Linux 4.19 Kernel Benchmarks AMD Ryzen Threadripper 2990WX 32-Core testing with a ASUS ROG ZENITH EXTREME (1402 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/1808192-RA-LINUX419K48&grs&sor&rro .
Linux 4.19 Kernel Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Linux 4.18.3 Linux 4.19 Git AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads) ASUS ROG ZENITH EXTREME (1402 BIOS) AMD Family 17h 32768MB Samsung SSD 970 EVO 500GB AMD Radeon RX Vega 8192MB Realtek ALC1220 ASUS VP28U Intel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac Wireless Ubuntu 18.04 4.18.3-041803-generic (x86_64) GNOME Shell 3.28.2 X Server 1.19.6 amdgpu 18.0.1 4.5 Mesa 18.0.5 (LLVM 6.0.0) GCC 7.3.0 ext4 3840x2160 4.18.0-999-generic (x86_64) 20180818 OpenBenchmarking.org Compiler 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-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 Disk Details - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand Python Details - Python 2.7.15rc1 + Python 3.6.5 Security Details - __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection
Linux 4.19 Kernel Benchmarks hpcc: Rand Ring Latency ramspeed: Average - Integer hpcc: Rand Ring Bandwidth hpcc: G-HPL hpcc: EP-STREAM Triad compilebench: Compile fs-mark: 1000 Files, 1MB Size compilebench: Initial Create stream: Scale blender: Barbershop - CPU-Only hpcc: G-Rand Access ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 compilebench: Read Compiled Tree stream: Copy build-llvm: Time To Compile hpcc: G-Ffte build-linux-kernel: Time To Compile x265: H.265 Video Encoding stream: Add hpcc: G-Ptrans stream: Triad sysbench: CPU sysbench: Memory fio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory openssl: RSA 4096-bit Performance fio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory hpcc: Max Ping Pong Bandwidth hpcc: EP-DGEMM fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size fs-mark: 5000 Files, 1MB Size, 4 Threads Linux 4.18.3 Linux 4.19 Git 3.30877 29059.98 0.32180 292.60633 0.64003 1993.89 236.07 523.79 36047.94 405.70 0.07884 537.34 122.89 3219.72 56995.10 217.00 10.75387 31.21 11.78 39934.02 1.95507 40040.94 56761.95 7318291.45 2401 3405 3458 5869.43 2369 13153.726 5.97520 140.23 253.17 1.81967 25012.30 0.35630 318.16600 0.61761 2063.10 228.83 507.98 35100.46 397.32 0.07730 529.02 124.67 3174.08 56262.64 214.62 10.64623 31.49 11.84 39741.12 1.96417 39941.80 56700.95 7312176.62 2399 3407 3459 5870.33 2369 11881.833 6.44631 128.53 260.33 OpenBenchmarking.org
HPC Challenge Test / Class: Random Ring Latency OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency Linux 4.18.3 Linux 4.19 Git 0.7445 1.489 2.2335 2.978 3.7225 SE +/- 0.06391, N = 3 SE +/- 0.01021, N = 3 3.30877 1.81967 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
RAMspeed SMP Type: Average - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer Linux 4.19 Git Linux 4.18.3 6K 12K 18K 24K 30K 25012.30 29059.98 1. (CC) gcc options: -O3 -march=native
HPC Challenge Test / Class: Random Ring Bandwidth OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth Linux 4.18.3 Linux 4.19 Git 0.0802 0.1604 0.2406 0.3208 0.401 SE +/- 0.00322, N = 3 SE +/- 0.00028, N = 3 0.32180 0.35630 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
HPC Challenge Test / Class: G-HPL OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL Linux 4.18.3 Linux 4.19 Git 70 140 210 280 350 SE +/- 3.55, N = 9 SE +/- 0.58, N = 3 292.61 318.17 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
HPC Challenge Test / Class: EP-STREAM Triad OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad Linux 4.19 Git Linux 4.18.3 0.144 0.288 0.432 0.576 0.72 SE +/- 0.00144, N = 3 SE +/- 0.00461, N = 3 0.61761 0.64003 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Linux 4.18.3 Linux 4.19 Git 400 800 1200 1600 2000 SE +/- 15.56, N = 3 SE +/- 15.96, N = 3 1993.89 2063.10
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size Linux 4.19 Git Linux 4.18.3 50 100 150 200 250 SE +/- 0.84, N = 3 SE +/- 1.21, N = 3 228.83 236.07 1. (CC) gcc options: -static
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Linux 4.19 Git Linux 4.18.3 110 220 330 440 550 SE +/- 5.66, N = 3 SE +/- 4.18, N = 3 507.98 523.79
Stream Type: Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale Linux 4.19 Git Linux 4.18.3 8K 16K 24K 32K 40K SE +/- 450.92, N = 5 SE +/- 324.25, N = 5 35100.46 36047.94 1. (CC) gcc options: -O3 -march=native -fopenmp
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Barbershop - Compute: CPU-Only Linux 4.18.3 Linux 4.19 Git 90 180 270 360 450 405.70 397.32
