2024 Server CPUs Benchmarks by Michael Larabel for a future article. 2 x Intel Xeon Max 9480 testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2405073-NE-UPLOAD15789&grs&sro .
2024 Server CPUs Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads) Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) Intel Device 1bce 512GB 2 x 1920GB KIOXIA KCD8XPUG1T92 ASPEED Ubuntu 24.04 6.9.0-060900rc3-generic (x86_64) GCC 13.2.0 ext4 1920x1200 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) 1008GB 2 x Intel X710 for 10GBASE-T INTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads) 512GB 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads) 1008GB 2 x Intel X710 for 10GBASE-T Intel Xeon Max 9468 @ 3.50GHz (48 Cores / 96 Threads) 576GB 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads) 1136GB 2 x Intel X710 for 10GBASE-T Intel Xeon Max 9480 @ 3.50GHz (56 Cores / 112 Threads) 576GB 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads) 1136GB 2 x Intel X710 for 10GBASE-T OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Xeon Platinum 8490H: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590 - Xeon Platinum 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590 - Xeon Platinum 8592+: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200 - Xeon Platinum 8592+ 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200 - Xeon Max 9468: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290 - Xeon Max 9468 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290 - Xeon Max 9480: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290 - Xeon Max 9480 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290 Java Details - OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1) Python Details - Python 3.12.2 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
2024 Server CPUs brl-cad: VGR Performance Metric onednn: Deconvolution Batch shapes_1d - CPU onednn: IP Shapes 3D - CPU askap: tConvolve OpenMP - Gridding onednn: Recurrent Neural Network Training - CPU llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPU npb: SP.C npb: LU.C openvino: Handwritten English Recognition FP16-INT8 - CPU askap: tConvolve MPI - Gridding ospray: particle_volume/ao/real_time ospray: particle_volume/scivis/real_time askap: tConvolve MPI - Degridding openvino: Face Detection FP16-INT8 - CPU openfoam: drivaerFastback, Medium Mesh Size - Execution Time minibude: OpenMP - BM1 minibude: OpenMP - BM1 openvino: Person Re-Identification Retail FP16 - CPU coremark: CoreMark Size 666 - Iterations Per Second lulesh: ospray-studio: 1 - 4K - 16 - Path Tracer - CPU john-the-ripper: bcrypt openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU john-the-ripper: Blowfish openssl: ChaCha20 openvino: Weld Porosity Detection FP16-INT8 - CPU onednn: Convolution Batch Shapes Auto - CPU xmrig: GhostRider - 1M ospray-studio: 3 - 4K - 16 - Path Tracer - CPU npb: EP.D openssl: SHA256 openssl: AES-256-GCM openssl: RSA4096 mt-dgemm: Sustained Floating-Point Rate tensorflow: CPU - 1 - ResNet-50 npb: CG.C llamafile: llava-v1.5-7b-q4 - CPU openssl: SHA512 astcenc: Exhaustive astcenc: Very Thorough aircrack-ng: tensorflow: CPU - 1 - GoogLeNet ospray-studio: 1 - 4K - 32 - Path Tracer - CPU m-queens: Time To Solve rocksdb: Rand Read primesieve: 1e12 john-the-ripper: WPA PSK speedb: Rand Read compress-7zip: Decompression Rating openssl: AES-128-GCM openssl: ChaCha20-Poly1305 pennant: leblancbig hpcg: 144 144 144 - 60 openvino: Face Detection Retail FP16-INT8 - CPU ospray: gravity_spheres_volume/dim_512/ao/real_time ospray: gravity_spheres_volume/dim_512/scivis/real_time minibude: OpenMP - BM2 minibude: OpenMP - BM2 openvino: Machine Translation EN To DE FP16 - CPU primesieve: 1e13 openssl: RSA4096 embree: Pathtracer ISPC - Asian Dragon Obj quantlib: Multi-Threaded relion: Basic - CPU npb: MG.C astcenc: Thorough embree: Pathtracer ISPC - Asian Dragon openradioss: Chrysler Neon 1M ospray-studio: 3 - 4K - 1 - Path Tracer - CPU embree: Pathtracer ISPC - Crown ospray-studio: 1 - 4K - 1 - Path Tracer - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU npb: IS.D openvkl: vklBenchmarkCPU ISPC incompact3d: input.i3d 193 Cells Per Direction graphics-magick: Resizing blender: Classroom - CPU-Only helsing: 14 digit openvino: Person Detection FP16 - CPU liquid-dsp: 256 - 256 - 32 blender: Pabellon Barcelona - CPU-Only blender: Barbershop - CPU-Only openvino: Person Detection FP16 - CPU srsran: PUSCH Processor Benchmark, Throughput Total graphics-magick: Sharpen onnx: T5 Encoder - CPU - Standard blender: BMW27 - CPU-Only blender: Fishy Cat - CPU-Only gromacs: MPI CPU - water_GMX50_bare ospray: gravity_spheres_volume/dim_512/pathtracer/real_time ospray-studio: 3 - 4K - 32 - Path Tracer - CPU liquid-dsp: 256 - 256 - 512 askap: tConvolve MT - Gridding luxcorerender: Rainbow Colors and Prism - CPU incompact3d: X3D-benchmarking input.i3d wrf: conus 2.5km blender: Junkshop - CPU-Only graphics-magick: Enhanced openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU kvazaar: Bosphorus 4K - Slow openvino: Machine Translation EN To DE FP16 - CPU kvazaar: Bosphorus 4K - Medium pgbench: 100 - 1000 - Read Write pgbench: 100 - 1000 - Read Write - Average Latency amg: build-linux-kernel: allmodconfig oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only openvino: Noise Suppression Poconet-Like FP16 - CPU astcenc: Medium oidn: RTLightmap.hdr.4096x4096 - CPU-Only liquid-dsp: 256 - 256 - 57 pytorch: CPU - 1 - ResNet-50 compress-7zip: Compression Rating dacapobench: Tradebeans pennant: sedovbig onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel appleseed: Material Tester onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: GPT-2 - CPU - Standard uvg266: Bosphorus 4K - Slow onednn: Deconvolution Batch shapes_3d - CPU lammps: Rhodopsin Protein uvg266: Bosphorus 4K - Medium speedb: Read While Writing lammps: 20k Atoms openvino: Noise Suppression Poconet-Like FP16 - CPU build-llvm: Ninja onednn: IP Shapes 1D - CPU onnx: ArcFace ResNet-100 - CPU - Standard octave-benchmark: openfoam: drivaerFastback, Small Mesh Size - Execution Time tensorflow: CPU - 512 - AlexNet dacapobench: Tradesoap cloverleaf: clover_bm16 onnx: T5 Encoder - CPU - Parallel liquid-dsp: 128 - 256 - 512 build-nodejs: Time To Compile pytorch: CPU - 1 - ResNet-152 onnx: GPT-2 - CPU - Parallel kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 4K - Super Fast tensorflow: CPU - 256 - AlexNet openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU graphics-magick: Swirl onnx: CaffeNet 12-int8 - CPU - Parallel cockroach: KV, 50% Reads - 512 pytorch: CPU - 64 - ResNet-50 pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 512 - ResNet-50 luxcorerender: Orange Juice - CPU build-linux-kernel: defconfig pytorch: CPU - 64 - ResNet-152 liquid-dsp: 128 - 256 - 57 onnx: yolov4 - CPU - Parallel y-cruncher: 1B pytorch: CPU - 256 - ResNet-152 openvino: Handwritten English Recognition FP16-INT8 - CPU openradioss: Rubber O-Ring Seal Installation openradioss: INIVOL and Fluid Structure Interaction Drop