2 x AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1004D BIOS) and llvmpipe on Red Hat Enterprise Linux 9.1 via the Phoronix Test Suite.
a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
b c Processor: AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 768GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.1, Kernel: 5.14.0-162.6.1.el9_1.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server 1.20.11, Compiler: GCC 11.3.1 20220421, File-System: xfs, Screen Resolution: 1600x1200
no smt a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
no smt b Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores)Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GBDisk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: llvmpipeMonitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.1, Kernel: 5.14.0-162.6.1.el9_1.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server 1.20.11, OpenGL: 4.5 Mesa 22.1.5 (LLVM 14.0.6 256 bits), Compiler: GCC 11.3.1 20220421, File-System: xfs, Screen Resolution: 1024x768
smt a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
smt b smt c smt d Changed Processor to 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) .
Zstd Compression This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 700 1400 2100 2800 3500 3033.9 3095.0 3049.4 2804.2 2865.9 2795.1 2513.4 2604.6 2528.7 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1514.8 1516.6 1517.4 1500.4 1511.5 1515.6 1519.1 1516.2 1513.5 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1233.8 1239.3 1241.1 1227.5 1234.2 1023.9 1122.4 1005.8 1024.8 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 1669.3 1651.0 1661.9 1669.7 1667.6 1664.3 1671.0 1664.0 1664.2 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 70 140 210 280 350 330.8 332.0 330.1 279.9 278.2 254.1 259.1 249.8 256.2 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 1704.8 1716.7 1715.6 1728.0 1727.8 1723.7 1726.3 1732.3 1731.2 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 5 10 15 20 25 19.1 19.1 19.1 19.8 19.8 18.8 19.5 19.2 19.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1472.6 1467.8 1470.5 1483.1 1483.8 1495.2 1483.5 1475.2 1479.1 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 892.7 909.4 916.9 955.6 1032.3 1051.4 1038.9 1046.6 1059.0 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1536.6 1537.5 1540.9 1542.5 1538.8 1539.5 1540.4 1540.9 1543.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 938.5 910.8 926.9 859.9 892.0 853.8 852.7 860.8 879.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 1677.9 1673.7 1675.4 1684.8 1682.8 1682.5 1676.5 1683.7 1677.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 9.22 9.29 9.30 9.39 9.76 9.78 9.87 9.82 9.81 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1383.7 1378.2 1384.0 1395.8 1397.6 1393.5 1392.4 1389.0 1391.7 1. (CC) gcc options: -O3 -pthread -lz
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Binary: Pathtracer - Model: Crown
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Binary: Pathtracer ISPC - Model: Crown
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Binary: Pathtracer - Model: Asian Dragon
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Binary: Pathtracer - Model: Asian Dragon Obj
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Binary: Pathtracer ISPC - Model: Asian Dragon
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
no smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt a: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt b: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt c: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
smt d: The test quit with a non-zero exit status. E: ./embree-4.0.0.x86_64.linux/bin/embree_pathtracer_ispc: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow a b c no smt a no smt b smt a smt b smt c smt d 15 30 45 60 75 40.63 40.86 40.76 47.13 47.43 64.63 66.22 65.49 66.08 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium a b c no smt a no smt b smt a smt b smt c smt d 15 30 45 60 75 41.40 41.39 41.47 47.97 47.93 65.56 65.69 65.59 65.49 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow a b c no smt a no smt b smt a smt b smt c smt d 40 80 120 160 200 139.92 139.07 140.10 155.56 159.79 132.67 136.33 135.80 135.56 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium a b c no smt a no smt b smt a smt b smt c smt d 40 80 120 160 200 143.31 144.21 143.81 159.63 161.40 140.78 138.33 140.89 136.42 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 80.90 81.61 80.31 70.02 69.94 75.91 74.11 73.57 73.24 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 81.90 80.68 84.55 75.50 74.03 76.64 76.70 78.72 75.50 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 83.45 84.77 82.70 76.05 74.37 77.96 77.00 76.14 78.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast a b c no smt a no smt b smt a smt b smt c smt d 60 120 180 240 300 296.93 290.59 291.03 269.62 268.77 250.71 274.63 243.36 270.76 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast a b c no smt a no smt b smt a smt b smt c smt d 70 140 210 280 350 307.49 303.99 301.40 288.41 280.18 296.72 267.04 288.09 256.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast a b c no smt a no smt b smt a smt b smt c smt d 70 140 210 280 350 310.73 305.52 309.64 278.62 271.45 302.55 295.18 303.43 303.63 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium a b c no smt a no smt b smt a smt b smt c smt d 11 22 33 44 55 33.03 33.13 33.10 38.38 38.65 47.56 46.62 46.57 46.21