HPC Challenge Test / Class: G-Random Access OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access Linux 4.19 Git Linux 4.18.3 0.0177 0.0354 0.0531 0.0708 0.0885 SE +/- 0.00046, N = 3 SE +/- 0.00015, N = 3 0.07730 0.07884 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Linux 4.19 Git Linux 4.18.3 120 240 360 480 600 SE +/- 9.18, N = 3 SE +/- 10.37, N = 3 529.02 537.34 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Linux 4.19 Git Linux 4.18.3 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 124.67 122.89 1. (CC) gcc options: -O3 -pthread -lz -llzma
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree Linux 4.19 Git Linux 4.18.3 700 1400 2100 2800 3500 SE +/- 13.27, N = 3 SE +/- 13.27, N = 3 3174.08 3219.72
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy Linux 4.19 Git Linux 4.18.3 12K 24K 36K 48K 60K SE +/- 655.76, N = 5 SE +/- 720.37, N = 5 56262.64 56995.10 1. (CC) gcc options: -O3 -march=native -fopenmp
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Linux 4.18.3 Linux 4.19 Git 50 100 150 200 250 217.00 214.62
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Linux 4.19 Git Linux 4.18.3 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.25, N = 3 10.65 10.75 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Linux 4.19 Git Linux 4.18.3 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.25, N = 3 10.65 10.75 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.13 Time To Compile Linux 4.19 Git Linux 4.18.3 7 14 21 28 35 SE +/- 0.41, N = 7 SE +/- 0.37, N = 8 31.49 31.21
x265 H.265 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x265 2.8 H.265 Video Encoding Linux 4.18.3 Linux 4.19 Git 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 11.78 11.84 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Linux 4.19 Git Linux 4.18.3 9K 18K 27K 36K 45K SE +/- 225.50, N = 5 SE +/- 301.24, N = 5 39741.12 39934.02 1. (CC) gcc options: -O3 -march=native -fopenmp
HPC Challenge Test / Class: G-Ptrans OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans Linux 4.18.3 Linux 4.19 Git 0.4419 0.8838 1.3257 1.7676 2.2095 SE +/- 0.01827, N = 3 SE +/- 0.02996, N = 3 1.95507 1.96417 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad Linux 4.19 Git Linux 4.18.3 9K 18K 27K 36K 45K SE +/- 165.34, N = 5 SE +/- 166.30, N = 5 39941.80 40040.94 1. (CC) gcc options: -O3 -march=native -fopenmp
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: CPU Linux 4.19 Git Linux 4.18.3 12K 24K 36K 48K 60K SE +/- 64.54, N = 3 SE +/- 23.70, N = 3 56700.95 56761.95 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
Sysbench Test: Memory OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: Memory Linux 4.19 Git Linux 4.18.3 1.6M 3.2M 4.8M 6.4M 8M SE +/- 11957.94, N = 3 SE +/- 3167.78, N = 3 7312176.62 7318291.45 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Linux 4.19 Git Linux 4.18.3 500 1000 1500 2000 2500 SE +/- 2.08, N = 3 SE +/- 0.67, N = 3 2399 2401 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Linux 4.18.3 Linux 4.19 Git 700 1400 2100 2800 3500 SE +/- 13.35, N = 3 SE +/- 26.43, N = 3 3405 3407 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Linux 4.18.3 Linux 4.19 Git 700 1400 2100 2800 3500 SE +/- 1.45, N = 3 SE +/- 1.33, N = 3 3458 3459 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.0f RSA 4096-bit Performance Linux 4.18.3 Linux 4.19 Git 1300 2600 3900 5200 6500 SE +/- 0.92, N = 3 SE +/- 2.78, N = 3 5869.43 5870.33 1. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Linux 4.18.3 Linux 4.19 Git 500 1000 1500 2000 2500 SE +/- 1.76, N = 3 SE +/- 1.00, N = 3 2369 2369 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
HPC Challenge Test / Class: Max Ping Pong Bandwidth OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth Linux 4.19 Git Linux 4.18.3 3K 6K 9K 12K 15K SE +/- 1104.31, N = 3 SE +/- 144.82, N = 3 11881.83 13153.73 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
HPC Challenge Test / Class: EP-DGEMM OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM Linux 4.18.3 Linux 4.19 Git 2 4 6 8 10 SE +/- 0.32651, N = 3 SE +/- 0.00603, N = 3 5.97520 6.44631 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -O3 -march=native -funroll-loops 2. ATLAS + Open MPI 2.1.1
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Linux 4.19 Git Linux 4.18.3 30 60 90 120 150 SE +/- 7.55, N = 12 SE +/- 10.71, N = 12 128.53 140.23 1. (CC) gcc options: -static
FS-Mark Test: 5000 Files, 1MB Size, 4 Threads OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Linux 4.18.3 Linux 4.19 Git 60 120 180 240 300 SE +/- 34.48, N = 12 SE +/- 9.14, N = 12 253.17 260.33 1. (CC) gcc options: -static
Phoronix Test Suite v10.8.5