Container pytorch: CPU - 512 - ResNet-152 y-cruncher: 500M onnx: yolov4 - CPU - Standard cloverleaf: clover_bm64_short openvino: Face Detection FP16-INT8 - CPU kvazaar: Bosphorus 4K - Ultra Fast openvino: Vehicle Detection FP16-INT8 - CPU onnx: fcn-resnet101-11 - CPU - Parallel uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Super Fast onnx: CaffeNet 12-int8 - CPU - Standard uvg266: Bosphorus 4K - Ultra Fast build-ffmpeg: Time To Compile onnx: bertsquad-12 - CPU - Standard openvino: Weld Porosity Detection FP16-INT8 - CPU liquid-dsp: 128 - 256 - 32 tensorflow: CPU - 512 - GoogLeNet draco: Church Facade tensorflow: CPU - 512 - ResNet-50 graphics-magick: HWB Color Space openvino: Person Vehicle Bike Detection FP16 - CPU memcached: 1:100 openvino: Person Re-Identification Retail FP16 - CPU svt-av1: Preset 12 - Bosphorus 4K onnx: bertsquad-12 - CPU - Parallel svt-av1: Preset 8 - Bosphorus 4K build-godot: Time To Compile x265: Bosphorus 4K gpaw: Carbon Nanotube ospray: particle_volume/pathtracer/real_time svt-av1: Preset 13 - Bosphorus 4K graphics-magick: Rotate nwchem: C240 Buckyball tensorflow: CPU - 256 - GoogLeNet build-gem5: Time To Compile build-imagemagick: Time To Compile liquid-dsp: 64 - 256 - 512 jpegxl: JPEG - 90 jpegxl: PNG - 90 draco: Lion onnx: super-resolution-10 - CPU - Parallel compress-zstd: 19 - Compression Speed onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel avifenc: 6 tensorflow: CPU - 256 - ResNet-50 vvenc: Bosphorus 4K - Faster appleseed: Disney Material duckdb: IMDB rawtherapee: Total Benchmark Time tensorflow: CPU - 64 - ResNet-50 svt-av1: Preset 4 - Bosphorus 4K compress-zstd: 19, Long Mode - Compression Speed liquid-dsp: 64 - 256 - 32 tensorflow: CPU - 64 - GoogLeNet onnx: super-resolution-10 - CPU - Standard graphics-magick: Noise-Gaussian avifenc: 0 avifenc: 6, Lossless compress-zstd: 19 - Decompression Speed openradioss: Cell Phone Drop Test onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard compress-zstd: 19, Long Mode - Decompression Speed build-mesa: Time To Compile liquid-dsp: 64 - 256 - 57 openvino: Face Detection Retail FP16-INT8 - CPU qmcpack: Li2_STO_ae graph500: 26 openfoam: drivaerFastback, Small Mesh Size - Mesh Time vvenc: Bosphorus 4K - Fast avifenc: 2 tensorflow: CPU - 64 - AlexNet build-php: Time To Compile ffmpeg: libx265 - Upload openfoam: drivaerFastback, Medium Mesh Size - Mesh Time node-web-tooling: jpegxl: JPEG - 100 build-wasmer: Time To Compile apache-iotdb: 500 - 100 - 800 - 400 numpy: jpegxl: PNG - 100 avifenc: 10, Lossless ffmpeg: libx265 - Video On Demand duckdb: TPC-H Parquet openvino: Road Segmentation ADAS FP16-INT8 - CPU apache-iotdb: 800 - 100 - 800 - 100 webp: Quality 100, Lossless, Highest Compression ffmpeg: libx265 - Platform apache-iotdb: 500 - 100 - 800 - 400 apache-iotdb: 800 - 100 - 800 - 100 graph500: 26 clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache srsran: PDSCH Processor Benchmark, Throughput Thread webp: Quality 100, Lossless openradioss: Bird Strike on Windshield appleseed: Emily dacapobench: Jython clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, Third Run build-python: Released Build, PGO + LTO Optimized dacapobench: Apache Lucene Search Index webp: Quality 100 build-python: Default webp: Quality 100, Highest Compression securemark: SecureMark-TLS synthmark: VoiceMark_100 quantlib: Single-Threaded liquid-dsp: 1 - 256 - 512 pybench: Total For Average Test Times liquid-dsp: 1 - 256 - 32 liquid-dsp: 1 - 256 - 57 dacapobench: Apache Kafka openradioss: Bumper Beam nginx: 1000 graph500: 26 graph500: 26 srsran: PUSCH Processor Benchmark, Throughput Thread askap: tConvolve MT - Degridding stockfish: Chess Benchmark onnx: T5 Encoder - CPU - Parallel onnx: T5 Encoder - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Standard onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel onnx: super-resolution-10 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: yolov4 - CPU - Standard onednn: Recurrent Neural Network Inference - CPU tensorflow: CPU - 1 - AlexNet srsran: PDSCH Processor Benchmark, Throughput Total compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression luxcorerender: Danish Mood - CPU luxcorerender: LuxCore Benchmark - CPU luxcorerender: DLSC - CPU easywave: e2Asean Grid + BengkuluSept2007 Source - 2400 easywave: e2Asean Grid + BengkuluSept2007 Source - 1200 namd: STMV with 1,066,628 Atoms namd: ATPase with 327,506 Atoms askap: tConvolve OpenMP - Degridding minife: Small rocksdb: Read While Writing cockroach: KV, 60% Reads - 512 cockroach: KV, 95% Reads - 512 pgbench: 100 - 1000 - Read Only - Average Latency pgbench: 100 - 1000 - Read Only john-the-ripper: MD5 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P 833892 6.15856 0.771506 19798.5 623.604 5.85 71245.26 135125.15 1643.43 21314.2 21.9324 21.8932 17891.6 167.83 420.6467 82.848 2071.189 5943.66 2194630.600449 23072.302 31380 94551 3606.12 3325.90 94513 316126421173 15943.17 0.650618 5808.8 36649 7562.80 61806994523 700239352717 974189.9 23.543705 10.53 33811.63 20.95 22219927723 4.2689 7.0885 147469.328 33.56 58026 15.211 265366170 4.576 401278 276179617 287862 768804693697 225038850730 4.955865 31.0738 9004.23 19.8458 19.5762 86.967 2174.192 477.77 51.820 27431.1 79.3805 179647.5 373.182 83448.70 51.2971 91.9925 207.20 1977 70.0540 1657 1068.43 2865.72 1734 12.9293413 229 68.61 93.348 298.56 3243800000 87.92 261.97 100.39 2616.9 157 357.355 25.89 34.83 8.762 24.6445 68006 1020833333 8088.11 13.54 357.009712 11980.806 35.96 216 115106.30 20.23 62.46 20.97 71227 14.040 1605097000 362.454 2.71 2.71 4209.10 333.9902 1.29 3500833333 51.46 388190 7270 16.03080 313.100 46.8491 126.152247 315.410 222.029 15.71 1.07743 28.716 17.85 10695360 34.892 13.95 187.017 0.539467 52.8167 7.532 42.219419 1278.45 4115 328.47 326.143 918566667 254.003 19.41 191.562 50.03 66.74 1205.30 0.43 502 784.304 108953.6 56.01 54.84 56.44 13.46 39.450 20.13 3181266667 18.1413 7.047 20.25 36.20 59.91 140.43 20.46 3.267 19.8593 39.48 356.38 74.57 17.84 3.03922 49.42 55.54 852.326 60.87 24.056 20.1453 3.58 3200600000 461.23 5670 148.45 265 16.50 4481667.95 9.79 164.250 16.0956 70.908 140.233 37.86 47.776 160.242 162.474 196 2070.3 448.46 210.934 14.724 744410000 43.202 42.905 4731 205.525 14.6 32.3433 3.169 143.67 15.060 53.490276 99.493 46.757 120.93 7.061 7.94 1890566667 380.14 227.423 158 69.931 6.278 1032.0 31.49 34.0021 1069.1 19.226 2539200000 6.43 109.30 31.384585 6.719 37.752 969.62 48.007 24.97 160.72685 15.76 28.754 34.933 87797206 455.57 28.100 4.923 49.84 145.574 55.99 90871770 0.52 49.79 294.33 85.16 465.50 680.2 1.31 117.41 120.750285 3801 486.05 481.66 277.39 3581 10.11 19.201 3.08 277205 711.378 3209.6 16882333 765 36506000 67074667 5106 79.54 129.7 96887479 3.06500 2.79694 30.9165 29.4080 1.27368 1.17292 3.19298 3.17002 21.3436 18.9319 5.21520 4.49976 62.1276 49.6376 4.86604 4.39649 329.036 116.315 8.59719 55.1204 50.3522 409.592 56.53 24688.5 2.144857 6.85 7.10 8.72 119.837 46.289 1.05274 2.97021 30471.5 35230.1 7841738 116603.7 131999.7 0.572 