retpoline-testing

AMD EPYC 7601 32-Core testing with a TYAN B8026T70AE24HR and ASPEED ASPEED Family on Ubuntu 17.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1801063-AL-RETPOLINE62&grs.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay DriverOpenCLCompilerFile-SystemScreen ResolutionnoretpolineRetpolineRetpoline + GCC EPYC 7601 EPYC 7601 EPYC 7601AMD 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)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- NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemandSystem Details- Python 2.7.14.

fio: Seq Write - Libaio - No - Yes - 2MB - Default Test Directoryfio: Rand Write - Libaio - No - Yes - 2MB - Default Test Directoryfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 1000 Files, 1MB Sizefio: Rand Read - Libaio - No - Yes - 2MB - Default Test Directoryfio: Seq Read - Libaio - No - Yes - 2MB - Default Test Directoryfio: Rand Read - Libaio - No - Yes - 4KB - Default Test Directoryt-test1: 1redis: GETrodinia: OpenMP CFD Solverfio: Seq Read - Libaio - No - Yes - 4KB - Default Test Directoryredis: SETredis: LPUSHt-test1: 2parboil: OpenMP MRI Griddingfio: Seq Write - Libaio - No - Yes - 4KB - Default Test Directoryscikit-learn: build-apache: Time To Compileapache: Static Web Page Servingc-ray: Total Timecachebench: Writefio: Rand Write - Libaio - No - Yes - 4KB - Default Test Directoryparboil: OpenMP CUTCPcompilebench: Initial Createjohn-the-ripper: Blowfishrodinia: OpenMP LavaMDbuild-linux-kernel: Time To Compilecachebench: Readpybench: Total For Average Test Timescompilebench: Compilelzbench: Zstd 1 - Compressioncompress-lzma: 256MB File Compressionstockfish: Total Timetjbench: Decompression Throughputcachebench: Read / Modify / Writeglibc-bench: pthread_onceglibc-bench: sqrtglibc-bench: ffslzbench: XZ 0 - Compressionredis: SADDredis: LPOPebizzy: noretpolineRetpolineRetpoline + GCC EPYC 7601 EPYC 7601 EPYC 76011971.101972.70581.87597.932509.832511.771176.2037.761394712.7910.971183.531131889.691117859.5014.38283.161081.2334.0031.7116587.343.5021622.771059.732.71410.853545831.6538.302205.7317941696.87335329.574507140.8322924.244.834.704.83241233207.561520530.2510932302158.032157.60629.27639.772615.602618.671165.9736.681362255.9210.761160.831161527.671147686.8714.46283.251091.5033.9132.2116838.763.4521556.981046.932.73406.413571431.8638.442215.2418011691.37336328.954507140.9922918.964.834.704.83241293172.501394465.7910735872156.872158.27631.30619.672637.272618.201128.5738.181352327.0211.081193.801162399.911123252.4214.66288.361072.5734.4732.1216716.483.4821835.761048.772.70406.913571531.8738.522214.2517951693.10335329.004501140.8722900.814.834.704.83241249051.081230732.38952691OpenBenchmarking.org

Flexible IO Tester

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76015001000150020002500SE +/- 1.26, N = 3SE +/- 3.77, N = 3SE +/- 4.03, N = 31971.102158.032156.871. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76012004006008001000SE +/- 0.58, N = 3SE +/- 1.86, N = 3SE +/- 1.86, N = 3982107510751. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76012004006008001000SE +/- 0.67, N = 3SE +/- 1.53, N = 3SE +/- 1.67, N = 3983107510761. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76015001000150020002500SE +/- 1.43, N = 3SE +/- 3.16, N = 3SE +/- 3.18, N = 31972.702157.602158.271. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

FS-Mark

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeEPYC 7601140280420560700SE +/- 1.13, N = 3SE +/- 1.74, N = 3SE +/- 4.00, N = 3581.87629.27631.301. (CC) gcc options: -static

FS-Mark

Test: 1000 Files, 1MB Size

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeEPYC 7601140280420560700SE +/- 5.75, N = 3SE +/- 1.90, N = 3SE +/- 3.59, N = 3597.93639.77619.671. (CC) gcc options: -static

