AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and NAVI31 45GB on Pop 22.04 via the Phoronix Test Suite.
v6.6.6 Stock Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32 GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: NAVI31 45GB (1760/1124MHz), Audio: AMD Device 14cc, Monitor: ASUS VP28U, Network: Aquantia Device 14c0 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Pop 22.04, Kernel: 6.6.6-76060606-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.267, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
v6.7 OS: Pop 22.04, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.56), Vulkan: 1.3.267, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 v6.7 v6.6.6 Stock 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.22, N = 3 90.57 48.27
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency v6.7 v6.6.6 Stock 8 16 24 32 40 SE +/- 1.45, N = 12 SE +/- 1.47, N = 12 31.97 34.69 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write v6.7 v6.6.6 Stock 7K 14K 21K 28K 35K SE +/- 1238.01, N = 12 SE +/- 1131.34, N = 12 31899 29356 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Quicksilver Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CTS2 v6.7 v6.6.6 Stock 5M 10M 15M 20M 25M SE +/- 38441.88, N = 3 SE +/- 32829.53, N = 3 23876667 23326667 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P2 v6.7 v6.6.6 Stock 5M 10M 15M 20M 25M SE +/- 14529.66, N = 3 SE +/- 34641.02, N = 3 22036667 22070000 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU v6.7 v6.6.6 Stock 50 100 150 200 250 SE +/- 0.26, N = 3 SE +/- 6.32, N = 15 169.15 249.98 MIN: 69.93 / MAX: 221.3 MIN: 40.51 / MAX: 811.65 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU v6.7 v6.6.6 Stock 40 80 120 160 200 SE +/- 0.29, N = 3 SE +/- 2.69, N = 15 188.83 128.73 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU v6.7 v6.6.6 Stock 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.07, N = 15 7.36 8.41 MIN: 3.93 / MAX: 27.08 MIN: 3.83 / MAX: 32.93 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU v6.7 v6.6.6 Stock 900 1800 2700 3600 4500 SE +/- 1.62, N = 3 SE +/- 35.82, N = 15 4254.67 3740.50 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.22, N = 15 20.42 25.08 MIN: 11.89 / MAX: 42.47 MIN: 11.1 / MAX: 59.25 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 300 600 900 1200 1500 SE +/- 1.78, N = 3 SE +/- 12.47, N = 15 1561.17 1271.04 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Barbershop - Compute: CPU-Only v6.7 v6.6.6 Stock 40 80 120 160 200 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 157.37 163.38
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency v6.7 v6.6.6 Stock 0.0578 0.1156 0.1734 0.2312 0.289 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.250 0.257 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only v6.7 v6.6.6 Stock 900K 1800K 2700K 3600K 4500K SE +/- 12389.83, N = 3 SE +/- 19489.13, N = 3 4004740 3886975 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing v6.7 v6.6.6 Stock 3M 6M 9M 12M 15M SE +/- 144991.37, N = 4 SE +/- 134947.32, N = 6 13040244 13467254 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: IO_uring v6.7 v6.6.6 Stock 500K 1000K 1500K 2000K 2500K SE +/- 27934.77, N = 3 SE +/- 109628.32, N = 12 2249186.66 1486513.95 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking v6.7 v6.6.6 Stock 16K 32K 48K 64K 80K SE +/- 80.89, N = 3 SE +/- 621.24, N = 15 74065.57 57664.20 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVL Tree v6.7 v6.6.6 Stock 140 280 420 560 700 SE +/- 0.67, N = 3 SE +/- 9.75, N = 14 635.15 432.83 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache v6.7 v6.6.6 Stock 300K 600K 900K 1200K 1500K SE +/- 23675.00, N = 12 SE +/- 16798.31, N = 3 1271089.94 1268835.49 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 80 160 240 320 400 SE +/- 0.25, N = 3 SE +/- 0.84, N = 3 374.51 383.15 MIN: 321.16 / MAX: 396.63 MIN: 303.22 / MAX: 402.09 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 85.22 83.26 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU v6.7 v6.6.6 Stock 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 1.37, N = 3 90.02 154.91 MIN: 35.71 / MAX: 120.27 MIN: 45.52 / MAX: 256.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU v6.7 v6.6.6 Stock 80 160 240 320 400 SE +/- 1.14, N = 3 SE +/- 1.84, N = 3 354.54 206.02 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 0.981 1.962 2.943 3.924 4.905 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.25 4.36 MIN: 1.95 / MAX: 30.92 MIN: 2.15 / MAX: 27 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 3K 6K 9K 12K 15K SE +/- 19.49, N = 3 SE +/- 10.92, N = 3 14310.25 13960.22 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 0.0878 0.1756 0.2634 0.3512 0.439 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.38 0.39 MIN: 0.18 / MAX: 19.31 MIN: 0.18 / MAX: 26.