1748146 9583000 4136969 16.5507 0.714699 17010.8 635.154 3.82 147311.14 261127.09 4744.05 41773.0 38.2235 38.2269 34614.1 423.18 196.49644 133.628 3340.694 15519.92 3902076.243612 43724.062 14138 183603 7862.58 5483.81 183583 624402972947 47654.95 0.438154 11263.2 16837 14946.76 119106802107 1369534328470 1916162.9 45.965955 4.39 58128.24 10.44 42846254477 8.3701 13.7518 53914.933 13.50 33411 7.881 525049998 2.325 793253 551286958 557054 1533026300727 442202532977 2.529807 60.8515 20937.58 36.1529 35.6026 140.828 3520.705 793.64 27.107 54601.1 132.2806 350187.5 203.407 163333.21 86.9845 152.7472 115.89 1063 124.7084 894 1843.61 3960.28 2716 6.39169817 95 35.91 50.831 654.84 6116566667 46.38 141.54 45.78 4853.6 265 288.471 13.74 19.13 15.450 42.8188 38813 1616966667 7630.06 5.96 196.808116 6674.12 21.15 342 189893.31 31.24 37.58 32.04 67315 14.856 3124402667 218.570 4.48 4.41 7356.63 484.5499 2.18 5361266667 35.53 592729 8050 11.28438 156.461 29.1487 225.34692 177.763 180.032 24.71 0.736170 42.281 27.65 17297027 50.521 15.96 122.314 0.783180 36.2493 8.036 28.556037 1899.64 4215 214.80 246.335 1126466667 172.990 15.77 144.640 67.64 69.05 1730.25 0.29 617 566.377 68524.7 37.08 37.44 37.55 18.70 29.981 14.03 3723666667 12.7546 5.008 14.08 25.12 88.39 107.36 14.59 2.364 15.5555 26.58 283.11 72.01 21.73 2.83498 54.88 55.40 696.980 55.26 19.506 16.5705 2.50 3558600000 576.08 5672 174.95 236 15.04 3245908.40 7.72 156.516 14.5280 65.224 118.572 37.04 41.563 149.088 154.502 172 1960.9 528.93 178.282 13.262 799496667 42.040 40.075 4733 188.890 15.2 30.0368 3.044 161.06 12.536 48.56418 125.882 53.758 115.47 6.698 8.16 2025000000 331.76 212.924 182 67.375 6.172 963.6 28.22 33.6082 992.1 18.293 2655500000 5.72 101.629 35.604097 6.480 37.311 996.47 46.644 24.56 162.02669 15.49 28.163 35.455 80169620 456.18 27.659 5.074 48.77 155.730 65.02 83651785 0.51 48.76 317.36 92.23 485.63 675.5 1.30 124.44 130.618252 3892 507.56 501.63 279.692 3689 10.05 18.931 3.07 275472 712.697 3210.1 16843333 767 36461000 66991333 5113 81.30 129.7 187761769 4.05881 3.46571 33.2899 29.7536 1.76353 1.43573 6.39031 5.62517 34.3054 27.5944 6.90619 5.55101 68.8299 60.3589 5.29287 4.72530 352.738 92.3473 10.83623 78.3989 64.2858 633.288 37.57 30108.7 1.469210 7.00 8.82 11.12 126.388 50.834 1.10900 2.21948 51476.2 46877.5 12321300 72110.1 82341.2 1.293 778141 18166000 916904 6.69692 0.841608 19141.8 703.474 4.08 109416.42 232012.77 2924.66 37265.9 30.8404 30.6799 31177.2 284.64 302.0641 106.395 2659.883 9515.86 2369998.356940 38433.973 23125 105781 5725.03 4656.92 105831 344150916937 26943.42 0.585804 8378.3 31993 8089.14 66573957920 744387683670 1036735.6 29.141078 6.43 63760.45 16.61 23886054770 4.6303 7.6240 153584.203 21.67 50798 14.257 297517946 4.250 428116 315178381 338146 889567506540 223625738013 4.182707 35.1361 12317.94 23.7293 23.1755 108.124 2703.088 592.20 48.406 31594.4 97.1861 195648.8 290.448 107321.89 54.4547 112.6611 157.56 1709 82.9663 1441 1159.66 4059.70 2004 10.1967066 230 63.61 89.070 403.20 3167200000 80.29 236.73 39.62 3088.7 167 460.775 23.72 31.91 10.477 27.1010 59522 1178766667 5062.07 14.28 323.245697 10602.408 32.08 228 81279.79 24.23 26.85 24.80 75396 13.264 1814760000 316.902 3.32 3.31 6757.26 327.7829 1.58 3806833333 77.52 441636 11004 16.96910 308.801 60.4094 118.779059 314.057 270.329 16.06 0.907161 34.301 16.64 12168413 37.460 9.40 165.048 0.398446 66.5162 6.458 33.065393 1486.12 7321 410.59 462.855 1152933333 214.431 27.21 248.682 38.02 39.20 1277.46 0.49 529 830.725 115715.8 63.06 63.60 63.30 14.74 34.591 23.49 3503200000 20.8795 6.701 23.33 21.87 54.14 128.74 23.41 3.391 22.9689 39.38 224.64 47.07 13.73 3.30836 35.10 35.56 908.187 39.31 21.357 25.1591 2.36 3148233333 462.78 4565 140.53 285 11.17 4752673.79 6.72 177.861 19.6773 79.437 122.718 38.93 43.048 193.138 174.832 203 1878.3 423.59 187.507 12.595 783770000 48.360 46.317 3861 234.540 18.0 33.3797 2.971 129.02 15.966 48.425051 99.184 42.775 91.51 7.876 9.80 1927766667 319.76 259.186 171 64.475 5.784 1221.8 27.90 34.4595 1242.6 17.258 2475500000 5.19 105.98 539613000 31.704905 7.392 34.791 819.89 41.846 26.93 148.40248 17.42 32.239 30.174 92709751 520.22 31.348 4.456 53.99 132.873 55.07 94616807 0.60 53.92 280.26 81.73 416523000 437.20 742.9 1.50 110.32 119.803392 3424 455.79 458.23 244.824 3242 11.36 17.076 3.47 309896 799.717 3600.5 18774333 691 40244000 73140667 5560 78.71 399698.78 1244300000 1299170000 129.5 109766345 2.15980 2.16966 29.9566 29.0185 1.20298 1.10042 3.23780 3.18392 16.5534 15.0376 4.01687 3.69649 50.8307 39.7451 4.26352 3.85774 302.266 109.670 9.11885 47.8953 43.5355 488.922 35.50 26378.1 1.847537 7.63 8.06 9.38 75.732 28.698 1.43787 4.64814 16936.8 31830.2 8926893 121465.2 135861.9 0.589 1699046 10922667 5186677 38.0813 0.738442 20204.9 626.138 3.05 228184.68 455312.09 5570.63 72004.0 54.1195 53.9348 59139.2 545.21 137.03802 199.734 4993.343 18375.63 4966250.777983 70826.734 12124 206778 10934.17 8719.37 205499 684284382760 48122.16 0.306795 16324.7 14358 16004.07 131976050120 1497529939377 2057021.6 58.253340 3.85 98764.93 7.49 46520760707 8.9091 14.6334 64181.293 12.69 24249 7.402 578392800 2.187 797093 586147871 573410 1769313146013 444099144270 2.159459 69.2976 24676.86 42.1295 41.9111 191.818 4795.462 1128.78 25.021 61499.6 173.2208 380867.5 155.741 220893.78 97.9383 199.6089 86.93 898 153.1622 759 2237.69 7437.81 3222 5.39125967 96 33.61 48.091 736.23 6077300000 41.85 125.87 43.41 5493.4 284 356.764 12.76 17.29 18.540 48.7576 33391 2027000000 6038.92 7.22 171.375778 5601.101 18.31 374 128566.81 40.92 28.17 41.58 33110 30.203 3609646333 189.739 5.09 5.03 9360.89 550.0168 2.40 6284300000 45.69 674239 12713 9.964526 153.922 31.4589 210.815856 171.231 236.648 27.11 0.624250 55.496 30.37 17585737 56.400 13.15 106.815 0.580664 38.4240 6.856 23.558932 2039.63 7492 378.05 354.754 1493833333 145.413 17.57 195.453 65.38 66.78 1681.44 0.46 689 605.589 77327.1 40.77 41.45 40.83 19.91 25.872 16.25 4450525000 14.1980 5.110 16.00 22.96 86.85 100.00 16.17 2.659 16.9672 31.90 234.24 73.81 14.67 3.05085 53.66 54.95 754.805 57.13 17.389 22.4251 2.48 3520766667 577.76 4693 169.75 256 11.69 3780240.56 6.95 165.495 15.4341 70.426 103.376 39.31 38.049 176.395 162.979 182 1809.7 501.39 157.363 11.493 883701250 42.974 39.524 3894 214.812 17.8 31.7109 2.805 150.33 13.256 43.695399 127.567 52.689 94.66 7.360 9.67 2154633333 291.37 251.305 194 60.526 5.613 1165.8 26.88 34.6628 1189.7 16.183 2620066667 5.18 97.911 667365000 29.325125 6.960 33.650 858.84 40.381 26.80 139.61713 17.02 31.610 30.472 89231850 519.89 30.966 4.579 53.29 144.258 57.13 92771639 0.59 53.22 286.78 82.73 484977000 423.30 755.5 1.50 113.15 129.956841 3466 443.58 438.60 244.952 3345 11.31 16.928 3.46 308434 799.491 3586.3 18200533 692 38950600 70499000 5611 86.11 381352.69 1204520000 1267480000 129.5 222610378 2.81739 2.80263 31.5324 28.8481 1.64919 1.32454 6.49693 5.83954 31.7907 26.0866 5.10948 4.29531 64.7891 44.5996 4.65431 3.98013 327.875 100.738 9.92684 70.4377 58.9394 538.225 30.76 30547.6 1.432362 7.70 