AMD Ryzen Threadripper 3990X 64-Core testing with a System76 Thelio Major (F4c Z5 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Pop 20.04 via the Phoronix Test Suite.
Threadripper 3990X Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: LG Ultra HD, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 20.04, Kernel: 5.4.0-7634-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: snd_usb_audio.ignore_ctl_error=1Compiler Notes: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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-arch=skylake --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=skylake --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,noatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security 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
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Threadripper 3990X 300 600 900 1200 1500 SE +/- 14.70, N = 3 1570.64 MIN: 1132.23 / MAX: 1629.16 1. (CC) gcc options: -O2 -lm -pthread -lmpi
PostMark This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Threadripper 3990X 1600 3200 4800 6400 8000 SE +/- 74.33, N = 3 7501 1. (CC) gcc options: -O3
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 512 MiB Threadripper 3990X 4K 8K 12K 16K 20K SE +/- 14.84, N = 3 18371.13 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 1024 MiB Threadripper 3990X 4K 8K 12K 16K 20K SE +/- 69.93, N = 3 18257.78 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB Threadripper 3990X 4K 8K 12K 16K 20K SE +/- 10.23, N = 3 18355.39 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 8192 MiB Threadripper 3990X 4K 8K 12K 16K 20K SE +/- 78.26, N = 3 18249.45 1. (CC) gcc 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 Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 26.63, N = 3 10219.79 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 3.40, N = 3 10584.60 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 4.03, N = 3 10534.18 1. (CC) gcc 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 Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 21.40, N = 3 10568.97 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 20.15, N = 3 10586.30 1. (CC) gcc options: -O3 -march=native
pmbench Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 50% Threadripper 3990X 0.0192 0.0384 0.0576 0.0768 0.096 SE +/- 0.0003, N = 3 0.0852 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 50% Threadripper 3990X 0.0222 0.0444 0.0666 0.0888 0.111 SE +/- 0.0005, N = 3 0.0987 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 50% Threadripper 3990X 0.0218 0.0436 0.0654 0.0872 0.109 SE +/- 0.0001, N = 3 0.0970 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 50% Threadripper 3990X 0.0223 0.0446 0.0669 0.0892 0.1115 SE +/- 0.0001, N = 3 0.0993 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 50% Threadripper 3990X 0.0217 0.0434 0.0651 0.0868 0.1085 SE +/- 0.0001, N = 3 0.0965 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 32 - Read-Write Ratio: 50% Threadripper 3990X 0.022 0.044 0.066 0.088 0.11 SE +/- 0.0003, N = 3 0.0978 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 64 - Read-Write Ratio: 50% Threadripper 3990X 0.021 0.042 0.063 0.084 0.105 SE +/- 0.0002, N = 3 0.0934 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 128 - Read-Write Ratio: 50% Threadripper 3990X 0.0295 0.059 0.0885 0.118 0.1475 SE +/- 0.0005, N = 3 0.1313 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0082 0.0164 0.0246 0.0328 0.041 SE +/- 0.0001, N = 3 0.0366 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0083 0.0166 0.0249 0.0332 0.0415 SE +/- 0.0001, N = 3 0.0369 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0083 0.0166 0.0249 0.0332 0.0415 SE +/- 0.0001, N = 3 0.0368 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0084 0.0168 0.0252 0.0336 0.042 SE +/- 0.0000, N = 3 0.0372 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0108 0.0216 0.0324 0.0432 0.054 SE +/- 0.0001, N = 3 0.0479 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0087 0.0174 0.0261 0.0348 0.0435 SE +/- 0.0001, N = 3 0.0385 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0116 0.0232 0.0348 0.0464 0.058 SE +/- 0.0012, N = 15 0.0517 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 32 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0088 0.0176 0.0264 0.0352 0.044 SE +/- 0.0001, N = 3 0.0391 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0114 0.0228 0.0342 0.0456 0.057 SE +/- 0.0002, N = 3 0.0506 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 64 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0088 0.0176 0.0264 0.0352 0.044 SE +/- 0.0009, N = 15 0.0390 