Linux 4.20 Kernel Benchmarks - Intel Core i9 Skylake X + AMD Threadripper Performance

Linux 4.20 kernel benchmarks by Michael Larabel on three systems for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1811151-SK-420LINUX492&obr_imw=y&gru&sor.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionAMD 2990WXIntel 7980XEIntel 7960X Linux 4.18.18 Linux 4.19.1 Linux 4.20 Git Linux 4.18.18 Linux 4.19.1 Linux 4.20 Git Linux 4.18.18 Linux 4.19.1 Linux 4.20 GitAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1501 BIOS)AMD Family 17h32768MBSamsung SSD 970 EVO 500GBAMD Radeon RX Vega 8GBRealtek ALC1220ASUS VP28UIntel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac WirelessUbuntu 18.104.18.18-041818-generic (x86_64)GNOME Shell 3.30.1X Server 1.20.1amdgpu 18.1.04.5 Mesa 18.2.2 (LLVM 7.0.0)1.1.70GCC 8.2.0ext43840x21604.19.1-041901-generic (x86_64)AMD Radeon RX Vega 64 8GB4.20.0-999-generic (x86_64) 20181112Intel Core i9-7980XE @ 4.20GHz (18 Cores / 36 Threads)ASUS PRIME X299-A (1503 BIOS)Intel Sky Lake-E DMI3 Registers16384MB240GB Force MP510NV120 12GBASUS PB278Intel Connection4.18.18-041818-generic (x86_64)modesetting 1.20.14.3 Mesa 18.2.22560x14404.19.1-041901-generic (x86_64)4.20.0-999-generic (x86_64) 20181112Intel Core i9-7960X @ 4.40GHz (16 Cores / 32 Threads)MSI X299 SLI PLUS (MS-7A93) v1.0 (1.A0 BIOS)256GB INTEL SSDPEKKW256G8Gigabyte AMD Radeon RX 550 2GBASUS VP28U4.18.18-041818-generic (x86_64)4.5 Mesa 18.2.2 (LLVM 7.0.0)1.1.703840x21604.19.1-041901-generic (x86_64)4.20.0-999-generic (x86_64) 20181112OpenBenchmarking.orgCompiler 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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- AMD 2990WX: Linux 4.18.18: Scaling Governor: acpi-cpufreq ondemand- AMD 2990WX: Linux 4.19.1: Scaling Governor: acpi-cpufreq ondemand- AMD 2990WX: Linux 4.20 Git: Scaling Governor: acpi-cpufreq ondemand- Intel 7980XE: Linux 4.18.18: Scaling Governor: intel_pstate powersave- Intel 7980XE: Linux 4.19.1: Scaling Governor: intel_pstate powersave- Intel 7980XE: Linux 4.20 Git: Scaling Governor: intel_pstate powersave- Intel 7960X: Linux 4.18.18: Scaling Governor: intel_pstate powersave- Intel 7960X: Linux 4.19.1: Scaling Governor: intel_pstate powersave- Intel 7960X: Linux 4.20 Git: Scaling Governor: intel_pstate powersaveGraphics Details- AMD 2990WX: Linux 4.18.18, AMD 2990WX: Linux 4.19.1, AMD 2990WX: Linux 4.20 Git, Intel 7960X: Linux 4.18.18, Intel 7960X: Linux 4.19.1, Intel 7960X: Linux 4.20 Git: GLAMORPython Details- Python 2.7.15+ + Python 3.6.7Security Details- AMD 2990WX: Linux 4.18.18: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- AMD 2990WX: Linux 4.19.1: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- AMD 2990WX: Linux 4.20 Git: __user pointer sanitization + Full AMD retpoline IBPB RSB filling + SSB disabled via prctl and seccomp- Intel 7980XE: Linux 4.18.18: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- Intel 7980XE: Linux 4.19.1: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- Intel 7980XE: Linux 4.20 Git: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW STIBP RSB filling + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- Intel 7960X: Linux 4.18.18: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- Intel 7960X: Linux 4.19.1: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- Intel 7960X: Linux 4.20 Git: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW STIBP RSB filling + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable

