Server Mitigations Ubuntu 20.04

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2004055-NI-SERVERS0527&sor&gru.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionXeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3 Defaults No Mitigations Defaults No Mitigations Defaults No Mitigations Defaults No MitigationsIntel Xeon E3-1275 v6 @ 4.20GHz (4 Cores / 8 Threads)ASUS P10S-M WS (4401 BIOS)Intel Xeon E3-1200 v6/7th16GBSamsung SSD 970 EVO Plus 500GBIntel HD P630 3GB (1150MHz)Realtek ALC1150DELL S2409W2 x Intel I210Ubuntu 20.045.4.0-21-generic (x86_64)GNOME Shell 3.36.0X Server 1.20.7modesetting 1.20.74.6 Mesa 20.0.2GCC 9.3.0ext41920x10802 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106 (V2.01.B40 BIOS)Intel Sky Lake-E DMI3 Registers94GB500GB Samsung SSD 860ASPEEDVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEllvmpipe 93GB3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits)2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)Intel Xeon E5-2687W v3 @ 3.50GHz (10 Cores / 20 Threads)MSI X99S SLI PLUS (MS-7885) v1.0 (1.E0 BIOS)Intel Xeon E7 v3/Xeon32GB80GB INTEL SSDSCKGW08NVIDIA GeForce GTX 770 2GBRealtek ALC892G237HLIntel I218-V4.3 Mesa 20.0.2NVIDIA NVE4 2GBOpenBenchmarking.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++,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- Xeon E3-1275 v6: Defaults: NONE / errors=remount-ro,relatime,rw- Xeon E3-1275 v6: No Mitigations: NONE / errors=remount-ro,relatime,rw- 2 x Xeon Gold 6138: Defaults: MQ-DEADLINE / errors=remount-ro,relatime,rw- 2 x Xeon Gold 6138: No Mitigations: MQ-DEADLINE / errors=remount-ro,relatime,rw- 2 x Xeon Gold 5220R: Defaults: MQ-DEADLINE / errors=remount-ro,relatime,rw- 2 x Xeon Gold 5220R: No Mitigations: MQ-DEADLINE / errors=remount-ro,relatime,rw- Xeon E5-2687W v3: Defaults: MQ-DEADLINE / errors=remount-ro,relatime,rw- Xeon E5-2687W v3: No Mitigations: MQ-DEADLINE / errors=remount-ro,relatime,rwProcessor Details- Xeon E3-1275 v6: Defaults: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xca- Xeon E3-1275 v6: No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xca- 2 x Xeon Gold 6138: Defaults: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x2000064- 2 x Xeon Gold 6138: No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x2000064- 2 x Xeon Gold 5220R: Defaults: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- 2 x Xeon Gold 5220R: No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon E5-2687W v3: Defaults: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x43- Xeon E5-2687W v3: No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x43Java Details- OpenJDK Runtime Environment (build 11.0.7-ea+9-post-Ubuntu-1ubuntu1)Python Details- + Python 3.8.2Security Details- Xeon E3-1275 v6: Defaults: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - Xeon E3-1275 v6: No Mitigations: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Vulnerable - 2 x Xeon Gold 6138: Defaults: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - 2 x Xeon Gold 6138: No Mitigations: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Vulnerable - 2 x Xeon Gold 5220R: Defaults: 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 + tsx_async_abort: Mitigation of TSX disabled - 2 x Xeon Gold 5220R: No Mitigations: itlb_multihit: KVM: Vulnerable + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Mitigation of TSX disabled - Xeon E5-2687W v3: Defaults: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected - Xeon E5-2687W v3: No Mitigations: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Not affected