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0112 0.0224 0.0336 0.0448 0.056 SE +/- 0.0001, N = 3 0.0499 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 128 - Read-Write Ratio: 100% Reads Threadripper 3990X 0.0122 0.0244 0.0366 0.0488 0.061 SE +/- 0.0010, N = 15 0.0540 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.011 0.022 0.033 0.044 0.055 SE +/- 0.0001, N = 3 0.0489 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 32 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0111 0.0222 0.0333 0.0444 0.0555 SE +/- 0.0000, N = 3 0.0492 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 64 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0134 0.0268 0.0402 0.0536 0.067 SE +/- 0.0004, N = 3 0.0596 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 128 - Read-Write Ratio: 100% Writes Threadripper 3990X 0.0272 0.0544 0.0816 0.1088 0.136 SE +/- 0.0014, N = 3 0.1209 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0245 0.049 0.0735 0.098 0.1225 SE +/- 0.0004, N = 3 0.1091 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.029 0.058 0.087 0.116 0.145 SE +/- 0.0018, N = 4 0.1289 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0283 0.0566 0.0849 0.1132 0.1415 SE +/- 0.0001, N = 3 0.1257 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0288 0.0576 0.0864 0.1152 0.144 SE +/- 0.0009, N = 3 0.1281 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0281 0.0562 0.0843 0.1124 0.1405 SE +/- 0.0001, N = 3 0.1251 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 32 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0288 0.0576 0.0864 0.1152 0.144 SE +/- 0.0007, N = 3 0.1282 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 64 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0283 0.0566 0.0849 0.1132 0.1415 SE +/- 0.0022, N = 3 0.1259 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 128 - Read-Write Ratio: 80% Reads 20% Writes Threadripper 3990X 0.0331 0.0662 0.0993 0.1324 0.1655 SE +/- 0.0021, N = 3 0.1470 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -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 Threadripper 3990X 5 10 15 20 25 SE +/- 0.24, N = 3 19.39 MIN: 10.32 / MAX: 24.29
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 8 Threadripper 3990X 5 10 15 20 25 SE +/- 0.19, N = 3 19.88 MIN: 10.36 / MAX: 24.5
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 32 Threadripper 3990X 5 10 15 20 25 SE +/- 0.23, N = 3 19.85 MIN: 10.32 / MAX: 24.06
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64 Threadripper 3990X 5 10 15 20 25 SE +/- 0.04, N = 3 19.55 MIN: 10.33 / MAX: 24.88
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 8 Threadripper 3990X 20K 40K 60K 80K 100K SE +/- 271.63, N = 3 100096.89 MIN: 98150 / MAX: 102650
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8 Threadripper 3990X 20K 40K 60K 80K 100K SE +/- 177.35, N = 3 101855.11 MIN: 100850 / MAX: 103070
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 Threadripper 3990X 200 400 600 800 1000 SE +/- 1.90, N = 3 846.09 MIN: 830.46 / MAX: 867.2
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 8 Threadripper 3990X 400 800 1200 1600 2000 SE +/- 4.75, N = 3 2041.93 MIN: 1980 / MAX: 2100
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 32 Threadripper 3990X 30K 60K 90K 120K 150K SE +/- 318.55, N = 3 132061 MIN: 130500 / MAX: 133550
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64 Threadripper 3990X 30K 60K 90K 120K 150K SE +/- 163.34, N = 3 130718.22 MIN: 129480 / MAX: 131930
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32 Threadripper 3990X 20K 40K 60K 80K 100K SE +/- 37.39, N = 3 112495.33 MIN: 112030 / MAX: 113830
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64 Threadripper 3990X 20K 40K 60K 80K 100K SE +/- 202.99, N = 3 113867.11 MIN: 112090 / MAX: 115040
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 32 Threadripper 3990X 400 800 1200 1600 2000 SE +/- 8.27, N = 3 1753.68 MIN: 1690 / MAX: 1900
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 64 Threadripper 3990X 400 800 1200 1600 2000 SE +/- 18.57, N = 3 2076.11 MIN: 1920 / MAX: 2480
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 Threadripper 3990X 1300 2600 3900 5200 6500 SE +/- 391.11, N = 15 6106
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 8 Threadripper 3990X 11K 22K 33K 44K 55K SE +/- 358.76, N = 3 49453
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 32 Threadripper 3990X 6K 12K 18K 24K 30K SE +/- 380.80, N = 3 28887
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 64 Threadripper 3990X 8K 16K 24K 32K 40K SE +/- 124.14, N = 3 38023