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 81.16 81.41 81.10 87.15 88.13 80.17 79.95 79.63 80.00
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 91.37 91.47 91.29 98.21 96.67 89.40 89.70 89.16 88.91
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast a b c no smt a no smt b smt a smt b smt c smt d 15 30 45 60 75 68.82 68.79 69.04 57.13 58.09 59.30 57.86 57.44 57.52
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast a b c no smt a no smt b smt a smt b smt c smt d 16 32 48 64 80 69.33 69.00 69.92 59.83 58.33 59.06 59.20 58.34 58.66
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast a b c no smt a no smt b smt a smt b smt c smt d 16 32 48 64 80 70.56 70.68 71.13 57.78 57.23 57.96 57.51 57.33 58.76
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast a b c no smt a no smt b smt a smt b smt c smt d 50 100 150 200 250 234.95 234.68 237.44 196.25 183.75 183.99 209.55 192.25 181.83
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast a b c no smt a no smt b smt a smt b smt c smt d 50 100 150 200 250 238.68 239.92 237.96 181.67 216.15 178.49 220.79 178.78 218.91
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast a b c no smt a no smt b smt a smt b smt c smt d 50 100 150 200 250 240.98 240.91 238.77 186.24 209.85 216.15 179.56 218.28 224.31
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 4K a b c no smt a no smt b smt a smt b smt c smt d 2 4 6 8 10 7.68 7.71 7.70 7.04 7.16 7.24 6.97 6.92 7.15 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K a b c no smt a no smt b smt a smt b smt c smt d 4 8 12 16 20 17.36 17.37 17.46 14.48 14.50 13.90 14.27 15.38 15.11 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 1080p a b c no smt a no smt b smt a smt b smt c smt d 4 8 12 16 20 14.69 14.67 14.76 14.28 13.72 14.08 13.57 13.97 13.68 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 1080p a b c no smt a no smt b smt a smt b smt c smt d 7 14 21 28 35 29.37 29.50 29.46 29.62 29.71 29.54 29.60 29.54 29.66 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under The Clear BSD License. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast a b c no smt a no smt b 1.3264 2.6528 3.9792 5.3056 6.632 5.820 5.809 5.808 5.890 5.895 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto Video Input: Bosphorus 4K - Video Preset: Fast
smt a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt d: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster a b c no smt a no smt b 3 6 9 12 15 12.34 12.39 12.40 12.48 12.31 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto Video Input: Bosphorus 4K - Video Preset: Faster
smt a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt d: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast a b c no smt a no smt b 3 6 9 12 15 12.44 12.40 12.44 12.36 12.37 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto Video Input: Bosphorus 1080p - Video Preset: Fast
smt a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt d: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster a b c no smt a no smt b 7 14 21 28 35 30.04 29.85 30.08 28.69 28.52 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto Video Input: Bosphorus 1080p - Video Preset: Faster
smt a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
smt d: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 1089 1075 1066 1098 1108 1318 1243 1235 1238 MIN: 179 / MAX: 7194 MIN: 179 / MAX: 6442 MIN: 180 / MAX: 6427 MIN: 297 / MAX: 4284 MIN: 297 / MAX: 4208 MIN: 391 / MAX: 3855 MIN: 390 / MAX: 3501 MIN: 392 / MAX: 4332 MIN: 392 / MAX: 3738
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 556 557 549 647 652 764 810 793 781 MIN: 61 / MAX: 5994 MIN: 61 / MAX: 6019 MIN: 60 / MAX: 5475 MIN: 101 / MAX: 4024 MIN: 102 / MAX: 3990 MIN: 139 / MAX: 3808 MIN: 138 / MAX: 3650 MIN: 139 / MAX: 3583 MIN: 139 / MAX: 3776
Build: allmodconfig
a: The test quit with a non-zero exit status.
b: The test quit with a non-zero exit status.
c: The test quit with a non-zero exit status.
no smt a: The test quit with a non-zero exit status.
no smt b: The test quit with a non-zero exit status.
smt a: The test quit with a non-zero exit status.
smt b: The test quit with a non-zero exit status.
smt c: The test quit with a non-zero exit status.
smt d: The test quit with a non-zero exit status.
