Tests for a future article.
Clang Built Processor: AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0803 BIOS), Chipset: AMD Device 1480, Memory: 16384MB, Disk: 2000GB Force MP600, Graphics: llvmpipe 16GB, Audio: AMD Device ab20, Network: Realtek Device 8125 + Intel I211 + Intel Device 2723
OS: Ubuntu 19.04, Kernel: 5.3.0-rc8-clanged (x86_64) 20190910, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0 + Clang 10.0.0-svn371485-1~exp1+0~20190910040723.259~1.gbp13c8b7, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandJava Notes: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: 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 Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling
GCC 9.1 Built OS: Ubuntu 19.04, Kernel: 5.3.0-rc8-gnued (x86_64) 20190910, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0 + Clang 10.0.0-svn371485-1~exp1+0~20190910040723.259~1.gbp13c8b7, File-System: ext4, Screen Resolution: 3840x2160
Clang Kernel OpenBenchmarking.org Phoronix Test Suite AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0803 BIOS) AMD Device 1480 16384MB 2000GB Force MP600 llvmpipe 16GB AMD Device ab20 Realtek Device 8125 + Intel I211 + Intel Device 2723 Ubuntu 19.04 5.3.0-rc8-clanged (x86_64) 20190910 5.3.0-rc8-gnued (x86_64) 20190910 GNOME Shell 3.32.2 X Server 1.20.4 modesetting 1.20.4 3.3 Mesa 19.0.8 (LLVM 8.0 128 bits) GCC 8.3.0 + Clang 10.0.0-svn371485-1~exp1+0~20190910040723.259~1.gbp13c8b7 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernels Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Clang Kernel Benchmarks System Logs - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 - NONE / errors=remount-ro,relatime,rw - Scaling Governor: acpi-cpufreq ondemand - OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04) - Python 2.7.16 + Python 3.7.3 - 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 Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling
Clang Built vs. GCC 9.1 Built Comparison Phoronix Test Suite Baseline +8.7% +8.7% +17.4% +17.4% +26.1% +26.1% +34.8% +34.8% 34.8% 28.6% 25% 9.1% 8.4% 7.9% 7.2% 5.4% 5.1% 4.9% 4.8% 4.7% 4.6% 4.4% 4.3% 4% 4% 3.8% 3.7% 3.3% 3.2% 2.9% 2.7% 2.7% 2.6% 2.4% 2.4% 2.2% 2.2% 2.2% 2.1% 2.1% TCP - Connections/s - 32 Userspace Total Replace 17% Loader 10.5% Add 10.3% 250 200 Average - Integer Delete Create Threads 5.9% exp 5.5% Read Compiled Tree Socket Activity Tsearch TCP - Latency - 1 1.F.1.S.N.S.F Initial Create 1 4.5% C.S.T Append 4.4% P.B.S S.V.M.P 4.1% Memory Copying Seq Read - Linux AIO - Yes - No - 4MB 1.F.1.S 3.9% Rand Read - Linux AIO - Yes - No - 4MB Forking T.F.A.T.T 3.7% 5.F.1.S.4.T 3.3% Rand Write - Linux AIO - Yes - No - 4MB 2 3.2% log2 Get 16 - Process Compile Seq Write - Linux AIO - Yes - No - 4MB sinh Context Switching Jython Memory Allocations Create Files Semaphores 2.1% Tradesoap asinh Ethr Systemd Total Boot Time Systemd Total Boot Time Memcached mcperf Systemd Total Boot Time Memcached mcperf Apache Siege Apache Siege RAMspeed SMP Memcached mcperf OSBench glibc bench Compile Bench Stress-NG Stress-NG Ethr FS-Mark Compile Bench t-test1 ctx_clock Memcached mcperf PHPBench Stress-NG Stress-NG Flexible IO Tester FS-Mark Flexible IO Tester Stress-NG PyBench FS-Mark Flexible IO Tester t-test1 glibc bench Memcached mcperf Hackbench Compile Bench Flexible IO Tester glibc bench Stress-NG DaCapo Benchmark OSBench OSBench Stress-NG DaCapo Benchmark glibc bench Clang Built GCC 9.1 Built
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions Clang Built GCC 9.1 Built 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 15.10 15.35 1. (CC) gcc options: -O2 -lz -ldl -lpthread
