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.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2401208-NE-SYSTEM76T58 System76 Thelio Kernels - Phoronix Test Suite System76 Thelio Kernels 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.
HTML result view exported from: https://openbenchmarking.org/result/2401208-NE-SYSTEM76T58&grs&sro .
System76 Thelio Kernels Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution v6.6.6 Stock v6.7 AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads) System76 Thelio Major (FA Z5 BIOS) AMD Device 14a4 4 x 32 GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2 1000GB CT1000T700SSD5 NAVI31 45GB (1760/1124MHz) AMD Device 14cc ASUS VP28U Aquantia Device 14c0 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411 Pop 22.04 6.6.6-76060606-generic (x86_64) GNOME Shell 42.5 X Server 1.21.1.4 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54) 1.3.267 GCC 11.4.0 ext4 3840x2160 6.7.0-060700-generic (x86_64) 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.56) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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 -v Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105 Python Details - Python 3.10.12 Security Details - 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
System76 Thelio Kernels tensorflow: CPU - 512 - ResNet-50 openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU stress-ng: Forking build-llvm: Ninja openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU stress-ng: SENDFILE build-linux-kernel: allmodconfig openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU stress-ng: Cloning pytorch: CPU - 1 - ResNet-50 pytorch: CPU - 16 - ResNet-50 speedb: Read Rand Write Rand stress-ng: Semaphores pytorch: CPU - 512 - ResNet-50 stress-ng: Pipe openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU stress-ng: Context Switching stress-ng: CPU Stress stress-ng: Mutex speedb: Update Rand stress-ng: Function Call stress-ng: Mixed Scheduler blender: Barbershop - CPU-Only speedb: Rand Read openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU speedb: Read While Writing stress-ng: Glibc Qsort Data Sorting stress-ng: Floating Point stress-ng: Hash pgbench: 100 - 1000 - Read Only stress-ng: NUMA stress-ng: Vector Shuffle stress-ng: Crypto stress-ng: Vector Math stress-ng: Memory Copying pgbench: 100 - 1000 - Read Only - Average Latency stress-ng: Matrix Math quicksilver: CORAL2 P1 stress-ng: Wide Vector Math build-nodejs: Time To Compile stress-ng: Fused Multiply-Add openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU compress-7zip: Decompression Rating openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU stress-ng: Malloc openvino: Vehicle Detection FP16-INT8 - CPU quicksilver: CTS2 openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU stress-ng: Vector Floating Point blender: BMW27 - CPU-Only stress-ng: Glibc C String Functions stress-ng: Zlib compress-7zip: Compression Rating lczero: Eigen svt-av1: Preset 13 - Bosphorus 4K stress-ng: System V Message Passing svt-av1: Preset 8 - Bosphorus 4K build-php: Time To Compile svt-av1: Preset 12 - Bosphorus 4K stress-ng: AVX-512 VNNI stress-ng: Poll svt-av1: Preset 4 - Bosphorus 4K quantlib: Multi-Threaded quantlib: Single-Threaded build-linux-kernel: defconfig encode-flac: WAV To FLAC rav1e: 1 tensorflow: CPU - 1 - ResNet-50 rav1e: 5 build-llvm: Unix Makefiles stress-ng: MMAP stress-ng: MEMFD rav1e: 6 stress-ng: Pthread y-cruncher: 500M y-cruncher: 1B rav1e: 10 quicksilver: CORAL2 P2 stress-ng: Atomic stress-ng: x86_64 RdRand openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU stress-ng: Matrix 3D Math stress-ng: CPU Cache