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 30K 60K 90K 120K 150K SE +/- 316.75, N = 3 SE +/- 181.97, N = 3 117409.53 113672.15 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 8 16 24 32 40 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 34.87 36.90 MIN: 20.35 / MAX: 61.86 MIN: 20.64 / MAX: 64.4 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 400 800 1200 1600 2000 SE +/- 12.63, N = 3 SE +/- 0.64, N = 3 1828.77 1728.88 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 6.21 6.37 MIN: 3.17 / MAX: 23.34 MIN: 3.34 / MAX: 29.67 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 1100 2200 3300 4400 5500 SE +/- 2.97, N = 3 SE +/- 7.01, N = 3 5045.51 4926.83 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 7.50 7.69 MIN: 3.43 / MAX: 27.91 MIN: 3.31 / MAX: 27.53 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU v6.7 v6.6.6 Stock 2K 4K 6K 8K 10K SE +/- 9.48, N = 3 SE +/- 4.62, N = 3 8161.26 7959.97 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Update Random v6.7 v6.6.6 Stock 100K 200K 300K 400K 500K SE +/- 227.10, N = 3 SE +/- 1868.95, N = 3 462917 444650 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read Random Write Random v6.7 v6.6.6 Stock 700K 1400K 2100K 2800K 3500K SE +/- 14008.04, N = 3 SE +/- 10648.79, N = 3 3348632 3101077 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read v6.7 v6.6.6 Stock 100M 200M 300M 400M 500M SE +/- 358460.93, N = 3 SE +/- 2124225.27, N = 3 468123627 453059822 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded v6.7 v6.6.6 Stock 60K 120K 180K 240K 300K SE +/- 922.38, N = 3 SE +/- 1629.93, N = 3 269955.5 266288.4 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 v6.7 v6.6.6 Stock 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.21, N = 3 43.19 46.38 MIN: 40.2 / MAX: 44.13 MIN: 43.06 / MAX: 47.63
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 v6.7 v6.6.6 Stock 11 22 33 44 55 SE +/- 0.20, N = 3 SE +/- 0.23, N = 3 43.29 46.86 MIN: 40.69 / MAX: 44.45 MIN: 43.35 / MAX: 48.24
Quicksilver Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P1 v6.7 v6.6.6 Stock 6M 12M 18M 24M 30M SE +/- 55075.71, N = 3 SE +/- 211266.03, N = 3 28040000 27280000 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pipe v6.7 v6.6.6 Stock 6M 12M 18M 24M 30M SE +/- 293042.41, N = 5 SE +/- 38316.59, N = 3 28997709.97 27118341.21 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating v6.7 v6.6.6 Stock 80K 160K 240K 320K 400K SE +/- 967.86, N = 3 SE +/- 1642.20, N = 3 363397 356395 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc v6.7 v6.6.6 Stock 30M 60M 90M 120M 150M SE +/- 1238064.72, N = 3 SE +/- 917737.04, N = 3 154494959.66 150760521.22 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MMAP v6.7 v6.6.6 Stock 200 400 600 800 1000 SE +/- 0.51, N = 3 SE +/- 0.43, N = 3 1042.84 1037.83 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MEMFD v6.7 v6.6.6 Stock 160 320 480 640 800 SE +/- 0.59, N = 3 SE +/- 0.47, N = 3 733.70 730.62 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: x86_64 RdRand v6.7 v6.6.6 Stock 2K 4K 6K 8K 10K SE +/- 0.18, N = 3 SE +/- 0.34, N = 3 11326.12 11327.06 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pthread v6.7 v6.6.6 Stock 30K 60K 90K 120K 150K SE +/- 142.99, N = 3 SE +/- 452.99, N = 3 125537.87 125130.59 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Zlib v6.7 v6.6.6 Stock 2K 4K 6K 8K 10K SE +/- 39.53, N = 3 SE +/- 15.44, N = 3 8041.12 7881.10 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math v6.7 v6.6.6 Stock 700K 1400K 2100K 2800K 3500K SE +/- 1754.36, N = 3 SE +/- 830.00, N = 3 3320137.02 3230461.50 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: NUMA v6.7 v6.6.6 Stock 200 400 600 800 1000 SE +/- 0.24, N = 3 SE +/- 1.80, N = 3 1068.09 1036.77 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: SENDFILE v6.7 v6.6.6 Stock 200K 400K 600K 800K 1000K SE +/- 4805.80, N = 3 SE +/- 5266.72, N = 3 1002168.85 816781.54 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle v6.7 v6.6.6 Stock 12K 24K 36K 48K 60K SE +/- 7.11, N = 3 SE +/- 29.85, N = 3 57494.65 55853.54 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mixed Scheduler v6.7 v6.6.6 Stock 12K 24K 36K 48K 60K SE +/- 246.60, N = 3 SE +/- 166.89, N = 3 55946.69 53828.66 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Function Call v6.7 v6.6.6 Stock 13K 26K 39K 52K 65K SE +/- 22.20, N = 3 SE +/- 468.48, N = 3 61613.76 59193.78 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Hash