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 2.01581 1.92340 1.88686 2.04003 1.93126 7.60566 7.42270 9.34981 8.26078 MIN: 1.81 MIN: 1.72 MIN: 1.68 MIN: 1.78 MIN: 1.77 MIN: 6.54 MIN: 6.44 MIN: 7.73 MIN: 7.09 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.8104 1.6208 2.4312 3.2416 4.052 1.56461 1.56257 1.56742 2.19645 2.12379 3.39151 3.49453 3.60194 3.50563 MIN: 1.41 MIN: 1.41 MIN: 1.39 MIN: 2 MIN: 1.9 MIN: 2.93 MIN: 3.11 MIN: 3.08 MIN: 3.19 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 3.11497 4.27858 4.39720 4.87883 4.79302 11.43260 7.30147 12.01300 12.15710 MIN: 2.47 MIN: 3.37 MIN: 3.21 MIN: 3.53 MIN: 3.4 MIN: 7.59 MIN: 5.77 MIN: 8.02 MIN: 8.52 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.224 0.448 0.672 0.896 1.12 0.534450 0.513068 0.546991 0.556069 0.629026 0.975357 0.971704 0.995710 0.975091 MIN: 0.49 MIN: 0.47 MIN: 0.5 MIN: 0.46 MIN: 0.51 MIN: 0.92 MIN: 0.82 MIN: 0.87 MIN: 0.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 5 10 15 20 25 8.74576 9.19570 3.83017 6.19257 7.98861 15.42100 19.54900 18.65940 11.75730 MIN: 3.65 MIN: 4.13 MIN: 2.72 MIN: 3.65 MIN: 3.88 MIN: 10.4 MIN: 10.67 MIN: 11.23 MIN: 8.17 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.8092 1.6184 2.4276 3.2368 4.046 1.87777 1.72975 1.63860 2.02286 2.02833 3.38833 3.59643 3.36535 2.97427 MIN: 1.23 MIN: 1.27 MIN: 1.2 MIN: 1.56 MIN: 1.43 MIN: 2.76 MIN: 2.7 MIN: 2.7 MIN: 2.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.156 0.312 0.468 0.624 0.78 0.693367 0.689064 0.692667 0.403590 0.400325 0.538539 0.551783 0.545118 0.630630 MIN: 0.64 MIN: 0.64 MIN: 0.65 MIN: 0.38 MIN: 0.38 MIN: 0.48 MIN: 0.49 MIN: 0.45 MIN: 0.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 5 10 15 20 25 7.35746 7.28243 7.38116 9.25292 9.31751 20.26950 20.57200 21.03010 20.97260 MIN: 4.85 MIN: 6.58 MIN: 6.77 MIN: 7.79 MIN: 8.07 MIN: 17.68 MIN: 18.25 MIN: 17.96 MIN: 18.21 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.2633 0.5266 0.7899 1.0532 1.3165 1.170040 1.166960 1.169190 0.664295 0.651301 0.978590 0.973555 0.972863 0.973984 MIN: 1.07 MIN: 1.07 MIN: 1.07 MIN: 0.63 MIN: 0.62 MIN: 0.93 MIN: 0.92 MIN: 0.92 MIN: 0.92 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.0918 0.1836 0.2754 0.3672 0.459 0.311405 0.312721 0.312289 0.254845 0.255796 0.407430 0.408074 0.394377 0.389223 MIN: 0.3 MIN: 0.28 MIN: 0.28 MIN: 0.18 MIN: 0.18 MIN: 0.27 MIN: 0.27 MIN: 0.29 MIN: 0.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.2775 0.555 0.8325 1.11 1.3875 0.555277 0.551966 0.556851 0.664359 0.670574 1.200490 1.181350 1.201460 1.233400 MIN: 0.53 MIN: 0.49 MIN: 0.53 MIN: 0.56 MIN: 0.55 MIN: 1.04 MIN: 1.08 MIN: 1.08 MIN: 1.08 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.0688 0.1376 0.2064 0.2752 0.344 0.304972 0.305731 0.305599 0.160361 0.164845 0.279638 0.291087 0.275917 0.247825 MIN: 0.28 MIN: 0.28 MIN: 0.28 MIN: 0.15 MIN: 0.15 MIN: 0.23 MIN: 0.23 MIN: 0.23 MIN: 0.23 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 907.49 903.27 906.14 1148.26 1124.75 1912.16 1890.28 1888.21 1957.77 MIN: 897.95 MIN: 894.76 MIN: 898.41 MIN: 1108.42 MIN: 1091.36 MIN: 1891.03 MIN: 1864.29 MIN: 1860.29 MIN: 1929.47 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 700 1400 2100 2800 3500 674.09 671.65 669.15 930.26 901.04 3187.00 3034.62 3011.21 3349.36 MIN: 667.01 MIN: 664.19 MIN: 661.71 MIN: 898.89 MIN: 864.28 MIN: 3034.82 MIN: 2821.2 MIN: 2853.26 MIN: 3325.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 911.25 912.11 915.08 1151.25 1119.17 1830.41 1937.65 1926.15 1883.76 MIN: 903.01 MIN: 902.43 MIN: 906.26 MIN: 1070.35 MIN: 1086.08 MIN: 1807.97 MIN: 1908.65 MIN: 1901.09 MIN: 1850.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1302 0.2604 0.3906 0.5208 0.651 0.415446 0.578466 0.417188 0.291687 0.291229 0.451472 0.450261 0.447820 0.457554 MIN: 0.4 MIN: 0.4 MIN: 0.4 MIN: 0.27 MIN: 0.27 MIN: 0.4 MIN: 0.37 MIN: 0.37 MIN: 0.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.6213 1.2426 1.8639 2.4852 3.1065 1.83147 1.84172 1.82264 1.65041 1.70057 2.70807 2.76140 2.70235 2.67303 MIN: 1.73 MIN: 1.76 MIN: 1.71 MIN: 1.41 MIN: 1.5 MIN: 2.09 MIN: 2.46 MIN: 2.27 MIN: 2.09 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1603 0.3206 0.4809 0.6412 0.8015 0.711588 0.712495 0.708563 0.462386 0.461174 0.672585 0.672768 0.676798 0.680395 MIN: 0.68 MIN: 0.68 MIN: 0.67 MIN: 0.42 MIN: 0.43 MIN: 0.52 MIN: 0.53 MIN: 0.53 MIN: 0.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 700 1400 2100 2800 3500 671.69 670.20 671.23 913.20 903.36 3269.05 3249.28 3153.22 3171.15 MIN: 664.46 MIN: 663.54 MIN: 662.9 MIN: 884.92 MIN: 874.93 MIN: 3243.11 MIN: 3226.78 MIN: 3059.88 MIN: 3148.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1521 0.3042 0.4563 0.6084 0.7605 0.357017 0.356875 0.353175 0.342836 0.347231 0.674455 0.675664 0.676124 0.672115 MIN: 0.31 MIN: 0.31 MIN: 0.31 MIN: 0.28 MIN: 0.3 MIN: 0.49 MIN: 0.55 MIN: 0.49 MIN: 0.49 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 909.69 917.08 911.76 1147.34 1139.63 1888.10 1894.07 1925.68 1912.74 MIN: 901.1 MIN: 909.14 MIN: 901.88 MIN: 1109.85 MIN: 1100.83 MIN: 1865.76 MIN: 1870.66 MIN: 1901.2 MIN: 1890.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 700 1400 2100 2800 3500 675.92 668.95 667.95 973.32 939.55 3133.65 3222.93 3185.64 3172.19 MIN: 668.99 MIN: 662.29 MIN: 660.93 MIN: 937.3 MIN: 904.78 MIN: 3037.06 MIN: 2927.41 MIN: 2949.58 MIN: 3155.85 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1356 0.2712 0.4068 0.5424 0.678 0.263997 0.263373 0.262920 0.316665 0.293564 0.591738 0.600199 0.593299 0.602831 MIN: 0.18 MIN: 0.2 MIN: 0.2 MIN: 0.24 MIN: 0.22 MIN: 0.43 MIN: 0.38 MIN: 0.39 MIN: 0.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1429 0.2858 0.4287 0.5716 0.7145 0.290200 0.291387 0.285432 0.316779 0.340498 0.621776 0.620907 0.634992 0.627133 MIN: 0.25 MIN: 0.23 MIN: 0.24 MIN: 0.25 MIN: 0.28 MIN: 0.45 MIN: 0.41 MIN: 0.55 MIN: 0.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache a b c no smt a no smt b smt a smt b smt c smt d 140 280 420 560 700 600.70 610.79 614.24 635.48 622.73 500.13 516.09 495.85 500.12 MIN: 57.75 / MAX: 6000 MIN: 58.14 / MAX: 6666.67 MIN: 57.14 / MAX: 6666.67 MIN: 85.35 / MAX: 6000 MIN: 83.22 / MAX: 5454.55 MIN: 65.15 / MAX: 6000 MIN: 89.55 / MAX: 6000 MIN: 51.06 / MAX: 6000 MIN: 69.61 / MAX: 6000
