AMD EPYC 7502P 32-Core testing with a Tyan S8030GM2NE (V7.900 BIOS) on FreeBSD head 1ff41cad716adeba0d408652c92c81e59e3ba316 with ARCHLEVEL=scalar
FreeBSD - AMD EPYC 7502P 32-Core Java Notes: OpenJDK Runtime Environment (build 11.0.10+9-1)Python Notes: Python 3.7.10
CPUTYPE=znver2 CPUTYPE=znver2 second run Processor: AMD EPYC 7502P 32-Core @ 2.50GHz (64 Cores), Motherboard: MFG-NOT-FILLED HWREV-NOT-FILLED, Chipset: AMD [AMD] Starship/Matisse Root Complex, Memory: 256GB, Disk: 2 x Generic NVMe Device, Graphics: ASPEED
OS: FreeBSD, Kernel: 13.0-RELEASE (x86_64), Compiler: Clang 11.0.1, File-System: zfs, Screen Resolution: 800x600
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-1)Python Notes: Python 3.9.18
ARCHLEVEL=scalar Processor: AMD EPYC 7502P 32-Core @ 2.50GHz (64 Cores), Motherboard: TYAN S8030GM2NE-NFX , Chipset: AMD [AMD] Starship/Matisse Root Complex, Memory: 256GB, Disk: 2 x Generic NVMe Device, Graphics: ASPEED
OS: FreeBSD, Kernel: 15.0-CURRENT (x86_64), Display Server: X Server 1.20.11, Compiler: Clang 17.0.6, File-System: zfs, Screen Resolution: 800x600
Timed HMMer Search This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 60 120 180 240 300 SE +/- 4.54, N = 9 SE +/- 4.06, N = 9 SE +/- 0.99, N = 3 SE +/- 0.10, N = 3 SE +/- 0.29, N = 3 277.40 273.95 263.04 148.52 147.31 1. (CC) clang options: -O3 -pthread -lhmmer -leasel -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: Launch Programs FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 20 40 60 80 100 SE +/- 1.05, N = 3 SE +/- 1.03, N = 3 SE +/- 0.91, N = 3 SE +/- 0.48, N = 3 SE +/- 0.08, N = 3 108.84 108.42 104.81 79.25 75.36 1. (CC) clang options: -lm
DaCapo Benchmark This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 1100 2200 3300 4400 5500 SE +/- 40.38, N = 4 SE +/- 23.43, N = 4 SE +/- 38.17, N = 20 SE +/- 35.14, N = 6 SE +/- 31.91, N = 4 5116 5059 3775 3727 3677
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 64 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 5.05, N = 3 SE +/- 2.60, N = 3 SE +/- 2.25, N = 3 6284.5 6284.5 8709.3 8709.3 8709.9 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 6K 12K 18K 24K 30K SE +/- 24.21, N = 3 SE +/- 6.44, N = 3 SE +/- 70.74, N = 3 SE +/- 40.43, N = 3 SE +/- 39.55, N = 3 24243 24318 28744 28758 28832 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 1024 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 6K 12K 18K 24K 30K SE +/- 20.74, N = 3 SE +/- 16.26, N = 3 SE +/- 67.88, N = 3 SE +/- 28.36, N = 3 SE +/- 40.60, N = 3 24942 24995 29343 29359 29379 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 512 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 5K 10K 15K 20K 25K SE +/- 15.25, N = 3 SE +/- 53.42, N = 3 SE +/- 11.29, N = 3 SE +/- 34.31, N = 3 SE +/- 37.12, N = 3 20245 20316 23438 23448 23472 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 6K 12K 18K 24K 30K SE +/- 40.38, N = 3 SE +/- 13.04, N = 3 SE +/- 322.06, N = 3 SE +/- 66.70, N = 3 SE +/- 39.72, N = 3 23130 23186 26463 26734 26795 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 102.71, N = 3 SE +/- 90.99, N = 15 SE +/- 1.76, N = 3 SE +/- 17.20, N = 3 SE +/- 16.00, N = 3 7281.29 7501.65 7814.16 8375.12 8424.09 1. (CC) clang options: -O3 -march=native
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 Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 31.74 30.60 30.55 27.68 27.53 1. (CC) clang options: -lm
