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: 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
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 smt b smt d smt c smt a no smt a no smt b a c b 700 1400 2100 2800 3500 2513.4 2528.7 2604.6 2795.1 2804.2 2865.9 3033.9 3049.4 3095.0 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed no smt a no smt b smt d a smt a smt c b c smt b 300 600 900 1200 1500 1500.4 1511.5 1513.5 1514.8 1515.6 1516.2 1516.6 1517.4 1519.1 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed smt c smt a smt d smt b no smt a a no smt b b c 300 600 900 1200 1500 1005.8 1023.9 1024.8 1122.4 1227.5 1233.8 1234.2 1239.3 1241.1 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed b c smt c smt d smt a no smt b a no smt a smt b 400 800 1200 1600 2000 1651.0 1661.9 1664.0 1664.2 1664.3 1667.6 1669.3 1669.7 1671.0 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed smt c smt a smt d smt b no smt b no smt a c a b 70 140 210 280 350 249.8 254.1 256.2 259.1 278.2 279.9 330.1 330.8 332.0 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 c b smt a smt b no smt b no smt a smt d smt c 400 800 1200 1600 2000 1704.8 1715.6 1716.7 1723.7 1726.3 1727.8 1728.0 1731.2 1732.3 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed smt a a b c smt c smt b smt d no smt a no smt b 5 10 15 20 25 18.8 19.1 19.1 19.1 19.2 19.5 19.6 19.8 19.8 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed b c a smt c smt d no smt a smt b no smt b smt a 300 600 900 1200 1500 1467.8 1470.5 1472.6 1475.2 1479.1 1483.1 1483.5 1483.8 1495.2 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 b smt c smt a smt d 200 400 600 800 1000 892.7 909.4 916.9 955.6 1032.3 1038.9 1046.6 1051.4 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 no smt b smt a smt b c smt c no smt a smt d 300 600 900 1200 1500 1536.6 1537.5 1538.8 1539.5 1540.4 1540.9 1540.9 1542.5 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 smt b smt a no smt a smt c smt d no smt b b c a 200 400 600 800 1000 852.7 853.8 859.9 860.8 879.6 892.0 910.8 926.9 938.5 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 b c smt b smt d a smt a no smt b smt c no smt a 400 800 1200 1600 2000 1673.7 1675.4 1676.5 1677.6 1677.9 1682.5 1682.8 1683.7 1684.8 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 d smt c smt b 3 6 9 12 15 9.22 9.29 9.30 9.39 9.76 9.78 9.81 9.82 9.87 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 b a c smt c smt d smt b smt a no smt a no smt b 300 600 900 1200 1500 1378.2 1383.7 1384.0 1389.0 1391.7 1392.4 1393.5 1395.8 1397.6 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 c b no smt a no smt b smt a smt c smt d smt b 15 30 45 60 75 40.63 40.76 40.86 47.13 47.43 64.63 65.49 66.08 66.22 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 b a c no smt b no smt a smt d smt a smt c smt b 15 30 45 60 75 41.39 41.40 41.47 47.93 47.97 65.49 65.56 65.59 65.69 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 smt a smt d smt c smt b b a c no smt a no smt b 40 80 120 160 200 132.67 135.56 135.80 136.33 139.07 139.92 140.10 155.56 159.79 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 smt d smt b smt a smt c a c b no smt a no smt b 40 80 120 160 200 136.42 138.33 140.78 140.89 143.31 143.81 144.21 159.63 161.40 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 no smt b no smt a smt d smt c smt b smt a c a b 20 40 60 80 100 69.94 70.02 73.24 73.57 74.11 75.91 80.31 80.90 81.61 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 no smt b no smt a smt d smt a smt b smt c b a c 20 40 60 80 100 74.03 75.50 75.50 76.64 76.70 78.72 80.68 81.90 84.55 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 no smt b no smt a smt c smt b smt a smt d c a b 20 40 60 80 100 74.37 76.05 76.14 77.00 77.96 78.85 82.70 83.45 84.77 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 smt c smt a no smt b no smt a smt d smt b b c a 60 120 180 240 300 243.36 250.71 268.77 269.62 270.76 274.63 290.59 291.03 296.93 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 smt d smt b no smt b smt c no smt a smt a c b a 70 140 210 280 350 256.45 267.04 280.18 288.09 288.41 296.72 301.40 303.99 307.49 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: Ultra Fast no smt b no smt a smt b smt a smt c smt d b c a 70 140 210 280 350 271.45 278.62 295.18 302.55 303.43 303.63 305.52 309.64 310.73 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 c b no smt a no smt b smt d smt c smt b smt a 11 22 33 44 55 33.03 33.10 33.13 38.38 38.65 46.21 46.57 46.62 47.56
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow smt c smt b smt d smt a c a b no smt a no smt b 20 40 60 80 100 79.63 79.95 80.00 80.17 81.10 81.16 81.41 87.15 88.13
