KSE +/- 19.86, N = 3SE +/- 52.61, N = 311896.4211983.661. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pFSGSBASE Enablednofsgsbase1122334455SE +/- 0.53, N = 3SE +/- 0.04, N = 348.8749.211. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadFSGSBASE Enablednofsgsbase20406080100SE +/- 1.10, N = 3SE +/- 1.38, N = 392.2891.651. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUFSGSBASE Enablednofsgsbase612182430SE +/- 0.24, N = 3SE +/- 0.07, N = 324.9825.15

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyFSGSBASE Enablednofsgsbase48121620SE +/- 0.05, N = 3SE +/- 0.16, N = 314.8114.91

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUFSGSBASE Enablednofsgsbase1.0082.0163.0244.0325.04SE +/- 0.03, N = 3SE +/- 0.03, N = 34.454.48

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileFSGSBASE Enablednofsgsbase918273645SE +/- 0.38, N = 8SE +/- 0.39, N = 837.4337.18

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaFSGSBASE Enablednofsgsbase20406080100SE +/- 0.14, N = 3SE +/- 0.44, N = 374.6675.12

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncFSGSBASE Enablednofsgsbase10002000300040005000SE +/- 8.32, N = 3SE +/- 8.46, N = 34485.354460.311. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileFSGSBASE Enablednofsgsbase60120180240300SE +/- 3.74, N = 4SE +/- 1.49, N = 3283.74285.30

Facebook RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadFSGSBASE Enablednofsgsbase30M60M90M120M150MSE +/- 833744.91, N = 3SE +/- 497372.75, N = 31422056481414481981. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

AOM AV1

Encoder Mode: Speed 4 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-PassFSGSBASE Enablednofsgsbase0.43880.87761.31641.75522.194SE +/- 0.00, N = 3SE +/- 0.00, N = 31.951.941. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETFSGSBASE Enablednofsgsbase400K800K1200K1600K2000KSE +/- 2456.08, N = 3SE +/- 4205.47, N = 31918164.831908415.461. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Apache HBase

Test: Random Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Read - Clients: 1FSGSBASE Enablednofsgsbase50100150200250SE +/- 2.57, N = 15SE +/- 2.20, N = 15213214

AOM AV1

Encoder Mode: Speed 8 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 RealtimeFSGSBASE Enablednofsgsbase612182430SE +/- 0.17, N = 3SE +/- 0.31, N = 323.7423.841. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointFSGSBASE Enablednofsgsbase816243240SE +/- 0.35, N = 3SE +/- 0.26, N = 332.7432.60

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3FSGSBASE Enablednofsgsbase200K400K600K800K1000KSE +/- 10256.56, N = 15SE +/- 9309.86, N = 3108718310826501. (CC) gcc options: -pthread -lpthread -O3 -march=native

dav1d

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pFSGSBASE Enablednofsgsbase70140210280350SE +/- 3.13, N = 3SE +/- 4.08, N = 3329.39328.03MIN: 204.26 / MAX: 425.36MIN: 183.84 / MAX: 426.681. (CC) gcc options: -O3 -march=native -pthread

Apache HBase

Test: Random Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Read - Clients: 1FSGSBASE Enablednofsgsbase10002000300040005000SE +/- 56.05, N = 15SE +/- 48.14, N = 1546434625

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomFSGSBASE Enablednofsgsbase306090120150SE +/- 0.13, N = 3SE +/- 0.75, N = 3113.58113.201. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

VP9 libvpx Encoding

Speed: Speed 0

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0FSGSBASE Enablednofsgsbase246810SE +/- 0.01, N = 3SE +/- 0.02, N = 36.146.121. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11

dav1d

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitFSGSBASE Enablednofsgsbase20406080100SE +/- 0.13, N = 3SE +/- 0.10, N = 387.2087.47MIN: 66.61 / MAX: 133.73MIN: 66.73 / MAX: 137.931. (CC) gcc options: -O3 -march=native -pthread

oneDNN

Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase1.28152.5633.84455.1266.4075SE +/- 0.00089, N = 3SE +/- 0.00720, N = 35.695625.67910MIN: 5.52MIN: 5.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water BenchmarkFSGSBASE Enablednofsgsbase0.79071.58142.37213.16283.9535SE +/- 0.001, N = 3SE +/- 0.006, N = 33.5063.5141. (CXX) g++ options: -O3 -march=native -pthread -lrt -lpthread -lm