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: Float + SSE - Size: 2D FFT Size 128 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 5K 10K 15K 20K 25K SE +/- 118.17, N = 3 SE +/- 185.18, N = 3 SE +/- 205.08, N = 7 SE +/- 21.11, N = 3 SE +/- 10.97, N = 3 20394 20582 23226 23466 23488 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 256 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 5K 10K 15K 20K 25K SE +/- 24.94, N = 3 SE +/- 35.48, N = 3 SE +/- 67.85, N = 3 SE +/- 75.98, N = 3 SE +/- 45.76, N = 3 20309 20322 22930 23159 23289 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 1024 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 5K 10K 15K 20K 25K SE +/- 25.38, N = 3 SE +/- 11.05, N = 3 SE +/- 34.07, N = 3 SE +/- 26.73, N = 3 SE +/- 9.82, N = 3 20835 20842 23809 23854 23862 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -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 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 7 14 21 28 35 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 SE +/- 0.23, N = 3 31.69 31.41 31.40 27.71 27.67 1. (CC) clang options: -lm
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 400K 800K 1200K 1600K 2000K SE +/- 333.33, N = 3 SE +/- 2403.70, N = 3 SE +/- 881.92, N = 3 1675333 1914667 1916667 1. (CC) clang options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Test: MD5
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./john-the-ripper: ./john: not found
ARCHLEVEL=scalar: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./john-the-ripper: ./john: not found
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: Float + SSE - Size: 1D FFT Size 512 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 6K 12K 18K 24K 30K SE +/- 19.88, N = 3 SE +/- 39.55, N = 3 SE +/- 5.93, N = 3 SE +/- 21.73, N = 3 SE +/- 38.41, N = 3 24749 24761 28090 28187 28192 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 82.89, N = 15 SE +/- 103.54, N = 15 SE +/- 27.29, N = 3 SE +/- 15.62, N = 3 SE +/- 27.14, N = 3 7470.22 7660.29 7841.88 8450.09 8487.10 1. (CC) clang options: -O3 -march=native
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 Processes ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 15 30 45 60 75 SE +/- 0.82, N = 15 SE +/- 0.57, N = 3 SE +/- 0.09, N = 3 SE +/- 0.58, N = 3 SE +/- 0.16, N = 3 67.95 67.32 61.91 61.07 59.84 1. (CC) clang options: -lm
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: Float + SSE - Size: 1D FFT Size 256 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 6K 12K 18K 24K 30K SE +/- 16.59, N = 3 SE +/- 60.05, N = 3 SE +/- 81.30, N = 3 SE +/- 67.34, N = 3 SE +/- 92.91, N = 3 23001 23040 25898 26076 26104 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 126.58, N = 12 SE +/- 105.89, N = 15 SE +/- 15.44, N = 3 SE +/- 2.46, N = 3 SE +/- 17.08, N = 3 7436.87 7471.44 7811.35 8318.29 8393.70 1. (CC) clang options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 81.76, N = 15 SE +/- 115.57, N = 15 SE +/- 16.00, N = 3 SE +/- 19.72, N = 3 SE +/- 20.28, N = 3 7449.32 7477.81 7769.45 8351.98 8399.65 1. (CC) clang options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 89.70, N = 15 SE +/- 85.57, N = 15 SE +/- 64.63, N = 3 SE +/- 87.53, N = 3 SE +/- 76.23, N = 3 7509.62 7634.17 7786.55 8365.68 8418.22 1. (CC) clang options: -O3 -march=native