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run a b c no smt a no smt b smt a smt b smt c smt d 140 280 420 560 700 625.91 627.20 621.88 666.43 649.52 524.04 527.88 524.75 515.11 MIN: 56.13 / MAX: 7500 MIN: 58.54 / MAX: 6000 MIN: 58.54 / MAX: 6666.67 MIN: 85.11 / MAX: 6666.67 MIN: 86.46 / MAX: 6000 MIN: 90.5 / MAX: 6666.67 MIN: 90.63 / MAX: 6666.67 MIN: 90.23 / MAX: 6000 MIN: 88.5 / MAX: 6000
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run a b c no smt a no smt b smt a smt b smt c smt d 140 280 420 560 700 625.16 628.37 636.18 665.00 662.01 534.82 538.63 530.47 527.80 MIN: 57.69 / MAX: 6000 MIN: 58.37 / MAX: 6666.67 MIN: 58.03 / MAX: 6666.67 MIN: 85.84 / MAX: 6000 MIN: 86.33 / MAX: 6000 MIN: 91.32 / MAX: 6000 MIN: 89.82 / MAX: 6000 MIN: 92.02 / MAX: 5454.55 MIN: 81.52 / MAX: 6000
Memcached Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:5 a b c no smt a no smt b smt a smt b smt c smt d 900K 1800K 2700K 3600K 4500K 4143044.21 4162812.47 4155273.46 2444886.82 2460416.33 2520253.00 2507331.29 2517750.47 2527084.87 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:10 a b c no smt a no smt b smt a smt b smt c smt d 1.5M 3M 4.5M 6M 7.5M 6861088.89 6792746.34 6839975.87 4244908.83 4220522.49 4530948.62 4392934.75 4549313.42 4569476.86 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:100 a b c no smt a no smt b smt a smt b smt c smt d 1000K 2000K 3000K 4000K 5000K 4878860.00 4876951.36 4852421.67 3192061.68 3216133.91 4383314.65 4357453.76 4394194.49 4403267.42 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare a b c no smt a no smt b smt a smt b smt c smt d 5 10 15 20 25 10.57 10.61 10.59 19.18 18.84 18.82 19.02 19.05 19.08 1. (CXX) g++ options: -O3
Neural Magic DeepSparse This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 42.99 42.90 42.74 97.44 97.38 97.02 96.91 97.00 96.72
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 1115.76 1118.44 1122.06 955.16 955.24 972.52 975.50 971.90 974.99
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 8 16 24 32 40 34.83 35.10 35.12 31.91 29.75 31.76 31.78 31.93 30.25
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 8 16 24 32 40 28.71 28.49 28.47 31.33 33.60 31.48 31.46 31.31 33.05
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 700 1400 2100 2800 3500 1566.56 1573.75 1571.83 3107.30 3086.36 3114.68 3114.43 3132.38 3116.09
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 7 14 21 28 35 30.59 30.46 30.49 30.42 30.64 30.75 30.75 30.58 30.72
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 40 80 120 160 200 197.10 196.54 197.66 191.26 175.32 188.58 188.41 189.41 183.95
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 1.2828 2.5656 3.8484 5.1312 6.414 5.0715 5.0859 5.0573 5.2262 5.7015 5.3004 5.3053 5.2773 5.4341
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 401.78 401.21 400.04 813.98 817.63 817.75 822.16 818.60 816.76
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 30 60 90 120 150 119.21 119.38 119.70 116.15 115.64 117.12 116.48 116.97 117.22
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 99.15 98.62 98.59 72.13 71.89 77.88 77.41 70.14 75.52
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 4 8 12 16 20 10.08 10.14 10.14 13.86 13.90 12.83 12.91 14.25 13.23
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 440.85 439.04 438.44 941.24 938.91 929.02 927.68 937.99 931.82
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 108.68 109.11 109.25 100.24 100.42 103.09 103.19 102.10 102.76
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 30 60 90 120 150 104.12 104.29 113.51 101.01 100.51 121.92 119.60 96.17 106.65
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 9.5962 9.5793 8.8004 9.8899 9.9395 8.1914 8.3506 10.3852 9.3656
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 500 1000 1500 2000 2500 1009.85 1012.35 1013.74 2204.75 2203.16 2230.31 2245.80 2253.14 2255.42
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 11 22 33 44 55 47.46 47.35 47.29 42.81 42.84 42.95 42.65 42.55 42.48
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 40 80 120 160 200 188.54 181.81 181.72 166.27 164.81 139.10 136.83 163.71 139.82
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 2 4 6 8 10 5.3018 5.4980 5.5007 6.0118 6.0650 7.1865 7.3054 6.1057 7.1490
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 300 600 900 1200 1500 619.75 619.94 625.55 1291.97 1292.80 1306.67 1306.58 1305.71 1301.18