Flexible IO Tester

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760130060090012001500SE +/- 11.00, N = 31251130413151. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76016001200180024003000SE +/- 0.24, N = 3SE +/- 0.45, N = 3SE +/- 22.27, N = 32509.832615.602637.271. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 7601300600900120015001252130613061. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76016001200180024003000SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 32511.772618.672618.201. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760130060090012001500SE +/- 17.24, N = 3SE +/- 13.29, N = 3SE +/- 1.94, N = 31176.201165.971128.571. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760160K120K180K240K300KSE +/- 4402.78, N = 3SE +/- 3375.56, N = 3SE +/- 591.14, N = 33010372984282889511. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

t-test1

Threads: 1

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1EPYC 7601918273645SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 337.7636.6838.181. (CC) gcc options: -pthread

Redis

Test: GET

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETEPYC 7601300K600K900K1200K1500KSE +/- 2966.06, N = 3SE +/- 27266.47, N = 3SE +/- 28137.42, N = 61394712.791362255.921352327.021. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Rodinia

Test: OpenMP CFD Solver

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverEPYC 76013691215SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 310.9710.7611.081. (CXX) g++ options: -O2 -lOpenCL

Flexible IO Tester

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760170K140K210K280K350KSE +/- 4646.93, N = 3SE +/- 1598.66, N = 3SE +/- 4452.90, N = 33029502971443056651. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760130060090012001500SE +/- 18.11, N = 3SE +/- 6.24, N = 3SE +/- 17.58, N = 31183.531160.831193.801. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

Redis

Test: SET

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETEPYC 7601200K400K600K800K1000KSE +/- 26854.76, N = 6SE +/- 7115.17, N = 3SE +/- 5879.00, N = 31131889.691161527.671162399.911. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: LPUSH

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPUSHEPYC 7601200K400K600K800K1000KSE +/- 8338.77, N = 3SE +/- 3427.20, N = 3SE +/- 6595.02, N = 31117859.501147686.871123252.421. (CC) gcc options: -ggdb -rdynamic -lm -pthread

t-test1

Threads: 2

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2EPYC 760148121620SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 314.3814.4614.661. (CC) gcc options: -pthread

Parboil

Test: OpenMP MRI Gridding

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingEPYC 760160120180240300SE +/- 0.38, N = 3SE +/- 0.14, N = 3SE +/- 1.39, N = 3283.16283.25288.361. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

Flexible IO Tester

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760160K120K180K240K300KSE +/- 3663.70, N = 3SE +/- 4389.73, N = 6SE +/- 1888.66, N = 32767782794042745301. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76012004006008001000SE +/- 14.34, N = 3SE +/- 17.15, N = 6SE +/- 7.38, N = 31081.231091.501072.571. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

Scikit-Learn

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1EPYC 7601816243240SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.48, N = 334.0033.9134.47

Timed Apache Compilation

Time To Compile

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To CompileEPYC 7601714212835SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 331.7132.2132.12

Apache Benchmark

Static Web Page Serving

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.7Static Web Page ServingEPYC 76014K8K12K16K20KSE +/- 41.45, N = 3SE +/- 97.15, N = 3SE +/- 296.19, N = 316587.3416838.7616716.481. (CC) gcc options: -shared -fPIC -O2 -pthread

C-Ray

Total Time

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeEPYC 76010.78751.5752.36253.153.9375SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.503.453.481. (CC) gcc options: -lm -lpthread -O3

lzbench

Test: XZ 0 - Process: Decompression

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: DecompressionEPYC 7601204060801007776771. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

CacheBench

Test: Write

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteEPYC 76015K10K15K20K25KSE +/- 53.65, N = 3SE +/- 133.19, N = 3SE +/- 25.70, N = 321622.7721556.9821835.761. (CC) gcc options: -lrt

Flexible IO Tester

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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 76012004006008001000SE +/- 11.43, N = 3SE +/- 17.28, N = 6SE +/- 11.31, N = 31059.731046.931048.771. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -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

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.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 DirectoryEPYC 760160K120K180K240K300KSE +/- 2932.09, N = 3SE +/- 4419.58, N = 6SE +/- 2976.09, N = 32712732680412685421. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

Parboil

Test: OpenMP CUTCP

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPEPYC 76010.61431.22861.84292.45723.0715SE +/- 0.01, N = 3SE +/- 0.04, N = 6SE +/- 0.01, N = 32.712.732.701. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