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Twitter HTTP Requests FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 1100 2200 3300 4400 5500 SE +/- 18.76, N = 5 SE +/- 27.41, N = 5 SE +/- 35.14, N = 25 SE +/- 28.07, N = 25 SE +/- 26.36, N = 5 5072.74 5054.72 4595.77 4561.16 4558.08
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 8192 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 84.14, N = 12 SE +/- 109.59, N = 15 SE +/- 11.56, N = 3 SE +/- 12.73, N = 3 SE +/- 12.83, N = 3 7091.12 7142.34 7396.97 7776.27 7789.36 1. (CC) clang options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 98.58, N = 15 SE +/- 13.62, N = 3 SE +/- 102.83, N = 15 SE +/- 29.22, N = 3 SE +/- 28.62, N = 3 7120.50 7374.92 7412.42 7798.64 7799.84 1. (CC) clang options: -O3 -march=native
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: Float + SSE - Size: 1D FFT Size 128 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 5K 10K 15K 20K 25K SE +/- 244.89, N = 3 SE +/- 187.99, N = 12 SE +/- 252.82, N = 3 SE +/- 126.52, N = 3 SE +/- 9.81, N = 3 20383 20448 22113 22284 22302 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 512 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 2K 4K 6K 8K 10K SE +/- 92.96, N = 3 SE +/- 61.77, N = 15 SE +/- 10.37, N = 3 SE +/- 11.24, N = 3 SE +/- 30.45, N = 3 7240.20 7369.31 7442.18 7856.04 7915.75 1. (CC) clang options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 128 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 2K 4K 6K 8K 10K SE +/- 54.21, N = 10 SE +/- 57.87, N = 15 SE +/- 18.72, N = 3 SE +/- 27.71, N = 3 SE +/- 11.68, N = 3 7240.60 7360.29 7452.25 7847.51 7911.60 1. (CC) clang options: -O3 -march=native
Bork File Encrypter Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 5 SE +/- 0.14, N = 3 15.87 15.84 15.76 14.86 14.63
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: 2D FFT Size 1024 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 1400 2800 4200 5600 7000 SE +/- 14.25, N = 3 SE +/- 17.99, N = 3 SE +/- 16.57, N = 3 SE +/- 15.43, N = 3 SE +/- 9.09, N = 3 6006.1 6132.4 6499.3 6503.8 6513.8 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 1024 MiB ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 2K 4K 6K 8K 10K SE +/- 69.85, N = 15 SE +/- 63.65, N = 15 SE +/- 19.17, N = 3 SE +/- 21.29, N = 3 SE +/- 17.36, N = 3 7235.17 7369.50 7437.53 7815.46 7821.80 1. (CC) clang options: -O3 -march=native
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: 2D FFT Size 64 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 2K 4K 6K 8K 10K SE +/- 66.19, N = 12 SE +/- 27.27, N = 3 SE +/- 70.83, N = 9 SE +/- 115.80, N = 3 SE +/- 96.75, N = 4 8032.7 8097.1 8598.9 8648.8 8667.2 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 2K 4K 6K 8K 10K SE +/- 20.15, N = 3 SE +/- 2.92, N = 3 SE +/- 28.74, N = 3 SE +/- 4.45, N = 3 SE +/- 4.20, N = 3 7418.4 7429.9 7920.8 7996.9 8002.2 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run 2K 4K 6K 8K 10K SE +/- 2.54, N = 3 SE +/- 1.37, N = 3 SE +/- 3.83, N = 3 SE +/- 3.35, N = 3 SE +/- 3.43, N = 3 9193.7 9197.8 9635.6 9638.2 9642.7 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 100K 200K 300K 400K 500K SE +/- 672.36, N = 3 SE +/- 371.98, N = 3 SE +/- 637.30, N = 3 SE +/- 2928.14, N = 3 SE +/- 784.01, N = 3 444678 445372 454674 464523 465484