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium smt d smt c smt a smt b c a b no smt b no smt a 20 40 60 80 100 88.91 89.16 89.40 89.70 91.29 91.37 91.47 96.67 98.21
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast no smt a smt c smt d smt b no smt b smt a b a c 15 30 45 60 75 57.13 57.44 57.52 57.86 58.09 59.30 68.79 68.82 69.04
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast no smt b smt c smt d smt a smt b no smt a b a c 16 32 48 64 80 58.33 58.34 58.66 59.06 59.20 59.83 69.00 69.33 69.92
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast no smt b smt c smt b no smt a smt a smt d a b c 16 32 48 64 80 57.23 57.33 57.51 57.78 57.96 58.76 70.56 70.68 71.13
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast smt d no smt b smt a smt c no smt a smt b b a c 50 100 150 200 250 181.83 183.75 183.99 192.25 196.25 209.55 234.68 234.95 237.44
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast smt a smt c no smt a no smt b smt d smt b c a b 50 100 150 200 250 178.49 178.78 181.67 216.15 218.91 220.79 237.96 238.68 239.92
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast smt b no smt a no smt b smt a smt c smt d c b a 50 100 150 200 250 179.56 186.24 209.85 216.15 218.28 224.31 238.77 240.91 240.98
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 smt c smt b no smt a smt d no smt b smt a a c b 2 4 6 8 10 6.92 6.97 7.04 7.15 7.16 7.24 7.68 7.70 7.71 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 smt a smt b no smt a no smt b smt d smt c a b c 4 8 12 16 20 13.90 14.27 14.48 14.50 15.11 15.38 17.36 17.37 17.46 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 smt b smt d no smt b smt c smt a no smt a b a c 4 8 12 16 20 13.57 13.68 13.72 13.97 14.08 14.28 14.67 14.69 14.76 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 c b smt a smt c smt b no smt a smt d no smt b 7 14 21 28 35 29.37 29.46 29.50 29.54 29.54 29.60 29.62 29.66 29.71 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 c b a no smt a no smt b 1.3264 2.6528 3.9792 5.3056 6.632 5.808 5.809 5.820 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 no smt b a b c no smt a 3 6 9 12 15 12.31 12.34 12.39 12.40 12.48 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 no smt a no smt b b a c 3 6 9 12 15 12.36 12.37 12.40 12.44 12.44 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 no smt b no smt a b a c 7 14 21 28 35 28.52 28.69 29.85 30.04 30.08 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 c b a no smt a no smt b smt c smt d smt b smt a 300 600 900 1200 1500 1066 1075 1089 1098 1108 1235 1238 1243 1318 MIN: 180 / MAX: 6427 MIN: 179 / MAX: 6442 MIN: 179 / MAX: 7194 MIN: 297 / MAX: 4284 MIN: 297 / MAX: 4208 MIN: 392 / MAX: 4332 MIN: 392 / MAX: 3738 MIN: 390 / MAX: 3501 MIN: 391 / MAX: 3855
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar c a b no smt a no smt b smt a smt d smt c smt b 200 400 600 800 1000 549 556 557 647 652 764 781 793 810 MIN: 60 / MAX: 5475 MIN: 61 / MAX: 5994 MIN: 61 / MAX: 6019 MIN: 101 / MAX: 4024 MIN: 102 / MAX: 3990 MIN: 139 / MAX: 3808 MIN: 139 / MAX: 3776 MIN: 139 / MAX: 3583 MIN: 138 / MAX: 3650
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 smt c smt d smt a smt b no smt a a no smt b b c 3 6 9 12 15 9.34981 8.26078 7.60566 7.42270 2.04003 2.01581 1.93126 1.92340 1.88686 MIN: 7.73 MIN: 7.09 MIN: 6.54 MIN: 6.44 MIN: 1.78 MIN: 1.81 MIN: 1.77 MIN: 1.72 MIN: 1.68 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 smt c smt d smt b smt a no smt a no smt b c a b 0.8104 1.6208 2.4312 3.2416 4.052 3.60194 3.50563 3.49453 3.39151 2.19645 2.12379 1.56742 1.56461 1.56257 MIN: 3.08 MIN: 3.19 MIN: 3.11 MIN: 2.93 MIN: 2 MIN: 1.9 MIN: 1.39 MIN: 1.41 MIN: 1.41 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 smt d smt c smt a smt b no smt a no smt b c b a 3 6 9 12 15 12.15710 12.01300 11.43260 7.30147 4.87883 4.79302 4.39720 4.27858 3.11497 MIN: 8.52 MIN: 8.02 MIN: 7.59 MIN: 5.77 MIN: 3.53 MIN: 3.4 MIN: 3.21 MIN: 3.37 MIN: 2.47 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU smt c smt a smt d smt b no smt b no smt a c a b 0.224 0.448 0.672 0.896 1.12 0.995710 0.975357 0.975091 0.971704 0.629026 0.556069 0.546991 0.534450 0.513068 MIN: 0.87 MIN: 0.92 MIN: 0.91 MIN: 0.82 MIN: 0.51 MIN: 0.46 MIN: 0.5 MIN: 0.49 MIN: 0.47 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU smt b smt c smt a smt d b a no smt b no smt a c 5 10 15 20 25 19.54900 18.65940 15.42100 11.75730 9.19570 8.74576 7.98861 6.19257 3.83017 MIN: 10.67 MIN: 11.23 MIN: 10.4 MIN: 8.17 MIN: 4.13 MIN: 3.65 MIN: 3.88 MIN: 