AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB on Ubuntu 19.10 via the Phoronix Test Suite.
GCC 10 Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Security Notes: itlb_multihit: Not affected + 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: conditional RSB filling + tsx_async_abort: Not affected
Sabrent Rocket 4.0 1TB Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 10.0.0 20191208, File-System: ext4, Screen Resolution: 3840x2160
GCC 10 AMD Threadripper 3960X PGO Optimization OpenBenchmarking.org Phoronix Test Suite AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 32768MB 1000GB Sabrent Rocket 4.0 1TB Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz) AMD Baffin HDMI/DP ASUS VP28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723 Ubuntu 19.10 5.4.0-nvme-hwmon (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 4.5 Mesa 19.2.1 (LLVM 9.0.0) GCC 10.0.0 20191208 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution GCC 10 AMD Threadripper 3960X PGO Optimization Benchmarks System Logs - --disable-multilib --enable-checking=release - NONE / errors=remount-ro,relatime,rw - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 - itlb_multihit: Not affected + 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: conditional RSB filling + tsx_async_abort: Not affected
GCC 10 vs. Sabrent Rocket 4.0 1TB Comparison Phoronix Test Suite Baseline +4649.8% +4649.8% +9299.6% +9299.6% +13949.4% +13949.4% 184% 3.2% 2.9% Float + SSE - 2D FFT Size 4096 501.7% C.u.1.0.3.s.i.i.C.L.9 3922.7% Float + SSE - 1D FFT Size 32 365.2% Total Time 3149.1% 280% Stock - 1D FFT Size 32 203.9% Time To Compile Stock - 2D FFT Size 4096 177.8% Stock - 2D FFT Size 32 172.2% Buffer Test - Heavy Contention - Read Only 159.6% Buffer Test - Normal Load - Read Only 153.3% Timed Time - Size 1,000 127.4% Dhrystone 2 122% P.R.W.S.S.M 18599% C.u.1.0.3.s.i.i.C.L.1 15446.7% Float + SSE - 2D FFT Size 32 1124.4% S.F.P.R 10815.3% WAV To MP3 26.7% Water Benchmark 25.6% P.P.A 18.9% A.C.P 13.2% WAV To FLAC 3.8% C.B.c - f32 P.P.S 1 2.9% FFTW XZ Compression FFTW Stockfish QMCPACK FFTW Timed ImageMagick Compilation FFTW FFTW PostgreSQL pgbench PostgreSQL pgbench SQLite Speedtest BYTE Unix Benchmark TTSIOD 3D Renderer Zstd Compression FFTW ACES DGEMM LAME MP3 Encoding GROMACS Timed MrBayes Analysis TSCP FLAC Audio Encoding MKL-DNN DNNL Himeno Benchmark SQLite GCC 10 Sabrent Rocket 4.0 1TB
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding GCC 10 Sabrent Rocket 4.0 1TB 700 1400 2100 2800 3500 SE +/- 3.58, N = 3 3359.12 3359.70 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding GCC 10 Sabrent Rocket 4.0 1TB 1200 2400 3600 4800 6000 SE +/- 0.00, N = 3 5433.8 5433.8 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding GCC 10 Sabrent Rocket 4.0 1TB 900 1800 2700 3600 4500 SE +/- 0.00, N = 3 4096.25 4096.25 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Sabrent Rocket 4.0 1TB GCC 10 30M 60M 90M 120M 150M SE +/- 1800355.11, N = 3 143335505 145207827 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill GCC 10 Sabrent Rocket 4.0 1TB 200K 400K 600K 800K 1000K SE +/- 3135.06, N = 3 1019862 1035308 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Sabrent Rocket 4.0 1TB GCC 10 5K 10K 15K 20K 25K SE +/- 19.92, N = 3 24460 24588 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing GCC 10 Sabrent Rocket 4.0 1TB 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 20082.88, N = 3 4889956 4937048 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 Sabrent Rocket 4.0 1TB GCC 10 2K 4K 6K 8K 10K SE +/- 16.77, N = 3 3436.6 10443.0 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 Sabrent Rocket 4.0 1TB GCC 10 2K 4K 6K 8K 10K SE +/- 11.02, N = 3 3862.4 10512.0 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Sabrent Rocket 4.0 1TB GCC 10 1400 2800 4200 5600 7000 SE +/- 7.80, N = 3 2407.0 6687.3 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 Sabrent Rocket 4.0 1TB GCC 10 3K 6K 9K 12K 15K SE +/- 15.37, N = 3 3309.7 15396.0 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 Sabrent Rocket 4.0 1TB GCC 10 10K 20K 30K 40K 50K SE +/- 56.20, N = 3 3708.4 45404.0 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Sabrent Rocket 4.0 1TB GCC 10 5K 10K 15K 20K 25K SE +/- 285.77, N = 3 3767.3 22667.0 -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math 1. (CC) gcc options: -pthread -lm