blogbench: Readblogbench: Writeiperf: 5201 - 30 Seconds - TCP - 1iperf: 5201 - 30 Seconds - TCP - 32sockperf: Throughputrocksdb: Rand Fillrocksdb: Seq Fillmcperf: Get - 16mcperf: Set - 16mcperf: Append - 16mcperf: Delete - 16mcperf: Replace - 16keydb: redis: LPUSHredis: SETnginx: Static Web Page Servingapache: Static Web Page Servinghbase: Increment - 4hbase: Rand Read - 4hbase: Seq Read - 4hbase: Async Rand Write - 4phpbench: PHP Benchmark Suitepgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Heavy Contention - Read Onlyapache-siege: 250hbase: Increment - 4hbase: Rand Read - 4hbase: Seq Read - 4hbase: Async Rand Write - 4leveldb: Seek Randrenaissance: Rand Forestrenaissance: Apache Spark ALSrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: Twitter HTTP Requestsrenaissance: In-Memory Database Shootoutrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Genetic Algorithm Using Jenetics + Futuresdacapobench: Jythondacapobench: Tradesoapbuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilebuild-php: Time To Compilebuild2: Time To Compileperl-benchmark: Pod2htmlperl-benchmark: Interpretersqlite-speedtest: Timed Time - Size 1,000sockperf: Latency Ping PongXeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3 Defaults No Mitigations Defaults No Mitigations Defaults No Mitigations Defaults No Mitigations6477283363663586685204867617743001003248122674.171418.875114.2119621.975108.9332575.741709562.632036733.2937413.3827301.8123474416392937514693681026106967.306636110061.94288639883.65169951352714.5524882.4826049.13422934.32723626.6645189.1845182.95411118.9671677.18840226572176.9921367.41299.772223.7600.119224780.0009926368.1433.3986445283647470194729026191098856091113455163813.994854.0100971.3163124.0101249.7460535.141791215.292175635.0046860.1235270.5226591479253694916665681731121451.018355121036.73222546193.95149821082414.0704730.4235893.83120321.33723339.0045027.5795007.48110751.7881645.88639286361172.5481348.51398.023219.1800.117219650.0009328457.3732.691203852523896343143341835739114175114282488890.245183.956358.753759.936701.9365949.971321227.171567680.2127430.1120351.021034718054176306111599675529354.416803562889.81593549389.09384219227652133.2535742.3177143.69630020.22125666.9857845.88216087.97826470.8546840.6624490679941.191304.45050.95880.0390.126539940.0037526577.4344.8882129085238363592432464417357176835177505108534.158999.967756.457494.368552.6407888.251414137.391607048.8334006.4424738.871213421613226837938600712564233.096037598979.96463147160.23328183178502131.6495703.4456983.42526619.94525213.7817749.77214649.67125007.4336553.6194390674640.044300.30750.21678.6620.124122030.0033016066.4623.9842215082241263671933326398750179667180768101109.846858.330394.7107712.729106.3416533.951371743.831706887.6731476.3324204.881200421155215577480632035603798.289346626099.89343445411.05332187187533110.9335593.3926961.55325609.62024250.4247163.34914068.52623067.1616606.9974824670137.478284.99448.74475.4630.118327070.0032901768.2583.9412238187232373695133593405922182743184392117411.758809.761641.5116085.768576.5418381.241422514.421665880.8334256.9024785.261205921377223657738633989596866.113606621603.18944843707.70330184180515110.6045685.4636965.35924796.58224532.4427193.92414030.63822828.0776535.2014841654337.450283.59648.31375.7120.118502060.0032593968.2493.739183041611096341293852326665451886569489488133.140187.937763.584443.936941.2448533.081280493.841550985.7923945.4116731.18881118668195195736557695162112.134818165170.19917845221220769518.2035619.4476449.64527571.43824481.4365838.7647368.54513778.5054769.19654115079107.825812.19882.492142.6710.155284230.0028414088.9274.80719065971123835326368713401516787881038858114148.356527.349633.8112817.550251.4561921.381355759.001605077.0631796.9622745.661013821439224396651558710176460.211767178879.32115368776.6239318518060017.1755695.2966468.93728313.08124696.0235725.5186856.77913307.7394674.32953714919105.274809.01780.833140.5860.149661180.0024774373.6204.030OpenBenchmarking.org

BlogBench

Test: Read

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: ReadNo MitigationsDefaults500K1000K1500K2000K2500KSE +/- 29090.95, N = 3SE +/- 20585.69, N = 3SE +/- 18200.59, N = 3SE +/- 22223.70, N = 3SE +/- 57701.61, N = 9SE +/- 33888.90, N = 9SE +/- 10337.24, N = 9SE +/- 9296.08, N = 92238187221508221290852038525190659718304166477286445281. (CC) gcc options: -O2 -pthread

