retpoline-testing

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1801075-AL-RETPOLINE03&export=pdf&grr&rdt&rro.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay DriverOpenCLCompilerFile-SystemScreen ResolutionEPYC 76012 x Xeon Gold 6138 noretpoline Retpoline Retpoline + GCC no retpoline Retpoline Retpoline + GCCAMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HRAMD Device 1450129024MB280GB INTEL SSDPE21D280GAASPEED ASPEED FamilyVE228Broadcom Limited NetXtreme BCM5720 Gigabit PCIeUbuntu 17.104.14.0-phx-retpoline (x86_64)GNOME Shell 3.26.1modesetting 1.19.5OpenCL 1.2 pocl 1.0 LLVM 5.0.0GCC 7.2.0 + Clang 5.0.0-3 + LLVM 5.0.0ext41920x10804.14.0-phx-retpoline-gcc-retpo (x86_64)2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106Intel Device 202096256MB256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150Intel I210 Gigabit Connection4.14.0-phx-retpoline (x86_64)GCC 7.2.04.14.0-phx-retpoline-gcc-retpo (x86_64)OpenBenchmarking.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- EPYC 7601: noretpoline: NONE / data=ordered,errors=remount-ro,relatime,rw- EPYC 7601: Retpoline: NONE / data=ordered,errors=remount-ro,relatime,rw- EPYC 7601: Retpoline + GCC: NONE / data=ordered,errors=remount-ro,relatime,rw- 2 x Xeon Gold 6138: no retpoline: CFQ / data=ordered,errors=remount-ro,relatime,rw- 2 x Xeon Gold 6138: Retpoline: CFQ / data=ordered,errors=remount-ro,relatime,rw- 2 x Xeon Gold 6138: Retpoline + GCC: CFQ / data=ordered,errors=remount-ro,relatime,rwProcessor Details- EPYC 7601: noretpoline: Scaling Governor: acpi-cpufreq ondemand- EPYC 7601: Retpoline: Scaling Governor: acpi-cpufreq ondemand- EPYC 7601: Retpoline + GCC: Scaling Governor: acpi-cpufreq ondemand- 2 x Xeon Gold 6138: no retpoline: Scaling Governor: intel_pstate powersave- 2 x Xeon Gold 6138: Retpoline: Scaling Governor: intel_pstate powersave- 2 x Xeon Gold 6138: Retpoline + GCC: Scaling Governor: intel_pstate powersaveSystem Details- Python 2.7.14.

pgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Normal Load - Read Onlyscikit-learn: apache: Static Web Page Servingpybench: Total For Average Test Timesredis: SETredis: GETredis: LPUSHredis: SADDredis: LPOPtjbench: Decompression Throughputglibc-bench: pthread_onceglibc-bench: sqrtglibc-bench: ffscompress-lzma: 256MB File Compressionstockfish: Total Timec-ray: Total Timebuild-linux-kernel: Time To Compilebuild-apache: Time To Compileebizzy: john-the-ripper: Blowfishcachebench: Read / Modify / Writecachebench: Writecachebench: Readlzbench: Zstd 1 - Compressionlzbench: XZ 0 - Compressionrodinia: OpenMP CFD Solverrodinia: OpenMP LavaMDparboil: OpenMP MRI Griddingparboil: OpenMP CUTCPt-test1: 2t-test1: 1compilebench: Initial Createcompilebench: Compilefs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 1000 Files, 1MB Sizefio: Seq Write - Libaio - No - Yes - 4KB - Default Test Directoryfio: Seq Write - Libaio - No - Yes - 2MB - Default Test Directoryfio: Seq Read - Libaio - No - Yes - 4KB - Default Test Directoryfio: Seq Read - Libaio - No - Yes - 2MB - Default Test Directoryfio: Rand Write - Libaio - No - Yes - 4KB - Default Test Directoryfio: Rand Write - Libaio - No - Yes - 2MB - Default Test Directoryfio: Rand Read - Libaio - No - Yes - 4KB - Default Test Directoryfio: Rand Read - Libaio - No - Yes - 2MB - Default Test DirectoryEPYC 76012 x Xeon Gold 6138 noretpoline Retpoline Retpoline + GCC no retpoline Retpoline Retpoline + GCC34.0016587.3417941131889.691394712.791117859.501233207.561520530.25140.834.834.704.83329.5745073.5038.3031.7110932303545822924.2421622.772205.733352410.9731.65283.162.7114.3837.76410.851696.87581.87597.931081.231971.101183.532511.771059.731972.701176.202509.8333.9116838.7618011161527.671362255.921147686.871293172.501394465.79140.994.834.704.83328.9545073.4538.4432.2110735873571422918.9621556.982215.243362410.7631.86283.252.7314.4636.68406.411691.37629.27639.771091.502158.031160.832618.671046.932157.601165.972615.6034.4716716.4817951162399.911352327.021123252.421249051.081230732.38140.874.834.704.83329.0045013.4838.5232.129526913571522900.8121835.762214.253352411.0831.87288.362.7014.6638.18406.911693.10631.30619.671072.572156.871193.802618.201048.772158.271128.572637.272136.64599258.14184.7522258.7213071564339.041627717.711357638.811589703.691423431.25145.813.8712.303.26281.8434373.1630.2526.249463214965225777.7924954.962973.08361329.7328.50407.912.3523.1265.91533.701496.78111.02128.67415.49514.75457.26519.38338.58523.89383.14543.052467.38597483.03185.6821347.6413061525833.211738340.061382896.041573307.831486377.46154.023.809.953.26281.2536543.1530.4626.319547734839925061.3323882.882872.09369309.9328.70413.852.3823.2966.56508.921694.04136.67133.73413.25526.12454.44518.49341.01514.67384.79543.183976.32577641.99186.0818757.6513151399642.271574731.421454926.311604656.601347143.44146.514.499.963.26282.0436133.1830.6326.329506715108924928.4423753.792839.793703110.5428.43405.252.3823.0464.45478.761637.02111.17129.63416.94527.34456.92518.48341.98512.18388.19543.37OpenBenchmarking.org