v6.7 v6.6.6 Stock 4M 8M 12M 16M 20M SE +/- 3053.25, N = 3 SE +/- 3192.96, N = 3 17551780.14 17033307.63 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing v6.7 v6.6.6 Stock 6M 12M 18M 24M 30M SE +/- 35321.93, N = 3 SE +/- 24713.27, N = 3 26702772.59 26211336.69 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Fused Multiply-Add v6.7 v6.6.6 Stock 15M 30M 45M 60M 75M SE +/- 42666.45, N = 3 SE +/- 21862.72, N = 3 72100478.14 70244822.75 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting v6.7 v6.6.6 Stock 400 800 1200 1600 2000 SE +/- 2.29, N = 3 SE +/- 3.32, N = 3 1953.71 1894.28 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Poll v6.7 v6.6.6 Stock 1.6M 3.2M 4.8M 6.4M 8M SE +/- 7207.98, N = 3 SE +/- 8703.67, N = 3 7499767.91 7394187.64 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Memory Copying v6.7 v6.6.6 Stock 5K 10K 15K 20K 25K SE +/- 57.39, N = 3 SE +/- 17.95, N = 3 24695.64 24004.53 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Semaphores v6.7 v6.6.6 Stock 20M 40M 60M 80M 100M SE +/- 673729.70, N = 3 SE +/- 315601.64, N = 3 100143123.74 93013794.86 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc C String Functions v6.7 v6.6.6 Stock 16M 32M 48M 64M 80M SE +/- 469274.41, N = 3 SE +/- 346470.68, N = 3 75382089.04 73865789.56 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point v6.7 v6.6.6 Stock 50K 100K 150K 200K 250K SE +/- 394.44, N = 3 SE +/- 217.62, N = 3 234027.64 228832.13 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Math v6.7 v6.6.6 Stock 110K 220K 330K 440K 550K SE +/- 258.25, N = 3 SE +/- 152.98, N = 3 499009.49 485001.34 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Crypto v6.7 v6.6.6 Stock 40K 80K 120K 160K 200K SE +/- 161.24, N = 3 SE +/- 260.91, N = 3 188548.45 183183.99 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Floating Point v6.7 v6.6.6 Stock 6K 12K 18K 24K 30K SE +/- 32.79, N = 3 SE +/- 16.76, N = 3 27569.66 26744.36 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex v6.7 v6.6.6 Stock 5M 10M 15M 20M 25M SE +/- 9399.14, N = 3 SE +/- 17585.48, N = 3 24181954.44 23109393.80 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix Math v6.7 v6.6.6 Stock 80K 160K 240K 320K 400K SE +/- 272.90, N = 3 SE +/- 637.54, N = 3 396041.26 385258.18 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Stress v6.7 v6.6.6 Stock 40K 80K 120K 160K 200K SE +/- 511.22, N = 3 SE +/- 1715.48, N = 3 194017.28 185200.38 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 v6.7 v6.6.6 Stock 13 26 39 52 65 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 52.69 57.32 MIN: 48.03 / MAX: 54.61 MIN: 52.6 / MAX: 59.56
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K v6.7 v6.6.6 Stock 3 6 9 12 15 SE +/- 0.044, N = 3 SE +/- 0.052, N = 3 9.208 9.081 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded v6.7 v6.6.6 Stock 900 1800 2700 3600 4500 SE +/- 17.53, N = 3 SE +/- 23.44, N = 3 4410.4 4354.9 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: ResNet-50 v6.7 v6.6.6 Stock 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 7.12 7.19
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: BMW27 - Compute: CPU-Only v6.7 v6.6.6 Stock 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 17.38 17.76
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K v6.7 v6.6.6 Stock 20 40 60 80 100 SE +/- 0.69, N = 3 SE +/- 0.57, N = 3 90.36 88.83 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K v6.7 v6.6.6 Stock 40 80 120 160 200 SE +/- 0.60, N = 3 SE +/- 1.21, N = 3 186.25 183.37 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K v6.7 v6.6.6 Stock 40 80 120 160 200 SE +/- 0.83, N = 3 SE +/- 0.41, N = 3 192.31 188.72 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
v6.6.6 Stock Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32 GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: NAVI31 45GB (1760/1124MHz), Audio: AMD Device 14cc, Monitor: ASUS VP28U, Network: Aquantia Device 14c0 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Pop 22.04, Kernel: 6.6.6-76060606-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.267, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 January 2024 11:40 by user system76.
v6.7 Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32 GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: NAVI31 45GB (1760/1124MHz), Audio: AMD Device 14cc, Monitor: ASUS VP28U, Network: Aquantia Device 14c0 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Pop 22.04, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.56), Vulkan: 1.3.267, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 January 2024 04:47 by user system76.