iPerf iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 1 Threadripper 3990X 20 40 60 80 100 100 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 1 Threadripper 3990X 200 400 600 800 1000 1000 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 32 Threadripper 3990X 700 1400 2100 2800 3500 3200 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 64 Threadripper 3990X 1400 2800 4200 5600 7000 6400 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32 Threadripper 3990X 7K 14K 21K 28K 35K 31999 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 64 Threadripper 3990X 9K 18K 27K 36K 45K SE +/- 359.22, N = 3 42331 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1 Threadripper 3990X 11K 22K 33K 44K 55K SE +/- 672.43, N = 4 50522 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1 Threadripper 3990X 0.2363 0.4726 0.7089 0.9452 1.1815 SE +/- 0.00, N = 3 1.05 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32 Threadripper 3990X 10K 20K 30K 40K 50K SE +/- 525.16, N = 3 46393 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64 Threadripper 3990X 10K 20K 30K 40K 50K SE +/- 630.92, N = 3 45934 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32 Threadripper 3990X 8 16 24 32 40 SE +/- 0.00, N = 3 33.6 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64 Threadripper 3990X 15 30 45 60 75 SE +/- 0.00, N = 3 67.1 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
WireGuard + Linux Networking Stack Stress Test This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test Threadripper 3990X 50 100 150 200 250 SE +/- 1.13, N = 3 239.33
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 256 Threadripper 3990X 700K 1400K 2100K 2800K 3500K SE +/- 8866.19, N = 3 3409419
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 512 Threadripper 3990X 600K 1200K 1800K 2400K 3000K SE +/- 6754.24, N = 3 3014960
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 1024 Threadripper 3990X 500K 1000K 1500K 2000K 2500K SE +/- 17218.74, N = 3 2506921
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 2048 Threadripper 3990X 400K 800K 1200K 1600K 2000K SE +/- 26981.41, N = 3 1889720
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 4096 Threadripper 3990X 300K 600K 900K 1200K 1500K SE +/- 8418.52, N = 3 1386353
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 128 Threadripper 3990X 700K 1400K 2100K 2800K 3500K SE +/- 84752.55, N = 12 3431694
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 256 Threadripper 3990X 600K 1200K 1800K 2400K 3000K SE +/- 53158.54, N = 15 2889002
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 512 Threadripper 3990X 800K 1600K 2400K 3200K 4000K SE +/- 75101.12, N = 15 3588883
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 1024 Threadripper 3990X 800K 1600K 2400K 3200K 4000K SE +/- 36971.31, N = 3 3749223
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 2048 Threadripper 3990X 600K 1200K 1800K 2400K 3000K SE +/- 27155.49, N = 3 2728090
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 4096 Threadripper 3990X 500K 1000K 1500K 2000K 2500K SE +/- 21721.79, N = 3 2234351
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 128 Threadripper 3990X 700K 1400K 2100K 2800K 3500K SE +/- 39729.18, N = 3 3064879
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 256 Threadripper 3990X 600K 1200K 1800K 2400K 3000K SE +/- 21511.77, N = 3 2861822
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 512 Threadripper 3990X 700K 1400K 2100K 2800K 3500K SE +/- 45311.47, N = 3 3125167
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 1024 Threadripper 3990X 600K 1200K 1800K 2400K 3000K SE +/- 30842.43, N = 3 2873231
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 2048 Threadripper 3990X 500K 1000K 1500K 2000K 2500K SE +/- 10712.90, N = 3 2563151
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 4096 Threadripper 3990X 500K 1000K 1500K 2000K 2500K SE +/- 10785.89, N = 3 2105078
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 128 Threadripper 3990X 300K 600K 900K 1200K 1500K SE +/- 69565.92, N = 15 1557612
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 256 Threadripper 3990X 400K 800K 1200K 1600K 2000K SE +/- 24634.89, N = 3 1850007
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 512 Threadripper 3990X 400K 800K 1200K 1600K 2000K SE +/- 22255.56, N = 15 1754429
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 1024 Threadripper 3990X 400K 800K 1200K 1600K 2000K SE +/- 25489.88, N = 5 1942012
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 2048 Threadripper 3990X 300K 600K 900K 1200K 1500K SE +/- 4713.78, N = 3 1207814
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 4096 Threadripper 3990X 200K 400K 600K 800K 1000K SE +/- 3723.03, N = 3 924709