8.88 12.74 102.125 37.660 2.25422 5.85267 48686.8 42114.6 12425519 73640.9 85613.1 1.149 881881 18438600 713937 5.30953 4.32465 4173.46 1200.75 1.47 58815.36 126171.52 2074.30 21766.5 16.0502 16.0869 18522 202.59 440.83113 63.620 1590.501 6717.65 1614763.703237 23848.540 37055 67875 3802.61 2935.47 67893 226597354153 19183.83 9.19434 5446.8 42837 5366.69 44439185187 507456728087 697707.2 19.768930 11.29 35116.55 7.67 16199261277 3.1204 5.1342 117588.992 36.13 68973 21.030 205346154 6.160 286552 211457048 207738 641200848170 161321058213 5.930957 25.2423 9087.12 15.3984 15.5028 70.213 1755.333 415.96 67.324 22861.0 64.9597 143755.3 412.371 85910.95 37.0051 75.4690 228.74 2357 58.4230 1988 860.64 3050.16 1243 13.9692376 245 86.67 123.832 285.95 2381800000 106.96 320.11 41.93 2170.7 114 219.532 31.66 42.78 7.545 19.9102 80742 838530000 3375.32 12.80 407.589406 13273.694 42.85 160 135075.07 17.52 28.73 18.13 69969 14.292 1588496667 428.387 2.27 2.26 4208.49 247.2979 1.08 2848933333 50.99 314716 6130 21.02112 319.043 40.7289 136.492406 330.104 176.333 13.36 1.26407 27.629 15.17 8795408 28.278 11.37 212.482 0.725974 47.2703 7.622 45.947435 1047.96 3887 351.29 337.004 800186667 270.380 19.99 191.111 40.23 53.13 986.04 0.33 394 687.671 103089.8 51.55 52.97 51.05 11.86 43.421 19.01 2670033333 16.1742 8.300 19.20 23.12 59.58 160.56 19.47 3.781 18.2179 41.43 236.52 63.10 16.33 2.62544 39.56 44.05 728.469 48.91 26.458 21.1702 2.50 2351900000 383.57 6707 117.53 286 12.54 4384040.52 7.13 146.097 16.3251 62.750 149.378 29.05 54.376 144.481 144.698 197 2530.5 375.73 220.569 16.075 632396667 39.100 43.362 5217 195.705 14.4 28.5164 3.730 119.73 14.101 58.379116 100.089 46.959 104.23 6.490 7.76 1640266667 333.73 217.880 150 76.915 6.836 1126.4 33.75 29.9973 1131.1 20.175 2138766667 5.27 121.19 31.781874 6.324 41.125 841.68 48.708 23.33 153.12467 15.59 26.864 35.657 82455664 461.61 26.249 4.916 47.34 146.868 55.74 85744542 0.55 47.32 314.44 90.02 446.40 702.6 1.40 126.89 132.132632 3785 465.06 470.02 275.385 3378 10.13 19.117 3.10 277647 711.101 3225.7 16906333 763 36537667 67130333 5108 83.44 129.7 8868.20 68019088 2.97094 4.57581 35.0665 33.3341 1.45280 1.37831 3.13366 3.02897 24.5535 21.2179 5.22781 5.67700 61.2547 47.2417 5.10914 4.58912 380.902 139.096 7.24187 61.8256 54.9599 734.804 48.28 21286.6 2.632077 6.03 6.30 7.46 173.014 63.428 1.45223 5.97130 6758.81 20091.1 7439663 110666.9 128125.9 0.559 1792636 7626333 3658790 13.4500 4.28399 3916.78 1966.88 1.77 135939.25 246822.52 3998.02 42939.2 29.5018 29.3496 36900.5 373.50 201.10956 108.397 2709.930 13102.28 2993136.601832 52102.668 16645 133866 7127.28 5576.86 134562 449908494927 37710.60 7.75431 10975.8 19701 10970.45 88635753413 1011898993323 1395446.4 39.345732 5.11 65396.22 7.77 32304222993 6.2126 10.2051 83665.758 18.24 38926 10.840 405533173 3.121 562875 419943570 401707 1277583382757 320396720447 2.881099 54.4054 17252.27 15.9777 15.3405 127.845 3196.123 795.63 33.921 45531.0 104.8425 288129.1 214.416 172614.10 72.3297 125.7494 125.15 1237 107.6299 1049 1691.79 3816.70 1776 7.29349117 108 44.71 65.026 568.81 4670966667 55.26 169.44 42.16 3787.0 199 199.079 16.55 23.17 13.392 35.9324 45211 1444066667 3347.93 9.64 189.686116 7157.961 24.99 269 174862.56 26.00 29.98 26.69 58952 16.963 3156261667 246.936 3.49 3.51 5565.23 441.6518 1.72 4825133333 46.49 491729 6681 13.21125 166.485 32.8141 243.236578 174.677 141.954 19.75 0.945075 47.512 22.25 13859254 46.705 17.15 134.419 0.662387 40.5671 12.617 28.993119 1604.11 4199 263.33 246.680 1091460000 175.625 17.91 135.976 51.91 52.63 1479.53 0.28 509 492.885 69221.4 42.35 41.68 41.65 16.91 32.143 15.84 3596400000 13.0869 6.334 16.30 24.00 70.73 114.29 16.68 3.110 14.4831 32.25 256.63 54.98 17.19 2.17463 44.75 45.09 604.755 46.13 20.788 16.6394 2.53 3254033333 467.91 6821 145.29 193 13.34 3373323.92 7.32 122.089 13.7366 54.823 123.882 27.26 42.873 137.503 122.617 148 1785 447.50 184.298 14.402 732560000 39.594 34.826 5342 173.909 13.8 24.7274 3.776 141.95 11.897 51.245898 127.703 55.442 111.71 5.991 7.62 1963233333 341.51 205.885 150 69.647 7.121 1040.2 27.51 27.6074 1041.8 18.474 2494050000 5.55 102.12 32.481993 6.023 38.653 932.59 46.871 22.34 134.78213 14.99 27.325 36.197 77501248 435.21 26.842 5.317 45.29 156.136 56.71 80770465 0.54 45.95 328.41 94.84 491.89 651.9 1.39 116.49 137.457437 3926 499.18 501.07 276.457 3643 10.01 18.812 3.09 277589 710.916 3207.0 16904667 763 36497667 67064000 5101 78.27 129.7 14665.0 137977203 4.05270 5.02267 40.4534 36.2283 2.02659 1.65270 6.00525 5.74491 30.4733 24.6510 7.34848 7.04111 72.8018 60.1120 5.74921 4.85818 460.673 121.670 8.39962 76.4227 69.4501 1498.584 37.76 30236.0 1.982932 6.23 6.81 10.17 182.123 74.866 1.88679 7.30065 4437.6 19876.5 9624417 71680.5 80804.7 1.027 976035 12958000 767812 6.09747 4.27481 4438.58 1180.85 1.54 69776.41 131606.86 2243.84 23250.2 18.5533 18.4851 20561.4 217.11 410.29005 70.843 1771.065 7207.74 1855135.326098 25831.838 33790 79144 4093.73 2877.32 79152 263740690067 20910.53 8.75105 6122.3 39238 6445.09 51840436763 592014115453 813667.6 22.539990 9.99 35234.06 8.13 18893980783 3.6276 5.9702 134048.964 31.47 62540 18.102 234469939 5.332 334076 244070674 243347 747710702660 187796174440 5.114161 30.5872 9686.39 16.3219 16.2652 78.105 1952.606 467.08 58.159 25441.5 71.8253 162727.4 384.384 86407.46 42.9834 83.4921 212.99 2123 65.3318 1792 894.87 3076.66 1356 12.7997582 213 76.87 107.237 301.30 2769066667 97.80 290.56 59.69 2514.0 130 215.127 28.49 38.48 8.282 22.3625 73366 944550000 3406.96 12.97 351.644165 12410.29 39.17 181 140144.01 18.24 38.50 18.84 72225 13.845 1597993333 384.063 2.39 2.38 4386.48 284.3336 1.14 3222533333 48.59 342363 5994 19.88246 301.136 42.2711 134.388009 296.799 168.859 13.89 1.19643 30.843 15.68 9988176 32.157 12.72 197.844 0.617190 42.2747 7.748 41.746192 1108.95 3884 357.57 346.213 882200000 252.648 18.07 188.930 41.34 54.47 1058.99 0.37 432 678.483 112265.3 51.35 51.56 51.86 12.50 40.501 19.24 2972400000 16.3898 7.959 19.58 24.94 59.32 146.03 19.29 3.704 16.9166 42.22 257.50 63.99 19.44 2.61721 40.82 45.32 705.606 50.09 24.840 20.0103 2.67 2739633333 398.40 6693 125.14 277 13.59 4315467.17 7.76 151.718 15.7394 65.359 143.808 31.40 48.487 143.480 149.996 194 2245.2 386.00 215.496 15.376 689003333 43.629 40.347 5188 190.063 14.5 28.4798 3.550 123.69 14.362 56.401698 99.619 47.086 103.56 6.572 7.72 1679700000 335.58 213.985 158 73.060 6.605 1127.5 31.92 29.4250 1133.3 19.650 2308966667 5.77 117.81 31.998248 6.501 39.876 852.36 47.951 23.77 150.66848 15.62 27.750 35.201 83475645 464.72 27.087 4.867 48.14 145.238 62.53 86354518 0.55 48.35 309.03 89.53 461.62 705.5 1.39 120.76 128.603449 3707 474.68 476.91 273.515 3396 10.13 18.847 3.10 277260 712.013 3229.1 16885333 762 36539000 67127667 5102 81.72 367199.06 129.7 9204.87 73592230 2.88734 4.64757 35.1110 33.9877 1.47249 1.41662 3.32030 3.37034 23.6565 23.6625 5.29027 5.91961 63.5353 49.9740 5.26075 4.67269 382.109 155.788 6.54965 61.0107 59.1795 632.146 43.67 15081.0 2.287766 6.29 6.82 8.00 145.236 