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL GCC 10 14 28 42 56 70 SE +/- 0.23, N = 3 63.63 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte GCC 10 3 6 9 12 15 SE +/- 0.05, N = 3 10.49 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte GCC 10 3 6 9 12 15 SE +/- 0.05, N = 3 10.49 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM GCC 10 8 16 24 32 40 SE +/- 0.38, N = 3 32.93 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans GCC 10 1.2324 2.4648 3.6972 4.9296 6.162 SE +/- 0.00581, N = 3 5.47737 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad GCC 10 0.4044 0.8088 1.2132 1.6176 2.022 SE +/- 0.00127, N = 3 1.79750 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access GCC 10 0.0321 0.0642 0.0963 0.1284 0.1605 SE +/- 0.00039, N = 3 0.14278 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency GCC 10 0.1032 0.2064 0.3096 0.4128 0.516 SE +/- 0.00067, N = 3 0.45863 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth GCC 10 0.7665 1.533 2.2995 3.066 3.8325 SE +/- 0.01038, N = 3 3.40678 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth GCC 10 5K 10K 15K 20K 25K SE +/- 313.29, N = 3 22977.00 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 GCC 10 Sabrent Rocket 4.0 1TB 0.5229 1.0458 1.5687 2.0916 2.6145 SE +/- 0.00388, N = 3 2.32419 2.30704 MIN: 2.26 -lm - MIN: 2.25 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 GCC 10 Sabrent Rocket 4.0 1TB 30 60 90 120 150 SE +/- 1.44, N = 3 123.99 120.15 MIN: 121.92 -lm - MIN: 119.49 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 GCC 10 Sabrent Rocket 4.0 1TB 40 80 120 160 200 SE +/- 0.35, N = 3 194.25 194.23 MIN: 192.53 -lm - MIN: 193.18 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 Sabrent Rocket 4.0 1TB GCC 10 12 24 36 48 60 SE +/- 0.14, N = 3 52.33 52.33 -lm - MIN: 51.67 MIN: 51.48 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Sabrent Rocket 4.0 1TB GCC 10 1500 3000 4500 6000 7500 SE +/- 21.70, N = 3 7060.1 7180.6 -O3 -lssl 1. (CC) gcc options: -pthread -m64 -lcrypto -ldl
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only Sabrent Rocket 4.0 1TB GCC 10 140K 280K 420K 560K 700K SE +/- 4887.19, N = 3 260493.71 676349.71 -O2 -lpq 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm
QMCPACK QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 Sabrent Rocket 4.0 1TB GCC 10 1500 3000 4500 6000 7500 7137.2 1878.0 1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm
Stockfish This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time Sabrent Rocket 4.0 1TB GCC 10 20M 40M 60M 80M 100M SE +/- 526550.53, N = 3 2442535 79359613 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Sabrent Rocket 4.0 1TB GCC 10 20 40 60 80 100 SE +/- 0.25, N = 3 83.27 70.01 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
TTSIOD 3D Renderer A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Sabrent Rocket 4.0 1TB GCC 10 200 400 600 800 1000 SE +/- 1.20634, N = 3 5.01883 938.47100 -O3 -fopenmp -fwhole-program 1. (CXX) g++ options: -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++
GCC 10 Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Security Notes: itlb_multihit: Not affected + 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: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 21 December 2019 18:23 by user pts.
Sabrent Rocket 4.0 1TB Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 10.0.0 20191208, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Security Notes: itlb_multihit: Not affected + 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: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 22 December 2019 00:11 by user pts.