stress-ng: Forkingstress-ng: Semaphoresstress-ng: Socket Activitystress-ng: Context Switchingstress-ng: System V Message Passingfs-mark: 5000 Files, 1MB Size, 4 Threadsfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizetesseract: 3840 x 2160xonotic: 3840 x 2160 - Ultraxonotic: 3840 x 2160 - Ultimatex264: H.264 Video Encodingmcperf: Getmcperf: Setmcperf: Deletejohn-the-ripper: Blowfishjohn-the-ripper: Traditional DESnpb: BT.Anpb: EP.Cnpb: FT.Anpb: FT.Bnpb: LU.Anpb: LU.Cnpb: SP.Apgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writevkmark: 3840 x 2160dacapobench: H2dacapobench: Jythondacapobench: Eclipsedacapobench: Tradesoapdacapobench: Tradebeanssqlite: Timed SQLite Insertionsparboil: OpenMP CUTCPparboil: OpenMP Stencilcloverleaf: Lagrangian-Eulerian Hydrodynamicsrodinia: OpenMP LavaMDrodinia: OpenMP CFD Solverrodinia: OpenMP Streamclusterbuild-gcc: Time To Compilebuild-linux-kernel: Time To Compilecompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19hackbench: 32 - Processm-queens: Time To Solveblender: BMW27 - CPU-Onlynumenta-nab: Time To Completionscikit-learn: AMD 2990WXIntel 7980XEIntel 7960X Linux 4.18.18 Linux 4.19.1 Linux 4.20 Git Linux 4.18.18 Linux 4.19.1 Linux 4.20 Git Linux 4.18.18 Linux 4.19.1 Linux 4.20 Git51435177695419505155860351235622513678.99288235204145616454038265165458721764750009538343725400517838163834544547185201360255794570185585213730857.421.5015.622.1811.789.1528.1575336.0716.2937.8221.3480.0517811052296178149818967150400251244969113082.52291223196146610653592658549473191751773339488183722392717831165164564527434531359454994634187465314733653.971.5315.542.3011.839.2026.7776136.1619.2037.8521.2480.0417711053277179905720082231764581247180324575.03281219195146613363995264721456971685913339578333720361918118163844534289704585558155464678188475358731835.981.5315.272.3811.839.2128.6676236.1816.5740.5921.2980.3217611090043305330711791155605508117744248277.57128116462741571165912911299813000900655504253354125141931630968603277168934455736020.212.397.252.2920.2611.6013.7991043.3010.5244.4848.78115.91163145112537314170211625163901208069563248158.40128112989681971129552899999443667900667502253534125134821057268473238169104445743019.962.397.412.2620.4311.5813.9491843.2110.5343.6648.81115.96162146107753306445815879177604587875059249181.6312411798964590116751291239950533390066250035353408446084983570644869184384781765319.732.417.622.2426.3511.5914.1995146.8710.4642.9248.82124.211691468571931088201091914732565812322212366.5371.0599.5264.5513411312672687113250274759422900095162952385561102311066943547522310628144037643083159983164282011.742.507.952.2921.3912.4413.6470944.7410.5848.9151.78123.2516814010008531548671097215675766789519912168.0171.2599.6964.9613410993969500110034274619419000095162952945613102331067243448117410107143837453066160373176285112.932.507.802.3021.7412.3114.0370845.0310.5648.9651.78122.931691409610830191011541816779258808744112468.3870.8999.5964.841110146741310957227475938276679516275267558310231106544344346509524144639564603172193359293612.702.527.922.3027.8412.3713.9173748.6210.6347.7751.78131.62175140OpenBenchmarking.org

Stress-NG

Test: Forking

Linux 4.19.1Linux 4.20 GitLinux 4.18.18OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingIntel 7980XEIntel 7960XAMD 2990WX20K40K60K80K100KSE +/- 160.90, N = 3SE +/- 400.99, N = 3SE +/- 1430.73, N = 12SE +/- 180.67, N = 3SE +/- 174.81, N = 3SE +/- 1280.90, N = 12SE +/- 405.10, N = 3SE +/- 357.77, N = 3SE +/- 459.33, N = 31125371000855229610775396108532779004385719514351. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Semaphores

