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&grr.

Xeon Cascade Lake R Intel FSGSBASEProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionnofsgsbaseFSGSBASE Enabled2 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- nofsgsbase: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5002f01- FSGSBASE Enabled: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c Java Details- nofsgsbase: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)- FSGSBASE Enabled: OpenJDK Runtime Environment (build 11.0.7-ea+9-post-Ubuntu-1ubuntu1) 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 FSGSBASEplaidml: No - Inference - NASNer Large - CPUmysqlslap: 512mysqlslap: 64numenta-nab: EXPoSEmysqlslap: 256renaissance: Savina Reactors.IOmysqlslap: 128plaidml: No - Inference - DenseNet 201 - CPUqmcpack: renaissance: Apache Spark ALScp2k: Fayalite-FIST Datayafaray: Total Time For Sample Scenemlpack: scikit_qdaplaidml: No - Inference - ResNet 50 - CPUcassandra: Writesplaidml: No - Inference - Inception V3 - CPUleveldb: Seq Fillleveldb: Seq Fillleveldb: Rand Deleterocksdb: Seq Fillmlpack: scikit_linearridgeregressionpgbench: Buffer Test - Heavy Contention - Read Writebuild-llvm: Time To Compilememtier-benchmark: Redisjava-gradle-perf: Reactorpmbench: 72 - 100% Readshbase: Increment - 1hbase: Increment - 1hbase: Rand Read - 1hbase: Rand Read - 1pgbench: Buffer Test - Normal Load - Read Writeplaidml: No - Inference - Mobilenet - CPUhbase: Seq Read - 1hbase: Seq Read - 1rocksdb: Rand Fill Synchbase: Async Rand Read - 1hbase: Async Rand Read - 1svt-av1: Enc Mode 0 - 1080ppgbench: Buffer Test - Heavy Contention - Read Onlybuild-gdb: Time To Compilepgbench: Buffer Test - Normal Load - Read Onlydav1d: Chimera 1080p 10-bitplaidml: No - Inference - VGG16 - CPUleveldb: Seek Randplaidml: No - Inference - VGG19 - CPUnamd: ATPase Simulation - 327,506 Atomsapache-siege: 200fio: Seq Write - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Seq Write - IO_uring - Yes - No - 2MB - Default Test Directoryvpxenc: Speed 0build-linux-kernel: Time To Compileleveldb: Rand Readleveldb: Hot Readnumenta-nab: Earthgecko Skylinepmbench: 72 - 100% Writesleveldb: Rand Fillleveldb: Rand Fillleveldb: Overwriteleveldb: Overwritemlpack: scikit_icakeydb: pmbench: 1 - 80% Reads 20% Writesrocksdb: Rand Fillrocksdb: Read While Writingrocksdb: Rand Readebizzy: gromacs: Water Benchmarkonednn: IP Batch All - bf16bf16bf16 - CPUaom-av1: Speed 6 Realtimenode-express-loadtest: himeno: Poisson Pressure Solverpostmark: Disk Transaction Performanceplaidml: No - Inference - IMDB LSTM - CPUaom-av1: Speed 0 Two-Passaom-av1: Speed 6 Two-Passdav1d: Chimera 1080pfio: Rand Write - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directorymlpack: scikit_svmnumenta-nab: Bayesian Changepointredis: SADDstress-ng: CPU Stressstress-ng: Atomicstress-ng: SENDFILEstress-ng: Context Switchingvpxenc: Speed 5aom-av1: Speed 8 Realtimebuild-apache: Time To Compileaom-av1: Speed 4 Two-Passonednn: Deconvolution Batch deconv_1d - bf16bf16bf16 - CPUdav1d: Summer Nature 4Ksvt-av1: Enc Mode 4 - 1080ponednn: IP Batch 1D - bf16bf16bf16 - CPUapache-siege: 50numenta-nab: Relative Entropymafft: Multiple Sequence Alignmenthmmer: Pfam Database Searchonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUsvt-av1: Enc Mode 8 - 1080predis: SETredis: LPOPredis: GETdav1d: Summer Nature 1080ponednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUlammps: Rhodopsin Proteinleveldb: Fill Syncleveldb: Fill Syncapache-siege: 10onednn: Deconvolution Batch deconv_3d - bf16bf16bf16 - CPUctx-clock: Context Switch Timeblogbench: WritenofsgsbaseFSGSBASE Enabled0.581401991500.84714324407.0831541.982688.52985.5961886.257113.62946.094.481342855.45809.4419.9761.4341896432.012634.266319285.3002635763.82288.7930.0451308323121446252762.90225510.601955090568119351370.12619694.855637135.384594395.90669187.4725.15113.20321.390.6107743531.701703466.1237.18193.01091.64689.6090.0812798.60110.0792.43910.075.12418712.100.0756186451539641114144819810826503.51451.113410.7893423966.3559795725850.650.272.91328.031356340028.4632.6012071005.9211983.6685800.80444432.107847877.5923.2423.8425.4741.947.39063180.775.6835.6791033180.6614.9132.66512.7271.4519349.2111908415.461707562.792340376.2335.166.3873517.1414460.3081.822746.889.46163125204550.571612051513.77915021837.0031591.962687.62896.1912027.693108.81846.034.451470235.50826.2689.6774.3571879501.964727.713744283.7372859981.40276.5800.0460291341321346434908.50170410.621895270653218952450.120618994.742715137.398593329.42768387.2024.98113.58120.640.6110448540.411893856.1437.43193.99992.27790.7750.0802809.6959.8799.3569.974.66428585.010.0756186093535627214220564810871833.50651.096410.8693953932.7626155725868.090.272.98329.391878880028.7132.7382087688.7511896.4290016.18447930.479410762.6723.0123.7425.7641.957.39154182.785.7705.6956233173.4514.8132.66012.7191.4492348.8741918164.832611119.752500801.50338.366.3972817.9504485.3501.822712.059.4615812424247OpenBenchmarking.org