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory GCC 9.1 Built Clang Built 1500 3000 4500 6000 7500 SE +/- 26.31, N = 3 SE +/- 38.66, N = 3 7222 6956 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory GCC 9.1 Built Clang Built 1200 2400 3600 4800 6000 SE +/- 97.85, N = 3 SE +/- 48.64, N = 3 5808 5625 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory GCC 9.1 Built Clang Built 1600 3200 4800 6400 8000 SE +/- 30.89, N = 3 SE +/- 35.23, N = 3 7244 6965 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory GCC 9.1 Built Clang Built 1300 2600 3900 5200 6500 SE +/- 59.58, N = 3 SE +/- 62.85, N = 3 5931 5781 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Clang Built GCC 9.1 Built 300 600 900 1200 1500 SE +/- 19.80, N = 3 SE +/- 16.40, N = 15 1374.00 1329.58 1. (CC) gcc options: -static
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Clang Built GCC 9.1 Built 120 240 360 480 600 SE +/- 7.78, N = 3 SE +/- 6.47, N = 3 577.63 577.13 1. (CC) gcc options: -static
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size, No Sync/FSync GCC 9.1 Built Clang Built 600 1200 1800 2400 3000 SE +/- 13.94, N = 3 SE +/- 19.80, N = 3 3027.60 2890.93 1. (CC) gcc options: -static
Compile Bench Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile GCC 9.1 Built Clang Built 500 1000 1500 2000 2500 SE +/- 2.77, N = 3 SE +/- 17.60, N = 3 2470.31 2405.90
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point GCC 9.1 Built Clang Built 6K 12K 18K 24K 30K 26813.47 26749.87 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale GCC 9.1 Built Clang Built 4K 8K 12K 16K 20K SE +/- 2.43, N = 5 SE +/- 2.47, N = 5 16343.48 16255.16 1. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad GCC 9.1 Built Clang Built 4K 8K 12K 16K 20K SE +/- 12.24, N = 5 SE +/- 17.16, N = 5 18092.22 18044.24 1. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Clang Built GCC 9.1 Built 4K 8K 12K 16K 20K SE +/- 53.63, N = 5 SE +/- 1.39, N = 5 18157.92 18137.70 1. (CC) gcc options: -O3 -march=native -fopenmp
t-test1 This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 Clang Built GCC 9.1 Built 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 21.27 22.23 1. (CC) gcc options: -pthread
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 GCC 9.1 Built Clang Built 4 8 12 16 20 SE +/- 0.17, N = 6 SE +/- 0.23, N = 3 14.05 14.73 MIN: 6.39 / MAX: 19.7 MIN: 6.49 / MAX: 19.64
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 32 Clang Built GCC 9.1 Built 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 14.53 14.56 MIN: 6.48 / MAX: 19.46 MIN: 6.45 / MAX: 20.53
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 GCC 9.1 Built Clang Built 200 400 600 800 1000 SE +/- 0.91, N = 3 SE +/- 0.91, N = 3 1068.54 1066.67 MIN: 1060 / MAX: 1080 MIN: 1050 / MAX: 1080
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 32 Clang Built GCC 9.1 Built 20K 40K 60K 80K 100K SE +/- 104.25, N = 3 SE +/- 304.84, N = 3 100554.89 100546.89 MIN: 97030 / MAX: 103660 MIN: 96500 / MAX: 103290
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32 GCC 9.1 Built Clang Built 40K 80K 120K 160K 200K SE +/- 216.53, N = 3 SE +/- 408.60, N = 3 170074.67 167820.22 MIN: 131250 / MAX: 207760 MIN: 128890 / MAX: 208680
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 32 Clang Built GCC 9.1 Built 800 1600 2400 3200 4000 SE +/- 3.65, N = 3 SE +/- 9.56, N = 3 3532.08 3514.17 MIN: 3440 / MAX: 3670 MIN: 3420 / MAX: 3590
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 Clang Built GCC 9.1 Built 3K 6K 9K 12K 15K SE +/- 210.17, N = 4 SE +/- 106.51, N = 3 14668 14637
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 32 GCC 9.1 Built Clang Built 12K 24K 36K 48K 60K SE +/- 7720.85, N = 15 SE +/- 10051.80, N = 15 53694 39835