BlogBench

Test: Write

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WriteNo MitigationsDefaults8K16K24K32K40KSE +/- 467.78, N = 3SE +/- 1695.50, N = 3SE +/- 1088.64, N = 3SE +/- 1279.44, N = 3SE +/- 1233.22, N = 3SE +/- 1263.52, N = 3SE +/- 145.70, N = 3SE +/- 145.77, N = 336474336362412623237238962383611238110961. (CC) gcc options: -O2 -pthread

iPerf

Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: TCP - Parallel: 1

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: TCP - Parallel: 1No MitigationsDefaults15K30K45K60K75KSE +/- 209.37, N = 3SE +/- 979.71, N = 3SE +/- 115.65, N = 3SE +/- 135.89, N = 3SE +/- 45.67, N = 3SE +/- 51.60, N = 3SE +/- 492.87, N = 3SE +/- 457.96, N = 370194635863695136719359243431435326341291. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

iPerf

Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: TCP - Parallel: 32

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: TCP - Parallel: 32No MitigationsDefaults16K32K48K64K80KSE +/- 569.85, N = 3SE +/- 557.92, N = 3SE +/- 347.97, N = 11SE +/- 364.79, N = 8SE +/- 117.22, N = 3SE +/- 210.56, N = 3SE +/- 478.95, N = 3SE +/- 53.38, N = 372902685203852336871335933332633418324641. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

Sockperf

Test: Throughput

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputNo MitigationsDefaults130K260K390K520K650KSE +/- 9010.49, N = 20SE +/- 4980.38, N = 25SE +/- 3747.04, N = 11SE +/- 1976.69, N = 5SE +/- 4690.41, N = 6SE +/- 3227.63, N = 13SE +/- 5568.73, N = 25SE +/- 2385.14, N = 256191094867614173573573914059223987503401512666541. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Facebook RocksDB

Test: Random Fill

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillNo MitigationsDefaults200K400K600K800K1000KSE +/- 3440.56, N = 3SE +/- 3718.84, N = 3SE +/- 5104.84, N = 3SE +/- 5040.53, N = 3SE +/- 564.78, N = 3SE +/- 171.10, N = 3SE +/- 450.36, N = 3SE +/- 354.47, N = 38856097743006787885188651827431796671768351417511. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Sequential Fill

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillNo MitigationsDefaults200K400K600K800K1000KSE +/- 1082.27, N = 3SE +/- 10398.91, N = 3SE +/- 1715.59, N = 3SE +/- 6623.34, N = 3SE +/- 549.70, N = 3SE +/- 95.29, N = 3SE +/- 239.82, N = 3SE +/- 125.91, N = 31113455100324810388586948941843921807681775051428241. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Memcached mcperf

Method: Get - Connections: 16

Xeon E3-1275 v62 x Xeon Gold 5220RXeon E5-2687W v32 x Xeon Gold 6138OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 16No MitigationsDefaults40K80K120K160K200KSE +/- 2615.25, N = 3SE +/- 872.88, N = 3SE +/- 335.20, N = 3SE +/- 4357.54, N = 12SE +/- 264.58, N = 3SE +/- 708.71, N = 3SE +/- 326.35, N = 3SE +/- 3188.13, N = 11163813.9122674.1117411.7101109.8114148.388133.1108534.188890.21. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Set - Connections: 16

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 16No MitigationsDefaults20K40K60K80K100KSE +/- 247.29, N = 3SE +/- 173.55, N = 3SE +/- 190.95, N = 3SE +/- 2922.93, N = 9SE +/- 49.72, N = 3SE +/- 3771.97, N = 9SE +/- 1238.35, N = 9SE +/- 1668.11, N = 994854.071418.858999.945183.958809.746858.356527.340187.91. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Append - Connections: 16

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Append - Connections: 16No MitigationsDefaults20K40K60K80K100KSE +/- 480.34, N = 3SE +/- 158.54, N = 3SE +/- 84.40, N = 3SE +/- 89.56, N = 3SE +/- 4883.48, N = 9SE +/- 1545.55, N = 9SE +/- 1113.05, N = 9SE +/- 300.69, N = 3100971.375114.267756.456358.761641.530394.749633.837763.51. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Delete - Connections: 16

Xeon E3-1275 v62 x Xeon Gold 5220RXeon E5-2687W v32 x Xeon Gold 6138OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Delete - Connections: 16No MitigationsDefaults30K60K90K120K150KSE +/- 212.40, N = 3SE +/- 541.89, N = 3SE +/- 352.84, N = 3SE +/- 361.82, N = 3SE +/- 553.89, N = 3SE +/- 237.15, N = 3SE +/- 186.49, N = 3SE +/- 206.80, N = 3163124.0119621.9116085.7107712.7112817.584443.957494.353759.91. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Replace - Connections: 16