3.65 MIN: 2.72 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 smt b smt a smt c smt d no smt b no smt a a b c 0.8092 1.6184 2.4276 3.2368 4.046 3.59643 3.38833 3.36535 2.97427 2.02833 2.02286 1.87777 1.72975 1.63860 MIN: 2.7 MIN: 2.76 MIN: 2.7 MIN: 2.3 MIN: 1.43 MIN: 1.56 MIN: 1.23 MIN: 1.27 MIN: 1.2 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 c b smt d smt b smt c smt a no smt a no smt b 0.156 0.312 0.468 0.624 0.78 0.693367 0.692667 0.689064 0.630630 0.551783 0.545118 0.538539 0.403590 0.400325 MIN: 0.64 MIN: 0.65 MIN: 0.64 MIN: 0.48 MIN: 0.49 MIN: 0.45 MIN: 0.48 MIN: 0.38 MIN: 0.38 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 smt c smt d smt b smt a no smt b no smt a c a b 5 10 15 20 25 21.03010 20.97260 20.57200 20.26950 9.31751 9.25292 7.38116 7.35746 7.28243 MIN: 17.96 MIN: 18.21 MIN: 18.25 MIN: 17.68 MIN: 8.07 MIN: 7.79 MIN: 6.77 MIN: 4.85 MIN: 6.58 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 c b smt a smt d smt b smt c no smt a no smt b 0.2633 0.5266 0.7899 1.0532 1.3165 1.170040 1.169190 1.166960 0.978590 0.973984 0.973555 0.972863 0.664295 0.651301 MIN: 1.07 MIN: 1.07 MIN: 1.07 MIN: 0.93 MIN: 0.92 MIN: 0.92 MIN: 0.92 MIN: 0.63 MIN: 0.62 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 smt b smt a smt c smt d b c a no smt b no smt a 0.0918 0.1836 0.2754 0.3672 0.459 0.408074 0.407430 0.394377 0.389223 0.312721 0.312289 0.311405 0.255796 0.254845 MIN: 0.27 MIN: 0.27 MIN: 0.29 MIN: 0.29 MIN: 0.28 MIN: 0.28 MIN: 0.3 MIN: 0.18 MIN: 0.18 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 smt d smt c smt a smt b no smt b no smt a c a b 0.2775 0.555 0.8325 1.11 1.3875 1.233400 1.201460 1.200490 1.181350 0.670574 0.664359 0.556851 0.555277 0.551966 MIN: 1.08 MIN: 1.08 MIN: 1.04 MIN: 1.08 MIN: 0.55 MIN: 0.56 MIN: 0.53 MIN: 0.53 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: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU b c a smt b smt a smt c smt d no smt b no smt a 0.0688 0.1376 0.2064 0.2752 0.344 0.305731 0.305599 0.304972 0.291087 0.279638 0.275917 0.247825 0.164845 0.160361 MIN: 0.28 MIN: 0.28 MIN: 0.28 MIN: 0.23 MIN: 0.23 MIN: 0.23 MIN: 0.23 MIN: 0.15 MIN: 0.15 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 smt d smt a smt b smt c no smt a no smt b a c b 400 800 1200 1600 2000 1957.77 1912.16 1890.28 1888.21 1148.26 1124.75 907.49 906.14 903.27 MIN: 1929.47 MIN: 1891.03 MIN: 1864.29 MIN: 1860.29 MIN: 1108.42 MIN: 1091.36 MIN: 897.95 MIN: 898.41 MIN: 894.76 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 smt d smt a smt b smt c no smt a no smt b a b c 700 1400 2100 2800 3500 3349.36 3187.00 3034.62 3011.21 930.26 901.04 674.09 671.65 669.15 MIN: 3325.75 MIN: 3034.82 MIN: 2821.2 MIN: 2853.26 MIN: 898.89 MIN: 864.28 MIN: 667.01 MIN: 664.19 MIN: 661.71 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 smt b smt c smt d smt a no smt a no smt b c b a 400 800 1200 1600 2000 1937.65 1926.15 1883.76 1830.41 1151.25 1119.17 915.08 912.11 911.25 MIN: 1908.65 MIN: 1901.09 MIN: 1850.75 MIN: 1807.97 MIN: 1070.35 MIN: 1086.08 MIN: 906.26 MIN: 902.43 MIN: 903.01 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 b smt d smt a smt b smt c c a no smt a no smt b 0.1302 0.2604 0.3906 0.5208 0.651 0.578466 0.457554 0.451472 0.450261 0.447820 0.417188 0.415446 0.291687 0.291229 MIN: 0.4 MIN: 0.34 MIN: 0.4 MIN: 0.37 MIN: 0.37 MIN: 0.4 MIN: 0.4 MIN: 0.27 MIN: 0.27 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 smt b smt a smt c smt d b a c no smt b no smt a 0.6213 1.2426 1.8639 2.4852 3.1065 2.76140 2.70807 2.70235 2.67303 1.84172 1.83147 1.82264 1.70057 1.65041 MIN: 2.46 MIN: 2.09 MIN: 2.27 MIN: 2.09 MIN: 1.76 MIN: 1.73 MIN: 1.71 MIN: 1.5 MIN: 1.41 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 b a c smt d smt c smt b smt a no smt a no smt b 0.1603 0.3206 0.4809 0.6412 0.8015 0.712495 0.711588 0.708563 0.680395 0.676798 0.672768 0.672585 0.462386 0.461174 MIN: 0.68 MIN: 0.68 MIN: 0.67 MIN: 0.53 MIN: 0.53 MIN: 0.53 MIN: 0.52 MIN: 0.42 MIN: 0.43 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 smt a smt b smt d smt c no smt a no smt b a c b 700 1400 2100 2800 3500 3269.05 3249.28 3171.15 3153.22 913.20 903.36 671.69 671.23 670.20 MIN: 3243.11 MIN: 3226.78 MIN: 3148.29 MIN: 3059.88 MIN: 884.92 MIN: 874.93 MIN: 664.46 MIN: 662.9 MIN: 663.54 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 smt c smt b smt a smt d a b c no smt b no smt a 0.1521 0.3042 0.4563 0.6084 0.7605 0.676124 0.675664 0.674455 0.672115 0.357017 0.356875 0.353175 0.347231 0.342836 MIN: 0.49 MIN: 0.55 MIN: 0.49 MIN: 0.49 MIN: 0.31 MIN: 0.31 MIN: 0.31 MIN: 0.3 MIN: 0.28 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 smt c smt d smt b smt a no smt a no smt b b c a 400 800 1200 1600 2000 1925.68 1912.74 1894.07 1888.10 1147.34 1139.63 917.08 911.76 909.69 MIN: 1901.2 MIN: 1890.93 MIN: 1870.66 MIN: 1865.76 MIN: 1109.85 MIN: 1100.83 MIN: 909.14 MIN: 901.88 MIN: 901.1 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 smt b smt c smt d smt a no smt a no smt b a b c 700 1400 2100 2800 3500 3222.93 3185.64 3172.19 3133.65 973.32 939.55 675.92 668.95 667.95 MIN: 2927.41 MIN: 2949.58 MIN: 3155.85 MIN: 3037.06 MIN: 937.3 MIN: 904.78 MIN: 668.99 MIN: 662.29 MIN: 660.