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Keyed Algorithms Threadripper 3990X 150 300 450 600 750 SE +/- 0.41, N = 3 695.04 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Unkeyed Algorithms Threadripper 3990X 90 180 270 360 450 SE +/- 0.45, N = 3 396.17 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Integer + Elliptic Curve Public Key Algorithms Threadripper 3990X 1100 2200 3300 4400 5500 SE +/- 0.61, N = 3 5278.60 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Decompression Threadripper 3990X 30 60 90 120 150 125 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Compression Threadripper 3990X 120 240 360 480 600 SE +/- 0.67, N = 3 535 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Decompression Threadripper 3990X 300 600 900 1200 1500 SE +/- 2.19, N = 3 1393 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Compression Threadripper 3990X 20 40 60 80 100 SE +/- 0.67, N = 3 106 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Decompression Threadripper 3990X 300 600 900 1200 1500 SE +/- 0.67, N = 3 1524 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Compression Threadripper 3990X 30 60 90 120 150 SE +/- 0.88, N = 3 113 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Decompression Threadripper 3990X 100 200 300 400 500 481 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Compression Threadripper 3990X 120 240 360 480 600 SE +/- 1.15, N = 3 547 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Decompression Threadripper 3990X 130 260 390 520 650 SE +/- 1.20, N = 3 610 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Compression Threadripper 3990X 50 100 150 200 250 SE +/- 0.88, N = 3 223 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Decompression Threadripper 3990X 160 320 480 640 800 720 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Compression Threadripper 3990X 60 120 180 240 300 SE +/- 0.58, N = 3 255 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Decompression Threadripper 3990X 300 600 900 1200 1500 SE +/- 0.33, N = 3 1212 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
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 4096 Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 26.11, N = 3 9899.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Threadripper 3990X 1500 3000 4500 6000 7500 SE +/- 71.88, N = 3 6822.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 Threadripper 3990X 12K 24K 36K 48K 60K SE +/- 868.09, N = 3 54555 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Threadripper 3990X 4K 8K 12K 16K 20K SE +/- 151.84, N = 3 18125 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
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 Threadripper 3990X 20 40 60 80 100 SE +/- 1.18, N = 5 95.38 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
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: chacha Threadripper 3990X 200 400 600 800 1000 SE +/- 0.75, N = 3 963.23 MIN: 491.1 / MAX: 2628.67 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: sha512 Threadripper 3990X 130 260 390 520 650 SE +/- 8.04, N = 5 606.25 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: poly1305-aes Threadripper 3990X 600 1200 1800 2400 3000 SE +/- 0.30, N = 3 2644.90 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
SciMark This test runs the ANSI C 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 test 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 SciMark 2.0 Computational Test: Composite Threadripper 3990X 140 280 420 560 700 SE +/- 3.93, N = 3 648.65 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo Threadripper 3990X 30 60 90 120 150 SE +/- 0.36, N = 3 154.31 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform Threadripper 3990X 70 140 210 280 350 SE +/- 3.94, N = 3 318.74 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply Threadripper 3990X 120 240 360 480 600 SE +/- 7.90, N = 3 563.65 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization Threadripper 3990X 200 400 600 800 1000 SE +/- 15.00, N = 3 944.86 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Threadripper 3990X 300 600 900 1200 1500 SE +/- 0.47, N = 3 1261.66 1. (CC) gcc options: -lm