stress-ng: IO_uring stress-ng: AVL Tree stress-ng: Futex pgbench: 100 - 1000 - Read Write - Average Latency pgbench: 100 - 1000 - Read Write v6.6.6 Stock v6.7 48.27 206.02 154.91 57664.20 162.961 1271.04 25.08 816781.54 250.165 8.41 3740.50 5992.45 57.32 46.86 3101077 93013794.86 46.38 27118341.21 36.90 1728.88 20153249.56 185200.38 23109393.80 444650 59193.78 53828.66 163.38 453059822 113672.15 13467254 1894.28 26744.36 17033307.63 3886975 1036.77 55853.54 183183.99 485001.34 24004.53 0.257 385258.18 27280000 3230461.50 121.214 70244822.75 0.39 4.36 6.37 556761 7.69 7959.97 13960.22 150760521.22 4926.83 23326667 83.26 383.15 228832.13 17.76 73865789.56 7881.10 356395 365 188.716 26211336.69 88.830 27.121 183.372 8158371.94 7394187.64 9.081 266288.4 4354.9 23.905 12.524 1.369 7.19 5.620 181.646 1037.83 730.62 7.370 125130.59 5.463 11.023 17.601 22070000 319.94 11327.06 249.98 128.73 2308.98 1268835.49 1486513.95 432.83 3008388.98 34.689 29356 90.57 354.54 90.02 74065.57 128.920 1561.17 20.42 1002168.85 213.968 7.36 4254.67 6798.10 52.69 43.29 3348632 100143123.74 43.19 28997709.97 34.87 1828.77 21313434.90 194017.28 24181954.44 462917 61613.76 55946.69 157.37 468123627 117409.53 13040244 1953.71 27569.66 17551780.14 4004740 1068.09 57494.65 188548.45 499009.49 24695.64 0.250 396041.26 28040000 3320137.02 118.048 72100478.14 0.38 4.25 6.21 570883 7.50 8161.26 14310.25 154494959.66 5045.51 23876667 85.22 374.51 234027.64 17.38 75382089.04 8041.12 363397 358 192.305 26702772.59 90.360 26.694 186.249 8282501.92 7499767.91 9.208 269955.5 4410.4 23.605 12.369 1.384 7.12 5.672 180.187 1042.84 733.70 7.398 125537.87 5.480 11.056 17.563 22036667 319.64 11326.12 169.15 188.83 4379.78 1271089.94 2249186.66 635.15 3014245.49 31.969 31899 OpenBenchmarking.org
TensorFlow Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 v6.6.6 Stock v6.7 20 40 60 80 100 SE +/- 0.22, N = 3 SE +/- 0.00, N = 3 48.27 90.57
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU v6.6.6 Stock v6.7 80 160 240 320 400 SE +/- 1.84, N = 3 SE +/- 1.14, N = 3 206.02 354.54 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU v6.6.6 Stock v6.7 30 60 90 120 150 SE +/- 1.37, N = 3 SE +/- 0.29, N = 3 154.91 90.02 MIN: 45.52 / MAX: 256.28 MIN: 35.71 / MAX: 120.27 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking v6.6.6 Stock v6.7 16K 32K 48K 64K 80K SE +/- 621.24, N = 15 SE +/- 80.89, N = 3 57664.20 74065.57 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 1.94, N = 3 SE +/- 0.09, N = 3 162.96 128.92
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 300 600 900 1200 1500 SE +/- 12.47, N = 15 SE +/- 1.78, N = 3 1271.04 1561.17 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 6 12 18 24 30 SE +/- 0.22, N = 15 SE +/- 0.02, N = 3 25.08 20.42 MIN: 11.1 / MAX: 59.25 MIN: 11.89 / MAX: 42.47 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: SENDFILE v6.6.6 Stock v6.7 200K 400K 600K 800K 1000K SE +/- 5266.72, N = 3 SE +/- 4805.80, N = 3 816781.54 1002168.85 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: allmodconfig v6.6.6 Stock v6.7 50 100 150 200 250 SE +/- 4.81, N = 9 SE +/- 0.47, N = 3 250.17 213.97
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU v6.6.6 Stock v6.7 2 4 6 8 10 SE +/- 0.07, N = 15 SE +/- 0.00, N = 3 8.41 7.36 MIN: 3.83 / MAX: 32.93 MIN: 3.93 / MAX: 27.08 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU v6.6.6 Stock v6.7 900 1800 2700 3600 4500 SE +/- 35.82, N = 15 SE +/- 1.62, N = 3 3740.50 4254.67 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Cloning OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Cloning v6.6.6 Stock v6.7 1500 3000 4500 6000 7500 SE +/- 50.66, N = 15 SE +/- 1.62, N = 3 5992.45 6798.10 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 v6.6.6 Stock v6.7 13 26 39 52 65 SE +/- 0.26, N = 3 SE +/- 0.25, N = 3 57.32 52.69 MIN: 52.6 / MAX: 59.56 MIN: 48.03 / MAX: 54.61