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresIntel 7960XIntel 7980XEAMD 2990WX700K1400K2100K2800K3500KSE +/- 20222.89, N = 3SE +/- 16732.64, N = 3SE +/- 6417.62, N = 3SE +/- 23531.05, N = 3SE +/- 29868.60, N = 3SE +/- 17411.62, N = 3SE +/- 12632.61, N = 3SE +/- 30994.92, N = 3SE +/- 11388.48, N = 33154867314170217814983108820305330717769543064458301910117990571. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Socket Activity

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket ActivityAMD 2990WXIntel 7980XEIntel 7960X4K8K12K16K20KSE +/- 36.09, N = 3SE +/- 244.14, N = 11SE +/- 383.18, N = 12SE +/- 61.29, N = 3SE +/- 58.37, N = 3SE +/- 117.12, N = 3SE +/- 47.03, N = 3SE +/- 112.75, N = 3SE +/- 85.66, N = 32008215879154181950511791109191896711625109721. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Context Switching

Linux 4.20 GitLinux 4.19.1Linux 4.18.18OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingAMD 2990WXIntel 7980XEIntel 7960X5M10M15M20M25MSE +/- 284727.00, N = 12SE +/- 25972.53, N = 3SE +/- 36278.05, N = 3SE +/- 70265.38, N = 3SE +/- 64635.93, N = 3SE +/- 409027.80, N = 12SE +/- 291215.37, N = 12SE +/- 47820.57, N = 3SE +/- 25045.08, N = 32317645817760458167792581639012015675766150400251558603515560550147325651. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: System V Message Passing

Linux 4.20 GitLinux 4.19.1Linux 4.18.18OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingAMD 2990WXIntel 7960XIntel 7980XE3M6M9M12M15MSE +/- 116883.95, N = 3SE +/- 4599.92, N = 3SE +/- 6026.69, N = 3SE +/- 90529.21, N = 3SE +/- 327.74, N = 3SE +/- 2753.88, N = 3SE +/- 236137.45, N = 3SE +/- 6344.13, N = 3SE +/- 445.06, N = 31247180380874417875059124496918069563789519912356225812322281177441. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

FS-Mark

Test: 5000 Files, 1MB Size, 4 Threads

Linux 4.20 GitLinux 4.19.1Linux 4.18.18OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 ThreadsIntel 7980XEAMD 2990WXIntel 7960X50100150200250SE +/- 2.72, N = 3SE +/- 32.75, N = 12SE +/- 1.84, N = 9SE +/- 4.40, N = 3SE +/- 10.15, N = 9SE +/- 1.93, N = 9SE +/- 15.81, N = 12SE +/- 3.56, N = 9SE +/- 1.72, N = 92492451242481301212481361231. (CC) gcc options: -static

FS-Mark

Test: 4000 Files, 32 Sub Dirs, 1MB Size

Linux 4.18.18Linux 4.20 GitLinux 4.19.1OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeIntel 7980XEAMD 2990WXIntel 7960X60120180240300SE +/- 5.60, N = 12SE +/- 4.17, N = 12SE +/- 2.01, N = 12SE +/- 5.75, N = 12SE +/- 1.76, N = 12SE +/- 1.59, N = 12SE +/- 0.78, N = 3SE +/- 1.86, N = 12SE +/- 1.02, N = 12277.5778.9966.53181.6375.0368.38158.4082.5268.011. (CC) gcc options: -static

Tesseract

Resolution: 3840 x 2160

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160AMD 2990WXIntel 7960X60120180240300SE +/- 0.68, N = 3SE +/- 0.26, N = 3SE +/- 0.91, N = 3SE +/- 0.27, N = 3SE +/- 4.22, N = 5SE +/- 0.24, N = 3291.0071.25288.0071.05281.0070.89