64.883 1.50214 5.92501 7046.56 18621.2 7366500 109388.2 120494.3 0.622 1607424 8957000 4075342 16.0901 4.17553 3836.73 2776.52 1.54 141954.15 257384.55 4351.59 45195.1 33.1125 33.1275 40368.6 401.45 186.32539 114.902 2872.562 14033.94 3279262.530349 53269.469 15357 155959 7689.32 5525.56 156658 522912403347 40032.81 7.06043 12115.0 18111 12793.01 103382860113 1181148957353 1627941.4 44.668302 4.37 66492.44 7.26 37564522053 7.2075 11.8875 65663.823 14.67 36179 9.285 473755946 2.691 657889 497907490 469131 1484669627050 372735215297 2.527363 62.6357 18561.91 15.3743 15.8207 133.990 3349.756 889.18 30.196 48534.8 112.7231 316359.2 201.382 171436.47 83.3395 129.7482 117.91 1143 116.6053 961 1801.89 3819.83 1852 6.66387510 97 40.38 58.248 569.60 5367033333 51.29 156.70 64.91 4386.6 227 185.46 15.29 21.45 14.127 39.3389 41971 1518933333 4382.97 6.51 187.224004 6840.057 23.45 301 176900.32 28.96 41.57 29.62 60046 16.655 3205161000 231.033 3.66 3.65 5933.65 483.1049 1.74 5036000000 35.46 525514 6672 12.10690 153.407 29.1955 239.726773 161.886 132.712 22.14 0.864358 52.244 24.65 15354400 51.816 18.72 128.066 0.759434 33.9621 12.578 27.577291 1677.62 4069 269.20 252.671 1206066667 171.174 14.86 136.689 52.23 54.19 1528.41 0.30 558 478.467 66816.9 38.30 37.91 37.84 16.64 30.530 14.96 3896500000 12.5974 6.266 14.92 25.72 81.65 110.56 14.74 2.961 14.4583 32.44 278.52 58.14 20.24 2.10480 46.25 44.40 581.769 45.79 20.008 17.9873 2.79 3337066667 477.33 6777 138.39 207 14.42 3392842.38 7.97 127.546 13.5190 55.979 122.704 27.90 43.911 135.436 124.263 143 1873.1 449.91 181.629 14.094 757176667 34.634 33.274 5322 169.850 13.3 24.6818 3.738 135.28 11.967 49.136175 131.795 56.776 107.30 6.052 7.46 2090466667 308.95 199.896 164 68.437 7.038 1039.2 27.63 27.7772 1046.0 18.138 2491340000 6.02 106.27 28.840157 6.077 38.136 940.40 46.571 23.30 159.31171 14.51 27.260 35.700 78057728 439.84 26.994 5.311 46.79 158.310 62.11 80139566 0.54 46.59 325.97 95.39 460.66 663.8 1.39 119.03 137.004266 3921 467.96 471.79 276.229 3537 10.03 18.824 3.09 277298 712.085 3222.8 16884000 763 36521333 66266000 5088 80.32 129.7 14463.4 149409082 3.95819 5.39123 40.5178 36.0039 2.08780 1.71875 6.51744 6.17796 34.2507 29.4448 7.30822 7.53259 73.9684 55.9019 5.88628 5.00222 475.254 121.780 8.26016 79.3770 69.2014 719.229 33.21 11866.7 1.711296 5.91 7.41 10.44 173.550 68.860 1.76778 2.56319 7304.58 21583.2 11223329 71696.5 76524.7 1.098 920725 14609417 OpenBenchmarking.org
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.38.2 VGR Performance Metric Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1M 2.2M 3.3M 4.4M 5.5M 713937 3658790 767812 4075342 833892 4136969 916904 5186677 1. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.00876, N = 3 SE +/- 0.10586, N = 3 SE +/- 0.02700, N = 3 SE +/- 0.09318, N = 3 SE +/- 0.00627, N = 3 SE +/- 0.10023, N = 3 SE +/- 0.08324, N = 3 SE +/- 0.32768, N = 3 5.30953 13.45000 6.09747 16.09010 6.15856 16.55070 6.69692 38.08130 MIN: 11.97 MIN: 9.89 MIN: 14.58 MIN: 3.74 MIN: 9.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.973 1.946 2.919 3.892 4.865 SE +/- 0.003490, N = 5 SE +/- 0.004988, N = 5 SE +/- 0.010419, N = 5 SE +/- 0.005278, N = 5 SE +/- 0.003025, N = 5 SE +/- 0.005935, N = 5 SE +/- 0.001432, N = 5 SE +/- 0.004380, N = 5 4.324650 4.283990 4.274810 4.175530 0.771506 0.714699 0.841608 0.738442 MIN: 4.21 MIN: 4.18 MIN: 4.18 MIN: 4.06 MIN: 0.81 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4K 8K 12K 16K 20K SE +/- 13.21, N = 5 SE +/- 40.14, N = 4 SE +/- 33.09, N = 5 SE +/- 13.50, N = 5 SE +/- 195.05, N = 15 SE +/- 139.77, N = 15 SE +/- 211.64, N = 15 SE +/- 221.77, N = 15 4173.46 3916.78 4438.58 3836.73 19798.50 17010.80 19141.80 20204.90 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 600 1200 1800 2400 3000 SE +/- 12.69, N = 3 SE +/- 119.20, N = 12 SE +/- 8.14, N = 3 SE +/- 31.34, N = 3 SE +/- 0.67, N = 3 SE +/- 2.79, N = 3 SE +/- 5.57, N = 3 SE +/- 4.22, N = 3 1200.75 1966.88 1180.85 2776.52 623.60 635.15 703.47 626.14 MIN: 1127.94 MIN: 1146.52 MIN: 1153.29 MIN: 2715.64 MIN: 598.72 MIN: 612.85 MIN: 649.83 MIN: 600.37 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Llamafile Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.7 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.3163 2.6326 3.9489 5.2652 6.5815 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 6 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 1.47 1.77 1.54 1.54 5.85 3.82 4.08 3.05
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50K 100K 150K 200K 250K SE +/- 67.02, N = 3 SE +/- 679.14, N = 4 SE +/- 9.58, N = 3 SE +/- 420.81, N = 4 SE +/- 150.79, N = 3 SE +/- 560.20, N = 4 SE +/- 31.76, N = 4 SE +/- 1528.09, N = 5 58815.36 135939.25 69776.41 141954.15 71245.26 147311.14 109416.42 228184.68 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100K 200K 300K 400K 500K SE +/- 71.37, N = 3 SE +/- 441.66, N = 5 SE +/- 37.04, N = 4 SE +/- 411.20, N = 5 SE +/- 130.20, N = 4 SE +/- 398.40, N = 5 SE +/- 213.44, N = 5 SE +/- 726.00, N = 5 126171.52 246822.52 131606.86 257384.55 135125.15 261127.09 232012.77 455312.09 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1200 2400 3600 4800 6000 SE +/- 3.41, N = 3 SE +/- 1.09, N = 3 SE +/- 4.55, N = 3 SE +/- 2.81, N = 3 SE +/- 1.46, N = 3 SE +/- 2.46, N = 3 SE +/- 0.73, N = 3 SE +/- 3.43, N = 3 2074.30 3998.02 2243.84 4351.59 1643.43 4744.05 2924.66 5570.63 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15K 30K 45K 60K 75K SE +/- 99.83, N = 3 SE +/- 194.30, N = 3 SE +/- 0.00, N = 3 SE +/- 802.88, N = 3 SE +/- 76.67, N = 3 SE +/- 412.68, N = 4 SE +/- 219.20, N = 3 SE +/- 1080.03, N = 3 21766.5 42939.2 23250.2 45195.1 21314.2 41773.0 37265.9 72004.0 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 16.05 29.50 18.55 33.11 21.93 38.22 30.84 54.12
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 16.09 29.35 18.49 33.13 21.89 38.23 30.68 53.93
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13K 26K 39K 52K 65K SE +/- 0.00, N = 3 SE +/- 143.60, N = 3 SE +/- 76.47, N = 3 SE +/- 0.00, N = 3 SE +/- 93.91, N = 3 SE +/- 378.22, N = 4 SE +/- 153.57, N = 3 SE +/- 480.95, N = 3 18522.0 36900.5 20561.4 40368.6 17891.6 34614.1 31177.2 59139.2 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 120 240 360 480 600 SE +/- 0.14, N = 3 SE +/- 0.58, N = 3 SE +/- 0.41, N = 3 SE +/- 0.54, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.69, N = 3 SE +/- 0.77, N = 3 202.59 373.50 217.11 401.45 167.83 423.18 284.64 545.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100 200 300 400 500 440.83 201.11 410.29 186.33 420.65 196.50 302.06 137.04 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.12, N = 4 SE +/- 1.28, N = 12 SE +/- 0.84, N = 15 SE +/- 1.85, N = 12 SE +/- 0.61, N = 5 SE +/- 0.81, N = 7 SE +/- 0.20, N = 6 SE +/- 1.02, N = 8 63.62 108.40 70.84 114.90 82.85 133.63 106.40 199.73 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1100 2200 3300 4400 5500 SE +/- 2.91, N = 4 SE +/- 32.01, N = 12 SE +/- 21.10, N = 15 SE +/- 46.19, N = 12 SE +/- 15.23, N = 5 SE +/- 20.15, N = 7 SE +/- 5.07, N = 6 SE +/- 25.44, N = 8 1590.50 2709.93 1771.07 2872.56 2071.19 3340.69 2659.88 4993.34 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4K 8K 12K 16K 20K SE +/- 3.72, N = 3 SE +/- 3.67, N = 3 SE +/- 0.46, N = 3 SE +/- 7.22, N = 3 SE +/- 3.97, N = 3 SE +/- 4.14, N = 3 SE +/- 5.57, N = 3 SE +/- 7.74, N = 3 6717.65 13102.28 7207.74 14033.94 5943.66 15519.92 9515.86 18375.63 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 1747.99, N = 3 SE +/- 7219.73, N = 3 SE +/- 5202.86, N = 3 SE +/- 20649.43, N = 3 SE +/- 9256.47, N = 3 SE +/- 12743.41, N = 3 SE +/- 4635.95, N = 3 SE +/- 9700.21, N = 3 1614763.70 2993136.60 1855135.33 3279262.53 2194630.60 3902076.24 2369998.36 4966250.78 1. (CC) gcc options: -O2 -lrt" -lrt