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: Float + SSE - Size: 1D FFT Size 64 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 4K 8K 12K 16K 20K SE +/- 65.64, N = 3 SE +/- 44.02, N = 3 SE +/- 30.75, N = 3 SE +/- 19.38, N = 3 SE +/- 8.51, N = 3 16649 16758 16765 17375 17411 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 1500 3000 4500 6000 7500 SE +/- 32.38, N = 3 SE +/- 35.69, N = 3 SE +/- 2.69, N = 3 SE +/- 31.46, N = 3 SE +/- 84.35, N = 3 6878.2 6909.5 7064.8 7110.7 7181.7 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
LibRaw LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 8 16 24 32 40 SE +/- 0.36, N = 3 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 33.13 33.77 34.31 34.53 34.55 -llcms2_fast_float -llcms2_threaded -llcms2_fast_float -llcms2_threaded 1. (CXX) clang++ options: -O2 -fopenmp -lz -llcms2 -lm
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: 2D FFT Size 512 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run 1500 3000 4500 6000 7500 SE +/- 14.08, N = 3 SE +/- 3.68, N = 3 SE +/- 0.37, N = 3 SE +/- 4.69, N = 3 SE +/- 2.60, N = 3 6780.2 6787.0 7053.9 7056.5 7058.3 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 5K 10K 15K 20K 25K SE +/- 282.16, N = 13 SE +/- 188.29, N = 3 SE +/- 126.62, N = 3 SE +/- 125.89, N = 3 SE +/- 53.23, N = 3 21735 21951 22035 22537 22625 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Dense LU Matrix Factorization FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 1200 2400 3600 4800 6000 SE +/- 20.98, N = 4 SE +/- 10.60, N = 4 SE +/- 4.77, N = 4 SE +/- 3.96, N = 4 SE +/- 2.30, N = 4 5175.65 5205.67 5379.97 5379.97 5381.95
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: 2D FFT Size 256 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1500 3000 4500 6000 7500 SE +/- 9.33, N = 3 SE +/- 7.73, N = 3 SE +/- 7.70, N = 3 SE +/- 6.32, N = 3 SE +/- 8.62, N = 3 6793.2 6798.1 7017.8 7039.2 7054.6 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run 1600 3200 4800 6400 8000 SE +/- 3.54, N = 3 SE +/- 12.53, N = 3 SE +/- 17.90, N = 3 SE +/- 2.14, N = 3 SE +/- 3.72, N = 3 7022.0 7042.3 7235.3 7265.5 7270.3 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Genetic Algorithm Using Jenetics + Futures ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 300 600 900 1200 1500 SE +/- 9.30, N = 5 SE +/- 3.24, N = 5 SE +/- 8.11, N = 5 SE +/- 9.19, N = 5 SE +/- 6.19, N = 5 1530.69 1503.06 1493.70 1485.83 1479.30
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: Float + SSE - Size: 2D FFT Size 2048 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 3K 6K 9K 12K 15K SE +/- 163.41, N = 3 SE +/- 58.94, N = 3 SE +/- 52.75, N = 3 SE +/- 54.23, N = 3 SE +/- 34.33, N = 3 13029 13165 13430 13437 13475 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1700 3400 5100 6800 8500 SE +/- 5.14, N = 3 SE +/- 0.60, N = 3 SE +/- 2.23, N = 3 SE +/- 1.12, N = 3 SE +/- 1.48, N = 3 7529.1 7538.9 7761.9 7765.5 7768.7 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 400 800 1200 1600 2000 SE +/- 3.79, N = 5 SE +/- 3.91, N = 5 SE +/- 3.73, N = 5 SE +/- 4.86, N = 5 SE +/- 1.48, N = 5 1767.43 1764.18 1726.03 1721.85 1716.26
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p CPUTYPE=znver2 second run ARCHLEVEL=scalar CPUTYPE=znver2 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core 16 32 48 64 80 SE +/- 0.96, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.26, N = 3 SE +/- 0.18, N = 3 69.89 71.11 71.65 71.69 71.90 1. (CXX) clang++ options: -O3 -lpthread -lrt -ldl