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 77.34 77.31 76.62 73.20 73.21 73.31 73.35 73.34 73.62
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 40 80 120 160 200 192.88 193.53 193.31 131.76 155.74 132.87 145.17 135.89 141.47
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 2 4 6 8 10 5.1812 5.1633 5.1696 7.5856 6.4174 7.5225 6.8844 7.3550 7.0640
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 70 140 210 280 350 149.74 149.82 149.69 308.43 308.30 314.62 314.25 315.33 316.03
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 70 140 210 280 350 319.98 319.96 320.05 304.21 303.74 303.33 304.08 303.25 301.92
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 14 28 42 56 70 60.25 59.92 60.49 48.18 48.93 47.51 45.96 48.77 46.78
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 5 10 15 20 25 16.58 16.67 16.52 20.74 20.42 21.03 21.74 20.49 21.36
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 140 280 420 560 700 314.84 316.29 316.63 649.30 647.76 658.21 658.34 662.26 660.21
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 30 60 90 120 150 152.14 151.60 151.39 145.35 145.36 145.40 145.27 144.47 144.91
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 87.96 89.34 89.55 69.11 69.33 73.29 68.29 70.38 66.08
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 4 8 12 16 20 11.36 11.19 11.16 14.46 14.42 13.64 14.64 14.20 15.13
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 42.96 42.83 42.92 97.40 97.34 97.29 97.35 96.91 97.89
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 1116.43 1116.29 1117.73 956.01 955.34 970.22 969.21 971.67 966.76
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 8 16 24 32 40 34.93 34.82 34.99 31.32 31.07 30.96 31.01 29.42 31.07
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c no smt a no smt b smt a smt b smt c smt d 8 16 24 32 40 28.62 28.71 28.57 31.92 32.18 32.30 32.24 33.99 32.18
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Hash a b c no smt a no smt b smt a smt b smt c smt d 9M 18M 27M 36M 45M 18954936.00 18955118.10 18961773.18 27408413.10 27422305.53 41966139.67 41989522.68 41972765.93 41965286.06 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: MMAP a b c no smt a no smt b smt a smt b smt c smt d 2K 4K 6K 8K 10K 1663.08 1664.75 1668.92 4520.48 3591.71 8360.76 9017.12 7633.16 7273.19 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: NUMA a b c no smt a no smt b smt a smt b smt c smt d 110 220 330 440 550 483.90 498.67 478.05 20.51 19.78 24.82 24.77 24.79 24.71 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Poll a b c no smt a no smt b smt a smt b smt c smt d 3M 6M 9M 12M 15M 12653709.64 12661687.46 12676101.41 10458275.24 10393402.01 15359471.73 15341564.16 15228320.07 15403597.24 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
Test: Zlib
a: The test run did not produce a result.
b: The test run did not produce a result.
c: The test run did not produce a result.
no smt a: The test run did not produce a result.
no smt b: The test run did not produce a result.
smt a: The test run did not produce a result.
smt b: The test run did not produce a result.
smt c: The test run did not produce a result.
smt d: The test run did not produce a result.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Futex a b c no smt a no smt b smt a smt b smt c smt d 800K 1600K 2400K 3200K 4000K 2794694.37 2805836.52 2794473.75 3746361.52 3802292.60 2333781.39 2396325.93 2067499.58 2077119.76 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: MEMFD a b c no smt a no smt b smt a smt b smt c smt d 120 240 360 480 600 518.46 507.74 507.97 303.56 308.67 464.70 564.05 413.34 394.49 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Mutex a b c no smt a no smt b smt a smt b smt c smt d 30M 60M 90M 120M 150M 59479783.64 60031543.97 59929401.40 63581395.67 65500297.73 136339636.91 135855921.28 138939958.50 137579874.56 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Atomic a b c no smt a no smt b smt a smt b smt c smt d 90 180 270 360 450 174.72 223.29 183.33 400.03 395.95 184.34 186.64 184.24 182.80 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Crypto a b c no smt a no smt b smt a smt b smt c smt d 100K 200K 300K 400K 500K 203073.15 203147.15 203095.44 435615.35 437065.75 466292.12 466609.22 468159.21 468006.00 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Malloc a b c no smt a no smt b smt a smt b smt c smt d 140M 280M 420M 560M 700M 312709034.05 314418461.02 313768771.26 456657338.84 456651508.04 634718750.41 634995429.66 639757070.52 640853365.54 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Forking a b c no smt a no smt b smt a smt b smt c smt d 14K 28K 42K 56K 70K 58156.36 58664.97 64299.62 43094.96 45685.28 36266.02 36020.16 34917.39 34685.85 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Pthread a b c no smt a no smt b smt a smt b smt c smt d 40K 80K 120K 160K 200K 109397.78 109356.78 109609.15 68076.03 67451.30 74978.51 180407.59 77834.39 91735.75 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
Test: IO_uring
a: The test run did not produce a result.
