2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite.
a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101148Java Notes: OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
b c Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
Epoch OpenBenchmarking.org Seconds, Fewer Is Better Epoch 4.19.4 Epoch3D Deck: Cone a c b 100 200 300 400 500 455.50 458.47 461.42 1. (F9X) gfortran options: -O3 -std=f2003 -Jobj -lsdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 c a b 200M 400M 600M 800M 1000M 880729000 879749000 842062000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 c a b 130M 260M 390M 520M 650M 623794000 615929000 610704000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 c a b 400M 800M 1200M 1600M 2000M 1727360000 1653580000 1641600000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 c a b 300M 600M 900M 1200M 1500M 1580110000 1540820000 1524900000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Rustls OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 c b a 400K 800K 1200K 1600K 2000K 1729925.11 1715553.24 1698216.97 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 c a b 300K 600K 900K 1200K 1500K 1392293.46 1390278.58 1365832.45 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: FastestDet a b c 10 20 30 40 50 33.63 37.50 42.04 MIN: 33.37 / MAX: 41.47 MIN: 36.47 / MAX: 39.01 MIN: 40.1 / MAX: 43.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: vision_transformer a b c 20 40 60 80 100 62.70 75.85 78.66 MIN: 61.66 / MAX: 71.71 MIN: 71.67 / MAX: 100.04 MIN: 74.66 / MAX: 141.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: regnety_400m a b c 30 60 90 120 150 130.33 145.07 146.13 MIN: 129.83 / MAX: 134.5 MIN: 142 / MAX: 364.83 MIN: 144.99 / MAX: 148.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: squeezenet_ssd a b c 13 26 39 52 65 48.87 55.33 58.88 MIN: 48.32 / MAX: 57.97 MIN: 54.25 / MAX: 188.52 MIN: 58.23 / MAX: 62.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: yolov4-tiny a b c 12 24 36 48 60 41.10 48.37 52.04 MIN: 40.13 / MAX: 48.66 MIN: 44.62 / MAX: 227.83 MIN: 47.36 / MAX: 54.47 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 a b c 9 18 27 36 45 32.32 37.78 40.60 MIN: 32.09 / MAX: 37.05 MIN: 37.49 / MAX: 49.72 MIN: 40.3 / MAX: 42.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: resnet50 a b c 11 22 33 44 55 40.59 45.84 47.57 MIN: 40.35 / MAX: 42.4 MIN: 45.14 / MAX: 142.04 MIN: 47.3 / MAX: 49.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: alexnet a b c 3 6 9 12 15 10.05 11.55 11.91 MIN: 9.71 / MAX: 11.49 MIN: 11.26 / MAX: 13 MIN: 11.57 / MAX: 13.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: resnet18 a b c 7 14 21 28 35 23.91 26.78 27.99 MIN: 23.77 / MAX: 25.2 MIN: 26.55 / MAX: 34.81 MIN: 27.8 / MAX: 29.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: vgg16 a b c 16 32 48 64 80 57.29 67.68 71.29 MIN: 56.41 / MAX: 59.7 MIN: 65.28 / MAX: 71.33 MIN: 69.89 / MAX: 75.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: googlenet a b c 10 20 30 40 50 38.09 43.26 45.04 MIN: 37.88 / MAX: 45.5 MIN: 43.04 / MAX: 44.82 MIN: 44.77 / MAX: 52.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: blazeface a b c 4 8 12 16 20 15.23 16.49 17.70 MIN: 15.12 / MAX: 16.82 MIN: 16.39 / MAX: 17.8 MIN: 17.07 / MAX: 21.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: efficientnet-b0 a c b 9 18 27 36 45 34.25 38.28 39.40 MIN: 32.27 / MAX: 339.49 MIN: 37.89 / MAX: 41.58 MIN: 36.7 / MAX: 209.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: mnasnet a b c 6 12 18 24 30 21.21 23.79 26.06 MIN: 20.88 / MAX: 61.55 MIN: 23.02 / MAX: 25.23 MIN: 24 / MAX: 282.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: shufflenet-v2 a c b 8 16 24 32 40 28.54 32.46 34.31 MIN: 28.22 / MAX: 31 MIN: 30.3 / MAX: 287 MIN: 29.7 / MAX: 325.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU-v3-v3 - Model: mobilenet-v3 a b c 7 14 21 28 35 27.96 28.66 32.02 MIN: 25.07 / MAX: 299.42 MIN: 25.96 / MAX: 214.05 MIN: 26.22 / MAX: 360.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU-v2-v2 - Model: mobilenet-v2 a c b 6 12 18 24 30 22.98 23.60 23.98 MIN: 22.48 / MAX: 24.91 MIN: 23.33 / MAX: 31.25 MIN: 23.73 / MAX: 32.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20241226 Target: CPU - Model: mobilenet a b c 9 18 27 36 45 32.32 37.78 40.60 MIN: 32.09 / MAX: 37.05 MIN: 37.49 / MAX: 49.72 MIN: 40.3 / MAX: 42.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 c a b 600K 1200K 1800K 2400K 3000K 2877947.2 2833287.3 2820653.3 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 b c a 16K 32K 48K 64K 80K 75010.2 74959.3 74941.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
BYTE Unix Benchmark OpenBenchmarking.org MWIPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: Whetstone Double b c a 600K 1200K 1800K 2400K 3000K 2714473.2 2714351.2 2713226.7 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: Dhrystone 2 b c a 3000M 6000M 9000M 12000M 15000M 12655563306.7 12636880431.6 12634644588.3 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
srsRAN Project OpenBenchmarking.org Mbps, More Is Better srsRAN Project 24.10 Test: PUSCH Processor Benchmark, Throughput Total b a c 2K 4K 6K 8K 10K 8082.6 7635.4 7631.4 1. (CXX) g++ options: -O3 -march=native -mtune=generic -fno-trapping-math -fno-math-errno -ldl