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultra

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltraAMD 2990WXIntel 7960X50100150200250SE +/- 2.72, N = 12SE +/- 0.22, N = 3SE +/- 1.07, N = 3SE +/- 0.27, N = 3SE +/- 2.78, N = 3SE +/- 0.39, N = 3235.0099.52223.0099.69219.0099.59

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultimate

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimateAMD 2990WXIntel 7960X4080120160200SE +/- 1.78, N = 3SE +/- 0.05, N = 3SE +/- 1.55, N = 3SE +/- 0.07, N = 3SE +/- 0.89, N = 3SE +/- 0.02, N = 3204.0064.55196.0064.96195.0064.84

x264

H.264 Video Encoding

Linux 4.20 GitLinux 4.19.1Linux 4.18.18OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingAMD 2990WXIntel 7960XIntel 7980XE306090120150SE +/- 2.02, N = 6SE +/- 1.09, N = 3SE +/- 1.47, N = 3SE +/- 0.23, N = 3SE +/- 1.76, N = 3SE +/- 1.89, N = 7SE +/- 1.25, N = 3SE +/- 2.57, N = 31461241461341281451341281. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Memcached mcperf

Method: Get

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: GetIntel 7980XEIntel 7960XAMD 2990WX30K60K90K120K150KSE +/- 661.39, N = 3SE +/- 230.69, N = 3SE +/- 463.94, N = 3SE +/- 394.61, N = 3SE +/- 821.55, N = 3SE +/- 1660.20, N = 12SE +/- 87.83, N = 3SE +/- 639.55, N = 3SE +/- 712.62, N = 31179891110146133611646211312661645112989109939610651. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Set

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: SetIntel 7980XEIntel 7960XAMD 2990WX16K32K48K64K80KSE +/- 541.62, N = 3SE +/- 347.18, N = 3SE +/- 1253.26, N = 12SE +/- 59.88, N = 3SE +/- 524.54, N = 3SE +/- 197.10, N = 3SE +/- 215.65, N = 3SE +/- 460.81, N = 3SE +/- 1240.70, N = 127415772687403826950068197359266741364590399521. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Delete

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: DeleteIntel 7980XEIntel 7960XAMD 2990WX30K60K90K120K150KSE +/- 835.85, N = 3SE +/- 586.19, N = 3SE +/- 1617.49, N = 12SE +/- 684.49, N = 3SE +/- 530.03, N = 3SE +/- 1524.39, N = 12SE +/- 469.70, N = 3SE +/- 491.02, N = 3SE +/- 460.84, N = 31167511095726472111659111325065165112955110034585491. (CC) gcc options: -O2 -lm -rdynamic

John The Ripper

Test: Blowfish

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: BlowfishAMD 2990WXIntel 7980XEIntel 7960X10K20K30K40K50KSE +/- 125.35, N = 3SE +/- 18.19, N = 3SE +/- 14.33, N = 3SE +/- 205.84, N = 3SE +/- 16.34, N = 3SE +/- 8.37, N = 3SE +/- 597.06, N = 3SE +/- 5.03, N = 34731928999274614587229112274754569729123274751. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

John The Ripper

Test: Traditional DES

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Traditional DESAMD 2990WXIntel 7980XEIntel 7960X40M80M120M160M200MSE +/- 1895478.92, N = 3SE +/- 22912.88, N = 3SE +/- 19502.14, N = 3SE +/- 2333744.80, N = 3SE +/- 171006.17, N = 3SE +/- 46918.37, N = 3SE +/- 647844.20, N = 3SE +/- 106273.76, N = 3SE +/- 13691.04, N = 31764750009981300094229000175177333994436679419000016859133399505333938276671. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

NAS Parallel Benchmarks

Test / Class: BT.A

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: BT.AAMD 2990WXIntel 7960XIntel 7980XE2004006008001000SE +/- 1.97, N = 3SE +/- 0.48, N = 3SE +/- 0.32, N = 3SE +/- 1.23, N = 3SE +/- 0.43, N = 3SE +/- 0.87, N = 3SE +/- 0.81, N = 3SE +/- 7.01, N = 3SE +/- 0.74, N = 39579519009539519009519489001. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: EP.C