b: The test run did not produce a result.
c: The test run did not produce a result.
no smt a: The test run did not produce a result.
no smt b: The test run did not produce a result.
smt a: The test run did not produce a result.
smt b: The test run did not produce a result.
smt c: The test run did not produce a result.
smt d: The test run did not produce a result.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: SENDFILE a b c no smt a no smt b smt a smt b smt c smt d 900K 1800K 2700K 3600K 4500K 1950323.96 1913590.77 1891202.37 3284433.20 3282827.50 4329963.26 4329824.38 4351871.12 4351920.42 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: CPU Cache a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 77.51 67.21 97.04 40.94 55.84 47.58 44.38 42.55 40.56 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: CPU Stress a b c no smt a no smt b smt a smt b smt c smt d 110K 220K 330K 440K 550K 205134.87 217072.27 217304.19 328297.04 326819.72 487359.39 487987.32 490300.48 489998.75 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Semaphores a b c no smt a no smt b smt a smt b smt c smt d 4M 8M 12M 16M 20M 18128283.29 18100474.36 18088584.67 13141129.68 13192391.85 20047519.05 19927313.52 19866440.86 19842969.28 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Matrix Math a b c no smt a no smt b smt a smt b smt c smt d 200K 400K 600K 800K 1000K 382305.69 382304.04 382328.50 932248.18 925984.24 946032.88 946660.88 952461.48 951700.17 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Vector Math a b c no smt a no smt b smt a smt b smt c smt d 300K 600K 900K 1200K 1500K 556875.59 556797.27 556833.50 920216.27 920642.34 1291689.33 1291704.57 1295970.28 1300693.93 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Function Call a b c no smt a no smt b smt a smt b smt c smt d 300K 600K 900K 1200K 1500K 621015.34 621003.92 621041.93 829106.63 829445.38 1414423.65 1413555.44 1422505.51 1425621.44 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
Test: x86_64 RdRand
a: The test run did not produce a result. E: stress-ng: error: [1836509] No stress workers invoked (one or more were unsupported)
b: The test run did not produce a result. E: stress-ng: error: [3544257] No stress workers invoked (one or more were unsupported)
c: The test run did not produce a result. E: stress-ng: error: [1223131] No stress workers invoked (one or more were unsupported)
no smt a: The test run did not produce a result. E: stress-ng: error: [4177065] No stress workers invoked (one or more were unsupported)
no smt b: The test run did not produce a result. E: stress-ng: error: [19683] No stress workers invoked (one or more were unsupported)
smt a: The test run did not produce a result. E: stress-ng: error: [55524] No stress workers invoked (one or more were unsupported)
smt b: The test run did not produce a result. E: stress-ng: error: [3903578] No stress workers invoked (one or more were unsupported)
smt c: The test run did not produce a result. E: stress-ng: error: [4007271] No stress workers invoked (one or more were unsupported)
smt d: The test run did not produce a result. E: stress-ng: error: [381360] No stress workers invoked (one or more were unsupported)
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Memory Copying a b c no smt a no smt b smt a smt b smt c smt d 4K 8K 12K 16K 20K 20106.51 20340.40 20297.91 11342.69 10949.90 15914.10 15430.18 15077.69 13370.33 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Socket Activity a b c no smt a no smt b smt a smt b smt c smt d 2K 4K 6K 8K 10K 8873.58 8851.65 8876.10 8968.28 8924.10 8748.99 8750.61 8747.83 8864.78 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Context Switching a b c no smt a no smt b smt a smt b smt c smt d 10M 20M 30M 40M 50M 18941003.97 16313126.86 16862185.54 47222624.49 44683906.68 12895047.73 12221058.34 12328933.65 12728401.45 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Glibc C String Functions a b c no smt a no smt b smt a smt b smt c smt d 8M 16M 24M 32M 40M 16257100.25 16168655.17 16537965.14 26755146.69 28009942.56 35687958.37 35996976.13 34602827.77 36111781.82 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Glibc Qsort Data Sorting a b c no smt a no smt b smt a smt b smt c smt d 600 1200 1800 2400 3000 1122.39 1132.35 1125.86 1978.80 1963.75 2564.48 2520.38 2517.26 2516.09 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: System V Message Passing a b c no smt a no smt b smt a smt b smt c smt d 3M 6M 9M 12M 15M 10473084.09 10471889.97 10475486.39 7402514.74 7372780.72 10103952.13 8586858.51 8609357.68 12418451.71 1. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread
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 FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 49.72 49.72 49.77 109.08 109.04 108.93 108.89 109.36 109.23 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 962.10 962.63 962.15 438.29 438.99 439.41 439.50 437.51 437.68 MIN: 879.24 / MAX: 1018.81 MIN: 893.43 / MAX: 1015.71 MIN: 888.7 / MAX: 1017.92 MIN: 416.93 / MAX: 496.86 MIN: 427.57 / MAX: 484.31 MIN: 410.81 / MAX: 465.4 MIN: 424.22 / MAX: 477.66 MIN: 400.05 / MAX: 473.91 MIN: 394.89 / MAX: 478.58 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 13 26 39 52 65 28.47 28.42 28.33 57.58 57.49 57.72 57.67 58.05 58.00 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 1671.46 1675.96 1679.03 828.67 830.04 827.07 827.03 821.93 822.50 MIN: 924.15 / MAX: 1977.46 MIN: 1231.52 / MAX: 1967.75 MIN: 865.58 / MAX: 1995.12 MIN: 730.29 / MAX: 1036.1 MIN: 722.6 / MAX: 1015.67 MIN: 724.84 / MAX: 1037.91 MIN: 723.77 / MAX: 1003.25 MIN: 725.25 / MAX: 1010.56 MIN: 717.65 / MAX: 997.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 13 26 39 52 65 27.97 28.23 27.89 57.18 57.19 57.29 57.31 57.71 57.62 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 400 800 1200 1600 2000 1701.70 1685.26 1704.02 833.99 834.17 833.15 832.70 826.67 828.01 MIN: 1395.71 / MAX: 2063.97 MIN: 891.16 / MAX: 1979.37 MIN: 828.99 / MAX: 1969.02 MIN: 723.91 / MAX: 1011.94 MIN: 732.01 / MAX: 1006.46 MIN: 725.84 / MAX: 1017.38 MIN: 723.65 / MAX: 1031.69 MIN: 724.1 / MAX: 1006.75 MIN: 716.19 / MAX: 1018.34 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 2K 4K 6K 8K 10K 2941.47 3085.53 3174.04 7979.05 7979.82 7953.21 7949.05 7993.18 7990.47 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 4 8 12 16 20 16.30 15.54 15.10 6.01 6.01 6.02 6.03 5.99 6.00 MIN: 7.91 / MAX: 51.62 MIN: 8.28 / MAX: 57.72 MIN: 6.94 / MAX: 60.59 MIN: 5.2 / MAX: 37.8 MIN: 5.02 / MAX: 36.88 MIN: 5.27 / MAX: 25.12 MIN: 5.17 / MAX: 38.35 MIN: 5.13 / MAX: 31.29 MIN: 5.21 / MAX: 25.51 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 50 100 150 200 250 95.76 95.48 95.59 208.82 210.14 208.13 208.19 210.19 209.24 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 110 220 330 440 550 499.32 500.83 500.30 229.46 228.01 230.21 230.06 227.93 228.94 MIN: 264.54 / MAX: 537.26 MIN: 418.76 / MAX: 546.62 MIN: 410.04 / MAX: 531.93 MIN: 217.93 / MAX: 265.81 MIN: 212.99 / MAX: 267.17 MIN: 211.56 / MAX: 253.58 MIN: 210.58 / MAX: 251.42 MIN: 210.46 / MAX: 252.96 MIN: 214.92 / MAX: 248.29 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 3K 6K 9K 12K 15K 5908.89 5894.27 5898.79 12119.66 12128.38 12117.16 12109.64 12168.05 12172.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 2 4 6 8 10 8.11 8.13 8.13 3.95 3.95 3.95 3.96 3.93 3.93 MIN: 5.39 / MAX: 69.87 MIN: 5.35 / MAX: 55.84 MIN: 3.83 / MAX: 59.87 MIN: 3.61 / MAX: 38 MIN: 3.68 / MAX: 42.53 MIN: 3.61 / MAX: 34.38 MIN: 3.66 / MAX: 32.83 MIN: 3.61 / MAX: 42.82 MIN: 3.61 / MAX: 23.62 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 2K 4K 6K 8K 10K 4914.17 4915.42 4910.13 10556.93 10549.24 10544.03 10549.15 10603.84 10587.30 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 9.76 9.75 9.76 4.54 4.54 4.54 4.54 4.52 4.52 MIN: 5.03 / MAX: 28.1 MIN: 5.25 / MAX: 35.53 MIN: 4.98 / MAX: 36.12 MIN: 4.12 / MAX: 27.91 MIN: 4.09 / MAX: 55.78 MIN: 4.07 / MAX: 35.16 MIN: 4.11 / MAX: 42.14 MIN: 4.12 / MAX: 33.17 MIN: 4.03 / MAX: 45.52 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 200 400 600 800 1000 540.41 541.03 535.78 1045.81 1048.74 1049.16 1050.37 1058.57 1057.74 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 20 40 60 80 100 88.71 88.61 89.46 45.86 45.73 45.71 45.66 45.31 45.34 MIN: 44.2 / MAX: 132.86 MIN: 47.57 / MAX: 124.67 MIN: 42.16 / MAX: 123.4 MIN: 39.29 / MAX: 91.13 MIN: 39.68 / MAX: 86.83 MIN: 39.78 / MAX: 73.33 MIN: 38.82 / MAX: 75.65 MIN: 39.35 / MAX: 73.19 MIN: 39.4 / MAX: 73.83 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 4K 8K 12K 16K 20K 9494.22 9496.95 9485.65 20836.10 20849.75 20610.23 20610.62 20684.29 20679.68 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 3 6 9 12 15 10.10 10.10 10.11 9.18 9.18 9.28 9.28 9.25 9.26 MIN: 5.46 / MAX: 35.41 MIN: 5.47 / MAX: 28.16 MIN: 5.43 / MAX: 36.27 MIN: 8.17 / MAX: 31.1 MIN: 8.21 / MAX: 24.31 MIN: 8.1 / MAX: 22.87 MIN: 8.13 / MAX: 24.28 MIN: 8.12 / MAX: 19.04 MIN: 8.12 / MAX: 30.29 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 2K 4K 6K 8K 10K 5750.74 5720.90 5724.81 9784.09 9758.74 9746.08 9680.44 9773.26 9767.