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteRetpoline + GCCRetpolineno retpoline9001800270036004500SE +/- 15.09, N = 3SE +/- 49.01, N = 6SE +/- 40.05, N = 33976.322467.382136.641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyRetpoline + GCCRetpolineno retpoline130K260K390K520K650KSE +/- 4346.70, N = 3SE +/- 1869.94, N = 3SE +/- 2613.28, N = 3577641.99597483.03599258.141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm

Scikit-Learn

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Retpoline + GCCRetpolineno retpolinenoretpoline4080120160200SE +/- 2.58, N = 3SE +/- 0.29, N = 3SE +/- 0.99, N = 3SE +/- 0.48, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3186.08185.68184.7534.4733.9134.00

Apache Benchmark

Static Web Page Serving

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.7Static Web Page ServingRetpoline + GCCRetpolineno retpolinenoretpoline5K10K15K20K25KSE +/- 51.11, N = 3SE +/- 63.48, N = 3SE +/- 139.49, N = 3SE +/- 296.19, N = 3SE +/- 97.15, N = 3SE +/- 41.45, N = 318757.6521347.6422258.7216716.4816838.7616587.341. (CC) gcc options: -shared -fPIC -O2 -pthread

PyBench

Total For Average Test Times

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesRetpoline + GCCRetpolineno retpolinenoretpoline400800120016002000SE +/- 1.53, N = 3SE +/- 1.76, N = 3SE +/- 11.33, N = 3SE +/- 7.97, N = 3131513061307179518011794

Redis

Test: SET

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETRetpoline + GCCRetpolineno retpolinenoretpoline300K600K900K1200K1500KSE +/- 55833.41, N = 6SE +/- 90449.67, N = 6SE +/- 28059.92, N = 3SE +/- 5879.00, N = 3SE +/- 7115.17, N = 3SE +/- 26854.76, N = 61399642.271525833.211564339.041162399.911161527.671131889.691. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: GET

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETRetpoline + GCCRetpolineno retpolinenoretpoline400K800K1200K1600K2000KSE +/- 80851.67, N = 6SE +/- 96355.24, N = 6SE +/- 50934.82, N = 6SE +/- 28137.42, N = 6SE +/- 27266.47, N = 3SE +/- 2966.06, N = 31574731.421738340.061627717.711352327.021362255.921394712.791. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: LPUSH

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPUSHRetpoline + GCCRetpolineno retpolinenoretpoline300K600K900K1200K1500KSE +/- 49927.23, N = 6SE +/- 51060.27, N = 6SE +/- 57810.96, N = 6SE +/- 6595.02, N = 3SE +/- 3427.20, N = 3SE +/- 8338.77, N = 31454926.311382896.041357638.811123252.421147686.871117859.501. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: SADD

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SADDRetpoline + GCCRetpolineno retpolinenoretpoline300K600K900K1200K1500KSE +/- 62798.70, N = 6SE +/- 95230.31, N = 6SE +/- 68212.97, N = 6SE +/- 7598.74, N = 3SE +/- 51667.16, N = 6SE +/- 19184.10, N = 41604656.601573307.831589703.691249051.081293172.501233207.561. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: LPOP