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Replace - Connections: 16No MitigationsDefaults20K40K60K80K100KSE +/- 300.08, N = 3SE +/- 239.83, N = 3SE +/- 2639.05, N = 9SE +/- 80.26, N = 3SE +/- 73.67, N = 3SE +/- 1793.31, N = 9SE +/- 3060.01, N = 6SE +/- 451.68, N = 3101249.775108.968576.529106.368552.636701.950251.436941.21. (CC) gcc options: -O2 -lm -rdynamic

KeyDB

Xeon E5-2687W v3Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.1No MitigationsDefaults120K240K360K480K600KSE +/- 2190.71, N = 3SE +/- 552.92, N = 3SE +/- 6242.43, N = 3SE +/- 780.39, N = 3SE +/- 6409.22, N = 3SE +/- 6677.70, N = 3SE +/- 2174.50, N = 3SE +/- 2599.40, N = 3561921.38448533.08460535.14332575.74418381.24416533.95407888.25365949.971. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

Redis

Test: LPUSH

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHNo MitigationsDefaults400K800K1200K1600K2000KSE +/- 12385.25, N = 3SE +/- 11769.75, N = 3SE +/- 14124.93, N = 15SE +/- 1086.39, N = 3SE +/- 17420.09, N = 15SE +/- 19819.76, N = 15SE +/- 20648.66, N = 15SE +/- 27018.39, N = 151791215.291709562.631422514.421371743.831414137.391321227.171355759.001280493.841. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SET

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETNo MitigationsDefaults500K1000K1500K2000K2500KSE +/- 12548.75, N = 3SE +/- 8659.59, N = 3SE +/- 25451.15, N = 15SE +/- 22461.09, N = 15SE +/- 12486.65, N = 3SE +/- 34935.38, N = 12SE +/- 25094.74, N = 14SE +/- 21392.75, N = 32175635.002036733.291706887.671665880.831607048.831567680.211605077.061550985.791. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

NGINX Benchmark

Static Web Page Serving

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingNo MitigationsDefaults10K20K30K40K50KSE +/- 125.28, N = 3SE +/- 125.50, N = 3SE +/- 438.85, N = 3SE +/- 128.75, N = 3SE +/- 34.48, N = 3SE +/- 265.88, N = 3SE +/- 286.46, N = 3SE +/- 90.82, N = 346860.1237413.3834256.9031476.3334006.4427430.1131796.9623945.411. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

Apache Benchmark

Static Web Page Serving

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingNo MitigationsDefaults8K16K24K32K40KSE +/- 232.87, N = 3SE +/- 64.23, N = 3SE +/- 335.47, N = 3SE +/- 395.32, N = 3SE +/- 327.02, N = 3SE +/- 339.27, N = 3SE +/- 313.41, N = 4SE +/- 164.03, N = 1535270.5227301.8124785.2624204.8824738.8720351.0222745.6616731.181. (CC) gcc options: -shared -fPIC -O2 -pthread

Apache HBase

Test: Increment - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Increment - Clients: 4No MitigationsDefaults6K12K18K24K30KSE +/- 275.14, N = 3SE +/- 312.72, N = 4SE +/- 105.08, N = 3SE +/- 140.39, N = 3SE +/- 146.72, N = 3SE +/- 183.36, N = 3SE +/- 167.68, N = 3SE +/- 48.15, N = 3265912347412134103471205912004101388811

Apache HBase

Test: Random Read - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 6138Xeon E5-2687W v32 x Xeon Gold 5220ROpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Read - Clients: 4No MitigationsDefaults10K20K30K40K50KSE +/- 431.33, N = 11SE +/- 385.72, N = 10SE +/- 257.81, N = 3SE +/- 158.37, N = 11SE +/- 126.04, N = 3SE +/- 134.28, N = 3SE +/- 90.89, N = 3SE +/- 352.22, N = 34792541639216131805421439186682137721155

Apache HBase

Test: Sequential Read - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 6138Xeon E5-2687W v32 x Xeon Gold 5220ROpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 4No MitigationsDefaults8K16K24K32K40KSE +/- 646.09, N = 15SE +/- 236.42, N = 13SE +/- 169.00, N = 3SE +/- 195.48, N = 3SE +/- 196.14, N = 3SE +/- 90.67, N = 3SE +/- 293.61, N = 4SE +/- 91.09, N = 33694929375226831763022439195192236521557