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: Float + SSE - Size: 2D FFT Size 32 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run CPUTYPE=znver2 5K 10K 15K 20K 25K SE +/- 12.71, N = 3 SE +/- 19.16, N = 3 SE +/- 43.31, N = 3 SE +/- 86.49, N = 3 SE +/- 22.93, N = 3 24199 24200 24812 24840 24883 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1600 3200 4800 6400 8000 SE +/- 39.91, N = 3 SE +/- 2.03, N = 3 SE +/- 16.65, N = 3 SE +/- 18.91, N = 3 SE +/- 49.21, N = 3 7254.6 7299.1 7390.6 7406.2 7428.8 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 2048 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1200 2400 3600 4800 6000 SE +/- 20.07, N = 3 SE +/- 22.51, N = 3 SE +/- 8.70, N = 3 SE +/- 17.42, N = 3 SE +/- 39.44, N = 3 5282.6 5291.2 5313.8 5322.3 5399.5 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 CPUTYPE=znver2 second run CPUTYPE=znver2 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 3K 6K 9K 12K 15K SE +/- 27.02, N = 3 SE +/- 18.22, N = 3 SE +/- 122.21, N = 3 SE +/- 9.06, N = 3 SE +/- 127.55, N = 3 12676 12677 12741 12773 12944 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 second run 3K 6K 9K 12K 15K SE +/- 98.67, N = 3 SE +/- 45.62, N = 3 SE +/- 81.05, N = 3 SE +/- 93.58, N = 3 SE +/- 48.56, N = 3 11749 11764 11788 11823 11986 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 500 1000 1500 2000 2500 SE +/- 5.05, N = 4 SE +/- 3.14, N = 4 SE +/- 3.54, N = 4 SE +/- 1.85, N = 4 SE +/- 0.72, N = 4 2342.56 2352.88 2384.52 2385.50 2386.36
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 256 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run 1600 3200 4800 6400 8000 SE +/- 18.75, N = 3 SE +/- 25.78, N = 3 SE +/- 2.02, N = 3 SE +/- 4.71, N = 3 SE +/- 3.67, N = 3 7454.9 7464.7 7475.1 7479.8 7591.9 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K CPUTYPE=znver2 second run ARCHLEVEL=scalar CPUTYPE=znver2 FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core 6 12 18 24 30 SE +/- 0.31, N = 3 SE +/- 0.27, N = 3 SE +/- 0.22, N = 3 SE +/- 0.29, N = 4 SE +/- 0.13, N = 3 27.16 27.37 27.45 27.52 27.62 1. (CXX) clang++ options: -O3 -lpthread -lrt -ldl
Node.js Express HTTP Load Test A Node.js Express server with a Node-based loadtest client for facilitating HTTP benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1500 3000 4500 6000 7500 SE +/- 87.07, N = 3 SE +/- 55.69, N = 9 SE +/- 63.73, N = 3 6945 6974 7048 1. Nodejs
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
ARCHLEVEL=scalar: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
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: 2D FFT Size 128 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 1600 3200 4800 6400 8000 SE +/- 79.88, N = 4 SE +/- 0.62, N = 3 SE +/- 6.75, N = 3 SE +/- 19.66, N = 3 SE +/- 7.29, N = 3 7142.2 7216.8 7228.7 7232.1 7247.7 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Coremark This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 200K 400K 600K 800K 1000K SE +/- 1547.63, N = 3 SE +/- 434.27, N = 3 SE +/- 1673.69, N = 3 SE +/- 906.06, N = 3 SE +/- 929.69, N = 3 936514.34 937393.60 945415.10 949509.67 950277.33 1. (CC) clang options: -O2 -lrt" -lrt
DaCapo Benchmark This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 second run 1100 2200 3300 4400 5500 SE +/- 9.81, N = 4 SE +/- 6.65, N = 4 SE +/- 21.21, N = 4 SE +/- 9.31, N = 4 SE +/- 3.42, N = 4 5188 5176 5146 5138 5125