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPOPRetpoline + GCCRetpolineno retpolinenoretpoline300K600K900K1200K1500KSE +/- 25234.38, N = 6SE +/- 77843.26, N = 6SE +/- 36207.27, N = 6SE +/- 11491.58, N = 3SE +/- 61195.38, N = 6SE +/- 1539.75, N = 31347143.441486377.461423431.251230732.381394465.791520530.251. (CC) gcc options: -ggdb -rdynamic -lm -pthread

libjpeg-turbo tjbench

Test: Decompression Throughput

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.1Test: Decompression ThroughputRetpoline + GCCRetpolineno retpolinenoretpoline306090120150SE +/- 6.27, N = 6SE +/- 1.27, N = 3SE +/- 5.29, N = 6SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3146.51154.02145.81140.87140.99140.831. (CC) gcc options: -O3 -lm

glibc bench

Benchmark: pthread_once

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceRetpoline + GCCRetpolineno retpolinenoretpoline1.08682.17363.26044.34725.434SE +/- 0.24, N = 6SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.493.803.874.834.834.83

glibc bench

Benchmark: sqrt

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtRetpoline + GCCRetpolineno retpolinenoretpoline3691215SE +/- 0.62, N = 6SE +/- 0.62, N = 6SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 39.969.9512.304.704.704.70

glibc bench

Benchmark: ffs

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsRetpoline + GCCRetpolineno retpolinenoretpoline1.08682.17363.26044.34725.434SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.263.263.264.834.834.83

LZMA Compression

256MB File Compression

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionRetpoline + GCCRetpolineno retpolinenoretpoline70140210280350SE +/- 2.80, N = 3SE +/- 0.60, N = 3SE +/- 0.34, N = 3SE +/- 0.42, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 3282.04281.25281.84329.00328.95329.571. (CXX) g++ options: -O2

Stockfish

Total Time

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgms, Fewer Is BetterStockfish 2014-11-26Total TimeRetpoline + GCCRetpolineno retpolinenoretpoline10002000300040005000SE +/- 210.25, N = 6SE +/- 202.73, N = 6SE +/- 37.22, N = 3SE +/- 2.65, N = 3SE +/- 3.48, N = 33613365434374501450745071. (CXX) g++ options: -lpthread -fno-exceptions -fno-rtti -ansi -pedantic -O3 -msse -msse3 -mpopcnt -flto

C-Ray

Total Time

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeRetpoline + GCCRetpolineno retpolinenoretpoline0.78751.5752.36253.153.9375SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.183.153.163.483.453.501. (CC) gcc options: -lm -lpthread -O3

Timed Linux Kernel Compilation

Time To Compile

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileRetpoline + GCCRetpolineno retpolinenoretpoline918273645SE +/- 0.80, N = 6SE +/- 0.77, N = 6SE +/- 0.75, N = 6SE +/- 0.63, N = 6SE +/- 0.76, N = 6SE +/- 0.68, N = 630.6330.4630.2538.5238.4438.30

Timed Apache Compilation

Time To Compile

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To CompileRetpoline + GCCRetpolineno retpolinenoretpoline714212835SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 326.3226.3126.2432.1232.2131.71

ebizzy

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3Retpoline + GCCRetpolineno retpolinenoretpoline200K400K600K800K1000KSE +/- 13692.48, N = 5SE +/- 13516.78, N = 6SE +/- 7835.23, N = 3SE +/- 23463.01, N = 6SE +/- 26430.87, N = 6SE +/- 19950.45, N = 3950671954773946321952691107358710932301. (CC) gcc options: -pthread -lpthread -O3 -march=native

John The Ripper

Test: Blowfish

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: BlowfishRetpoline + GCCRetpolineno retpolinenoretpoline11K22K33K44K55KSE +/- 357.46, N = 3SE +/- 1882.95, N = 6SE +/- 562.61, N = 3SE +/- 232.00, N = 3SE +/- 192.26, N = 3SE +/- 400.35, N = 35108948399496523571535714354581. (CC) gcc options: -fopenmp -lcrypt

CacheBench

Test: Read / Modify / Write

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteRetpoline + GCCRetpolineno retpolinenoretpoline6K12K18K24K30KSE +/- 226.86, N = 3SE +/- 271.49, N = 3SE +/- 112.30, N = 3SE +/- 12.91, N = 3SE +/- 9.68, N = 3SE +/- 5.63, N = 324928.4425061.3325777.7922900.8122918.9622924.241. (CC) gcc options: -lrt