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: CPUnofsgsbaseFSGSBASE Enabled0.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.57

MariaDB

Clients: 512

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512nofsgsbaseFSGSBASE Enabled4080120160200SE +/- 0.52, N = 3SE +/- 2.84, N = 91401611. (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

MariaDB

Clients: 64

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64nofsgsbaseFSGSBASE Enabled4080120160200SE +/- 2.50, N = 5SE +/- 2.42, N = 61992051. (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

Numenta Anomaly Benchmark

Detector: EXPoSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: EXPoSEnofsgsbaseFSGSBASE Enabled30060090012001500SE +/- 5.29, N = 3SE +/- 15.42, N = 31500.851513.78

MariaDB

Clients: 256

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256nofsgsbaseFSGSBASE Enabled306090120150SE +/- 0.32, N = 3SE +/- 0.58, N = 31431501. (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

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOnofsgsbaseFSGSBASE Enabled5K10K15K20K25KSE +/- 803.93, N = 16SE +/- 370.01, N = 2024407.0821837.00

MariaDB

Clients: 128

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128nofsgsbaseFSGSBASE Enabled4080120160200SE +/- 0.65, N = 3SE +/- 0.48, N = 31541591. (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

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPUnofsgsbaseFSGSBASE Enabled0.44550.8911.33651.7822.2275SE +/- 0.01, N = 3SE +/- 0.01, N = 31.981.96

QMCPACK

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.8nofsgsbaseFSGSBASE Enabled60012001800240030002688.52687.61. (CXX) g++ options: -O3 -march=native -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -lm

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSnofsgsbaseFSGSBASE Enabled6001200180024003000SE +/- 41.50, N = 25SE +/- 32.22, N = 252985.602896.19

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST DatanofsgsbaseFSGSBASE Enabled4008001200160020001886.262027.69

YafaRay

Total Time For Sample Scene

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample ScenenofsgsbaseFSGSBASE Enabled306090120150SE +/- 3.44, N = 15SE +/- 2.93, N = 15113.63108.821. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdanofsgsbaseFSGSBASE Enabled1020304050SE +/- 0.45, N = 11SE +/- 0.77, N = 1246.0946.03

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUnofsgsbaseFSGSBASE Enabled1.0082.0163.0244.0325.04SE +/- 0.03, N = 3SE +/- 0.03, N = 34.484.45

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesnofsgsbaseFSGSBASE Enabled30K60K90K120K150KSE +/- 1934.98, N = 15SE +/- 2666.43, N = 15134285147023

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUnofsgsbaseFSGSBASE Enabled1.23752.4753.71254.956.1875SE +/- 0.02, N = 3SE +/- 0.03, N = 35.455.50

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillnofsgsbaseFSGSBASE Enabled2004006008001000SE +/- 3.18, N = 3SE +/- 3.79, N = 3809.44826.271. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillnofsgsbaseFSGSBASE Enabled3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 39.99.61. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Random Delete