Numpy Benchmark This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better Numpy Benchmark FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 70 140 210 280 350 SE +/- 1.41, N = 3 SE +/- 0.11, N = 3 SE +/- 0.19, N = 3 296.57 299.81 299.93
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
ARCHLEVEL=scalar: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
GNU MPC GNU MPC is a C library for the arithmetic of complex numbers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Global Score, More Is Better GNU MPC 1.1.0 Multi-Precision Benchmark CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core 1500 3000 4500 6000 7500 SE +/- 12.02, N = 3 SE +/- 6.67, N = 3 SE +/- 6.67, N = 3 7017 7033 7083 1. (CC) clang options: -lm -O2 -MT -MD -MP -MF
Multi-Precision Benchmark
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
ARCHLEVEL=scalar: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Fast Fourier Transform FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 400 800 1200 1600 2000 SE +/- 8.37, N = 4 SE +/- 9.22, N = 4 SE +/- 6.31, N = 4 SE +/- 5.63, N = 4 SE +/- 2.49, N = 4 1619.48 1626.30 1631.73 1633.82 1634.53
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: 2D FFT Size 4096 CPUTYPE=znver2 second run CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 1100 2200 3300 4400 5500 SE +/- 9.56, N = 3 SE +/- 2.90, N = 3 SE +/- 4.79, N = 3 SE +/- 22.33, N = 3 SE +/- 14.87, N = 3 5216.5 5229.3 5230.0 5243.8 5259.4 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 17M 34M 51M 68M 85M SE +/- 944399.61, N = 4 SE +/- 630102.70, N = 15 SE +/- 713551.25, N = 15 76513933 76836714 77138674 1. (CXX) clang++ options: -fprofile-use -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto
Total Time
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./stockfish: ./stockfish: not found
ARCHLEVEL=scalar: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./stockfish: ./stockfish: not found
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Sparse Matrix Multiply FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 400 800 1200 1600 2000 SE +/- 5.08, N = 4 SE +/- 4.09, N = 4 SE +/- 4.30, N = 4 SE +/- 3.37, N = 4 SE +/- 0.62, N = 4 2074.37 2075.80 2076.83 2082.38 2088.59
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 ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core 2K 4K 6K 8K 10K SE +/- 8.04, N = 3 SE +/- 25.62, N = 3 SE +/- 31.46, N = 3 SE +/- 0.43, N = 3 SE +/- 27.66, N = 3 9017.2 9024.8 9024.9 9028.6 9069.1 1. (CC) clang options: -pthread -O3 -fomit-frame-pointer -mtune=native -fstrict-aliasing -ffast-math -lm
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation FreeBSD - AMD EPYC 7502P 32-Core FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 CPUTYPE=znver2 second run ARCHLEVEL=scalar 300 600 900 1200 1500 SE +/- 1.63, N = 4 SE +/- 0.61, N = 4 SE +/- 0.24, N = 4 SE +/- 0.38, N = 4 SE +/- 0.30, N = 4 1505.59 1505.88 1506.02 1506.32 1511.63
Scikit-Learn Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.22.1 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run 30 60 90 120 150 SE +/- 0.24, N = 3 SE +/- 0.19, N = 3 SE +/- 0.14, N = 3 141.58 141.37 141.04
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'numpy'
ARCHLEVEL=scalar: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'numpy'