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15K 30K 45K 60K 75K SE +/- 211.12, N = 6 SE +/- 206.20, N = 5 SE +/- 217.67, N = 6 SE +/- 207.54, N = 5 SE +/- 182.38, N = 15 SE +/- 272.44, N = 4 SE +/- 437.51, N = 4 SE +/- 359.29, N = 3 23848.54 52102.67 25831.84 53269.47 23072.30 43724.06 38433.97 70826.73 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8K 16K 24K 32K 40K SE +/- 28.06, N = 3 SE +/- 72.42, N = 3 SE +/- 83.47, N = 3 SE +/- 51.39, N = 3 SE +/- 62.46, N = 3 SE +/- 34.10, N = 3 SE +/- 37.49, N = 3 SE +/- 7.13, N = 3 37055 16645 33790 15357 31380 14138 23125 12124
John The Ripper Test: bcrypt OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40K 80K 120K 160K 200K SE +/- 8.84, N = 3 SE +/- 866.68, N = 3 SE +/- 8.67, N = 3 SE +/- 576.80, N = 3 SE +/- 10.67, N = 3 SE +/- 292.24, N = 3 SE +/- 46.28, N = 3 SE +/- 288.38, N = 3 67875 133866 79144 155959 94551 183603 105781 206778 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 7.17, N = 3 SE +/- 4.05, N = 3 SE +/- 9.37, N = 3 SE +/- 3.66, N = 3 SE +/- 4.52, N = 3 SE +/- 8.98, N = 3 SE +/- 4.97, N = 3 SE +/- 3.37, N = 3 3802.61 7127.28 4093.73 7689.32 3606.12 7862.58 5725.03 10934.17 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 8.09, N = 3 SE +/- 4.11, N = 3 SE +/- 5.68, N = 3 SE +/- 8.70, N = 3 SE +/- 0.81, N = 3 SE +/- 11.51, N = 3 SE +/- 0.73, N = 3 SE +/- 6.25, N = 3 2935.47 5576.86 2877.32 5525.56 3325.90 5483.81 4656.92 8719.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40K 80K 120K 160K 200K SE +/- 17.33, N = 3 SE +/- 116.69, N = 3 SE +/- 8.67, N = 3 SE +/- 169.28, N = 3 SE +/- 11.39, N = 3 SE +/- 348.45, N = 3 SE +/- 79.75, N = 3 SE +/- 649.08, N = 3 67893 134562 79152 156658 94513 183583 105831 205499 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 150000M 300000M 450000M 600000M 750000M SE +/- 415487944.57, N = 3 SE +/- 329510485.23, N = 3 SE +/- 312824840.64, N = 3 SE +/- 863978337.15, N = 3 SE +/- 232288636.76, N = 3 SE +/- 271318554.29, N = 3 SE +/- 3335467.26, N = 3 SE +/- 303075210.03, N = 3 226597354153 449908494927 263740690067 522912403347 316126421173 624402972947 344150916937 684284382760 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10K 20K 30K 40K 50K SE +/- 234.43, N = 4 SE +/- 80.58, N = 3 SE +/- 21.27, N = 3 SE +/- 233.95, N = 3 SE +/- 2.71, N = 3 SE +/- 53.98, N = 3 SE +/- 47.41, N = 3 SE +/- 39.08, N = 3 19183.83 37710.60 20910.53 40032.81 15943.17 47654.95 26943.42 48122.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.005800, N = 7 SE +/- 0.039215, N = 7 SE +/- 0.017741, N = 7 SE +/- 0.015670, N = 7 SE +/- 0.001388, N = 7 SE +/- 0.001522, N = 7 SE +/- 0.002339, N = 7 SE +/- 0.001169, N = 7 9.194340 7.754310 8.751050 7.060430 0.650618 0.438154 0.585804 0.306795 MIN: 6.88 MIN: 6.74 MIN: 7.59 MIN: 6.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Xmrig Variant: GhostRider - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3K 6K 9K 12K 15K SE +/- 12.93, N = 3 SE +/- 14.02, N = 3 SE +/- 14.78, N = 3 SE +/- 7.44, N = 3 SE +/- 23.16, N = 3 SE +/- 4.03, N = 3 SE +/- 44.68, N = 3 SE +/- 64.69, N = 3 5446.8 10975.8 6122.3 12115.0 5808.8 11263.2 8378.3 16324.7 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9K 18K 27K 36K 45K SE +/- 36.47, N = 3 SE +/- 25.12, N = 3 SE +/- 74.33, N = 3 SE +/- 10.97, N = 3 SE +/- 61.20, N = 3 SE +/- 29.96, N = 3 SE +/- 26.00, N = 3 SE +/- 8.00, N = 3 42837 19701 39238 18111 36649 16837 31993 14358
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3K 6K 9K 12K 15K SE +/- 155.10, N = 12 SE +/- 4.83, N = 4 SE +/- 6.53, N = 3 SE +/- 10.93, N = 4 SE +/- 6.77, N = 3 SE +/- 100.23, N = 4 SE +/- 22.33, N = 3 SE +/- 30.19, N = 4 5366.69 10970.45 6445.09 12793.01 7562.80 14946.76 8089.14 16004.07 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30000M 60000M 90000M 120000M 150000M SE +/- 27466135.54, N = 3 SE +/- 126029257.64, N = 3 SE +/- 33334799.97, N = 3 SE +/- 70647143.49, N = 3 SE +/- 159515825.53, N = 3 SE +/- 66583540.43, N = 3 SE +/- 23323764.84, N = 3 SE +/- 29142783.86, N = 3 44439185187 88635753413 51840436763 103382860113 61806994523 119106802107 66573957920 131976050120 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300000M 600000M 900000M 1200000M 1500000M SE +/- 119857064.56, N = 3 SE +/- 108288170.03, N = 3 SE +/- 63026881.96, N = 3 SE +/- 112278705.55, N = 3 SE +/- 2848140790.67, N = 3 SE +/- 1397764228.85, N = 3 SE +/- 3966858436.56, N = 3 SE +/- 1320809584.03, N = 3 507456728087 1011898993323 592014115453 1181148957353 700239352717 1369534328470 744387683670 1497529939377 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400K 800K 1200K 1600K 2000K SE +/- 165.80, N = 3 SE +/- 355.69, N = 3 SE +/- 200.66, N = 3 SE +/- 277.84, N = 3 SE +/- 92.46, N = 3 SE +/- 862.96, N = 3 SE +/- 92.62, N = 3 SE +/- 6745.42, N = 3 697707.2 1395446.4 813667.6 1627941.4 974189.9 1916162.9 1036735.6 2057021.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13 26 39 52 65 SE +/- 0.04, N = 4 SE +/- 0.06, N = 7 SE +/- 0.09, N = 5 SE +/- 0.04, N = 7 SE +/- 0.09, N = 5 SE +/- 0.28, N = 7 SE +/- 0.08, N = 6 SE +/- 0.11, N = 8 19.77 39.35 22.54 44.67 23.54 45.97 29.14 58.25 1. (CC) gcc options: -O3 -march=native -fopenmp
TensorFlow Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.09, N = 4 SE +/- 0.07, N = 3 SE +/- 0.10, N = 4 SE +/- 0.04, N = 15 SE +/- 0.05, N = 4 SE +/- 0.06, N = 15 SE +/- 0.05, N = 9 SE +/- 0.03, N = 15 11.29 5.11 9.99 4.37 10.53 4.39 6.43 3.85
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20K 40K 60K 80K 100K SE +/- 313.88, N = 7 SE +/- 545.92, N = 15 SE +/- 260.16, N = 15 SE +/- 560.41, N = 15 SE +/- 243.41, N = 12 SE +/- 178.23, N = 8 SE +/- 328.18, N = 8 SE +/- 271.54, N = 6 35116.55 65396.22 35234.06 66492.44 33811.63 58128.24 63760.45 98764.93 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Llamafile Test: llava-v1.5-7b-q4 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.7 Test: llava-v1.5-7b-q4 - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 4 SE +/- 0.09, N = 15 SE +/- 0.17, N = 4 SE +/- 1.08, N = 12 7.67 7.77 8.13 7.26 20.95 10.44 16.61 7.49