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillFSGSBASE Enablednofsgsbase40K80K120K160K200KSE +/- 172.09, N = 3SE +/- 226.90, N = 31860931864511. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUFSGSBASE Enablednofsgsbase3691215SE +/- 0.12, N = 3SE +/- 0.09, N = 310.6210.60

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase0.32670.65340.98011.30681.6335SE +/- 0.00269, N = 3SE +/- 0.00164, N = 31.449231.45193MIN: 1.4MIN: 1.411. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyFSGSBASE Enablednofsgsbase130K260K390K520K650KSE +/- 2139.37, N = 3SE +/- 3396.56, N = 3593329.43594395.911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase246810SE +/- 0.00089, N = 3SE +/- 0.01144, N = 36.397286.38735MIN: 6.3MIN: 6.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Apache Siege

Concurrent Users: 10

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 10FSGSBASE Enablednofsgsbase5K10K15K20K25KSE +/- 150.23, N = 3SE +/- 164.71, N = 322712.0522746.881. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaFSGSBASE Enablednofsgsbase1020304050SE +/- 0.77, N = 12SE +/- 0.45, N = 1146.0346.09

PostgreSQL pgbench

Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read OnlyFSGSBASE Enablednofsgsbase130K260K390K520K650KSE +/- 1415.39, N = 3SE +/- 680.20, N = 3618994.74619694.861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchFSGSBASE Enablednofsgsbase3691215SE +/- 0.17, N = 3SE +/- 0.10, N = 312.7212.731. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13ATPase Simulation - 327,506 AtomsFSGSBASE Enablednofsgsbase0.13750.2750.41250.550.6875SE +/- 0.00455, N = 14SE +/- 0.00071, N = 30.611040.61077

QMCPACK

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.8FSGSBASE Enablednofsgsbase60012001800240030002687.62688.51. (CXX) g++ options: -O3 -march=native -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -lm

oneDNN

Harness: IP Batch All - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase1224364860SE +/- 0.02, N = 3SE +/- 0.03, N = 351.1051.11MIN: 50.05MIN: 50.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Apache Siege

Concurrent Users: 50

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 50FSGSBASE Enablednofsgsbase7K14K21K28K35KSE +/- 194.24, N = 3SE +/- 188.88, N = 333173.4533180.661. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

oneDNN

Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase246810SE +/- 0.01137, N = 3SE +/- 0.00338, N = 37.391547.39063MIN: 7.23MIN: 7.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 - Engine: CPUFSGSBASE Enablednofsgsbase3691215SE +/- 0.00175, N = 3SE +/- 0.00883, N = 39.461589.46163MIN: 9.31MIN: 9.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncFSGSBASE Enablednofsgsbase0.4050.811.2151.622.025SE +/- 0.00, N = 3SE +/- 0.00, N = 31.81.81. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

SVT-AV1

Encoder Mode: Enc Mode 0 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pFSGSBASE Enablednofsgsbase0.0270.0540.0810.1080.135SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1200.1201. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

AOM AV1

Encoder Mode: Speed 0 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-PassFSGSBASE Enablednofsgsbase0.06080.12160.18240.24320.304SE +/- 0.00, N = 3SE +/- 0.00, N = 30.270.271. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

pmbench

Concurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writes

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% WritesFSGSBASE Enablednofsgsbase0.0170.0340.0510.0680.085SE +/- 0.0002, N = 3SE +/- 0.0002, N = 30.07560.07561. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction PerformanceFSGSBASE Enablednofsgsbase12002400360048006000SE +/- 44.00, N = 3SE +/- 44.00, N = 3572557251. (CC) gcc options: -O3 -march=native

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionFSGSBASE Enablednofsgsbase0.45230.90461.35691.80922.2615SE +/- 0.02, N = 9SE +/- 0.03, N = 151.962.01

Apache Siege

Concurrent Users: 200

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200FSGSBASE Enablednofsgsbase10K20K30K40K50KSE +/- 1308.05, N = 12SE +/- 254.67, N = 348540.4143531.701. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