Apache HBase

Test: Async Random Write - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Async Random Write - Clients: 4No MitigationsDefaults4K8K12K16K20KSE +/- 445.81, N = 12SE +/- 194.46, N = 3SE +/- 60.29, N = 3SE +/- 5.69, N = 3SE +/- 26.91, N = 3SE +/- 96.81, N = 3SE +/- 64.13, N = 3SE +/- 37.03, N = 31666514693793861117738748066515736

PHPBench

PHP Benchmark Suite

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteNo MitigationsDefaults150K300K450K600K750KSE +/- 1307.07, N = 3SE +/- 49.17, N = 3SE +/- 49.02, N = 3SE +/- 1349.74, N = 3SE +/- 523.19, N = 3SE +/- 680.48, N = 3SE +/- 341.73, N = 3SE +/- 1278.98, N = 3681731681026633989632035600712599675558710557695

PostgreSQL pgbench

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

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyDefaultsNo Mitigations130K260K390K520K650KSE +/- 2138.58, N = 3SE +/- 1072.68, N = 3SE +/- 1667.57, N = 3SE +/- 3500.01, N = 3SE +/- 228.14, N = 3SE +/- 156.88, N = 3SE +/- 90.34, N = 3SE +/- 81.36, N = 3603798.29596866.11564233.10529354.42176460.21162112.13121451.02106967.311. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read OnlyDefaultsNo Mitigations130K260K390K520K650KSE +/- 2731.37, N = 3SE +/- 2508.79, N = 3SE +/- 7109.36, N = 3SE +/- 4246.39, N = 3SE +/- 720.15, N = 3SE +/- 2143.18, N = 3SE +/- 73.52, N = 3SE +/- 109.52, N = 3626099.89621603.19598979.96562889.82178879.32165170.20121036.73110061.941. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Apache Siege

Concurrent Users: 250

Xeon E5-2687W v32 x Xeon Gold 6138Xeon E3-1275 v62 x Xeon Gold 5220ROpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250No MitigationsDefaults15K30K45K60K75KSE +/- 168.43, N = 3SE +/- 1122.01, N = 15SE +/- 995.90, N = 15SE +/- 85.34, N = 3SE +/- 113.17, N = 3SE +/- 568.87, N = 3SE +/- 175.05, N = 368776.6249389.0947160.2346193.9539883.6545411.0543707.701. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Apache HBase

Test: Increment - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Increment - Clients: 4No MitigationsDefaults100200300400500SE +/- 1.53, N = 3SE +/- 2.39, N = 4SE +/- 2.85, N = 3SE +/- 5.21, N = 3SE +/- 4.18, N = 3SE +/- 4.84, N = 3SE +/- 6.56, N = 3SE +/- 2.31, N = 3149169328384330332393452

Apache HBase

Test: Random Read - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Read - Clients: 4No MitigationsDefaults50100150200250SE +/- 0.82, N = 11SE +/- 0.91, N = 10SE +/- 2.33, N = 3SE +/- 1.99, N = 11SE +/- 0.88, N = 3SE +/- 2.85, N = 3SE +/- 1.15, N = 3SE +/- 1.53, N = 38295183219184187185212

Apache HBase

Test: Sequential Read - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Sequential Read - Clients: 4No MitigationsDefaults50100150200250SE +/- 2.21, N = 15SE +/- 1.18, N = 13SE +/- 1.15, N = 3SE +/- 2.19, N = 3SE +/- 2.08, N = 4SE +/- 1.53, N = 3SE +/- 1.00, N = 3108135178227180187180207

Apache HBase

Test: Async Random Write - Clients: 4

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Async Random Write - Clients: 4No MitigationsDefaults150300450600750SE +/- 8.79, N = 12SE +/- 3.61, N = 3SE +/- 3.71, N = 3SE +/- 0.33, N = 3SE +/- 6.94, N = 3SE +/- 5.84, N = 3SE +/- 4.48, N = 3241271502652515533600695

LevelDB

Benchmark: Seek Random

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomNo MitigationsDefaults306090120150SE +/- 0.031, N = 3SE +/- 0.054, N = 3SE +/- 0.097, N = 3SE +/- 0.096, N = 3SE +/- 0.369, N = 3SE +/- 1.343, N = 3SE +/- 0.974, N = 3SE +/- 0.884, N = 34.0704.55217.17518.203110.604110.933131.649133.2531. (CXX) g++ options: -O3 -lsnappy -lpthread

