Debian Linux GCC 8 Benchmark -mindirect-branch=thunk

GCC 8 benchmarking of user-space with -mindirect-branch=thunk and -mindirect-branch=thunk-inline for retpolines. Tests by Michael Larabel for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1801161-PTS-DEBIANTE65&grt&sor.

Debian Linux GCC 8 Benchmark -mindirect-branch=thunkProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionStock-mindirect-branch=thunk-mindirect-branch=thunk-inlineIntel Core i9-7980XE @ 4.40GHz (18 Cores / 36 Threads)ASUS PRIME X299-A (1004 BIOS)Intel Device 202016384MB120GB Force MP500LLVMpipeRealtek ALC1220Acer B286HKIntel ConnectionDebian 9.34.15.0-rc8-retpo-underflow (x86_64) 20180115GNOME Shell 3.22.3modesetting 1.19.23.3 Mesa 13.0.6 Gallium 0.4 (LLVM 3.9 256 bits)GCC 8.0.1 20180115ext43840x2160OpenBenchmarking.orgEnvironment Details- Stock: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- -mindirect-branch=thunk: CXXFLAGS=-O3-march=native-mindirect-branch=thunk CFLAGS=-O3-march=native-mindirect-branch=thunk- -mindirect-branch=thunk-inline: CXXFLAGS=-O3-march=native-mindirect-branch=thunk-inline CFLAGS=-O3-march=native-mindirect-branch=thunk-inline Compiler Details- --disable-multilib --enable-checking=releaseDisk Details- Stock, -mindirect-branch=thunk: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: intel_pstate powersavePython Details- Stock, -mindirect-branch=thunk: Python 2.7.13 + Python 3.5.3Security Details- KPTI Full retpoline with underflow protection Protection

Debian Linux GCC 8 Benchmark -mindirect-branch=thunkbullet: Raytestsbullet: 3000 Fallbullet: 1000 Stackbullet: 1000 Convexbullet: Prim Trimeshbullet: Convex Trimeshffmpeg: H.264 HD To NTSC DVmpcbench: Multi-Precision Benchmarkhpcg: hpcc: G-HPLhpcc: G-Fftepgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Heavy Contention - Read Writeredis: GETredis: SETstockfish: Total Timetscp: AI Chess PerformanceStock-mindirect-branch=thunk-mindirect-branch=thunk-inline2.533.884.444.370.921.0813.29100131.3885.930905.8847511387.0911290.862222262.581399046.62290413867942.784.114.574.651.001.2313.8996431.3586.046205.5856411104.8611147.892187123.331280528.47307411853572.896.534.834.931.031.2814.1398301.3885.975475.5602211460.4310540.602160702.131457026.9232281116421OpenBenchmarking.org

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: RaytestsStock-mindirect-branch=thunk-mindirect-branch=thunk-inline0.65031.30061.95092.60123.2515SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 32.532.782.891. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallStock-mindirect-branch=thunk-mindirect-branch=thunk-inline246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 2.39, N = 33.884.116.531. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackStock-mindirect-branch=thunk-mindirect-branch=thunk-inline1.08682.17363.26044.34725.434SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 34.444.574.831. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Convex

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexStock-mindirect-branch=thunk-mindirect-branch=thunk-inline1.10932.21863.32794.43725.5465SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 34.374.654.931. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshStock-mindirect-branch=thunk-mindirect-branch=thunk-inline0.23180.46360.69540.92721.159SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 30.921.001.031. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Convex Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshStock-mindirect-branch=thunk-mindirect-branch=thunk-inline0.2880.5760.8641.1521.44SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 31.081.231.281. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

FFmpeg

H.264 HD To NTSC DV

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 3.3.3H.264 HD To NTSC DVStock-mindirect-branch=thunk-mindirect-branch=thunk-inline48121620SE +/- 0.31, N = 6SE +/- 0.30, N = 6SE +/- 0.32, N = 613.2913.8914.131. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lxcb -lxcb-shm -lxcb-xfixes -lxcb-shape -lasound -lm -llzma -lbz2 -pthread -O3 -march=native -std=c11 -fomit-frame-pointer -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT

GNU MPC

Multi-Precision Benchmark

OpenBenchmarking.orgGlobal Score, More Is BetterGNU MPC 1.1.0Multi-Precision BenchmarkStock-mindirect-branch=thunk-inline-mindirect-branch=thunk2K4K6K8K10KSE +/- 43.72, N = 3SE +/- 75.72, N = 3SE +/- 84.52, N = 310013983096431. (CC) gcc options: -lm -O3 -march=native -MT -MD -MP -MF

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.0-mindirect-branch=thunk-inlineStock-mindirect-branch=thunk0.31050.6210.93151.2421.5525SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.381.381.35

HPC Challenge

Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPL-mindirect-branch=thunk-mindirect-branch=thunk-inlineStock20406080100SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.29, N = 386.0585.9885.931. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops2. BLAS + Open MPI 2.0.2

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-FfteStock-mindirect-branch=thunk-mindirect-branch=thunk-inline1.32412.64823.97235.29646.6205SE +/- 0.18843, N = 3SE +/- 0.01968, N = 3SE +/- 0.02991, N = 35.884755.585645.560221. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops2. BLAS + Open MPI 2.0.2

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-FfteStock-mindirect-branch=thunk-mindirect-branch=thunk-inline1.32412.64823.97235.29646.6205SE +/- 0.18843, N = 3SE +/- 0.01968, N = 3SE +/- 0.02991, N = 35.884755.585645.560221. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops2. BLAS + Open MPI 2.0.2

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 Write-mindirect-branch=thunk-inlineStock-mindirect-branch=thunk2K4K6K8K10KSE +/- 63.39, N = 3SE +/- 221.41, N = 6SE +/- 276.43, N = 611460.4311387.0911104.861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read WriteStock-mindirect-branch=thunk-mindirect-branch=thunk-inline2K4K6K8K10KSE +/- 264.90, N = 6SE +/- 326.63, N = 6SE +/- 43.65, N = 311290.8611147.8910540.601. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETStock-mindirect-branch=thunk-mindirect-branch=thunk-inline500K1000K1500K2000K2500KSE +/- 43689.11, N = 3SE +/- 40180.95, N = 6SE +/- 41655.36, N = 62222262.582187123.332160702.131. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SET-mindirect-branch=thunk-inlineStock-mindirect-branch=thunk300K600K900K1200K1500KSE +/- 2554.75, N = 3SE +/- 34299.85, N = 6SE +/- 160590.96, N = 61457026.921399046.621280528.471. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Stockfish

Total Time

OpenBenchmarking.orgms, Fewer Is BetterStockfish 2014-11-26Total TimeStock-mindirect-branch=thunk-mindirect-branch=thunk-inline7001400210028003500SE +/- 6.11, N = 3SE +/- 44.96, N = 3SE +/- 56.05, N = 32904307432281. (CXX) g++ options: -lpthread -O3 -march=native -fno-exceptions -fno-rtti -ansi -pedantic -msse -msse3 -mpopcnt -flto

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceStock-mindirect-branch=thunk-mindirect-branch=thunk-inline300K600K900K1200K1500KSE +/- 18404.85, N = 6SE +/- 10473.03, N = 5SE +/- 17216.49, N = 51386794118535711164211. (CC) gcc options: -O3 -march=native


Phoronix Test Suite v10.8.5