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 2 4 6 8 10 8.34 8.38 8.37 4.90 4.91 4.92 4.95 4.90 4.91 MIN: 6.61 / MAX: 55.54 MIN: 6.4 / MAX: 32.33 MIN: 6.83 / MAX: 50.24 MIN: 4.46 / MAX: 56.52 MIN: 4.49 / MAX: 34.72 MIN: 4.52 / MAX: 34.8 MIN: 4.54 / MAX: 24.23 MIN: 4.5 / MAX: 29.95 MIN: 4.51 / MAX: 27.27 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 40K 80K 120K 160K 200K 112346.36 111378.39 112186.25 160545.41 162294.47 173926.92 175754.35 173620.31 172228.34 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.1485 0.297 0.4455 0.594 0.7425 0.65 0.66 0.66 0.57 0.58 0.53 0.53 0.53 0.53 MIN: 0.32 / MAX: 20.68 MIN: 0.32 / MAX: 19.99 MIN: 0.31 / MAX: 22.67 MIN: 0.5 / MAX: 13.02 MIN: 0.5 / MAX: 12.8 MIN: 0.5 / MAX: 24.2 MIN: 0.5 / MAX: 9.61 MIN: 0.5 / MAX: 9.15 MIN: 0.5 / MAX: 8.86 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 30K 60K 90K 120K 150K 74495.17 74353.41 74486.08 127833.52 127770.39 148316.88 147582.87 148047.13 149647.68 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c no smt a no smt b smt a smt b smt c smt d 0.2453 0.4906 0.7359 0.9812 1.2265 1.09 1.09 1.09 1.01 1.01 0.97 0.97 0.96 0.97 MIN: 0.49 / MAX: 19.01 MIN: 0.48 / MAX: 25.82 MIN: 0.49 / MAX: 22.06 MIN: 0.86 / MAX: 8.97 MIN: 0.86 / MAX: 8.72 MIN: 0.87 / MAX: 9.78 MIN: 0.87 / MAX: 10.96 MIN: 0.87 / MAX: 9.72 MIN: 0.86 / MAX: 13.31 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill a b c no smt a no smt b smt a smt b smt c smt d 110K 220K 330K 440K 550K 533927 534681 536551 478629 468210 423027 417882 416006 415428 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Read a b c no smt a no smt b smt a smt b smt c smt d 300M 600M 900M 1200M 1500M 468231434 466888888 468069792 1209611055 1213540299 1225662852 1231168093 1234570512 1231916197 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Update Random a b c no smt a no smt b smt a smt b smt c smt d 120K 240K 360K 480K 600K 544384 545556 543572 462018 452228 413199 411513 419985 420514 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Sequential Fill a b c no smt a no smt b smt a smt b smt c smt d 120K 240K 360K 480K 600K 542256 545396 544565 465700 464044 414168 413708 414282 414047 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill Sync a b c no smt a no smt b smt a smt b smt c smt d 90K 180K 270K 360K 450K 376601 373002 356922 350673 344040 388052 401295 394852 404463 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read While Writing a b c no smt a no smt b smt a smt b smt c smt d 3M 6M 9M 12M 15M 9296185 8620352 8316379 7643831 7913568 15317250 13830689 13948914 13098097 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read Random Write Random a b c no smt a no smt b smt a smt b smt c smt d 600K 1200K 1800K 2400K 3000K 2926458 2891962 2910023 2079804 2063831 1787682 1761416 1613913 1752904 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 March 2023 19:46 by user .
b Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 March 2023 04:27 by user .
c Processor: AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 768GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.1, Kernel: 5.14.0-162.6.1.el9_1.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server 1.20.11, Compiler: GCC 11.3.1 20220421, File-System: xfs, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 March 2023 07:00 by user .
no smt a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 March 2023 17:20 by user phoronix.
no smt b Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: llvmpipe, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.1, Kernel: 5.14.0-162.6.1.el9_1.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server 1.20.11, OpenGL: 4.5 Mesa 22.1.5 (LLVM 14.0.6 256 bits), Compiler: GCC 11.3.1 20220421, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 March 2023 19:43 by user phoronix.
smt a Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 March 2023 05:04 by user phoronix.
smt b Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 March 2023 07:43 by user phoronix.
smt c Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 March 2023 10:38 by user phoronix.
smt d Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: llvmpipe, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.1, Kernel: 5.14.0-162.6.1.el9_1.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server 1.20.11, OpenGL: 4.5 Mesa 22.1.5 (LLVM 14.0.6 256 bits), Compiler: GCC 11.3.1 20220421, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.9.14Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 March 2023 12:53 by user phoronix.