CacheBench

Test: Write

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteRetpoline + GCCRetpolineno retpolinenoretpoline5K10K15K20K25KSE +/- 82.06, N = 3SE +/- 197.71, N = 3SE +/- 34.79, N = 3SE +/- 25.70, N = 3SE +/- 133.19, N = 3SE +/- 53.65, N = 323753.7923882.8824954.9621835.7621556.9821622.771. (CC) gcc options: -lrt

CacheBench

Test: Read

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadRetpoline + GCCRetpolineno retpolinenoretpoline6001200180024003000SE +/- 11.39, N = 3SE +/- 12.31, N = 3SE +/- 7.30, N = 3SE +/- 0.98, N = 3SE +/- 0.02, N = 3SE +/- 9.38, N = 32839.792872.092973.082214.252215.242205.731. (CC) gcc options: -lrt

lzbench

Test: Zstd 1 - Process: Decompression

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: DecompressionRetpoline + GCCRetpolineno retpolinenoretpoline2004006008001000SE +/- 3.00, N = 3SE +/- 4.18, N = 3SE +/- 4.58, N = 3SE +/- 3.93, N = 3SE +/- 4.51, N = 3SE +/- 4.33, N = 39839829759109119111. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Zstd 1 - Process: Compression

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: CompressionRetpoline + GCCRetpolineno retpolinenoretpoline80160240320400SE +/- 2.08, N = 3SE +/- 2.52, N = 3SE +/- 0.88, N = 3SE +/- 1.20, N = 3SE +/- 1.33, N = 3SE +/- 1.33, N = 33703693613353363351. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: XZ 0 - Process: Decompression

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: DecompressionRetpoline + GCCRetpolineno retpolinenoretpoline20406080100SE +/- 1.77, N = 6SE +/- 2.00, N = 6SE +/- 1.03, N = 68687897776771. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: XZ 0 - Process: Compression

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: CompressionRetpoline + GCCRetpolineno retpolinenoretpoline714212835SE +/- 0.50, N = 6SE +/- 0.56, N = 6SE +/- 0.72, N = 63130322424241. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Rodinia

Test: OpenMP CFD Solver

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverRetpoline + GCCRetpolineno retpolinenoretpoline3691215SE +/- 0.30, N = 6SE +/- 0.15, N = 5SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 310.549.939.7311.0810.7610.971. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP LavaMD

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDRetpoline + GCCRetpolineno retpolinenoretpoline714212835SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 328.4328.7028.5031.8731.8631.651. (CXX) g++ options: -O2 -lOpenCL

Parboil

Test: OpenMP MRI Gridding

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingRetpoline + GCCRetpolineno retpolinenoretpoline90180270360450SE +/- 6.86, N = 4SE +/- 6.92, N = 3SE +/- 6.83, N = 3SE +/- 1.39, N = 3SE +/- 0.14, N = 3SE +/- 0.38, N = 3405.25413.85407.91288.36283.25283.161. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

Parboil

Test: OpenMP CUTCP

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPRetpoline + GCCRetpolineno retpolinenoretpoline0.61431.22861.84292.45723.0715SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 6SE +/- 0.01, N = 32.382.382.352.702.732.711. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

t-test1

Threads: 2

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2Retpoline + GCCRetpolineno retpolinenoretpoline612182430SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 323.0423.2923.1214.6614.4614.381. (CC) gcc options: -pthread

t-test1

Threads: 1

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1Retpoline + GCCRetpolineno retpolinenoretpoline1530456075SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 364.4566.5665.9138.1836.6837.761. (CC) gcc options: -pthread

Compile Bench

Test: Initial Create

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateRetpoline + GCCRetpolineno retpolinenoretpoline120240360480600SE +/- 27.64, N = 3SE +/- 25.41, N = 3SE +/- 1.88, N = 3SE +/- 4.20, N = 3SE +/- 3.88, N = 3SE +/- 2.54, N = 3478.76508.92533.70406.91406.41410.85

Compile Bench

Test: Compile

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileRetpoline + GCCRetpolineno retpolinenoretpoline400800120016002000SE +/- 40.27, N = 6SE +/- 62.71, N = 6SE +/- 7.13, N = 3SE +/- 4.84, N = 3SE +/- 3.64, N = 3SE +/- 9.70, N = 31637.021694.041496.781693.101691.371696.87