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeletenofsgsbaseFSGSBASE Enabled170340510680850SE +/- 2.15, N = 3SE +/- 1.02, N = 3761.43774.361. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Facebook RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillnofsgsbaseFSGSBASE Enabled40K80K120K160K200KSE +/- 107.10, N = 3SE +/- 190.16, N = 31896431879501. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionnofsgsbaseFSGSBASE Enabled0.45230.90461.35691.80922.2615SE +/- 0.03, N = 15SE +/- 0.02, N = 92.011.96

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 WritenofsgsbaseFSGSBASE Enabled10002000300040005000SE +/- 25.55, N = 9SE +/- 59.91, N = 32634.274727.711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompilenofsgsbaseFSGSBASE Enabled60120180240300SE +/- 1.49, N = 3SE +/- 3.74, N = 4285.30283.74

Memtier_benchmark

Protocol: Redis

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: RedisnofsgsbaseFSGSBASE Enabled600K1200K1800K2400K3000KSE +/- 13554.01, N = 3SE +/- 74458.90, N = 152635763.822859981.401. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

Java Gradle Build

Gradle Build: Reactor

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactornofsgsbaseFSGSBASE Enabled60120180240300SE +/- 2.12, N = 3SE +/- 3.18, N = 3288.79276.58

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% ReadsnofsgsbaseFSGSBASE Enabled0.01040.02080.03120.04160.052SE +/- 0.0004, N = 15SE +/- 0.0012, N = 120.04510.04601. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Apache HBase

Test: Increment - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Increment - Clients: 1nofsgsbaseFSGSBASE Enabled70140210280350SE +/- 2.70, N = 15SE +/- 2.52, N = 11308291

Apache HBase

Test: Increment - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Increment - Clients: 1nofsgsbaseFSGSBASE Enabled7001400210028003500SE +/- 28.49, N = 15SE +/- 30.10, N = 1132313413

Apache HBase

Test: Random Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Read - Clients: 1nofsgsbaseFSGSBASE Enabled50100150200250SE +/- 2.20, N = 15SE +/- 2.57, N = 15214213

Apache HBase

Test: Random Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Read - Clients: 1nofsgsbaseFSGSBASE Enabled10002000300040005000SE +/- 48.14, N = 15SE +/- 56.05, N = 1546254643

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 WritenofsgsbaseFSGSBASE Enabled11002200330044005500SE +/- 34.32, N = 3SE +/- 59.24, N = 62762.904908.501. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUnofsgsbaseFSGSBASE Enabled3691215SE +/- 0.09, N = 3SE +/- 0.12, N = 310.6010.62

Apache HBase

Test: Sequential Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 1nofsgsbaseFSGSBASE Enabled4080120160200SE +/- 1.75, N = 15SE +/- 3.62, N = 15195189

Apache HBase

Test: Sequential Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 1nofsgsbaseFSGSBASE Enabled11002200330044005500SE +/- 44.45, N = 15SE +/- 93.78, N = 1550905270

Facebook RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncnofsgsbaseFSGSBASE Enabled14002800420056007000SE +/- 26.46, N = 3SE +/- 511.75, N = 15568165321. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Apache HBase

Test: Async Random Read - Clients: 1

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Async Random Read - Clients: 1nofsgsbaseFSGSBASE Enabled4080120160200SE +/- 3.36, N = 12SE +/- 3.20, N = 15193189

Apache HBase

Test: Async Random Read - Clients: 1

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Async Random Read - Clients: 1nofsgsbaseFSGSBASE Enabled11002200330044005500SE +/- 78.77, N = 12SE +/- 81.85, N = 1551375245

SVT-AV1

Encoder Mode: Enc Mode 0 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pnofsgsbaseFSGSBASE Enabled0.0270.0540.0810.1080.135SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1200.1201. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 OnlynofsgsbaseFSGSBASE Enabled130K260K390K520K650KSE +/- 680.20, N = 3SE +/- 1415.39, N = 3619694.86618994.741. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed GDB GNU Debugger Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompilenofsgsbaseFSGSBASE Enabled306090120150SE +/- 0.05, N = 3SE +/- 0.07, N = 3135.38137.40

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 OnlynofsgsbaseFSGSBASE Enabled130K260K390K520K650KSE +/- 3396.56, N = 3SE +/- 2139.37, N = 3594395.91593329.431. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

dav1d

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitnofsgsbaseFSGSBASE Enabled20406080100SE +/- 0.10, N = 3SE +/- 0.13, N = 387.4787.20MIN: 66.73 / MAX: 137.93MIN: 66.61 / MAX: 133.731. (CC) gcc options: -O3 -march=native -pthread