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU smt d smt b smt c smt a no smt a no smt b a b c 0.1356 0.2712 0.4068 0.5424 0.678 0.602831 0.600199 0.593299 0.591738 0.316665 0.293564 0.263997 0.263373 0.262920 MIN: 0.48 MIN: 0.38 MIN: 0.39 MIN: 0.43 MIN: 0.24 MIN: 0.22 MIN: 0.18 MIN: 0.2 MIN: 0.2 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 smt c smt d smt a smt b no smt b no smt a b a c 0.1429 0.2858 0.4287 0.5716 0.7145 0.634992 0.627133 0.621776 0.620907 0.340498 0.316779 0.291387 0.290200 0.285432 MIN: 0.55 MIN: 0.4 MIN: 0.45 MIN: 0.41 MIN: 0.28 MIN: 0.25 MIN: 0.23 MIN: 0.25 MIN: 0.24 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 smt c smt d smt a smt b a b c no smt b no smt a 140 280 420 560 700 495.85 500.12 500.13 516.09 600.70 610.79 614.24 622.73 635.48 MIN: 51.06 / MAX: 6000 MIN: 69.61 / MAX: 6000 MIN: 65.15 / MAX: 6000 MIN: 89.55 / MAX: 6000 MIN: 57.75 / MAX: 6000 MIN: 58.14 / MAX: 6666.67 MIN: 57.14 / MAX: 6666.67 MIN: 83.22 / MAX: 5454.55 MIN: 85.35 / MAX: 6000
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run smt d smt a smt c smt b c a b no smt b no smt a 140 280 420 560 700 515.11 524.04 524.75 527.88 621.88 625.91 627.20 649.52 666.43 MIN: 88.5 / MAX: 6000 MIN: 90.5 / MAX: 6666.67 MIN: 90.23 / MAX: 6000 MIN: 90.63 / MAX: 6666.67 MIN: 58.54 / MAX: 6666.67 MIN: 56.13 / MAX: 7500 MIN: 58.54 / MAX: 6000 MIN: 86.46 / MAX: 6000 MIN: 85.11 / MAX: 6666.67
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run smt d smt c smt a smt b a b c no smt b no smt a 140 280 420 560 700 527.80 530.47 534.82 538.63 625.16 628.37 636.18 662.01 665.00 MIN: 81.52 / MAX: 6000 MIN: 92.02 / MAX: 5454.55 MIN: 91.32 / MAX: 6000 MIN: 89.82 / MAX: 6000 MIN: 57.69 / MAX: 6000 MIN: 58.37 / MAX: 6666.67 MIN: 58.03 / MAX: 6666.67 MIN: 86.33 / MAX: 6000 MIN: 85.84 / 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 no smt a no smt b smt b smt c smt a smt d a c b 900K 1800K 2700K 3600K 4500K 2444886.82 2460416.33 2507331.29 2517750.47 2520253.00 2527084.87 4143044.21 4155273.46 4162812.47 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 no smt b no smt a smt b smt a smt c smt d b c a 1.5M 3M 4.5M 6M 7.5M 4220522.49 4244908.83 4392934.75 4530948.62 4549313.42 4569476.86 6792746.34 6839975.87 6861088.89 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 no smt a no smt b smt b smt a smt c smt d c b a 1000K 2000K 3000K 4000K 5000K 3192061.68 3216133.91 4357453.76 4383314.65 4394194.49 4403267.42 4852421.67 4876951.36 4878860.00 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 c b smt a no smt b smt b smt c smt d no smt a 5 10 15 20 25 10.57 10.59 10.61 18.82 18.84 19.02 19.05 19.08 19.18 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 c b a smt d smt b smt c smt a no smt b no smt a 20 40 60 80 100 42.74 42.90 42.99 96.72 96.91 97.00 97.02 97.38 97.44
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 c b a smt b smt d smt a smt c no smt b no smt a 200 400 600 800 1000 1122.06 1118.44 1115.76 975.50 974.99 972.52 971.90 955.24 955.16
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 no smt b smt d smt a smt b no smt a smt c a b c 8 16 24 32 40 29.75 30.25 31.76 31.78 31.91 31.93 34.83 35.10 35.12
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 no smt b smt d smt a smt b no smt a smt c a b c 8 16 24 32 40 33.60 33.05 31.48 31.46 31.33 31.31 28.71 28.49 28.47
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 c b no smt b no smt a smt b smt a smt d smt c 700 1400 2100 2800 3500 1566.56 1571.83 1573.75 3086.36 3107.30 3114.43 3114.68 3116.09 3132.38
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 smt b smt a smt d no smt b a smt c c b no smt a 7 14 21 28 35 30.75 30.75 30.72 30.64 30.59 30.58 30.49 30.46 30.42
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 no smt b smt d smt b smt a smt c no smt a b a c 40 80 120 160 200 175.32 183.95 188.41 188.58 189.41 191.26 196.54 197.10 197.66
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 no smt b smt d smt b smt a smt c no smt a b a c 1.2828 2.5656 3.8484 5.1312 6.414 5.7015 5.4341 5.3053 5.3004 5.2773 5.2262 5.0859 5.0715 5.0573