Renaissance

Test: Random Forest

Xeon E3-1275 v62 x Xeon Gold 5220RXeon E5-2687W v32 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random ForestNo MitigationsDefaults12002400360048006000SE +/- 54.67, N = 5SE +/- 52.75, N = 5SE +/- 36.85, N = 5SE +/- 63.72, N = 25SE +/- 46.78, N = 5SE +/- 32.46, N = 5SE +/- 44.38, N = 25SE +/- 52.01, N = 54730.424882.485593.395685.465619.455695.305703.455742.32

Renaissance

Test: Apache Spark ALS

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSNo MitigationsDefaults15003000450060007500SE +/- 56.93, N = 5SE +/- 40.48, N = 25SE +/- 47.83, N = 5SE +/- 65.03, N = 8SE +/- 85.73, N = 5SE +/- 73.05, N = 8SE +/- 93.24, N = 5SE +/- 63.46, N = 55893.836049.136449.656468.946961.556965.366983.437143.70

Renaissance

Test: Savina Reactors.IO

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IONo MitigationsDefaults6K12K18K24K30KSE +/- 158.78, N = 5SE +/- 97.30, N = 5SE +/- 647.17, N = 25SE +/- 520.34, N = 20SE +/- 365.16, N = 25SE +/- 619.97, N = 25SE +/- 233.51, N = 25SE +/- 283.35, N = 520321.3422934.3324796.5825609.6226619.9530020.2227571.4428313.08

Renaissance

Test: Apache Spark PageRank

Xeon E3-1275 v62 x Xeon Gold 5220RXeon E5-2687W v32 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankNo MitigationsDefaults5K10K15K20K25KSE +/- 185.35, N = 5SE +/- 164.69, N = 5SE +/- 252.92, N = 5SE +/- 165.93, N = 25SE +/- 153.33, N = 5SE +/- 102.15, N = 5SE +/- 321.17, N = 5SE +/- 289.82, N = 723339.0023626.6624250.4224532.4424481.4424696.0225213.7825666.99

Renaissance

Test: Twitter HTTP Requests

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Twitter HTTP RequestsNo MitigationsDefaults2K4K6K8K10KSE +/- 35.76, N = 5SE +/- 34.89, N = 25SE +/- 55.95, N = 5SE +/- 65.80, N = 5SE +/- 93.34, N = 5SE +/- 91.17, N = 5SE +/- 62.92, N = 5SE +/- 86.77, N = 65027.585189.185725.525838.767163.357193.927749.777845.88

Renaissance

Test: In-Memory Database Shootout

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database ShootoutNo MitigationsDefaults3K6K9K12K15KSE +/- 62.93, N = 5SE +/- 55.86, N = 5SE +/- 39.69, N = 5SE +/- 38.21, N = 5SE +/- 86.51, N = 25SE +/- 83.54, N = 5SE +/- 182.50, N = 5SE +/- 185.95, N = 55007.485182.956856.787368.5514030.6414068.5314649.6716087.98

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeNo MitigationsDefaults6K12K18K24K30KSE +/- 95.58, N = 11SE +/- 114.33, N = 8SE +/- 114.06, N = 12SE +/- 89.19, N = 25SE +/- 278.89, N = 6SE +/- 206.12, N = 5SE +/- 273.31, N = 25SE +/- 369.52, N = 2510751.7911118.9713307.7413778.5122828.0823067.1625007.4326470.85

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + FuturesNo MitigationsDefaults15003000450060007500SE +/- 4.16, N = 5SE +/- 5.95, N = 5SE +/- 8.29, N = 5SE +/- 21.62, N = 5SE +/- 49.14, N = 5SE +/- 83.22, N = 5SE +/- 41.77, N = 5SE +/- 75.38, N = 51645.891677.194674.334769.206535.206607.006553.626840.66

DaCapo Benchmark

Java Test: Jython

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonNo MitigationsDefaults12002400360048006000SE +/- 45.86, N = 6SE +/- 44.17, N = 4SE +/- 51.23, N = 5SE +/- 49.06, N = 20SE +/- 42.13, N = 4SE +/- 60.79, N = 4SE +/- 62.64, N = 4SE +/- 41.12, N = 439284022439044904824484153715411