Compile Bench

Test: Initial Create

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateEPYC 760190180270360450SE +/- 2.54, N = 3SE +/- 3.88, N = 3SE +/- 4.20, N = 3410.85406.41406.91

John The Ripper

Test: Blowfish

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: BlowfishEPYC 76018K16K24K32K40KSE +/- 400.35, N = 3SE +/- 192.26, N = 3SE +/- 232.00, N = 33545835714357151. (CC) gcc options: -fopenmp -lcrypt

Rodinia

Test: OpenMP LavaMD

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDEPYC 7601714212835SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 331.6531.8631.871. (CXX) g++ options: -O2 -lOpenCL

Timed Linux Kernel Compilation

Time To Compile

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileEPYC 7601918273645SE +/- 0.68, N = 6SE +/- 0.76, N = 6SE +/- 0.63, N = 638.3038.4438.52

CacheBench

Test: Read

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadEPYC 76015001000150020002500SE +/- 9.38, N = 3SE +/- 0.02, N = 3SE +/- 0.98, N = 32205.732215.242214.251. (CC) gcc options: -lrt

PyBench

Total For Average Test Times

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesEPYC 7601400800120016002000SE +/- 7.97, N = 3SE +/- 11.33, N = 3179418011795

Compile Bench

Test: Compile

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileEPYC 7601400800120016002000SE +/- 9.70, N = 3SE +/- 3.64, N = 3SE +/- 4.84, N = 31696.871691.371693.10

lzbench

Test: Zstd 1 - Process: Compression

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: CompressionEPYC 760170140210280350SE +/- 1.33, N = 3SE +/- 1.33, N = 3SE +/- 1.20, N = 33353363351. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

LZMA Compression

256MB File Compression

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionEPYC 760170140210280350SE +/- 0.18, N = 3SE +/- 0.22, N = 3SE +/- 0.42, N = 3329.57328.95329.001. (CXX) g++ options: -O2

Stockfish

Total Time

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgms, Fewer Is BetterStockfish 2014-11-26Total TimeEPYC 760110002000300040005000SE +/- 3.48, N = 3SE +/- 2.65, N = 34507450745011. (CXX) g++ options: -lpthread -fno-exceptions -fno-rtti -ansi -pedantic -O3 -msse -msse3 -mpopcnt -flto

libjpeg-turbo tjbench

Test: Decompression Throughput

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.1Test: Decompression ThroughputEPYC 7601306090120150SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3140.83140.99140.871. (CC) gcc options: -O3 -lm

lzbench

Test: Zstd 1 - Process: Decompression

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: DecompressionEPYC 76012004006008001000SE +/- 4.33, N = 3SE +/- 4.51, N = 3SE +/- 3.93, N = 39119119101. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

CacheBench

Test: Read / Modify / Write

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteEPYC 76015K10K15K20K25KSE +/- 5.63, N = 3SE +/- 9.68, N = 3SE +/- 12.91, N = 322924.2422918.9622900.811. (CC) gcc options: -lrt

glibc bench

Benchmark: pthread_once

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceEPYC 76011.08682.17363.26044.34725.434SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.834.834.83

glibc bench

Benchmark: sqrt

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtEPYC 76011.05752.1153.17254.235.2875SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.704.704.70

glibc bench

Benchmark: ffs

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsEPYC 76011.08682.17363.26044.34725.434SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.834.834.83

lzbench

Test: XZ 0 - Process: Compression

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: CompressionEPYC 76016121824302424241. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Redis

Test: SADD

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SADDEPYC 7601300K600K900K1200K1500KSE +/- 19184.10, N = 4SE +/- 51667.16, N = 6SE +/- 7598.74, N = 31233207.561293172.501249051.081. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: LPOP

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPOPEPYC 7601300K600K900K1200K1500KSE +/- 1539.75, N = 3SE +/- 61195.38, N = 6SE +/- 11491.58, N = 31520530.251394465.791230732.381. (CC) gcc options: -ggdb -rdynamic -lm -pthread

ebizzy

noretpolineRetpolineRetpoline + GCCOpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3EPYC 7601200K400K600K800K1000KSE +/- 19950.45, N = 3SE +/- 26430.87, N = 6SE +/- 23463.01, N = 6109323010735879526911. (CC) gcc options: -pthread -lpthread -O3 -march=native

Phoronix Test Suite v10.8.4