OpenSSL Algorithm: SHA512 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10000M 20000M 30000M 40000M 50000M SE +/- 500176.69, N = 3 SE +/- 3500318.33, N = 3 SE +/- 1250834.62, N = 3 SE +/- 14339684.98, N = 3 SE +/- 203213936.42, N = 3 SE +/- 481040738.21, N = 3 SE +/- 37654528.63, N = 3 SE +/- 14734422.48, N = 3 16199261277 32304222993 18893980783 37564522053 22219927723 42846254477 23886054770 46520760707 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Exhaustive Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.0003, N = 3 SE +/- 0.0033, N = 3 SE +/- 0.0011, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0024, N = 3 SE +/- 0.0164, N = 3 SE +/- 0.0072, N = 3 SE +/- 0.0157, N = 3 3.1204 6.2126 3.6276 7.2075 4.2689 8.3701 4.6303 8.9091 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Very Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Very Thorough Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.0016, N = 3 SE +/- 0.0055, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0022, N = 3 SE +/- 0.0054, N = 3 SE +/- 0.0379, N = 3 SE +/- 0.0294, N = 3 SE +/- 0.0007, N = 3 5.1342 10.2051 5.9702 11.8875 7.0885 13.7518 7.6240 14.6334 1. (CXX) g++ options: -O3 -flto -pthread
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30K 60K 90K 120K 150K SE +/- 36.42, N = 3 SE +/- 1027.07, N = 15 SE +/- 122.31, N = 3 SE +/- 1131.21, N = 15 SE +/- 1953.08, N = 3 SE +/- 1197.41, N = 15 SE +/- 840.59, N = 3 SE +/- 773.70, N = 3 117588.99 83665.76 134048.96 65663.82 147469.33 53914.93 153584.20 64181.29 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
TensorFlow Device: CPU - Batch Size: 1 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: GoogLeNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.27, N = 7 SE +/- 0.20, N = 15 SE +/- 0.27, N = 6 SE +/- 0.23, N = 12 SE +/- 0.19, N = 6 SE +/- 0.23, N = 15 SE +/- 0.21, N = 6 SE +/- 0.12, N = 6 36.13 18.24 31.47 14.67 33.56 13.50 21.67 12.69
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15K 30K 45K 60K 75K SE +/- 134.33, N = 3 SE +/- 37.55, N = 3 SE +/- 64.91, N = 3 SE +/- 13.86, N = 3 SE +/- 102.40, N = 3 SE +/- 64.24, N = 3 SE +/- 90.37, N = 3 SE +/- 16.05, N = 3 68973 38926 62540 36179 58026 33411 50798 24249
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.031, N = 3 SE +/- 0.021, N = 5 SE +/- 0.035, N = 3 SE +/- 0.028, N = 5 SE +/- 0.025, N = 4 SE +/- 0.021, N = 6 SE +/- 0.030, N = 4 SE +/- 0.028, N = 6 21.030 10.840 18.102 9.285 15.211 7.881 14.257 7.402 1. (CXX) g++ options: -fopenmp -O2 -march=native
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 120M 240M 360M 480M 600M SE +/- 81327.78, N = 3 SE +/- 1120857.00, N = 3 SE +/- 86315.43, N = 3 SE +/- 785893.13, N = 3 SE +/- 3338569.32, N = 3 SE +/- 1411218.60, N = 3 SE +/- 1119855.47, N = 3 SE +/- 82996.27, N = 3 205346154 405533173 234469939 473755946 265366170 525049998 297517946 578392800 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.006, N = 7 SE +/- 0.004, N = 9 SE +/- 0.010, N = 7 SE +/- 0.005, N = 10 SE +/- 0.019, N = 8 SE +/- 0.006, N = 10 SE +/- 0.007, N = 8 SE +/- 0.008, N = 11 6.160 3.121 5.332 2.691 4.576 2.325 4.250 2.187 1. (CXX) g++ options: -O3
John The Ripper Test: WPA PSK OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200K 400K 600K 800K 1000K SE +/- 987.33, N = 3 SE +/- 5122.51, N = 3 SE +/- 1274.00, N = 3 SE +/- 788.50, N = 3 SE +/- 1599.31, N = 3 SE +/- 2519.00, N = 3 SE +/- 864.17, N = 3 SE +/- 15579.94, N = 15 286552 562875 334076 657889 401278 793253 428116 797093 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Speedb Test: Random Read OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 130M 260M 390M 520M 650M SE +/- 3698537.65, N = 15 SE +/- 8491098.40, N = 15 SE +/- 2763560.64, N = 13 SE +/- 2955608.21, N = 3 SE +/- 168680.90, N = 3 SE +/- 5393159.45, N = 3 SE +/- 242146.75, N = 3 SE +/- 5399265.88, N = 15 211457048 419943570 244070674 497907490 276179617 551286958 315178381 586147871 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 120K 240K 360K 480K 600K SE +/- 916.22, N = 3 SE +/- 2598.93, N = 3 SE +/- 374.59, N = 3 SE +/- 6276.88, N = 3 SE +/- 61.74, N = 3 SE +/- 185.14, N = 3 SE +/- 119.21, N = 3 SE +/- 28320.74, N = 3 207738 401707 243347 469131 287862 557054 338146 573410 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400000M 800000M 1200000M 1600000M 2000000M SE +/- 43545680.66, N = 3 SE +/- 268465891.11, N = 3 SE +/- 56355870.99, N = 3 SE +/- 697208281.49, N = 3 SE +/- 28627701.54, N = 3 SE +/- 159598753.20, N = 3 SE +/- 1253503549.61, N = 3 SE +/- 1622921637.03, N = 3 641200848170 1277583382757 747710702660 1484669627050 768804693697 1533026300727 889567506540 1769313146013 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100000M 200000M 300000M 400000M 500000M SE +/- 6370607.14, N = 3 SE +/- 4148679.28, N = 3 SE +/- 37795783.50, N = 3 SE +/- 36941390.18, N = 3 SE +/- 766713911.50, N = 3 SE +/- 132227134.30, N = 3 SE +/- 120899798.30, N = 3 SE +/- 82161991.11, N = 3 161321058213 320396720447 187796174440 372735215297 225038850730 442202532977 223625738013 444099144270 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.3345 2.669 4.0035 5.338 6.6725 SE +/- 0.025580, N = 6 SE +/- 0.010204, N = 7 SE +/- 0.023904, N = 7 SE +/- 0.008354, N = 7 SE +/- 0.022393, N = 7 SE +/- 0.019069, N = 15 SE +/- 0.022698, N = 7 SE +/- 0.013568, N = 6 5.930957 2.881099 5.114161 2.527363 4.955865 2.529807 4.182707 2.159459 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
High Performance Conjugate Gradient X Y Z: 144 144 144 - RT: 60 OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.08, N = 3 SE +/- 0.29, N = 3 SE +/- 0.37, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.94, N = 3 25.24 54.41 30.59 62.64 31.07 60.85 35.14 69.30 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5K 10K 15K 20K 25K SE +/- 18.13, N = 3 SE +/- 12.64, N = 3 SE +/- 7.39, N = 3 SE +/- 3.89, N = 3 SE +/- 5.45, N = 3 SE +/- 12.64, N = 3 SE +/- 4.30, N = 3 SE +/- 17.69, N = 3 9087.12 17252.27 9686.39 18561.91 9004.23 20937.58 12317.94 24676.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.17, N = 3 SE +/- 0.22, N = 3 SE +/- 0.18, N = 15 SE +/- 0.32, N = 15 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.36, N = 3 15.40 15.98 16.32 15.37 19.85 36.15 23.73 42.13
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.22, N = 15 SE +/- 0.24, N = 12 SE +/- 0.18, N = 15 SE +/- 0.22, N = 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 15.50 15.34 16.27 15.82 19.58 35.60 23.18 41.91
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.31, N = 3 SE +/- 1.48, N = 3 SE +/- 0.96, N = 4 SE +/- 0.93, N = 3 SE +/- 0.31, N = 3 SE +/- 0.99, N = 3 SE +/- 0.03, N = 3 SE +/- 1.93, N = 15 70.21 127.85 78.11 133.99 86.97 140.83 108.12 191.82 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1000 2000 3000 4000 5000 SE +/- 7.81, N = 3 SE +/- 36.96, N = 3 SE +/- 23.93, N = 4 SE +/- 23.14, N = 3 SE +/- 7.77, N = 3 SE +/- 24.63, N = 3 SE +/- 0.70, N = 3 SE +/- 48.20, N = 15 1755.33 3196.12 1952.61 3349.76 2174.19 3520.71 2703.09 4795.46 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 1.21, N = 3 SE +/- 1.99, N = 3 SE +/- 4.09, N = 3 SE +/- 1.13, N = 3 SE +/- 0.17, N = 3 SE +/- 3.48, N = 3 SE +/- 0.54, N = 3 SE +/- 0.85, N = 3 415.96 795.63 467.08 889.18 477.77 793.64 592.20 1128.78 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 67.32 33.92 58.16 30.20 51.82 27.11 48.41 25.02 1. (CXX) g++ options: -O3