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: AES-256 Threadripper 3990X 1200 2400 3600 4800 6000 SE +/- 10.28, N = 3 5732.82 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Twofish Threadripper 3990X 80 160 240 320 400 SE +/- 0.15, N = 3 384.46 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Blowfish Threadripper 3990X 100 200 300 400 500 SE +/- 0.09, N = 3 469.85 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: CAST-256 Threadripper 3990X 30 60 90 120 150 SE +/- 0.06, N = 3 151.03 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Threadripper 3990X 500 1000 1500 2000 2500 2276 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Threadripper 3990X 150 300 450 600 750 SE +/- 0.33, N = 3 684 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Threadripper 3990X 200 400 600 800 1000 SE +/- 5.61, N = 3 780 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Threadripper 3990X 200 400 600 800 1000 SE +/- 3.18, N = 3 1129 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Threadripper 3990X 400 800 1200 1600 2000 SE +/- 9.29, N = 3 1673 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Threadripper 3990X 200 400 600 800 1000 SE +/- 2.03, N = 3 849 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Threadripper 3990X 300 600 900 1200 1500 SE +/- 5.78, N = 3 1447 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 4K Threadripper 3990X 80 160 240 320 400 SE +/- 1.65, N = 3 373.11 MIN: 137.3 / MAX: 412.17 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 1080p Threadripper 3990X 200 400 600 800 1000 SE +/- 3.39, N = 3 888.57 MIN: 299.83 / MAX: 1007.83 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p 10-bit Threadripper 3990X 50 100 150 200 250 SE +/- 0.49, N = 3 207.21 MIN: 147.69 / MAX: 332.83 1. (CC) gcc options: -pthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Realtime Threadripper 3990X 0.45 0.9 1.35 1.8 2.25 2 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Threadripper 3990X 0.576 1.152 1.728 2.304 2.88 SE +/- 0.01, N = 3 2.56 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 5 Two-Pass Threadripper 3990X 0.7808 1.5616 2.3424 3.1232 3.904 SE +/- 0.01, N = 3 3.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Threadripper 3990X 4 8 12 16 20 SE +/- 0.09, N = 3 18.17 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Threadripper 3990X 0.8933 1.7866 2.6799 3.5732 4.4665 SE +/- 0.01, N = 3 3.97 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Threadripper 3990X 8 16 24 32 40 SE +/- 0.06, N = 3 35.43 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-AV1 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 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-AV1 0.8 Encoder Mode: Enc Mode 0 - Input: 1080p Threadripper 3990X 0.0302 0.0604 0.0906 0.1208 0.151 SE +/- 0.000, N = 3 0.134 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p Threadripper 3990X 3 6 9 12 15 SE +/- 0.122, N = 3 9.944 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Threadripper 3990X 20 40 60 80 100 SE +/- 0.21, N = 3 100.08 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 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-HEVC 1.4.1 1080p 8-bit YUV To HEVC Video Encode Threadripper 3990X 50 100 150 200 250 SE +/- 0.69, N = 3 211.92 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
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 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p Threadripper 3990X 80 160 240 320 400 SE +/- 1.44, N = 3 389.12 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Threadripper 3990X 90 180 270 360 450 SE +/- 1.61, N = 3 397.10 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Threadripper 3990X 70 140 210 280 350 SE +/- 1.78, N = 3 333.66 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
x264 This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Threadripper 3990X 40 80 120 160 200 SE +/- 0.72, N = 3 189.32 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
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 Threadripper 3990X 30M 60M 90M 120M 150M SE +/- 1251533.54, N = 13 150946128 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Threadripper 3990X 3 6 9 12 15 SE +/- 0.047, N = 3 9.032 1. (CC) gcc options: -lm -lpthread -O3
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair Threadripper 3990X 1.3201 2.6402 3.9603 5.2804 6.6005 SE +/- 0.01218, N = 3 5.86701 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Threadripper 3990X 4 8 12 16 20 SE +/- 0.00, N = 3 18.16 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential Threadripper 3990X 0.5239 1.0478 1.5717 2.0956 2.6195 SE +/- 0.00305, N = 3 2.32841 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic Threadripper 3990X 0.7894 1.5788 2.3682 3.1576 3.947 SE +/- 0.00243, N = 3 3.50853 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
Open Porous Media This is a test of Open Porous Media, a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile depends upon MPI/Flow already being installed on the system. Install instructions at https://opm-project.org/?page_id=36. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 1 Threadripper 3990X 70 140 210 280 350 SE +/- 1.38, N = 3 333.81 1. flow 2020.04