Linux 4.18.18Linux 4.20 GitLinux 4.19.1OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: EP.CAMD 2990WXIntel 7980XEIntel 7960X2004006008001000SE +/- 1.05, N = 3SE +/- 11.35, N = 3SE +/- 0.82, N = 3SE +/- 0.45, N = 3SE +/- 3.73, N = 3SE +/- 0.96, N = 3SE +/- 8.47, N = 12SE +/- 0.84, N = 3SE +/- 0.25, N = 38346556298336626278186676291. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: FT.A

Linux 4.19.1Linux 4.20 GitLinux 4.18.18OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: FT.AIntel 7960XIntel 7980XEAMD 2990WX11002200330044005500SE +/- 9.59, N = 3SE +/- 21.05, N = 3SE +/- 2.90, N = 3SE +/- 19.26, N = 3SE +/- 27.52, N = 3SE +/- 2.47, N = 3SE +/- 12.68, N = 3SE +/- 20.19, N = 3SE +/- 32.68, N = 35294502237225267500337205238504237251. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: FT.B

Linux 4.19.1Linux 4.20 GitLinux 4.18.18OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: FT.BIntel 7960XIntel 7980XEAMD 2990WX12002400360048006000SE +/- 6.54, N = 3SE +/- 9.20, N = 3SE +/- 0.90, N = 3SE +/- 6.39, N = 3SE +/- 1.86, N = 3SE +/- 5.14, N = 3SE +/- 13.27, N = 3SE +/- 4.88, N = 3SE +/- 2.39, N = 35613535339275583535336195561533540051. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: LU.A

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.AAMD 2990WXIntel 7960X4K8K12K16K20KSE +/- 64.41, N = 3SE +/- 14.78, N = 3SE +/- 174.32, N = 3SE +/- 14.21, N = 3SE +/- 163.94, N = 3SE +/- 7.71, N = 31811810231178381023117831102331. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: LU.C

Linux 4.19.1Linux 4.20 GitLinux 4.18.18OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.CAMD 2990WXIntel 7960X4K8K12K16K20KSE +/- 9.74, N = 3SE +/- 1.49, N = 3SE +/- 64.98, N = 3SE +/- 12.83, N = 3SE +/- 26.55, N = 3SE +/- 1.97, N = 31651610672163841065416383106691. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: SP.A

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: SP.AAMD 2990WXIntel 7960XIntel 7980XE100200300400500SE +/- 0.66, N = 3SE +/- 0.07, N = 3SE +/- 0.56, N = 3SE +/- 1.97, N = 3SE +/- 0.08, N = 3SE +/- 0.52, N = 3SE +/- 1.35, N = 3SE +/- 0.52, N = 3SE +/- 3.60, N = 34564344124544354124534344081. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

PostgreSQL pgbench

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

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyIntel 7980XEIntel 7960XAMD 2990WX110K220K330K440K550KSE +/- 3611.80, N = 3SE +/- 3068.67, N = 3SE +/- 4742.42, N = 3SE +/- 512.57, N = 3SE +/- 808.36, N = 3SE +/- 2068.85, N = 3SE +/- 4900.08, N = 3SE +/- 2218.25, N = 3SE +/- 869.67, N = 35141934752234547185134824811744527434460844346504289701. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteIntel 7980XEIntel 7960XAMD 2990WX3K6K9K12K15KSE +/- 219.72, N = 3SE +/- 401.94, N = 12SE +/- 25.75, N = 3SE +/- 103.93, N = 12SE +/- 156.58, N = 3SE +/- 55.95, N = 8SE +/- 646.38, N = 9SE +/- 411.64, N = 10SE +/- 109.19, N = 1216309106285201105721010745319835952445851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

VKMark

Resolution: 3840 x 2160

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2018-05-30Resolution: 3840 x 2160AMD 2990WXIntel 7960X12002400360048006000SE +/- 6.39, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 35581144636021440359414381. (CXX) g++ options: -lvulkan -ldl -pthread -pipe -std=c++14 -O0 -MD -MQ -MF