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 4K c a b 3 6 9 12 15 11.05 11.02 10.93 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Palabos OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 500 c b a 120 240 360 480 600 558.06 556.41 556.41 1. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm
Palabos OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 400 c a b 110 220 330 440 550 531.73 530.00 529.25 1. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm
OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 1000 c a b 140 280 420 560 700 661.55 659.94 659.84 1. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM c a b 300000M 600000M 900000M 1200000M 1500000M 1531952540600 1529363548300 1529285362960 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM b c a 400000M 800000M 1200000M 1600000M 2000000M 1788600410900 1788351156160 1787346309360 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 c b a 20000M 40000M 60000M 80000M 100000M 78929554520 78904969300 78840468670 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 a b c 50000M 100000M 150000M 200000M 250000M 242548530680 242399788540 242005934470 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 c a b 150000M 300000M 450000M 600000M 750000M 686536891250 686377188830 685952939270 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 b a c 200000M 400000M 600000M 800000M 1000000M 983433981080 983205666540 981347683260 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 a c b 20 40 60 80 100 75.93 75.24 71.43 1. (CXX) g++ options: -O3
OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 c a b 20 40 60 80 100 77.09 76.40 75.34 1. (CXX) g++ options: -O3
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d c a b 40 80 120 160 200 159.31 160.91 163.13 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Palabos OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 100 a c b 160 320 480 640 800 734.58 734.15 729.04 1. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm
QuantLib Size: S
a: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
b: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
c: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
Stockfish OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 17 Chess Benchmark c a b 120M 240M 360M 480M 600M 557325172 512969802 477502351 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 1080p b c a 7 14 21 28 35 28.79 28.78 28.76 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Rustls OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 b c a 600K 1200K 1800K 2400K 3000K 2963208.68 2869856.83 2839244.84 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Rustls OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a b c 400K 800K 1200K 1600K 2000K 2073385.56 2060813.40 2035952.96 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
NAMD OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: STMV with 1,066,628 Atoms c b a 1.2863 2.5726 3.8589 5.1452 6.4315 5.71674 5.65973 5.65889
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU c a b 3K 6K 9K 12K 15K 11909 11987 12038
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b c 1300 2600 3900 5200 6500 6054 6085 6104
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 b a c 20 40 60 80 100 79.85 74.92 73.96 1. (CXX) g++ options: -O3
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU b a c 1100 2200 3300 4400 5500 5143 5158 5174
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b c 1100 2200 3300 4400 5500 5169 5196 5202
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 b c a 20 40 60 80 100 78.14 76.26 75.97 1. (CXX) g++ options: -O3
Laghos OpenBenchmarking.org Major Kernels Total Rate, More Is Better Laghos 3.1 Test: Sedov Blast Wave, ube_922_hex.mesh a c b 90 180 270 360 450 404.65 403.45 397.50 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 a c b 40 80 120 160 200 160.28 155.34 154.18 1. (CXX) g++ options: -O3
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a c b 4K 8K 12K 16K 20K 20412 20511 20522
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU b a c 700 1400 2100 2800 3500 3035 3042 3054
RELION OpenBenchmarking.org Seconds, Fewer Is Better RELION 5.0 Test: Basic - Device: CPU b c a 20 40 60 80 100 74.22 74.58 76.04 1. (CXX) g++ options: -fPIC -std=c++14 -fopenmp -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi
OSPRay OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time a b c 10 20 30 40 50 42.91 42.87 42.80
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU b a c 600 1200 1800 2400 3000 2585 2603 2620
OSPRay OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/ao/real_time b a c 10 20 30 40 50 43.40 43.39 43.19
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b c 40 80 120 160 200 190 190 191
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b c 600 1200 1800 2400 3000 2573 2575 2599
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU b a c 40 80 120 160 200 163 164 164
OSPRay OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time b a c 11 22 33 44 55 50.51 50.41 50.35
Rustls OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 b c a 90K 180K 270K 360K 450K 403088.18 402383.42 399853.90 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Palabos Grid Size: 4000
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.