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUnofsgsbaseFSGSBASE Enabled612182430SE +/- 0.07, N = 3SE +/- 0.24, N = 325.1524.98

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomnofsgsbaseFSGSBASE Enabled306090120150SE +/- 0.75, N = 3SE +/- 0.13, N = 3113.20113.581. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUnofsgsbaseFSGSBASE Enabled510152025SE +/- 0.12, N = 3SE +/- 0.18, N = 321.3920.64

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13ATPase Simulation - 327,506 AtomsnofsgsbaseFSGSBASE Enabled0.13750.2750.41250.550.6875SE +/- 0.00071, N = 3SE +/- 0.00455, N = 140.610770.61104

Apache Siege

Concurrent Users: 200

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200nofsgsbaseFSGSBASE Enabled10K20K30K40K50KSE +/- 254.67, N = 3SE +/- 1308.05, N = 1243531.7048540.411. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

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 DirectorynofsgsbaseFSGSBASE Enabled4080120160200SE +/- 6.41, N = 15SE +/- 2.96, N = 31701891. (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 DirectorynofsgsbaseFSGSBASE Enabled80160240320400SE +/- 12.84, N = 15SE +/- 6.17, N = 33463851. (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

VP9 libvpx Encoding

Speed: Speed 0

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0nofsgsbaseFSGSBASE Enabled246810SE +/- 0.02, N = 3SE +/- 0.01, N = 36.126.141. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompilenofsgsbaseFSGSBASE Enabled918273645SE +/- 0.39, N = 8SE +/- 0.38, N = 837.1837.43

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadnofsgsbaseFSGSBASE Enabled20406080100SE +/- 0.66, N = 3SE +/- 0.05, N = 393.0194.001. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadnofsgsbaseFSGSBASE Enabled20406080100SE +/- 1.38, N = 3SE +/- 1.10, N = 391.6592.281. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylinenofsgsbaseFSGSBASE Enabled20406080100SE +/- 0.29, N = 3SE +/- 0.50, N = 389.6190.78

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% WritesnofsgsbaseFSGSBASE Enabled0.01830.03660.05490.07320.0915SE +/- 0.0009, N = 3SE +/- 0.0010, N = 50.08120.08021. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillnofsgsbaseFSGSBASE Enabled2004006008001000SE +/- 8.40, N = 3SE +/- 3.59, N = 3798.60809.701. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillnofsgsbaseFSGSBASE Enabled3691215SE +/- 0.10, N = 3SE +/- 0.03, N = 310.09.81. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwritenofsgsbaseFSGSBASE Enabled2004006008001000SE +/- 2.31, N = 3SE +/- 1.81, N = 3792.44799.361. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwritenofsgsbaseFSGSBASE Enabled3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 310.09.91. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icanofsgsbaseFSGSBASE Enabled20406080100SE +/- 0.44, N = 3SE +/- 0.14, N = 375.1274.66

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.1nofsgsbaseFSGSBASE Enabled90K180K270K360K450KSE +/- 5862.96, N = 3SE +/- 4575.82, N = 3418712.10428585.011. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

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% WritesnofsgsbaseFSGSBASE Enabled0.0170.0340.0510.0680.085SE +/- 0.0002, N = 3SE +/- 0.0002, N = 30.07560.07561. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillnofsgsbaseFSGSBASE Enabled40K80K120K160K200KSE +/- 226.90, N = 3SE +/- 172.09, N = 31864511860931. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingnofsgsbaseFSGSBASE Enabled1.2M2.4M3.6M4.8M6MSE +/- 54477.77, N = 3SE +/- 27153.16, N = 3539641153562721. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadnofsgsbaseFSGSBASE Enabled30M60M90M120M150MSE +/- 497372.75, N = 3SE +/- 833744.91, N = 31414481981422056481. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3nofsgsbaseFSGSBASE Enabled200K400K600K800K1000KSE +/- 9309.86, N = 3SE +/- 10256.56, N = 15108265010871831. (CC) gcc options: -pthread -lpthread -O3 -march=native