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Thread Threadripper 3990X 0.7722 1.5444 2.3166 3.0888 3.861 SE +/- 0.049, N = 3 3.432 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Thread Threadripper 3990X 0.9245 1.849 2.7735 3.698 4.6225 SE +/- 0.021, N = 3 4.109 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread Threadripper 3990X 2 4 6 8 10 SE +/- 0.047, N = 3 6.157 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Process Threadripper 3990X 0.6399 1.2798 1.9197 2.5596 3.1995 SE +/- 0.088, N = 15 2.844 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Threadripper 3990X 3 6 9 12 15 SE +/- 0.10, N = 3 12.35 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Process Threadripper 3990X 0.7522 1.5044 2.2566 3.0088 3.761 SE +/- 0.044, N = 3 3.343 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Process Threadripper 3990X 0.8861 1.7722 2.6583 3.5444 4.4305 SE +/- 0.010, N = 3 3.938 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process Threadripper 3990X 1.3291 2.6582 3.9873 5.3164 6.6455 SE +/- 0.017, N = 3 5.907 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Threadripper 3990X 3 6 9 12 15 SE +/- 0.05, N = 3 11.76 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Threadripper 3990X 6 12 18 24 30 SE +/- 0.01, N = 3 23.02 1. (CC) gcc options: -lpthread
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 Threadripper 3990X 3K 6K 9K 12K 15K SE +/- 39.46, N = 3 15157.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Threadripper 3990X 0.5175 1.035 1.5525 2.07 2.5875 SE +/- 0.03, N = 3 2.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Threadripper 3990X 1300 2600 3900 5200 6500 SE +/- 12.33, N = 3 5982.02 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Threadripper 3990X 6 12 18 24 30 SE +/- 0.03, N = 3 23.1 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Threadripper 3990X 130 260 390 520 650 SE +/- 0.41, N = 3 613.25 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill Threadripper 3990X 6 12 18 24 30 SE +/- 0.06, N = 3 23.1 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill Threadripper 3990X 130 260 390 520 650 SE +/- 1.58, N = 3 611.54 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read Threadripper 3990X 20 40 60 80 100 SE +/- 0.10, N = 3 110.52 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random Threadripper 3990X 40 80 120 160 200 SE +/- 0.02, N = 3 169.99 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete Threadripper 3990X 130 260 390 520 650 SE +/- 0.63, N = 3 601.91 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill Threadripper 3990X 6 12 18 24 30 SE +/- 0.34, N = 4 24.2 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill Threadripper 3990X 130 260 390 520 650 SE +/- 8.06, N = 4 584.82 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 Threadripper 3990X 2 4 6 8 10 SE +/- 0.012, N = 3 6.468 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 Threadripper 3990X 4 8 12 16 20 SE +/- 0.04, N = 3 14.55 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Hugin Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Threadripper 3990X 10 20 30 40 50 SE +/- 0.19, N = 3 45.45
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock spinlock Threadripper 3990X 10 20 30 40 50 SE +/- 0.03, N = 3 43.2 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock std::mutex Threadripper 3990X 4 8 12 16 20 SE +/- 0.00, N = 3 16.4 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock std::mutex Threadripper 3990X 5 10 15 20 25 SE +/- 0.07, N = 3 19.7 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Semaphore Release And Acquire Threadripper 3990X 3 6 9 12 15 SE +/- 0.06, N = 3 11.9 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock spinlock_amd Threadripper 3990X 10 20 30 40 50 SE +/- 0.06, N = 3 45.3 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock pthread_mutex Threadripper 3990X 3 6 9 12 15 SE +/- 0.03, N = 3 11.0 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock ticket_spinlock Threadripper 3990X 7 14 21 28 35 SE +/- 0.03, N = 3 30.3 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA Threadripper 3990X 300 600 900 1200 1500 SE +/- 8.16, N = 3 1460.59 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD Threadripper 3990X 300 600 900 1200 1500 SE +/- 3.44, N = 3 1353.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Threadripper 3990X 110K 220K 330K 440K 550K SE +/- 484.89, N = 3 495432.6 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Threadripper 3990X 3K 6K 9K 12K 15K SE +/- 31.41, N = 3 14721.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Threadripper 3990X 300M 600M 900M 1200M 1500M SE +/- 8262060.93, N = 3 1460773913.