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish CPUTYPE=znver2 second run FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 13K 26K 39K 52K 65K SE +/- 95.30, N = 3 SE +/- 7.09, N = 3 SE +/- 12.14, N = 3 59778 59893 59906 1. (CC) clang options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Test: Blowfish
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./john-the-ripper: ./john: not found
ARCHLEVEL=scalar: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./john-the-ripper: ./john: not found
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Monte Carlo FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run ARCHLEVEL=scalar 300 600 900 1200 1500 SE +/- 1.22, N = 4 SE +/- 1.13, N = 4 SE +/- 0.35, N = 4 SE +/- 0.17, N = 4 SE +/- 0.29, N = 4 1329.41 1330.95 1331.88 1332.19 1332.19
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree FreeBSD - AMD EPYC 7502P 32-Core CPUTYPE=znver2 CPUTYPE=znver2 second run FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 ARCHLEVEL=scalar 3K 6K 9K 12K 15K SE +/- 296.31, N = 15 SE +/- 341.60, N = 15 SE +/- 204.95, N = 15 SE +/- 212.96, N = 15 SE +/- 175.21, N = 15 14870.51 14624.27 14485.97 13505.86 13472.98
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO CPUTYPE=znver2 FreeBSD - AMD EPYC 7502P 32-Core FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run ARCHLEVEL=scalar 4K 8K 12K 16K 20K SE +/- 706.21, N = 15 SE +/- 351.86, N = 20 SE +/- 396.93, N = 20 SE +/- 353.27, N = 15 SE +/- 312.32, N = 15 16663.92 16548.55 15976.17 15658.39 15538.27
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 Threads FreeBSD - AMD EPYC 7502P 32-Core ARCHLEVEL=scalar FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 CPUTYPE=znver2 second run CPUTYPE=znver2 2 4 6 8 10 SE +/- 0.072005, N = 3 SE +/- 0.096140, N = 15 SE +/- 0.424281, N = 12 SE +/- 0.009165, N = 3 SE +/- 0.018485, N = 3 6.167094 5.974928 5.281369 2.146562 2.142588 1. (CC) clang options: -lm
FreeBSD - AMD EPYC 7502P 32-Core Java Notes: OpenJDK Runtime Environment (build 11.0.10+9-1)Python Notes: Python 3.7.10
Testing initiated at 16 April 2021 13:01 by user ocochard.
CPUTYPE=znver2 Java Notes: OpenJDK Runtime Environment (build 11.0.10+9-1)Python Notes: Python 3.7.10
Testing initiated at 16 April 2021 21:47 by user ocochard.
CPUTYPE=znver2 second run Processor: AMD EPYC 7502P 32-Core @ 2.50GHz (64 Cores), Motherboard: MFG-NOT-FILLED HWREV-NOT-FILLED, Chipset: AMD [AMD] Starship/Matisse Root Complex, Memory: 256GB, Disk: 2 x Generic NVMe Device, Graphics: ASPEED
OS: FreeBSD, Kernel: 13.0-RELEASE (x86_64), Compiler: Clang 11.0.1, File-System: zfs, Screen Resolution: 800x600
Java Notes: OpenJDK Runtime Environment (build 11.0.10+9-1)Python Notes: Python 3.7.10
Testing initiated at 17 April 2021 11:29 by user ocochard.
FreeBSD commit 1ff41cad716adeba0d408652c92c81e59e3ba316 Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-1)Python Notes: Python 3.9.18
Testing initiated at 26 December 2023 08:00 by user ocochard.
ARCHLEVEL=scalar Processor: AMD EPYC 7502P 32-Core @ 2.50GHz (64 Cores), Motherboard: TYAN S8030GM2NE-NFX, Chipset: AMD [AMD] Starship/Matisse Root Complex, Memory: 256GB, Disk: 2 x Generic NVMe Device, Graphics: ASPEED
OS: FreeBSD, Kernel: 15.0-CURRENT (x86_64), Display Server: X Server 1.20.11, Compiler: Clang 17.0.6, File-System: zfs, Screen Resolution: 800x600
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-1)Python Notes: Python 3.9.18
Testing initiated at 26 December 2023 17:39 by user ocochard.