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 v6.6.6 Stock v6.7 11 22 33 44 55 SE +/- 0.23, N = 3 SE +/- 0.20, N = 3 46.86 43.29 MIN: 43.35 / MAX: 48.24 MIN: 40.69 / MAX: 44.45
Speedb Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read Random Write Random v6.6.6 Stock v6.7 700K 1400K 2100K 2800K 3500K SE +/- 10648.79, N = 3 SE +/- 14008.04, N = 3 3101077 3348632 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Semaphores v6.6.6 Stock v6.7 20M 40M 60M 80M 100M SE +/- 315601.64, N = 3 SE +/- 673729.70, N = 3 93013794.86 100143123.74 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 v6.6.6 Stock v6.7 11 22 33 44 55 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 46.38 43.19 MIN: 43.06 / MAX: 47.63 MIN: 40.2 / MAX: 44.13
Stress-NG Test: Pipe OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pipe v6.6.6 Stock v6.7 6M 12M 18M 24M 30M SE +/- 38316.59, N = 3 SE +/- 293042.41, N = 5 27118341.21 28997709.97 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.24, N = 3 36.90 34.87 MIN: 20.64 / MAX: 64.4 MIN: 20.35 / MAX: 61.86 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 400 800 1200 1600 2000 SE +/- 0.64, N = 3 SE +/- 12.63, N = 3 1728.88 1828.77 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Context Switching v6.6.6 Stock v6.7 5M 10M 15M 20M 25M SE +/- 190129.10, N = 15 SE +/- 193579.79, N = 15 20153249.56 21313434.90 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Stress v6.6.6 Stock v6.7 40K 80K 120K 160K 200K SE +/- 1715.48, N = 3 SE +/- 511.22, N = 3 185200.38 194017.28 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex v6.6.6 Stock v6.7 5M 10M 15M 20M 25M SE +/- 17585.48, N = 3 SE +/- 9399.14, N = 3 23109393.80 24181954.44 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Speedb Test: Update Random OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Update Random v6.6.6 Stock v6.7 100K 200K 300K 400K 500K SE +/- 1868.95, N = 3 SE +/- 227.10, N = 3 444650 462917 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Function Call OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Function Call v6.6.6 Stock v6.7 13K 26K 39K 52K 65K SE +/- 468.48, N = 3 SE +/- 22.20, N = 3 59193.78 61613.76 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Mixed Scheduler OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mixed Scheduler v6.6.6 Stock v6.7 12K 24K 36K 48K 60K SE +/- 166.89, N = 3 SE +/- 246.60, N = 3 53828.66 55946.69 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Barbershop - Compute: CPU-Only v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 163.38 157.37
Speedb Test: Random Read OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read v6.6.6 Stock v6.7 100M 200M 300M 400M 500M SE +/- 2124225.27, N = 3 SE +/- 358460.93, N = 3 453059822 468123627 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 30K 60K 90K 120K 150K SE +/- 181.97, N = 3 SE +/- 316.75, N = 3 113672.15 117409.53 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Speedb Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing v6.6.6 Stock v6.7 3M 6M 9M 12M 15M SE +/- 134947.32, N = 6 SE +/- 144991.37, N = 4 13467254 13040244 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting v6.6.6 Stock v6.7 400 800 1200 1600 2000 SE +/- 3.32, N = 3 SE +/- 2.29, N = 3 1894.28 1953.71 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Floating Point v6.6.6 Stock v6.7 6K 12K 18K 24K 30K SE +/- 16.76, N = 3 SE +/- 32.79, N = 3 26744.36 27569.66 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Hash OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Hash v6.6.6 Stock v6.7 4M 8M 12M 16M 20M SE +/- 3192.96, N = 3 SE +/- 3053.25, N = 3 17033307.63 17551780.14 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only v6.6.6 Stock v6.7 900K 1800K 2700K 3600K 4500K SE +/- 19489.13, N = 3 SE +/- 12389.83, N = 3 3886975 4004740 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: NUMA v6.6.6 Stock v6.7 200 400 600 800 1000 SE +/- 1.80, N = 3 SE +/- 0.24, N = 3 1036.77 1068.09 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle v6.6.6 Stock v6.7 12K 24K 36K 48K 60K SE +/- 29.85, N = 3 SE +/- 7.11, N = 3 55853.54 57494.65 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Crypto v6.6.6 Stock v6.7 40K 80K 120K 160K 200K SE +/- 260.91, N = 3 SE +/- 161.24, N = 3 183183.99 188548.45 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Math v6.6.6 Stock v6.7 110K 220K 330K 440K 550K SE +/- 152.98, N = 3 SE +/- 258.25, N = 3 485001.34 499009.49 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Memory Copying v6.6.6 Stock v6.7 5K 10K 15K 20K 25K SE +/- 17.95, N = 3 SE +/- 57.39, N = 3 24004.53 24695.64 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency v6.6.6 Stock v6.7 0.0578 0.1156 0.1734 0.2312 0.289 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.257 0.250 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix Math v6.6.6 Stock v6.7 80K 160K 240K 320K 400K SE +/- 637.54, N = 3 SE +/- 272.90, N = 3 385258.18 396041.26 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Quicksilver Input: CORAL2 P1 OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P1 v6.6.6 Stock v6.7 6M 12M 18M 24M 30M SE +/- 211266.03, N = 3 SE +/- 55075.71, N = 3 27280000 28040000 1. (CXX) g++ options: -fopenmp -O3 -march=native
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math v6.6.6 Stock v6.7 700K 1400K 2100K 2800K 3500K SE +/- 830.00, N = 3 SE +/- 1754.36, N = 3 3230461.50 3320137.02 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 19.8.1 Time To Compile v6.6.6 Stock v6.7 30 60 90 120 150 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 121.21 118.05
Stress-NG Test: Fused Multiply-Add OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Fused Multiply-Add v6.6.6 Stock v6.7 15M 30M 45M 60M 75M SE +/- 21862.72, N = 3 SE +/- 42666.45, N = 3 70244822.75 72100478.14 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 0.0878 0.1756 0.2634 0.3512 0.439 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.39 0.38 MIN: 0.18 / MAX: 26.28 MIN: 0.18 / MAX: 19.31 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 0.981 1.962 2.943 3.924 4.905 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.36 4.25 MIN: 2.15 / MAX: 27 MIN: 1.95 / MAX: 30.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.37 6.21 MIN: 3.34 / MAX: 29.67 MIN: 3.17 / MAX: 23.34 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating v6.6.6 Stock v6.7 120K 240K 360K 480K 600K SE +/- 3472.31, N = 3 SE +/- 1033.82, N = 3 556761 570883 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 7.69 7.50 MIN: 3.31 / MAX: 27.53 MIN: 3.43 / MAX: 27.91 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 2K 4K 6K 8K 10K SE +/- 4.62, N = 3 SE +/- 9.48, N = 3 7959.97 8161.26 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 3K 6K 9K 12K 15K SE +/- 10.92, N = 3 SE +/- 19.49, N = 3 13960.22 14310.25 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc v6.6.6 Stock v6.7 30M 60M 90M 120M 150M SE +/- 917737.04, N = 3 SE +/- 1238064.72, N = 3 150760521.22 154494959.66 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 1100 2200 3300 4400 5500 SE +/- 7.01, N = 3 SE +/- 2.97, N = 3 4926.83 5045.51 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Quicksilver Input: CTS2 OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CTS2 v6.6.6 Stock v6.7 5M 10M 15M 20M 25M SE +/- 32829.53, N = 3 SE +/- 38441.88, N = 3 23326667 23876667 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 83.26 85.22 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU v6.6.6 Stock v6.7 80 160 240 320 400 SE +/- 0.84, N = 3 SE +/- 0.25, N = 3 383.15 374.51 MIN: 303.22 / MAX: 402.09 MIN: 321.16 / MAX: 396.63 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point v6.6.6 Stock v6.7 50K 100K 150K 200K 250K SE +/- 217.62, N = 3 SE +/- 394.44, N = 3 228832.13 234027.64 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: BMW27 - Compute: CPU-Only v6.6.6 Stock v6.7 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 17.76 17.38
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc C String Functions v6.6.6 Stock v6.7 16M 32M 48M 64M 80M SE +/- 346470.68, N = 3 SE +/- 469274.41, N = 3 73865789.56 75382089.04 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Zlib OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Zlib v6.6.6 Stock v6.7 2K 4K 6K 8K 10K SE +/- 15.44, N = 3 SE +/- 39.53, N = 3 7881.10 8041.12 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating v6.6.6 Stock v6.7 80K 160K 240K 320K 400K SE +/- 1642.20, N = 3 SE +/- 967.86, N = 3 356395 363397 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.30 Backend: Eigen v6.6.6 Stock v6.7 80 160 240 320 400 SE +/- 2.67, N = 3 SE +/- 4.26, N = 4 365 358 1. (CXX) g++ options: -flto -pthread
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 0.41, N = 3 SE +/- 0.83, N = 3 188.72 192.31 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing v6.6.6 Stock v6.7 6M 12M 18M 24M 30M SE +/- 24713.27, N = 3 SE +/- 35321.93, N = 3 26211336.69 26702772.59 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K v6.6.6 Stock v6.7 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.69, N = 3 88.83 90.36 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 8.1.9 Time To Compile v6.6.6 Stock v6.7 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 27.12 26.69
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 1.21, N = 3 SE +/- 0.60, N = 3 183.37 186.25 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG Test: AVX-512 VNNI OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVX-512 VNNI v6.6.6 Stock v6.7 2M 4M 6M 8M 10M SE +/- 86949.56, N = 5 SE +/- 3726.82, N = 3 8158371.94 8282501.92 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Poll OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Poll v6.6.6 Stock v6.7 1.6M 3.2M 4.8M 6.4M 8M SE +/- 8703.67, N = 3 SE +/- 7207.98, N = 3 7394187.64 7499767.91 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K v6.6.6 Stock v6.7 3 6 9 12 15 SE +/- 0.052, N = 3 SE +/- 0.044, N = 3 9.081 9.208 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded v6.6.6 Stock v6.7 60K 120K 180K 240K 300K SE +/- 1629.93, N = 3 SE +/- 922.38, N = 3 266288.4 269955.5 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded v6.6.6 Stock v6.7 900 1800 2700 3600 4500 SE +/- 23.44, N = 3 SE +/- 17.53, N = 3 4354.9 4410.4 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: defconfig v6.6.6 Stock v6.7 6 12 18 24 30 SE +/- 0.22, N = 6 SE +/- 0.27, N = 4 23.91 23.61
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.4 WAV To FLAC v6.6.6 Stock v6.7 3 6 9 12 15 SE +/- 0.03, N = 5 SE +/- 0.02, N = 5 12.52 12.37 1. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 1 v6.6.6 Stock v6.7 0.3114 0.6228 0.9342 1.2456 1.557 SE +/- 0.004, N = 3 SE +/- 0.001, N = 3 1.369 1.384
TensorFlow Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: ResNet-50 v6.6.6 Stock v6.7 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 7.19 7.12