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking Threadripper 3990X 13K 26K 39K 52K 65K SE +/- 241.73, N = 3 60696.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Threadripper 3990X 200K 400K 600K 800K 1000K SE +/- 5007.79, N = 3 949686.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Threadripper 3990X 16 32 48 64 80 SE +/- 1.23, N = 15 70.26 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Threadripper 3990X 5K 10K 15K 20K 25K SE +/- 73.19, N = 3 23368.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores Threadripper 3990X 2M 4M 6M 8M 10M SE +/- 11474.50, N = 3 10722588.88 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math Threadripper 3990X 50K 100K 150K 200K 250K SE +/- 954.98, N = 3 230751.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math Threadripper 3990X 100K 200K 300K 400K 500K SE +/- 1278.06, N = 3 473591.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Threadripper 3990X 2K 4K 6K 8K 10K SE +/- 27.54, N = 3 8257.30 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Threadripper 3990X 5K 10K 15K 20K 25K SE +/- 105.85, N = 3 24136.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Threadripper 3990X 6M 12M 18M 24M 30M SE +/- 769564.30, N = 15 28982280.72 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Threadripper 3990X 800K 1600K 2400K 3200K 4000K SE +/- 16774.19, N = 3 3561879.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Threadripper 3990X 200 400 600 800 1000 SE +/- 5.80, N = 3 778.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Threadripper 3990X 7M 14M 21M 28M 35M SE +/- 471967.42, N = 4 32343962.39 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU Threadripper 3990X 8 16 24 32 40 SE +/- 0.26, N = 3 32.32
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU Threadripper 3990X 200 400 600 800 1000 SE +/- 5.76, N = 3 816.51
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU Threadripper 3990X 4 8 12 16 20 SE +/- 0.04, N = 3 14.96
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU Threadripper 3990X 2 4 6 8 10 SE +/- 0.05, N = 3 6.34
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU Threadripper 3990X 0.7785 1.557 2.3355 3.114 3.8925 SE +/- 0.01, N = 3 3.46
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU Threadripper 3990X 3 6 9 12 15 SE +/- 0.03, N = 3 11.23
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU Threadripper 3990X 0.2858 0.5716 0.8574 1.1432 1.429 SE +/- 0.00, N = 3 1.27
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Threadripper 3990X 60M 120M 180M 240M 300M SE +/- 2212152.30, N = 15 269407550 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 Threadripper 3990X 100K 200K 300K 400K 500K SE +/- 776.78, N = 3 448660 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 Threadripper 3990X 5K 10K 15K 20K 25K SE +/- 65.24, N = 3 23076 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 Threadripper 3990X 2M 4M 6M 8M 10M SE +/- 22196.42, N = 3 7889991 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
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 Threadripper 3990X 9K 18K 27K 36K 45K SE +/- 401.80, N = 3 41680.36 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 Threadripper 3990X 7K 14K 21K 28K 35K SE +/- 94.29, N = 3 32120.29 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Threadripper 3990X 11 22 33 44 55 SE +/- 0.06, N = 3 48.17 1. git version 2.25.1
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 Threadripper 3990X 3 6 9 12 15 SE +/- 0.12, N = 3 12.11 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Threadripper 3990X 6 12 18 24 30 SE +/- 0.12, N = 3 24.87 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Threadripper 3990X 13 26 39 52 65 SE +/- 0.16, N = 3 57.88 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Threadripper 3990X 11 22 33 44 55 SE +/- 0.14, N = 3 46.98 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Threadripper 3990X 20 40 60 80 100 SE +/- 0.55, N = 3 82.78 1. (CC) gcc options: -lm
Threadripper 3990X Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: LG Ultra HD, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 20.04, Kernel: 5.4.0-7634-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: snd_usb_audio.ignore_ctl_error=1Compiler Notes: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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-arch=skylake --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=skylake --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,noatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security 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 13 August 2020 14:43 by user phoronix.