Apache HBase

Test: Async Random Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Async Random Read - Clients: 1FSGSBASE Enablednofsgsbase4080120160200SE +/- 3.20, N = 15SE +/- 3.36, N = 12189193

Apache HBase

Test: Async Random Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Async Random Read - Clients: 1FSGSBASE Enablednofsgsbase11002200330044005500SE +/- 81.85, N = 15SE +/- 78.77, N = 1252455137

Apache HBase

Test: Sequential Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 1FSGSBASE Enablednofsgsbase4080120160200SE +/- 3.62, N = 15SE +/- 1.75, N = 15189195

Apache HBase

Test: Sequential Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 1FSGSBASE Enablednofsgsbase11002200330044005500SE +/- 93.78, N = 15SE +/- 44.45, N = 1552705090

Facebook RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncFSGSBASE Enablednofsgsbase14002800420056007000SE +/- 511.75, N = 15SE +/- 26.46, N = 3653256811. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesFSGSBASE Enablednofsgsbase30K60K90K120K150KSE +/- 2666.43, N = 15SE +/- 1934.98, N = 15147023134285

Memtier_benchmark

Protocol: Redis

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: RedisFSGSBASE Enablednofsgsbase600K1200K1800K2400K3000KSE +/- 74458.90, N = 15SE +/- 13554.01, N = 32859981.402635763.821. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

YafaRay

Total Time For Sample Scene

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneFSGSBASE Enablednofsgsbase306090120150SE +/- 2.93, N = 15SE +/- 3.44, N = 15108.82113.631. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

Node.js Express HTTP Load Test

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestFSGSBASE Enablednofsgsbase2K4K6K8K10KSE +/- 152.70, N = 15SE +/- 181.89, N = 15939593421. Nodejs v10.19.0

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOFSGSBASE Enablednofsgsbase5K10K15K20K25KSE +/- 370.01, N = 20SE +/- 803.93, N = 1621837.0024407.08

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSFSGSBASE Enablednofsgsbase6001200180024003000SE +/- 32.22, N = 25SE +/- 41.50, N = 252896.192985.60

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin ProteinFSGSBASE Enablednofsgsbase48121620SE +/- 0.30, N = 3SE +/- 0.31, N = 1517.9517.141. (CXX) g++ options: -O3 -march=native -rdynamic -ljpeg -lpng -lz -lfftw3 -lm

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence AlignmentFSGSBASE Enablednofsgsbase0.59961.19921.79882.39842.998SE +/- 0.054, N = 15SE +/- 0.056, N = 152.6602.6651. (CC) gcc options: -std=c99 -O3 -lm -lpthread

pmbench

Concurrent Worker Threads: 72 - Read-Write Ratio: 100% Reads

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 72 - Read-Write Ratio: 100% ReadsFSGSBASE Enablednofsgsbase0.01040.02080.03120.04160.052SE +/- 0.0012, N = 12SE +/- 0.0004, N = 150.04600.04511. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

BlogBench

Test: Write

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WriteFSGSBASE Enablednofsgsbase5K10K15K20K25KSE +/- 920.31, N = 3SE +/- 1371.68, N = 324247204551. (CC) gcc options: -O3 -march=native -pthread

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryFSGSBASE Enablednofsgsbase4080120160200SE +/- 2.96, N = 3SE +/- 6.41, N = 151891701. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryFSGSBASE Enablednofsgsbase80160240320400SE +/- 6.17, N = 3SE +/- 12.84, N = 153853461. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Geometric Mean Of All Test Results

Result Composite - Xeon Cascade Lake R Intel FSGSBASE

OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - Xeon Cascade Lake R Intel FSGSBASEFSGSBASE Enablednofsgsbase20406080100101.3897.90

Number Of First Place Finishes

Wins - 111 Tests

FSGSBASE Enabled63 [56.8%]nofsgsbase48 [43.2%]Number Of First Place FinishesWins - 111 TestsOpenBenchmarking.org

Number Of Last Place Finishes

Losses - 111 Tests

FSGSBASE Enabled43 [38.7%]nofsgsbase68 [61.3%]Number Of Last Place FinishesLosses - 111 TestsOpenBenchmarking.org

Phoronix Test Suite v10.8.5