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 c b a no smt a smt d no smt b smt a smt c smt b 200 400 600 800 1000 400.04 401.21 401.78 813.98 816.76 817.63 817.75 818.60 822.16
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 c b a smt d smt a smt c smt b no smt a no smt b 30 60 90 120 150 119.70 119.38 119.21 117.22 117.12 116.97 116.48 116.15 115.64
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 smt c no smt b no smt a smt d smt b smt a c b a 20 40 60 80 100 70.14 71.89 72.13 75.52 77.41 77.88 98.59 98.62 99.15
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 smt c no smt b no smt a smt d smt b smt a c b a 4 8 12 16 20 14.25 13.90 13.86 13.23 12.91 12.83 10.14 10.14 10.08
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream c b a smt b smt a smt d smt c no smt b no smt a 200 400 600 800 1000 438.44 439.04 440.85 927.68 929.02 931.82 937.99 938.91 941.24
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream c b a smt b smt a smt d smt c no smt b no smt a 20 40 60 80 100 109.25 109.11 108.68 103.19 103.09 102.76 102.10 100.42 100.24
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream smt c no smt b no smt a a b smt d c smt b smt a 30 60 90 120 150 96.17 100.51 101.01 104.12 104.29 106.65 113.51 119.60 121.92
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream smt c no smt b no smt a a b smt d c smt b smt a 3 6 9 12 15 10.3852 9.9395 9.8899 9.5962 9.5793 9.3656 8.8004 8.3506 8.1914
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 b no smt a smt a smt b smt c smt d 500 1000 1500 2000 2500 1009.85 1012.35 1013.74 2203.16 2204.75 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 smt a no smt b no smt a smt b smt c smt d 11 22 33 44 55 47.46 47.35 47.29 42.95 42.84 42.81 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 smt b smt a smt d smt c no smt b no smt a c b a 40 80 120 160 200 136.83 139.10 139.82 163.71 164.81 166.27 181.72 181.81 188.54
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream smt b smt a smt d smt c no smt b no smt a c b a 2 4 6 8 10 7.3054 7.1865 7.1490 6.1057 6.0650 6.0118 5.5007 5.4980 5.3018
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 d smt c smt b smt a 300 600 900 1200 1500 619.75 619.94 625.55 1291.97 1292.80 1301.18 1305.71 1306.58 1306.67
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 smt d smt b smt c smt a no smt b no smt a 20 40 60 80 100 77.34 77.31 76.62 73.62 73.35 73.34 73.31 73.21 73.20
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream no smt a smt a smt c smt d smt b no smt b a c b 40 80 120 160 200 131.76 132.87 135.89 141.47 145.17 155.74 192.88 193.31 193.53
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream no smt a smt a smt c smt d smt b no smt b a c b 2 4 6 8 10 7.5856 7.5225 7.3550 7.0640 6.8844 6.4174 5.1812 5.1696 5.1633
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream c a b no smt b no smt a smt b smt a smt c smt d 70 140 210 280 350 149.69 149.74 149.82 308.30 308.43 314.25 314.62 315.33 316.03
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream c a b no smt a smt b no smt b smt a smt c smt d 70 140 210 280 350 320.05 319.98 319.96 304.21 304.08 303.74 303.33 303.25 301.92
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream smt b smt d smt a no smt a smt c no smt b b a c 14 28 42 56 70 45.96 46.78 47.51 48.18 48.77 48.93 59.92 60.25 60.49
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream smt b smt d smt a no smt a smt c no smt b b a c 5 10 15 20 25 21.74 21.36 21.03 20.74 20.49 20.42 16.67 16.58 16.52
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 b no smt a smt a smt b smt d smt c 140 280 420 560 700 314.84 316.29 316.63 647.76 649.30 658.21 658.34 660.21 662.26
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 smt a no smt b no smt a smt b smt d smt c 30 60 90 120 150 152.14 151.60 151.39 145.40 145.36 145.35 145.27 144.91 144.47
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 smt d smt b no smt a no smt b smt c smt a a b c 20 40 60 80 100 66.08 68.29 69.11 69.33 70.38 73.29 87.96 89.34 89.55
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 smt d smt b no smt a no smt b smt c smt a a b c 4 8 12 16 20 15.13 14.64 14.46 14.42 14.20 13.64 11.36 11.19 11.16
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 b c a smt c smt a no smt b smt b no smt a smt d 20 40 60 80 100 42.83 42.92 42.96 96.91 97.29 97.34 97.35 97.40 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 c a b smt c smt a smt b smt d no smt a no smt b 200 400 600 800 1000 1117.73 1116.43 1116.29 971.67 970.22 969.21 966.76 956.01 955.34