FS-Mark

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeRetpoline + GCCRetpolineno retpolinenoretpoline140280420560700SE +/- 7.23, N = 6SE +/- 0.54, N = 3SE +/- 2.97, N = 6SE +/- 4.00, N = 3SE +/- 1.74, N = 3SE +/- 1.13, N = 3111.17136.67111.02631.30629.27581.871. (CC) gcc options: -static

FS-Mark

Test: 1000 Files, 1MB Size

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeRetpoline + GCCRetpolineno retpolinenoretpoline140280420560700SE +/- 2.15, N = 6SE +/- 0.20, N = 3SE +/- 2.17, N = 3SE +/- 3.59, N = 3SE +/- 1.90, N = 3SE +/- 5.75, N = 3129.63133.73128.67619.67639.77597.931. (CC) gcc options: -static

Flexible IO Tester

Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline60K120K180K240K300KSE +/- 361.30, N = 3SE +/- 241.21, N = 3SE +/- 614.11, N = 3SE +/- 1888.66, N = 3SE +/- 4389.73, N = 6SE +/- 3663.70, N = 31042321033081038682745302794042767781. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline2004006008001000SE +/- 1.44, N = 3SE +/- 0.97, N = 3SE +/- 2.46, N = 3SE +/- 7.38, N = 3SE +/- 17.15, N = 6SE +/- 14.34, N = 3416.94413.25415.491072.571091.501081.231. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline2004006008001000SE +/- 4.34, N = 4SE +/- 1.86, N = 3SE +/- 1.86, N = 3SE +/- 0.58, N = 3254253248107510759821. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline5001000150020002500SE +/- 0.39, N = 3SE +/- 0.90, N = 3SE +/- 8.78, N = 4SE +/- 4.03, N = 3SE +/- 3.77, N = 3SE +/- 1.26, N = 3527.34526.12514.752156.872158.031971.101. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline70K140K210K280K350KSE +/- 379.04, N = 3SE +/- 33.79, N = 3SE +/- 246.03, N = 3SE +/- 4452.90, N = 3SE +/- 1598.66, N = 3SE +/- 4646.93, N = 31142271136081143113056652971443029501. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline30060090012001500SE +/- 1.52, N = 3SE +/- 0.14, N = 3SE +/- 0.98, N = 3SE +/- 17.58, N = 3SE +/- 6.24, N = 3SE +/- 18.11, N = 3456.92454.44457.261193.801160.831183.531. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline30060090012001500SE +/- 0.33, N = 3SE +/- 0.33, N = 32502502501306130612521. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline6001200180024003000SE +/- 0.05, N = 3SE +/- 0.25, N = 3SE +/- 0.72, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3518.48518.49519.382618.202618.672511.771. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline60K120K180K240K300KSE +/- 451.27, N = 3SE +/- 444.91, N = 3SE +/- 484.83, N = 3SE +/- 2976.09, N = 3SE +/- 4419.58, N = 6SE +/- 2932.09, N = 38549285249846412685422680412712731. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline2004006008001000SE +/- 1.80, N = 3SE +/- 1.78, N = 3SE +/- 1.94, N = 3SE +/- 11.31, N = 3SE +/- 17.28, N = 6SE +/- 11.43, N = 3341.98341.01338.581048.771046.931059.731. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline2004006008001000SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 1.67, N = 3SE +/- 1.53, N = 3SE +/- 0.67, N = 3246248252107610759831. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

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

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline5001000150020002500SE +/- 2.16, N = 3SE +/- 2.04, N = 3SE +/- 0.94, N = 3SE +/- 3.18, N = 3SE +/- 3.16, N = 3SE +/- 1.43, N = 3512.18514.67523.892158.272157.601972.701. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline60K120K180K240K300KSE +/- 504.90, N = 3SE +/- 309.68, N = 3SE +/- 1071.43, N = 3SE +/- 591.14, N = 3SE +/- 3375.56, N = 3SE +/- 4402.78, N = 39704396194957822889512984283010371. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline30060090012001500SE +/- 2.02, N = 3SE +/- 1.24, N = 3SE +/- 4.29, N = 3SE +/- 1.94, N = 3SE +/- 13.29, N = 3SE +/- 17.24, N = 3388.19384.79383.141128.571165.971176.201. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline30060090012001500SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 11.00, N = 32622622621315130412511. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Flexible IO Tester

Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

2 x Xeon Gold 6138EPYC 7601OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryRetpoline + GCCRetpolineno retpolinenoretpoline6001200180024003000SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 1.17, N = 3SE +/- 22.27, N = 3SE +/- 0.45, N = 3SE +/- 0.24, N = 3543.37543.18543.052637.272615.602509.831. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Phoronix Test Suite v10.8.5