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU c a b 6 12 18 24 30 25.39 25.72 26.04 MIN: 10.78 / MAX: 87.72 MIN: 10.36 / MAX: 59.49 MIN: 9.89 / MAX: 73.93 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU c b a 1500 3000 4500 6000 7500 6951.71 6771.73 6669.51 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 4K a c b 9 18 27 36 45 39.60 39.04 38.52 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a c b 110 220 330 440 550 499.71 499.76 499.92 MIN: 449.21 / MAX: 571.54 MIN: 466.23 / MAX: 522.51 MIN: 479.24 / MAX: 552.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU c a b 20 40 60 80 100 95.91 95.79 95.78 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU c a b 60 120 180 240 300 267.08 267.41 267.41 MIN: 243.4 / MAX: 286.84 MIN: 216.32 / MAX: 362.62 MIN: 244.77 / MAX: 328.68 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU c b a 40 80 120 160 200 179.45 179.29 179.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b c 160 320 480 640 800 749 751 755
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU b a c 11 22 33 44 55 47.71 47.76 48.05 MIN: 39.39 / MAX: 104.16 MIN: 36.58 / MAX: 94.91 MIN: 35.89 / MAX: 151.58 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU b a c 200 400 600 800 1000 1005.17 1004.04 998.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b c 140 280 420 560 700 638 640 641
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b c 11 22 33 44 55 47.76 47.84 48.12 MIN: 42.27 / MAX: 95.66 MIN: 40.4 / MAX: 93.82 MIN: 43.74 / MAX: 95.68 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b c 200 400 600 800 1000 1004.23 1002.63 996.74 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Laghos OpenBenchmarking.org Major Kernels Total Rate, More Is Better Laghos 3.1 Test: Triple Point Problem c b a 40 80 120 160 200 204.16 203.72 202.39 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 1.1453 2.2906 3.4359 4.5812 5.7265 5.07 5.09 5.09 MIN: 4.31 / MAX: 24 MIN: 4.4 / MAX: 27.98 MIN: 4.35 / MAX: 26.38 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 2K 4K 6K 8K 10K 9438.66 9405.62 9401.19 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c 2 4 6 8 10 6.09 6.09 6.10 MIN: 5.01 / MAX: 32 MIN: 4.9 / MAX: 31.14 MIN: 4.96 / MAX: 28.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c 7K 14K 21K 28K 35K 31408.22 31395.35 31348.09 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU a b c 0.9473 1.8946 2.8419 3.7892 4.7365 4.21 4.21 4.21 MIN: 3.52 / MAX: 21.19 MIN: 3.83 / MAX: 23.73 MIN: 3.57 / MAX: 20.4 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU b c a 2K 4K 6K 8K 10K 11377.20 11360.69 11355.93 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a c b 4 8 12 16 20 15.03 15.03 15.04 MIN: 13.37 / MAX: 48.6 MIN: 13.1 / MAX: 58.58 MIN: 13.62 / MAX: 54.33 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a c b 700 1400 2100 2800 3500 3190.93 3190.21 3188.25 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c 3 6 9 12 15 13.51 13.54 13.54 MIN: 11.72 / MAX: 45 MIN: 12.3 / MAX: 45.77 MIN: 11.78 / MAX: 41.47 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c 800 1600 2400 3200 4000 3548.57 3541.66 3540.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU b c a 9 18 27 36 45 37.50 37.54 37.62 MIN: 29.82 / MAX: 58.47 MIN: 32.61 / MAX: 58.23 MIN: 31.29 / MAX: 56.