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C GCC 9.1 Built Clang Built 5K 10K 15K 20K 25K SE +/- 29.41, N = 3 SE +/- 47.84, N = 3 25591.65 25345.11 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C GCC 9.1 Built Clang Built 150 300 450 600 750 SE +/- 1.48, N = 3 SE +/- 3.44, N = 3 694.29 686.51 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D GCC 9.1 Built Clang Built 150 300 450 600 750 SE +/- 1.44, N = 3 SE +/- 0.25, N = 3 687.75 679.10 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C GCC 9.1 Built Clang Built 2K 4K 6K 8K 10K SE +/- 15.97, N = 3 SE +/- 15.41, N = 3 8853.73 8832.09 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C GCC 9.1 Built Clang Built 6K 12K 18K 24K 30K SE +/- 8.98, N = 3 SE +/- 6.33, N = 3 26470.56 26335.94 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C GCC 9.1 Built Clang Built 3K 6K 9K 12K 15K SE +/- 5.92, N = 3 SE +/- 8.35, N = 3 13985.91 13943.75 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B GCC 9.1 Built Clang Built 2K 4K 6K 8K 10K SE +/- 67.50, N = 3 SE +/- 64.12, N = 3 9118.67 9029.27 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: In-Memory Database Shootout Clang Built GCC 9.1 Built 1300 2600 3900 5200 6500 SE +/- 36.68, N = 40 SE +/- 46.74, N = 8 5890.74 6004.02
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 2019-09-09 1080p 8-bit YUV To VP9 Video Encode GCC 9.1 Built Clang Built 50 100 150 200 250 SE +/- 3.02, N = 4 SE +/- 2.74, N = 4 214.46 213.46 1. (CC) gcc options: -fPIE -fPIC -flto -O3 -O2 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process GCC 9.1 Built Clang Built 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.55, N = 3 36.91 37.90 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process GCC 9.1 Built Clang Built 16 32 48 64 80 SE +/- 1.03, N = 3 SE +/- 0.47, N = 3 71.29 72.63 1. (CC) gcc options: -lpthread
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos Clang Built GCC 9.1 Built 10 20 30 40 50 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 42.26 42.46
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Clang Built GCC 9.1 Built 1.2128 2.4256 3.6384 4.8512 6.064 SE +/- 0.04, N = 12 SE +/- 0.05, N = 3 5.11 5.39
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt GCC 9.1 Built Clang Built 0.5018 1.0036 1.5054 2.0072 2.509 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 2.20 2.23
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Clang Built GCC 9.1 Built 0.3893 0.7786 1.1679 1.5572 1.9465 SE +/- 0.02, N = 4 SE +/- 0.02, N = 3 1.72 1.73
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Clang Built GCC 9.1 Built 6K 12K 18K 24K 30K SE +/- 59.25, N = 3 SE +/- 23.37, N = 3 29192.15 29122.33 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Bsearch Clang Built GCC 9.1 Built 2K 4K 6K 8K 10K SE +/- 73.09, N = 15 SE +/- 94.07, N = 3 7845.33 7837.79 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking GCC 9.1 Built Clang Built 15K 30K 45K 60K 75K SE +/- 339.76, N = 3 SE +/- 101.18, N = 3 67886.88 65434.71 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Hsearch Clang Built GCC 9.1 Built 20K 40K 60K 80K 100K SE +/- 152.70, N = 3 SE +/- 694.98, N = 3 97978.26 96577.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Lsearch Clang Built GCC 9.1 Built 40 80 120 160 200 SE +/- 0.20, N = 3 SE +/- 0.56, N = 3 176.20 176.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Tsearch GCC 9.1 Built Clang Built 110 220 330 440 550 SE +/- 4.36, N = 3 SE +/- 0.51, N = 3 487.09 464.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: CPU Stress Clang Built GCC 9.1 Built 900 1800 2700 3600 4500 SE +/- 8.13, N = 3 SE +/- 7.18, N = 3 4323.62 4312.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Clang Built GCC 9.1 Built 1.2M 2.4M 3.6M 4.8M 6M SE +/- 10292.63, N = 3 SE +/- 21479.46, N = 3 5831608.05 5709566.