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water BenchmarknofsgsbaseFSGSBASE Enabled0.79071.58142.37213.16283.9535SE +/- 0.006, N = 3SE +/- 0.001, N = 33.5143.5061. (CXX) g++ options: -O3 -march=native -pthread -lrt -lpthread -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: CPUnofsgsbaseFSGSBASE Enabled1224364860SE +/- 0.03, N = 3SE +/- 0.02, N = 351.1151.10MIN: 50.21MIN: 50.051. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

Encoder Mode: Speed 6 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 RealtimenofsgsbaseFSGSBASE Enabled3691215SE +/- 0.09, N = 3SE +/- 0.08, N = 310.7810.861. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Node.js Express HTTP Load Test

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestnofsgsbaseFSGSBASE Enabled2K4K6K8K10KSE +/- 181.89, N = 15SE +/- 152.70, N = 15934293951. Nodejs v10.19.0

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolvernofsgsbaseFSGSBASE Enabled9001800270036004500SE +/- 0.38, N = 3SE +/- 0.87, N = 33966.363932.761. (CC) gcc options: -O3 -march=native -mavx2

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction PerformancenofsgsbaseFSGSBASE Enabled12002400360048006000SE +/- 44.00, N = 3SE +/- 44.00, N = 3572557251. (CC) gcc options: -O3 -march=native

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUnofsgsbaseFSGSBASE Enabled2004006008001000SE +/- 3.24, N = 3SE +/- 11.90, N = 4850.65868.09

AOM AV1

Encoder Mode: Speed 0 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-PassnofsgsbaseFSGSBASE Enabled0.06080.12160.18240.24320.304SE +/- 0.00, N = 3SE +/- 0.00, N = 30.270.271. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

AOM AV1

Encoder Mode: Speed 6 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-PassnofsgsbaseFSGSBASE Enabled0.67051.3412.01152.6823.3525SE +/- 0.02, N = 3SE +/- 0.00, N = 32.912.981. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

dav1d

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pnofsgsbaseFSGSBASE Enabled70140210280350SE +/- 4.08, N = 3SE +/- 3.13, N = 3328.03329.39MIN: 183.84 / MAX: 426.68MIN: 204.26 / MAX: 425.361. (CC) gcc options: -O3 -march=native -pthread

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 DirectorynofsgsbaseFSGSBASE Enabled4080120160200SE +/- 0.88, N = 3SE +/- 0.33, N = 31351871. (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: 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 DirectorynofsgsbaseFSGSBASE Enabled20K40K60K80K100KSE +/- 100.00, N = 3SE +/- 251.66, N = 363400888001. (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

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmnofsgsbaseFSGSBASE Enabled714212835SE +/- 0.02, N = 3SE +/- 0.14, N = 328.4628.71

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointnofsgsbaseFSGSBASE Enabled816243240SE +/- 0.26, N = 3SE +/- 0.35, N = 332.6032.74

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDnofsgsbaseFSGSBASE Enabled400K800K1200K1600K2000KSE +/- 30688.88, N = 15SE +/- 2516.35, N = 32071005.922087688.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressnofsgsbaseFSGSBASE Enabled3K6K9K12K15KSE +/- 52.61, N = 3SE +/- 19.86, N = 311983.6611896.421. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicnofsgsbaseFSGSBASE Enabled20K40K60K80K100KSE +/- 1320.48, N = 3SE +/- 1267.27, N = 385800.8090016.181. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEnofsgsbaseFSGSBASE Enabled100K200K300K400K500KSE +/- 104.27, N = 3SE +/- 1247.48, N = 3444432.10447930.471. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingnofsgsbaseFSGSBASE Enabled2M4M6M8M10MSE +/- 27584.57, N = 3SE +/- 154150.18, N = 37847877.599410762.671. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

VP9 libvpx Encoding

Speed: Speed 5

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5nofsgsbaseFSGSBASE Enabled612182430SE +/- 0.08, N = 3SE +/- 0.09, N = 323.2423.011. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11

AOM AV1

Encoder Mode: Speed 8 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 RealtimenofsgsbaseFSGSBASE Enabled612182430SE +/- 0.31, N = 3SE +/- 0.17, N = 323.8423.741. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompilenofsgsbaseFSGSBASE Enabled612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 325.4725.76

AOM AV1

Encoder Mode: Speed 4 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-PassnofsgsbaseFSGSBASE Enabled0.43880.87761.31641.75522.194SE +/- 0.00, N = 3SE +/- 0.00, N = 31.941.951. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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: CPUnofsgsbaseFSGSBASE Enabled246810SE +/- 0.00338, N = 3SE +/- 0.01137, N = 37.390637.39154MIN: 7.23MIN: 7.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KnofsgsbaseFSGSBASE Enabled4080120160200SE +/- 0.93, N = 3SE +/- 2.74, N = 3180.77182.78MIN: 91.75 / MAX: 195.31MIN: 88.23 / MAX: 199.521. (CC) gcc options: -O3 -march=native -pthread