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c 1100 2200 3300 4400 5500 5096.13 5092.60 5085.52 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU c a b 9 18 27 36 45 39.26 39.29 39.36 MIN: 31.98 / MAX: 70.5 MIN: 32.59 / MAX: 69.46 MIN: 33.81 / MAX: 75.48 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU c a b 1000 2000 3000 4000 5000 4862.29 4858.25 4855.51 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c 0.1283 0.2566 0.3849 0.5132 0.6415 0.56 0.57 0.57 MIN: 0.51 / MAX: 20.56 MIN: 0.51 / MAX: 45.57 MIN: 0.51 / MAX: 18.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU b c a 30K 60K 90K 120K 150K 137459.28 136174.80 134020.93 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU b a c 5 10 15 20 25 20.29 20.30 20.34 MIN: 17.92 / MAX: 98.47 MIN: 18.42 / MAX: 53.61 MIN: 17.23 / MAX: 77.56 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU a b c 2K 4K 6K 8K 10K 9365.24 9360.81 9344.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a c b 0.0833 0.1666 0.2499 0.3332 0.4165 0.36 0.36 0.37 MIN: 0.33 / MAX: 45.82 MIN: 0.33 / MAX: 47.54 MIN: 0.33 / MAX: 45.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c 40K 80K 120K 160K 200K 164808.53 158277.32 157712.09 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 3 6 9 12 15 10.61 10.61 10.69 MIN: 8.51 / MAX: 44.19 MIN: 8.75 / MAX: 49.94 MIN: 8.86 / MAX: 55.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 4K 8K 12K 16K 20K 17881.36 17864.80 17734.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU b a c 2 4 6 8 10 6.41 6.42 6.42 MIN: 4.86 / MAX: 30.37 MIN: 4.91 / MAX: 29.23 MIN: 5.39 / MAX: 28.39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU b a c 1600 3200 4800 6400 8000 7462.48 7461.75 7455.49 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c 1.0418 2.0836 3.1254 4.1672 5.209 4.62 4.63 4.63 MIN: 3.61 / MAX: 26.86 MIN: 3.64 / MAX: 25.83 MIN: 3.65 / MAX: 27.38 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU b a c 2K 4K 6K 8K 10K 10339.33 10334.31 10331.07 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b c 0.5175 1.035 1.5525 2.07 2.5875 2.3 2.3 2.3 MIN: 1.81 / MAX: 19.11 MIN: 1.94 / MAX: 25.03 MIN: 1.84 / MAX: 19.42 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b c 4K 8K 12K 16K 20K 20737.16 20684.11 20660.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU c b a 2K 4K 6K 8K 10K 10227 10233 10279
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 c a b 16 32 48 64 80 72.06 69.99 65.87 1. (CXX) g++ options: -O3
7-Zip Compression OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression Test: Decompression Rating b c a 300K 600K 900K 1200K 1500K 1192798 1181592 1178953 1. 7-Zip 24.08 (x64) : Copyright (c) 1999-2024 Igor Pavlov : 2024-08-11
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression Test: Compression Rating a c b 200K 400K 600K 800K 1000K 784684 776559 773934 1. 7-Zip 24.08 (x64) : Copyright (c) 1999-2024 Igor Pavlov : 2024-08-11
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 c a b 20 40 60 80 100 78.73 75.67 72.24 1. (CXX) g++ options: -O3
WebP Image Encode OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100, Lossless, Highest Compression c b a 0.126 0.252 0.378 0.504 0.63 0.56 0.56 0.56 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 c b a 40 80 120 160 200 163.84 159.58 158.71 1. (CXX) g++ options: -O3
QuantLib Size: XXS
a: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
b: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
c: The test quit with a non-zero exit status. E: Error: INVALID BENCHMARK RUN.