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Matrix Math GCC 9.1 Built Clang Built 20K 40K 60K 80K 100K SE +/- 321.18, N = 3 SE +/- 94.48, N = 3 96317.59 95406.28 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Vector Math GCC 9.1 Built Clang Built 7K 14K 21K 28K 35K SE +/- 34.91, N = 3 SE +/- 33.07, N = 3 31976.43 31874.11 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Memory Copying GCC 9.1 Built Clang Built 2K 4K 6K 8K 10K SE +/- 98.77, N = 3 SE +/- 40.81, N = 3 9295.15 8935.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity GCC 9.1 Built Clang Built 2K 4K 6K 8K 10K SE +/- 44.67, N = 3 SE +/- 74.55, N = 3 9483.81 9024.37 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching GCC 9.1 Built Clang Built 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 231151.58, N = 15 SE +/- 72287.76, N = 15 6098248.33 5957895.07 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc C String Functions GCC 9.1 Built Clang Built 300K 600K 900K 1200K 1500K SE +/- 8632.05, N = 3 SE +/- 22689.42, N = 15 1257798.52 1251619.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc Qsort Data Sorting Clang Built GCC 9.1 Built 50 100 150 200 250 SE +/- 2.01, N = 3 SE +/- 2.06, N = 11 233.82 232.18 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Clang Built GCC 9.1 Built 3M 6M 9M 12M 15M SE +/- 245301.68, N = 15 SE +/- 224717.33, N = 15 15500462.01 14895391.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Barbershop - Compute: CPU-Only GCC 9.1 Built Clang Built 100 200 300 400 500 SE +/- 0.47, N = 3 SE +/- 0.57, N = 3 461.31 466.26
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get GCC 9.1 Built Clang Built 20K 40K 60K 80K 100K SE +/- 1296.67, N = 3 SE +/- 822.92, N = 3 91279.97 88738.70 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set Clang Built GCC 9.1 Built 11K 22K 33K 44K 55K SE +/- 718.32, N = 3 SE +/- 217.49, N = 3 52635.03 51841.00 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Append Clang Built GCC 9.1 Built 12K 24K 36K 48K 60K SE +/- 1445.42, N = 15 SE +/- 694.52, N = 3 57100.47 54709.40 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Delete GCC 9.1 Built Clang Built 20K 40K 60K 80K 100K SE +/- 905.78, N = 15 SE +/- 1168.28, N = 3 94802.37 88403.00 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Prepend Clang Built GCC 9.1 Built 12K 24K 36K 48K 60K SE +/- 644.56, N = 3 SE +/- 720.37, N = 5 54661.90 54210.94 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Replace Clang Built GCC 9.1 Built 14K 28K 42K 56K 70K SE +/- 4635.11, N = 15 SE +/- 154.39, N = 3 63502.24 54286.00 1. (CC) gcc options: -O2 -lm -rdynamic
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Clang Built GCC 9.1 Built 200 400 600 800 1000 SE +/- 4.48, N = 3 SE +/- 7.36, N = 3 895 928
NGINX Benchmark This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving GCC 9.1 Built Clang Built 9K 18K 27K 36K 45K SE +/- 24.15, N = 3 SE +/- 160.84, N = 3 40021.67 39499.96 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving GCC 9.1 Built Clang Built 8K 16K 24K 32K 40K SE +/- 136.72, N = 3 SE +/- 129.65, N = 3 38007.35 37463.67 1. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 GCC 9.1 Built Clang Built 20K 40K 60K 80K 100K SE +/- 2503.78, N = 15 SE +/- 3407.74, N = 15 101988.65 93475.09 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Geekbench This is a benchmark of Geekbench 5 Pro. The test profile automates the execution of Geekbench 5 under the Phoronix Test Suite, assuming you have a valid license key for Geekbench 5 Pro. This test will not work without a valid license key for Geekbench Pro. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better Geekbench 5.0 Test: CPU Multi Core GCC 9.1 Built Clang Built 2K 4K 6K 8K 10K SE +/- 0.88, N = 3 SE +/- 5.61, N = 3 10839 10831