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 smt c smt a smt b no smt b smt d no smt a b a c 8 16 24 32 40 29.42 30.96 31.01 31.07 31.07 31.32 34.82 34.93 34.99
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 smt c smt a smt b no smt b smt d no smt a b a c 8 16 24 32 40 33.99 32.30 32.24 32.18 32.18 31.92 28.71 28.62 28.57
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 d smt a smt c smt b 9M 18M 27M 36M 45M 18954936.00 18955118.10 18961773.18 27408413.10 27422305.53 41965286.06 41966139.67 41972765.93 41989522.68 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 b no smt a smt d smt c smt a smt b 2K 4K 6K 8K 10K 1663.08 1664.75 1668.92 3591.71 4520.48 7273.19 7633.16 8360.76 9017.12 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 no smt b no smt a smt d smt b smt c smt a c a b 110 220 330 440 550 19.78 20.51 24.71 24.77 24.79 24.82 478.05 483.90 498.67 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 no smt b no smt a a b c smt c smt b smt a smt d 3M 6M 9M 12M 15M 10393402.01 10458275.24 12653709.64 12661687.46 12676101.41 15228320.07 15341564.16 15359471.73 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 smt c smt d smt a smt b c a b no smt a no smt b 800K 1600K 2400K 3200K 4000K 2067499.58 2077119.76 2333781.39 2396325.93 2794473.75 2794694.37 2805836.52 3746361.52 3802292.60 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 no smt a no smt b smt d smt c smt a b c a smt b 120 240 360 480 600 303.56 308.67 394.49 413.34 464.70 507.74 507.97 518.46 564.05 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 c b no smt a no smt b smt b smt a smt d smt c 30M 60M 90M 120M 150M 59479783.64 59929401.40 60031543.97 63581395.67 65500297.73 135855921.28 136339636.91 137579874.56 138939958.50 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 smt d c smt c smt a smt b b no smt b no smt a 90 180 270 360 450 174.72 182.80 183.33 184.24 184.34 186.64 223.29 395.95 400.03 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 c b no smt a no smt b smt a smt b smt d smt c 100K 200K 300K 400K 500K 203073.15 203095.44 203147.15 435615.35 437065.75 466292.12 466609.22 468006.00 468159.21 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 c b no smt b no smt a smt a smt b smt c smt d 140M 280M 420M 560M 700M 312709034.05 313768771.26 314418461.02 456651508.04 456657338.84 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 smt d smt c smt b smt a no smt a no smt b a b c 14K 28K 42K 56K 70K 34685.85 34917.39 36020.16 36266.02 43094.96 45685.28 58156.36 58664.97 64299.62 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 no smt b no smt a smt a smt c smt d b a c smt b 40K 80K 120K 160K 200K 67451.30 68076.03 74978.51 77834.39 91735.75 109356.78 109397.78 109609.15 180407.59 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 c b a no smt b no smt a smt b smt a smt c smt d 900K 1800K 2700K 3600K 4500K 1891202.37 1913590.77 1950323.96 3282827.50 3284433.20 4329824.38 4329963.26 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 smt d no smt a smt c smt b smt a no smt b b a c 20 40 60 80 100 40.56 40.94 42.55 44.38 47.58 55.84 67.21 77.51 97.04 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 b no smt a smt a smt b smt d smt c 110K 220K 330K 440K 550K 205134.87 217072.27 217304.19 326819.72 328297.04 487359.39 487987.32 489998.75 490300.48 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 no smt a no smt b c b a smt d smt c smt b smt a 4M 8M 12M 16M 20M 13141129.68 13192391.85 18088584.67 18100474.36 18128283.29 19842969.28 19866440.86 19927313.52 20047519.05 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 b a c no smt b no smt a smt a smt b smt d smt c 200K 400K 600K 800K 1000K 382304.04 382305.69 382328.50 925984.24 932248.18 946032.88 946660.88 951700.17 952461.48 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 b c a no smt a no smt b smt a smt b smt c smt d 300K 600K 900K 1200K 1500K 556797.27 556833.50 556875.59 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 b a c no smt a no smt b smt b smt a smt c smt d 300K 600K 900K 1200K 1500K 621003.92 621015.34 621041.93 829106.63 829445.38 1413555.44 1414423.65 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 no smt b no smt a smt d smt c smt b smt a a c b 4K 8K 12K 16K 20K 10949.90 11342.69 13370.33 15077.69 15430.18 15914.10 20106.51 20297.91 20340.40 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 smt c smt a smt b b smt d a c no smt b no smt a 2K 4K 6K 8K 10K 8747.83 8748.99 8750.61 8851.65 8864.78 8873.58 8876.10 8924.10 8968.28 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: Context Switching smt b smt c smt d smt a b c a no smt b no smt a 10M 20M 30M 40M 50M 12221058.34 12328933.65 12728401.45 12895047.73 16313126.86 16862185.54 18941003.97 44683906.68 47222624.49 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: Glibc C String Functions b a c no smt a no smt b smt c smt a smt b smt d 8M 16M 24M 32M 40M 16168655.17 16257100.25 16537965.14 26755146.69 28009942.56 34602827.77 35687958.37 35996976.13 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 c b no smt b no smt a smt d smt c smt b smt a 600 1200 1800 2400 3000 1122.39 1125.86 1132.35 1963.75 1978.80 2516.09 2517.26 2520.38 2564.48 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 no smt b no smt a smt b smt c smt a b a c smt d 3M 6M 9M 12M 15M 7372780.72 7402514.74 8586858.51 8609357.68 10103952.13 10471889.97 10473084.09 10475486.39 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 smt b smt a no smt b no smt a smt d smt c 20 40 60 80 100 49.72 49.72 49.77 108.89 108.93 109.04 109.08 109.23 109.36 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 b c a smt b smt a no smt b no smt a smt d smt c 200 400 600 800 1000 962.63 962.15 962.10 439.50 439.41 438.99 438.29 437.68 437.51 MIN: 893.43 / MAX: 1015.71 MIN: 888.7 / MAX: 1017.92 MIN: 879.24 / MAX: 1018.81 MIN: 424.22 / MAX: 477.66 MIN: 410.81 / MAX: 465.4 MIN: 427.57 / MAX: 484.31 MIN: 416.93 / MAX: 496.86 MIN: 394.89 / MAX: 478.58 MIN: 400.05 / MAX: 473.91 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 c b a no smt b no smt a smt b smt a smt d smt c 13 26 39 52 65 28.33 28.42 28.47 57.49 57.58 57.67 57.72 58.00 58.05 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 c b a no smt b no smt a smt a smt b smt d smt c 400 800 1200 1600 2000 1679.03 1675.96 1671.46 830.04 828.67 827.07 827.03 822.50 821.93 MIN: 865.58 / MAX: 1995.12 MIN: 1231.52 / MAX: 1967.75 MIN: 924.15 / MAX: 1977.46 MIN: 722.6 / MAX: 1015.67 MIN: 730.29 / MAX: 1036.1 MIN: 724.84 / MAX: 1037.91 MIN: 723.77 / MAX: 1003.25 MIN: 717.65 / MAX: 997.43 MIN: 725.25 / MAX: 1010.56 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 c a b no smt a no smt b smt a smt b smt d smt c 13 26 39 52 65 27.89 27.97 28.23 57.18 57.19 57.29 57.31 57.62 57.71 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 c a b no smt b no smt a smt a smt b smt d smt c 400 800 1200 1600 2000 1704.02 1701.70 1685.26 834.17 833.99 833.15 832.70 828.01 826.67 MIN: 828.99 / MAX: 1969.02 MIN: 1395.71 / MAX: 2063.97 MIN: 891.16 / MAX: 1979.37 MIN: 732.01 / MAX: 1006.46 MIN: 723.91 / MAX: 1011.94 MIN: 725.84 / MAX: 1017.38 MIN: 723.65 / MAX: 1031.69 MIN: 716.19 / MAX: 1018.34 MIN: 724.1 / MAX: 1006.75 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 smt b smt a no smt a no smt b smt d smt c 2K 4K 6K 8K 10K 2941.47 3085.53 3174.04 7949.05 7953.21 7979.05 7979.82 7990.47 7993.18 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 smt b smt a no smt b no smt a smt d smt c 4 8 12 16 20 16.30 15.54 15.10 6.03 6.02 6.01 6.01 6.00 5.99 MIN: 7.91 / MAX: 51.62 MIN: 8.28 / MAX: 57.72 MIN: 6.94 / MAX: 60.59 MIN: 5.17 / MAX: 38.35 MIN: 5.27 / MAX: 25.12 MIN: 5.02 / MAX: 36.88 MIN: 5.2 / MAX: 37.8 MIN: 5.21 / MAX: 25.51 MIN: 5.13 / MAX: 31.29 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: Face Detection FP16-INT8 - Device: CPU b c a smt a smt b no smt a smt d no smt b smt c 50 100 150 200 250 95.48 95.59 95.76 208.13 208.19 208.82 209.24 210.14 210.19 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 b c a smt a smt b no smt a smt d no smt b smt c 110 220 330 440 550 500.83 500.30 499.32 230.21 230.06 229.46 228.94 228.01 227.93 MIN: 418.76 / MAX: 546.62 MIN: 410.04 / MAX: 531.93 MIN: 264.54 / MAX: 537.26 MIN: 211.56 / MAX: 253.58 MIN: 210.58 / MAX: 251.42 MIN: 217.93 / MAX: 265.81 MIN: 214.92 / MAX: 248.29 MIN: 212.99 / MAX: 267.17 MIN: 210.46 / MAX: 252.96 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 b c a smt b smt a no smt a no smt b smt c smt d 3K 6K 9K 12K 15K 5894.27 5898.79 5908.89 12109.64 12117.16 12119.66 12128.38 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 c b a smt b smt a no smt b no smt a smt d smt c 2 4 6 8 10 8.13 8.13 8.11 3.96 3.95 3.95 3.95 3.93 3.93 MIN: 3.83 / MAX: 59.87 MIN: 5.35 / MAX: 55.84 MIN: 5.39 / MAX: 69.87 MIN: 3.66 / MAX: 32.83 MIN: 3.61 / MAX: 34.38 MIN: 3.68 / MAX: 42.53 MIN: 3.61 / MAX: 38 MIN: 3.61 / MAX: 23.62 MIN: 3.61 / MAX: 42.82 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 c a b smt a smt b no smt b no smt a smt d smt c 2K 4K 6K 8K 10K 4910.13 4914.17 4915.42 10544.03 10549.15 10549.24 10556.93 10587.30 10603.84 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 