DaCapo Benchmark

Java Test: H2

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Intel 7960XAMD 2990WXIntel 7980XE15003000450060007500SE +/- 43.10, N = 4SE +/- 70.57, N = 16SE +/- 14.05, N = 4SE +/- 47.02, N = 4SE +/- 84.77, N = 4SE +/- 44.16, N = 4SE +/- 43.54, N = 10SE +/- 64.65, N = 16SE +/- 102.85, N = 5374554996847376455796860395655467064

DaCapo Benchmark

Java Test: Jython

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonIntel 7960XIntel 7980XEAMD 2990WX10002000300040005000SE +/- 16.96, N = 4SE +/- 23.47, N = 4SE +/- 20.60, N = 4SE +/- 18.08, N = 4SE +/- 13.28, N = 4SE +/- 38.01, N = 4SE +/- 18.03, N = 4SE +/- 52.80, N = 4SE +/- 22.10, N = 4306632384634308332774570460346784869

DaCapo Benchmark

Java Test: Eclipse

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: EclipseIntel 7960XIntel 7980XEAMD 2990WX4K8K12K16K20KSE +/- 76.76, N = 4SE +/- 52.54, N = 4SE +/- 157.52, N = 4SE +/- 26.49, N = 4SE +/- 35.32, N = 4SE +/- 79.09, N = 4SE +/- 37.99, N = 4SE +/- 95.58, N = 4SE +/- 105.04, N = 4159981689318558160371691018746172191843818847

DaCapo Benchmark

Java Test: Tradesoap

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapIntel 7960XIntel 7980XEAMD 2990WX11002200330044005500SE +/- 34.96, N = 10SE +/- 59.16, N = 4SE +/- 51.03, N = 16SE +/- 48.30, N = 5SE +/- 46.63, N = 16SE +/- 86.25, N = 4SE +/- 50.99, N = 5SE +/- 67.20, N = 4SE +/- 43.96, N = 4316444555213317644455314335947815358

DaCapo Benchmark

Java Test: Tradebeans

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansIntel 7960XAMD 2990WXIntel 7980XE16003200480064008000SE +/- 6.33, N = 4SE +/- 36.60, N = 4SE +/- 58.44, N = 4SE +/- 8.17, N = 4SE +/- 71.04, N = 4SE +/- 37.79, N = 4SE +/- 15.46, N = 4SE +/- 90.43, N = 8SE +/- 45.43, N = 4282073087360285173367430293673187653

SQLite

Timed SQLite Insertions

Linux 4.18.18Linux 4.20 GitLinux 4.19.1OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.22Timed SQLite InsertionsIntel 7960XIntel 7980XEAMD 2990WX1326395265SE +/- 0.41, N = 12SE +/- 0.24, N = 3SE +/- 6.59, N = 9SE +/- 1.05, N = 12SE +/- 0.23, N = 12SE +/- 0.01, N = 3SE +/- 0.68, N = 12SE +/- 0.32, N = 3SE +/- 5.53, N = 911.7420.2157.4212.7019.7335.9812.9319.9653.971. (CC) gcc options: -O2 -lz -ldl -lpthread

Parboil

Test: OpenMP CUTCP

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPAMD 2990WXIntel 7980XEIntel 7960X0.5671.1341.7012.2682.835SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 7SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 31.502.392.501.532.392.501.532.412.521. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP Stencil

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilIntel 7980XEIntel 7960XAMD 2990WX48121620SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.37, N = 12SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.58, N = 12SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.21, N = 127.257.9515.627.417.8015.547.627.9215.271. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

Linux 4.18.18Linux 4.20 GitLinux 4.19.1OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsAMD 2990WXIntel 7980XEIntel 7960X0.53551.0711.60652.1422.6775SE +/- 0.07, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 9SE +/- 0.01, N = 3SE +/- 0.12, N = 11SE +/- 0.01, N = 32.182.292.292.242.302.382.262.302.301. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Rodinia

