PGO GCC Comparison

Intel Core i9-7980XE testing with a ASUS PRIME X299-A (1401 BIOS) and AMD Radeon RX Vega 8192MB on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1807196-RA-PGOGCCCOM18.

PGO GCC ComparisonProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionGCC 9.0 SVNGCC 9.0 SVN - PGOGCC 7.3.0GCC 7.3.0 - PGOIntel Core i9-7980XE @ 4.20GHz (18 Cores / 36 Threads)ASUS PRIME X299-A (1401 BIOS)Intel Sky Lake-E DMI3 Registers16384MB256GB INTEL SSDPEKKW256G8AMD Radeon RX Vega 8192MBRealtek ALC1220Acer B286HKIntel ConnectionUbuntu 18.044.18.0-999-generic (x86_64) 20180717GNOME Shell 3.28.1X Server 1.19.6modesetting 1.19.64.5 Mesa 18.1.1- padoka PPA (LLVM 6.0.0)GCC 9.0.0 20180718 + Clang 6.0.0-1ubuntu2ext43840x2160GCC 7.3.0 + Clang 6.0.0-1ubuntu2OpenBenchmarking.orgEnvironment Details- CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Details- GCC 9.0 SVN: --disable-multilib --enable-checking=release- GCC 9.0 SVN - PGO: --disable-multilib --enable-checking=release- GCC 7.3.0: --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-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - GCC 7.3.0 - PGO: --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-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: intel_pstate powersaveSecurity Details- KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW Protection

PGO GCC Comparisontscp: AI Chess Performanceebizzy: GCC 9.0 SVNGCC 9.0 SVN - PGOGCC 7.3.0GCC 7.3.0 - PGO1401474594604150815563518413673776174351471097634262OpenBenchmarking.org

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 9.0 SVNGCC 9.0 SVN - PGOGCC 7.3.0GCC 7.3.0 - PGO300K600K900K1200K1500KSE +/- 1127.67, N = 5SE +/- 824.60, N = 5SE +/- 1269.44, N = 5SE +/- 961.91, N = 51401474150815513673771471097-fprofile-correction-fprofile-correction1. (CC) gcc options: -O3 -march=native

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3GCC 9.0 SVNGCC 9.0 SVN - PGOGCC 7.3.0GCC 7.3.0 - PGO140K280K420K560K700KSE +/- 10200.81, N = 6SE +/- 11609.60, N = 6SE +/- 17756.33, N = 6SE +/- 9868.21, N = 6594604635184617435634262-fprofile-correction-fprofile-correction1. (CC) gcc options: -pthread -lpthread -O3 -march=native

Phoronix Test Suite v10.8.4