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 1080p c a b 20 40 60 80 100 96.10 95.44 94.72 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
GROMACS OpenBenchmarking.org Ns Per Day, More Is Better GROMACS Input: water_GMX50_bare a c b 3 6 9 12 15 12.69 12.29 12.13 1. GROMACS version: 2024.2-Ubuntu_2024.2_1
srsRAN Project OpenBenchmarking.org Mbps, More Is Better srsRAN Project 24.10 Test: PDSCH Processor Benchmark, Throughput Total b a c 30K 60K 90K 120K 150K 132681.9 129795.7 128169.6 1. (CXX) g++ options: -O3 -march=native -mtune=generic -fno-trapping-math -fno-math-errno -ldl
C-Ray OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 5K - Rays Per Pixel: 16 b a c 8 16 24 32 40 32.07 32.10 32.31 1. (CC) gcc options: -lpthread -lm
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 2024 Implementation: MPI CPU - Input: water_GMX50_bare a c b 5 10 15 20 25 19.99 19.87 19.70 1. (CXX) g++ options: -O3 -lm
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 b c a 7 14 21 28 35 30.39 30.19 26.13 1. (CXX) g++ options: -O3
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 4K b c a 30 60 90 120 150 121.82 115.68 110.45 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 b c a 7 14 21 28 35 31.05 30.94 30.83 1. (CXX) g++ options: -O3
Etcpak OpenBenchmarking.org Mpx/s, More Is Better Etcpak 2.0 Benchmark: Multi-Threaded - Configuration: ETC2 a c b 200 400 600 800 1000 875.75 856.22 853.03 1. (CXX) g++ options: -flto -pthread
Rustls OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a c b 20K 40K 60K 80K 100K 82349.22 82326.54 82232.23 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 c a b 40 80 120 160 200 167.59 158.95 158.65 1. (CXX) g++ options: -O3
C-Ray OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 4K - Rays Per Pixel: 16 c a b 5 10 15 20 25 18.22 18.26 18.50 1. (CC) gcc options: -lpthread -lm
x265 OpenBenchmarking.org Frames Per Second, More Is Better x265 Video Input: Bosphorus 4K c a b 8 16 24 32 40 35.01 34.90 34.83 1. x265 [info]: HEVC encoder version 3.6+1-aa7f602f7
OpenBenchmarking.org Frames Per Second, More Is Better x265 4.1 Video Input: Bosphorus 4K c a b 8 16 24 32 40 36.03 35.86 35.78 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 4K b c a 40 80 120 160 200 187.69 184.33 154.09 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 c b a 13 26 39 52 65 56.60 54.25 54.03 1. (CXX) g++ options: -O3
ACES DGEMM OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate b a c 800 1600 2400 3200 4000 3796.86 3788.09 3782.57 1. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 1080p b c a 70 140 210 280 350 328.08 321.12 316.40 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction a c b 0.9338 1.8676 2.8014 3.7352 4.669 3.97435308 4.05741787 4.15029907 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 1080p c a b 140 280 420 560 700 636.98 551.64 480.53 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
WebP Image Encode OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100, Highest Compression c b a 0.8123 1.6246 2.4369 3.2492 4.0615 3.61 3.59 3.57 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
x265 OpenBenchmarking.org Frames Per Second, More Is Better x265 Video Input: Bosphorus 1080p b a c 20 40 60 80 100 98.77 97.18 97.06 1. x265 [info]: HEVC encoder version 3.6+1-aa7f602f7
OpenBenchmarking.org Frames Per Second, More Is Better x265 4.1 Video Input: Bosphorus 1080p a b c 20 40 60 80 100 100.86 99.95 98.10 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction b a c 0.3182 0.6364 0.9546 1.2728 1.591 1.28448296 1.29827499 1.41423202 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
C-Ray OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 1080p - Rays Per Pixel: 16 c a b 1.1977 2.3954 3.5931 4.7908 5.9885 4.865 5.041 5.323 1. (CC) gcc options: -lpthread -lm
VVenC Video Input: Bosphorus 4K - Video Preset: Fast
a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Video Input: Bosphorus 1080p - Video Preset: Faster
a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Video Input: Bosphorus 1080p - Video Preset: Fast
a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Video Input: Bosphorus 4K - Video Preset: Faster
a: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
b: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
c: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101148Java Notes: OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 December 2024 18:54 by user phoronix.
b Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101148Java Notes: OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 December 2024 23:48 by user phoronix.
c Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101148Java Notes: OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 30 December 2024 13:48 by user phoronix.