DaCapo Benchmark

Java Test: Tradesoap

Xeon E5-2687W v3Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapNo MitigationsDefaults15003000450060007500SE +/- 65.18, N = 3SE +/- 26.70, N = 4SE +/- 80.41, N = 4SE +/- 45.80, N = 4SE +/- 16.83, N = 4SE +/- 66.56, N = 4SE +/- 12.73, N = 4SE +/- 60.00, N = 2049195079636165726543670167466799

Timed Linux Kernel Compilation

Time To Compile

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileNo MitigationsDefaults4080120160200SE +/- 0.35, N = 10SE +/- 0.37, N = 12SE +/- 0.37, N = 10SE +/- 0.32, N = 13SE +/- 0.80, N = 3SE +/- 0.81, N = 3SE +/- 1.18, N = 3SE +/- 0.63, N = 337.4537.4840.0441.19105.27107.83172.55176.99

Timed LLVM Compilation

Time To Compile

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileNo MitigationsDefaults30060090012001500SE +/- 3.45, N = 3SE +/- 2.40, N = 3SE +/- 4.04, N = 3SE +/- 4.03, N = 3SE +/- 6.25, N = 3SE +/- 4.46, N = 3SE +/- 0.89, N = 3SE +/- 1.45, N = 3283.60284.99300.31304.45809.02812.201348.511367.41

Timed PHP Compilation

Time To Compile

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileNo MitigationsDefaults20406080100SE +/- 0.10, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.28, N = 3SE +/- 0.20, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 348.3148.7450.2250.9680.8382.4998.0299.77

Build2

Time To Compile

2 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3Xeon E3-1275 v6OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To CompileDefaultsNo Mitigations50100150200250SE +/- 0.30, N = 3SE +/- 0.21, N = 3SE +/- 0.23, N = 3SE +/- 0.21, N = 3SE +/- 0.21, N = 3SE +/- 0.56, N = 3SE +/- 0.50, N = 3SE +/- 0.33, N = 375.4675.7178.6680.04140.59142.67219.18223.76

Perl Benchmarks

Test: Pod2html

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2htmlNo MitigationsDefaults0.03490.06980.10470.13960.1745SE +/- 0.00025928, N = 3SE +/- 0.00011071, N = 3SE +/- 0.00033629, N = 3SE +/- 0.00038123, N = 3SE +/- 0.00004149, N = 3SE +/- 0.00040353, N = 3SE +/- 0.00037082, N = 3SE +/- 0.00070236, N = 30.117219650.119224780.118327070.118502060.124122030.126539940.149661180.15528423

Perl Benchmarks

Test: Interpreter

Xeon E3-1275 v6Xeon E5-2687W v32 x Xeon Gold 5220R2 x Xeon Gold 6138OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: InterpreterNo MitigationsDefaults0.00080.00160.00240.00320.004SE +/- 0.00000418, N = 3SE +/- 0.00000140, N = 3SE +/- 0.00000822, N = 3SE +/- 0.00002291, N = 3SE +/- 0.00000338, N = 3SE +/- 0.00000821, N = 3SE +/- 0.00000968, N = 3SE +/- 0.00000081, N = 30.000932840.000992630.002477430.002841400.003259390.003290170.003301600.00375265

SQLite Speedtest

Timed Time - Size 1,000

Xeon E3-1275 v62 x Xeon Gold 61382 x Xeon Gold 5220RXeon E5-2687W v3OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000No MitigationsDefaults20406080100SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.21, N = 3SE +/- 0.88, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 357.3768.1466.4677.4368.2568.2673.6288.931. (CC) gcc options: -O2 -ldl -lz -lpthread

Sockperf

Test: Latency Ping Pong

Xeon E3-1275 v62 x Xeon Gold 5220R2 x Xeon Gold 6138Xeon E5-2687W v3OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping PongNo MitigationsDefaults1.09982.19963.29944.39925.499SE +/- 0.013, N = 5SE +/- 0.012, N = 5SE +/- 0.026, N = 5SE +/- 0.032, N = 5SE +/- 0.033, N = 5SE +/- 0.059, N = 5SE +/- 0.041, N = 5SE +/- 0.048, N = 92.6913.3983.7393.9413.9844.8884.0304.8071. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Phoronix Test Suite v10.8.4