OpenBenchmarking.org Mpixels/sec, More Is Better Geekbench 5.0 Test: CPU Multi Core - Gaussian Blur GCC 9.1 Built Clang Built 170 340 510 680 850 SE +/- 0.29, N = 3 SE +/- 1.95, N = 3 770.23 767.10
OpenBenchmarking.org images/sec, More Is Better Geekbench 5.0 Test: CPU Multi Core - Face Detection GCC 9.1 Built Clang Built 30 60 90 120 150 SE +/- 0.26, N = 3 SE +/- 0.55, N = 3 133.57 132.40
OpenBenchmarking.org Gpixels/sec, More Is Better Geekbench 5.0 Test: CPU Multi Core - Horizon Detection GCC 9.1 Built Clang Built 50 100 150 200 250 SE +/- 0.43, N = 3 SE +/- 0.23, N = 3 238.23 236.57
OpenBenchmarking.org Mpixels/sec, More Is Better Geekbench 5.0 Test: CPU Single Core - Gaussian Blur Clang Built GCC 9.1 Built 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 1.25, N = 3 85.40 84.20
OpenBenchmarking.org images/sec, More Is Better Geekbench 5.0 Test: CPU Single Core - Face Detection Clang Built GCC 9.1 Built 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.19, N = 3 11.03 10.87
OpenBenchmarking.org Gpixels/sec, More Is Better Geekbench 5.0 Test: CPU Single Core - Horizon Detection Clang Built GCC 9.1 Built 7 14 21 28 35 SE +/- 2.43, N = 3 SE +/- 1.41, N = 3 28.47 27.97
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite GCC 9.1 Built Clang Built 140K 280K 420K 560K 700K SE +/- 2585.10, N = 3 SE +/- 5301.30, N = 3 664976 637793
BRL-CAD BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.28.0 VGR Performance Metric GCC 9.1 Built Clang Built 40K 80K 120K 160K 200K 182506 181568 1. (CXX) g++ options: -std=c++98 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files GCC 9.1 Built Clang Built 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 10.93 11.17 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Clang Built GCC 9.1 Built 4 8 12 16 20 SE +/- 0.24, N = 15 SE +/- 0.25, N = 3 14.69 15.56 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs GCC 9.1 Built Clang Built 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.33, N = 3 36.68 36.80 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes GCC 9.1 Built Clang Built 7 14 21 28 35 SE +/- 0.36, N = 3 SE +/- 0.21, N = 3 28.55 28.80 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations GCC 9.1 Built Clang Built 15 30 45 60 75 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 67.62 69.13 1. (CC) gcc options: -lm
Clang Built Processor: AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0803 BIOS), Chipset: AMD Device 1480, Memory: 16384MB, Disk: 2000GB Force MP600, Graphics: llvmpipe 16GB, Audio: AMD Device ab20, Network: Realtek Device 8125 + Intel I211 + Intel Device 2723
OS: Ubuntu 19.04, Kernel: 5.3.0-rc8-clanged (x86_64) 20190910, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0 + Clang 10.0.0-svn371485-1~exp1+0~20190910040723.259~1.gbp13c8b7, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandJava Notes: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: 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 Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling
Testing initiated at 10 September 2019 13:22 by user phoronix.
GCC 9.1 Built Processor: AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0803 BIOS), Chipset: AMD Device 1480, Memory: 16384MB, Disk: 2000GB Force MP600, Graphics: llvmpipe 16GB, Audio: AMD Device ab20, Network: Realtek Device 8125 + Intel I211 + Intel Device 2723
OS: Ubuntu 19.04, Kernel: 5.3.0-rc8-gnued (x86_64) 20190910, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0 + Clang 10.0.0-svn371485-1~exp1+0~20190910040723.259~1.gbp13c8b7, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandJava Notes: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: 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 Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling
Testing initiated at 10 September 2019 19:22 by user phoronix.