Test: OpenMP LavaMD

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDAMD 2990WXIntel 7980XEIntel 7960X714212835SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.28, N = 3SE +/- 0.03, N = 3SE +/- 0.32, N = 3SE +/- 0.30, N = 311.7820.2621.3911.8320.4321.7411.8326.3527.841. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP CFD Solver

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverAMD 2990WXIntel 7980XEIntel 7960X3691215SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 6SE +/- 0.02, N = 3SE +/- 0.01, N = 39.1511.6012.449.2011.5812.319.2111.5912.371. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP Streamcluster

Linux 4.18.18Linux 4.20 GitLinux 4.19.1OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterIntel 7960XIntel 7980XEAMD 2990WX714212835SE +/- 0.20, N = 5SE +/- 0.02, N = 3SE +/- 0.71, N = 12SE +/- 0.27, N = 3SE +/- 0.23, N = 4SE +/- 0.76, N = 12SE +/- 0.20, N = 5SE +/- 0.28, N = 3SE +/- 0.32, N = 313.6413.7928.1513.9114.1928.6613.9414.0326.771. (CXX) g++ options: -O2 -lOpenCL

Timed GCC Compilation

Time To Compile

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileIntel 7960XAMD 2990WXIntel 7980XE2004006008001000708761918709753910737762951

Timed Linux Kernel Compilation

Time To Compile

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileAMD 2990WXIntel 7980XEIntel 7960X1122334455SE +/- 0.46, N = 7SE +/- 0.54, N = 7SE +/- 0.78, N = 3SE +/- 0.47, N = 6SE +/- 0.50, N = 8SE +/- 0.86, N = 3SE +/- 0.41, N = 9SE +/- 0.61, N = 7SE +/- 0.93, N = 336.0743.3044.7436.1643.2145.0336.1846.8748.62

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

Linux 4.20 GitLinux 4.18.18Linux 4.19.1OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Intel 7980XEIntel 7960XAMD 2990WX510152025SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.41, N = 9SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.31, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.49, N = 1210.4610.6316.5710.5210.5816.2910.5310.5619.201. (CC) gcc options: -O3 -pthread -lz

Hackbench

Count: 32 - Type: Process

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessAMD 2990WXIntel 7980XEIntel 7960X1122334455SE +/- 0.25, N = 3SE +/- 0.40, N = 3SE +/- 0.64, N = 3SE +/- 0.62, N = 4SE +/- 0.10, N = 3SE +/- 0.71, N = 3SE +/- 0.56, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 337.8244.4848.9137.8543.6648.9640.5942.9247.771. (CC) gcc options: -lpthread

m-queens

Time To Solve

Linux 4.19.1Linux 4.20 GitLinux 4.18.18OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveAMD 2990WXIntel 7980XEIntel 7960X1224364860SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 321.2448.8151.7821.2948.8251.7821.3448.7851.781. (CXX) g++ options: -fopenmp -O2 -march=native

Blender

Blend File: BMW27 - Compute: CPU-Only

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-OnlyAMD 2990WXIntel 7980XEIntel 7960X30609012015080.04115.96122.9380.05115.91123.2580.32124.21131.62

Numenta Anomaly Benchmark

Time To Completion

Linux 4.19.1Linux 4.18.18Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 2018-11-09Time To CompletionIntel 7980XEIntel 7960XAMD 2990WX4080120160200SE +/- 0.80, N = 3SE +/- 0.10, N = 3SE +/- 1.96, N = 3SE +/- 0.45, N = 3SE +/- 1.25, N = 3SE +/- 0.80, N = 3SE +/- 0.84, N = 3SE +/- 0.62, N = 3SE +/- 3.04, N = 3162169177163168178169175176

Scikit-Learn

Linux 4.18.18Linux 4.19.1Linux 4.20 GitOpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1AMD 2990WXIntel 7960XIntel 7980XE306090120150SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.34, N = 3SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.27, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 3110140145110140146110140146

Phoronix Test Suite v10.8.5