c a b smt b smt a no smt b no smt a smt d smt c 3 6 9 12 15 9.76 9.76 9.75 4.54 4.54 4.54 4.54 4.52 4.52 MIN: 4.98 / MAX: 36.12 MIN: 5.03 / MAX: 28.1 MIN: 5.25 / MAX: 35.53 MIN: 4.11 / MAX: 42.14 MIN: 4.07 / MAX: 35.16 MIN: 4.09 / MAX: 55.78 MIN: 4.12 / MAX: 27.91 MIN: 4.03 / MAX: 45.52 MIN: 4.12 / MAX: 33.17 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 c a b no smt a no smt b smt a smt b smt d smt c 200 400 600 800 1000 535.78 540.41 541.03 1045.81 1048.74 1049.16 1050.37 1057.74 1058.57 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 c a b no smt a no smt b smt a smt b smt d smt c 20 40 60 80 100 89.46 88.71 88.61 45.86 45.73 45.71 45.66 45.34 45.31 MIN: 42.16 / MAX: 123.4 MIN: 44.2 / MAX: 132.86 MIN: 47.57 / MAX: 124.67 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: 39.4 / MAX: 73.83 MIN: 39.35 / MAX: 73.19 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 c a b smt a smt b smt d smt c no smt a no smt b 4K 8K 12K 16K 20K 9485.65 9494.22 9496.95 20610.23 20610.62 20679.68 20684.29 20836.10 20849.75 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 c b a smt b smt a smt d smt c no smt b no smt a 3 6 9 12 15 10.11 10.10 10.10 9.28 9.28 9.26 9.25 9.18 9.18 MIN: 5.43 / MAX: 36.27 MIN: 5.47 / MAX: 28.16 MIN: 5.46 / MAX: 35.41 MIN: 8.13 / MAX: 24.28 MIN: 8.1 / MAX: 22.87 MIN: 8.12 / MAX: 30.29 MIN: 8.12 / MAX: 19.04 MIN: 8.21 / MAX: 24.31 MIN: 8.17 / MAX: 31.1 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 b c a smt b smt a no smt b smt d smt c no smt a 2K 4K 6K 8K 10K 5720.90 5724.81 5750.74 9680.44 9746.08 9758.74 9767.99 9773.26 9784.09 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 b c a smt b smt a smt d no smt b smt c no smt a 2 4 6 8 10 8.38 8.37 8.34 4.95 4.92 4.91 4.91 4.90 4.90 MIN: 6.4 / MAX: 32.33 MIN: 6.83 / MAX: 50.24 MIN: 6.61 / MAX: 55.54 MIN: 4.54 / MAX: 24.23 MIN: 4.52 / MAX: 34.8 MIN: 4.51 / MAX: 27.27 MIN: 4.49 / MAX: 34.72 MIN: 4.5 / MAX: 29.95 MIN: 4.46 / MAX: 56.52 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: Age Gender Recognition Retail 0013 FP16 - Device: CPU b c a no smt a no smt b smt d smt c smt a smt b 40K 80K 120K 160K 200K 111378.39 112186.25 112346.36 160545.41 162294.47 172228.34 173620.31 173926.92 175754.35 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 c b a no smt b no smt a smt d smt c smt b smt a 0.1485 0.297 0.4455 0.594 0.7425 0.66 0.66 0.65 0.58 0.57 0.53 0.53 0.53 0.53 MIN: 0.31 / MAX: 22.67 MIN: 0.32 / MAX: 19.99 MIN: 0.32 / MAX: 20.68 MIN: 0.5 / MAX: 12.8 MIN: 0.5 / MAX: 13.02 MIN: 0.5 / MAX: 8.86 MIN: 0.5 / MAX: 9.15 MIN: 0.5 / MAX: 9.61 MIN: 0.5 / MAX: 24.2 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 b c a no smt b no smt a smt b smt c smt a smt d 30K 60K 90K 120K 150K 74353.41 74486.08 74495.17 127770.39 127833.52 147582.87 148047.13 148316.88 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 c b a no smt b no smt a smt d smt b smt a smt c 0.2453 0.4906 0.7359 0.9812 1.2265 1.09 1.09 1.09 1.01 1.01 0.97 0.97 0.97 0.96 MIN: 0.49 / MAX: 22.06 MIN: 0.48 / MAX: 25.82 MIN: 0.49 / MAX: 19.01 MIN: 0.86 / MAX: 8.72 MIN: 0.86 / MAX: 8.97 MIN: 0.86 / MAX: 13.31 MIN: 0.87 / MAX: 10.96 MIN: 0.87 / MAX: 9.78 MIN: 0.87 / MAX: 9.72 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 smt d smt c smt b smt a no smt b no smt a a b c 110K 220K 330K 440K 550K 415428 416006 417882 423027 468210 478629 533927 534681 536551 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 b c a no smt a no smt b smt a smt b smt d smt c 300M 600M 900M 1200M 1500M 466888888 468069792 468231434 1209611055 1213540299 1225662852 1231168093 1231916197 1234570512 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 smt b smt a smt c smt d no smt b no smt a c a b 120K 240K 360K 480K 600K 411513 413199 419985 420514 452228 462018 543572 544384 545556 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 smt b smt d smt a smt c no smt b no smt a a c b 120K 240K 360K 480K 600K 413708 414047 414168 414282 464044 465700 542256 544565 545396 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 no smt b no smt a c b a smt a smt c smt b smt d 90K 180K 270K 360K 450K 344040 350673 356922 373002 376601 388052 394852 401295 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 no smt a no smt b c b a smt d smt b smt c smt a 3M 6M 9M 12M 15M 7643831 7913568 8316379 8620352 9296185 13098097 13830689 13948914 15317250 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 smt c smt d smt b smt a no smt b no smt a b c a 600K 1200K 1800K 2400K 3000K 1613913 1752904 1761416 1787682 2063831 2079804 2891962 2910023 2926458 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.