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 5 v6.6.6 Stock v6.7 1.2762 2.5524 3.8286 5.1048 6.381 SE +/- 0.008, N = 3 SE +/- 0.009, N = 3 5.620 5.672
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Unix Makefiles v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 0.10, N = 3 SE +/- 0.32, N = 3 181.65 180.19
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MMAP v6.6.6 Stock v6.7 200 400 600 800 1000 SE +/- 0.43, N = 3 SE +/- 0.51, N = 3 1037.83 1042.84 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MEMFD v6.6.6 Stock v6.7 160 320 480 640 800 SE +/- 0.47, N = 3 SE +/- 0.59, N = 3 730.62 733.70 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 6 v6.6.6 Stock v6.7 2 4 6 8 10 SE +/- 0.022, N = 3 SE +/- 0.031, N = 3 7.370 7.398
Stress-NG Test: Pthread OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pthread v6.6.6 Stock v6.7 30K 60K 90K 120K 150K SE +/- 452.99, N = 3 SE +/- 142.99, N = 3 125130.59 125537.87 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 500M v6.6.6 Stock v6.7 1.233 2.466 3.699 4.932 6.165 SE +/- 0.006, N = 3 SE +/- 0.004, N = 3 5.463 5.480
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 1B v6.6.6 Stock v6.7 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 11.02 11.06
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 10 v6.6.6 Stock v6.7 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 17.60 17.56
Quicksilver Input: CORAL2 P2 OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P2 v6.6.6 Stock v6.7 5M 10M 15M 20M 25M SE +/- 34641.02, N = 3 SE +/- 14529.66, N = 3 22070000 22036667 1. (CXX) g++ options: -fopenmp -O3 -march=native
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Atomic v6.6.6 Stock v6.7 70 140 210 280 350 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 319.94 319.64 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: x86_64 RdRand v6.6.6 Stock v6.7 2K 4K 6K 8K 10K SE +/- 0.34, N = 3 SE +/- 0.18, N = 3 11327.06 11326.12 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU v6.6.6 Stock v6.7 50 100 150 200 250 SE +/- 6.32, N = 15 SE +/- 0.26, N = 3 249.98 169.15 MIN: 40.51 / MAX: 811.65 MIN: 69.93 / MAX: 221.3 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU v6.6.6 Stock v6.7 40 80 120 160 200 SE +/- 2.69, N = 15 SE +/- 0.29, N = 3 128.73 188.83 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Stress-NG Test: Matrix 3D Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix 3D Math v6.6.6 Stock v6.7 900 1800 2700 3600 4500 SE +/- 161.28, N = 15 SE +/- 46.41, N = 13 2308.98 4379.78 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache v6.6.6 Stock v6.7 300K 600K 900K 1200K 1500K SE +/- 16798.31, N = 3 SE +/- 23675.00, N = 12 1268835.49 1271089.94 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: IO_uring v6.6.6 Stock v6.7 500K 1000K 1500K 2000K 2500K SE +/- 109628.32, N = 12 SE +/- 27934.77, N = 3 1486513.95 2249186.66 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: AVL Tree OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVL Tree v6.6.6 Stock v6.7 140 280 420 560 700 SE +/- 9.75, N = 14 SE +/- 0.67, N = 3 432.83 635.15 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Futex v6.6.6 Stock v6.7 600K 1200K 1800K 2400K 3000K SE +/- 38705.18, N = 12 SE +/- 51913.47, N = 15 3008388.98 3014245.49 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lz
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency v6.6.6 Stock v6.7 8 16 24 32 40 SE +/- 1.47, N = 12 SE +/- 1.45, N = 12 34.69 31.97 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write v6.6.6 Stock v6.7 7K 14K 21K 28K 35K SE +/- 1131.34, N = 12 SE +/- 1238.01, N = 12 29356 31899 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Phoronix Test Suite v10.8.4