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pnofsgsbaseFSGSBASE Enabled1.29832.59663.89495.19326.4915SE +/- 0.082, N = 3SE +/- 0.067, N = 35.6835.7701. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPUnofsgsbaseFSGSBASE Enabled1.28152.5633.84455.1266.4075SE +/- 0.00720, N = 3SE +/- 0.00089, N = 35.679105.69562MIN: 5.5MIN: 5.521. (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: 50nofsgsbaseFSGSBASE Enabled7K14K21K28K35KSE +/- 188.88, N = 3SE +/- 194.24, N = 333180.6633173.451. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropynofsgsbaseFSGSBASE Enabled48121620SE +/- 0.16, N = 3SE +/- 0.05, N = 314.9114.81

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence AlignmentnofsgsbaseFSGSBASE Enabled0.59961.19921.79882.39842.998SE +/- 0.056, N = 15SE +/- 0.054, N = 152.6652.6601. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchnofsgsbaseFSGSBASE Enabled3691215SE +/- 0.10, N = 3SE +/- 0.17, N = 312.7312.721. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

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: CPUnofsgsbaseFSGSBASE Enabled0.32670.65340.98011.30681.6335SE +/- 0.00164, N = 3SE +/- 0.00269, N = 31.451931.44923MIN: 1.41MIN: 1.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pnofsgsbaseFSGSBASE Enabled1122334455SE +/- 0.04, N = 3SE +/- 0.53, N = 349.2148.871. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETnofsgsbaseFSGSBASE Enabled400K800K1200K1600K2000KSE +/- 4205.47, N = 3SE +/- 2456.08, N = 31908415.461918164.831. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPnofsgsbaseFSGSBASE Enabled600K1200K1800K2400K3000KSE +/- 9534.81, N = 3SE +/- 14141.11, N = 31707562.792611119.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETnofsgsbaseFSGSBASE Enabled500K1000K1500K2000K2500KSE +/- 18114.33, N = 3SE +/- 31845.75, N = 32340376.202500801.501. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pnofsgsbaseFSGSBASE Enabled70140210280350SE +/- 1.40, N = 3SE +/- 1.19, N = 3335.16338.36MIN: 172.66 / MAX: 372.4MIN: 185.24 / MAX: 374.841. (CC) gcc options: -O3 -march=native -pthread

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: CPUnofsgsbaseFSGSBASE Enabled246810SE +/- 0.01144, N = 3SE +/- 0.00089, N = 36.387356.39728MIN: 6.3MIN: 6.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin ProteinnofsgsbaseFSGSBASE Enabled48121620SE +/- 0.31, N = 15SE +/- 0.30, N = 317.1417.951. (CXX) g++ options: -O3 -march=native -rdynamic -ljpeg -lpng -lz -lfftw3 -lm

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncnofsgsbaseFSGSBASE Enabled10002000300040005000SE +/- 8.46, N = 3SE +/- 8.32, N = 34460.314485.351. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncnofsgsbaseFSGSBASE Enabled0.4050.811.2151.622.025SE +/- 0.00, N = 3SE +/- 0.00, N = 31.81.81. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread

Apache Siege

Concurrent Users: 10

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 10nofsgsbaseFSGSBASE Enabled5K10K15K20K25KSE +/- 164.71, N = 3SE +/- 150.23, N = 322746.8822712.051. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

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: CPUnofsgsbaseFSGSBASE Enabled3691215SE +/- 0.00883, N = 3SE +/- 0.00175, N = 39.461639.46158MIN: 9.35MIN: 9.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimenofsgsbaseFSGSBASE Enabled306090120150SE +/- 0.67, N = 31251241. (CC) gcc options: -O3 -march=native

BlogBench

Test: Write

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WritenofsgsbaseFSGSBASE Enabled5K10K15K20K25KSE +/- 1371.68, N = 3SE +/- 920.31, N = 320455242471. (CC) gcc options: -O3 -march=native -pthread

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 FSGSBASEnofsgsbaseFSGSBASE Enabled2040608010097.90101.38

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

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

Phoronix Test Suite v10.8.5