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13K 26K 39K 52K 65K SE +/- 19.45, N = 3 SE +/- 6.92, N = 3 SE +/- 20.13, N = 3 SE +/- 83.09, N = 3 SE +/- 9.84, N = 3 SE +/- 14.34, N = 3 SE +/- 15.15, N = 3 SE +/- 56.68, N = 3 22861.0 45531.0 25441.5 48534.8 27431.1 54601.1 31594.4 61499.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.76, N = 3 SE +/- 0.09, N = 3 SE +/- 0.89, N = 15 SE +/- 0.09, N = 3 SE +/- 0.22, N = 4 SE +/- 0.35, N = 3 SE +/- 0.29, N = 4 64.96 104.84 71.83 112.72 79.38 132.28 97.19 173.22 MIN: 63.12 / MAX: 67.81 MIN: 101.05 / MAX: 112.02 MIN: 69.55 / MAX: 76.73 MIN: 102 / MAX: 125.96 MIN: 76.07 / MAX: 85.98 MIN: 125 / MAX: 146.52 MIN: 92.96 / MAX: 102.04 MIN: 164.07 / MAX: 187.8
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 80K 160K 240K 320K 400K SE +/- 155.19, N = 3 SE +/- 286.86, N = 3 SE +/- 40.48, N = 3 SE +/- 160.59, N = 3 SE +/- 105.60, N = 3 SE +/- 362.38, N = 3 SE +/- 63.14, N = 3 SE +/- 248.00, N = 3 143755.3 288129.1 162727.4 316359.2 179647.5 350187.5 195648.8 380867.5 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
RELION Test: Basic - Device: CPU OpenBenchmarking.org Seconds, Fewer Is Better RELION 4.0.1 Test: Basic - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 90 180 270 360 450 SE +/- 2.98, N = 3 SE +/- 3.24, N = 12 SE +/- 4.65, N = 9 SE +/- 2.66, N = 12 SE +/- 7.14, N = 9 SE +/- 2.65, N = 3 SE +/- 2.68, N = 7 SE +/- 1.41, N = 3 412.37 214.42 384.38 201.38 373.18 203.41 290.45 155.74 1. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50K 100K 150K 200K 250K SE +/- 436.97, N = 10 SE +/- 1415.96, N = 9 SE +/- 382.59, N = 10 SE +/- 1298.67, N = 9 SE +/- 152.92, N = 9 SE +/- 1262.04, N = 9 SE +/- 406.29, N = 9 SE +/- 1422.07, N = 7 85910.95 172614.10 86407.46 171436.47 83448.70 163333.21 107321.89 220893.78 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Thorough Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.05, N = 4 SE +/- 0.03, N = 4 SE +/- 0.03, N = 5 SE +/- 0.01, N = 4 SE +/- 0.19, N = 5 SE +/- 0.05, N = 4 SE +/- 0.55, N = 5 37.01 72.33 42.98 83.34 51.30 86.98 54.45 97.94 1. (CXX) g++ options: -O3 -flto -pthread
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.04, N = 5 SE +/- 0.63, N = 6 SE +/- 0.11, N = 5 SE +/- 1.20, N = 15 SE +/- 0.05, N = 5 SE +/- 0.13, N = 7 SE +/- 0.13, N = 6 SE +/- 0.26, N = 8 75.47 125.75 83.49 129.75 91.99 152.75 112.66 199.61 MIN: 72.93 / MAX: 78.77 MIN: 120.06 / MAX: 135.13 MIN: 80.58 / MAX: 88.97 MIN: 110.67 / MAX: 151.91 MIN: 88.57 / MAX: 98.54 MIN: 143.8 / MAX: 168.98 MIN: 107.88 / MAX: 117.19 MIN: 185.98 / MAX: 216.64
OpenRadioss Model: Chrysler Neon 1M OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 3 SE +/- 0.14, N = 3 228.74 125.15 212.99 117.91 207.20 115.89 157.56 86.93
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 500 1000 1500 2000 2500 SE +/- 1.20, N = 3 SE +/- 2.65, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 1.45, N = 3 SE +/- 0.00, N = 3 2357 1237 2123 1143 1977 1063 1709 898
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.05, N = 4 SE +/- 0.14, N = 6 SE +/- 0.02, N = 4 SE +/- 0.48, N = 6 SE +/- 0.07, N = 5 SE +/- 0.12, N = 6 SE +/- 0.05, N = 5 SE +/- 0.07, N = 7 58.42 107.63 65.33 116.61 70.05 124.71 82.97 153.16 MIN: 55.81 / MAX: 61.43 MIN: 102.22 / MAX: 114.8 MIN: 60.89 / MAX: 69.91 MIN: 107.47 / MAX: 129.72 MIN: 63.26 / MAX: 79.13 MIN: 115.3 / MAX: 143.82 MIN: 79.09 / MAX: 87.11 MIN: 143.78 / MAX: 166.08
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400 800 1200 1600 2000 SE +/- 0.33, N = 3 SE +/- 1.76, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 1988 1049 1792 961 1657 894 1441 759
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 500 1000 1500 2000 2500 SE +/- 2.29, N = 3 SE +/- 1.56, N = 3 SE +/- 2.94, N = 3 SE +/- 1.74, N = 3 SE +/- 2.65, N = 3 SE +/- 0.66, N = 3 SE +/- 0.47, N = 3 SE +/- 11.53, N = 3 860.64 1691.79 894.87 1801.89 1068.43 1843.61 1159.66 2237.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1600 3200 4800 6400 8000 SE +/- 15.55, N = 4 SE +/- 12.99, N = 4 SE +/- 18.08, N = 4 SE +/- 4.96, N = 4 SE +/- 6.56, N = 3 SE +/- 23.92, N = 4 SE +/- 8.92, N = 4 SE +/- 155.00, N = 15 3050.16 3816.70 3076.66 3819.83 2865.72 3960.28 4059.70 7437.81 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
OpenVKL Benchmark: vklBenchmarkCPU ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 700 1400 2100 2800 3500 SE +/- 6.66, N = 3 SE +/- 8.62, N = 3 SE +/- 13.96, N = 3 SE +/- 4.36, N = 3 SE +/- 1.53, N = 3 SE +/- 6.74, N = 3 SE +/- 2.08, N = 3 SE +/- 13.62, N = 3 1243 1776 1356 1852 1734 2716 2004 3222 MIN: 95 / MAX: 19286 MIN: 177 / MAX: 27371 MIN: 107 / MAX: 20909 MIN: 191 / MAX: 28947 MIN: 104 / MAX: 26188 MIN: 188 / MAX: 30888 MIN: 134 / MAX: 29750 MIN: 248 / MAX: 36519
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.04445674, N = 4 SE +/- 0.01741826, N = 5 SE +/- 0.01708632, N = 4 SE +/- 0.05695382, N = 15 SE +/- 0.01004100, N = 4 SE +/- 0.04312801, N = 5 SE +/- 0.02923582, N = 4 SE +/- 0.03329814, N = 5 13.96923760 7.29349117 12.79975820 6.66387510 12.92934130 6.39169817 10.19670660 5.39125967 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
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Resizing Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 245 108 213 97 229 95 230 96 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Classroom - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.38, N = 3 SE +/- 0.40, N = 3 SE +/- 0.25, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.22, N = 3 86.67 44.71 76.87 40.38 68.61 35.91 63.61 33.61
Helsing Digit Range: 14 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.53, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.42, N = 3 SE +/- 0.26, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 123.83 65.03 107.24 58.25 93.35 50.83 89.07 48.09 1. (CC) gcc options: -O2 -pthread
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 160 320 480 640 800 SE +/- 1.23, N = 3 SE +/- 1.28, N = 3 SE +/- 0.52, N = 3 SE +/- 0.55, N = 3 SE +/- 0.04, N = 3 SE +/- 0.69, N = 3 SE +/- 0.95, N = 3 SE +/- 1.42, N = 3 285.95 568.81 301.30 569.60 298.56 654.84 403.20 736.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 256 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1300M 2600M 3900M 5200M 6500M SE +/- 1320353.49, N = 3 SE +/- 2447674.63, N = 3 SE +/- 1338323.99, N = 3 SE +/- 895048.11, N = 3 SE +/- 4021608.30, N = 3 SE +/- 10496401.50, N = 3 SE +/- 2516611.48, N = 3 SE +/- 6711433.03, N = 3 2381800000 4670966667 2769066667 5367033333 3243800000 6116566667 3167200000 6077300000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Pabellon Barcelona - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.31, N = 3 SE +/- 0.08, N = 3 SE +/- 0.44, N = 3 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 SE +/- 0.26, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 106.96 55.26 97.80 51.29 87.92 46.38 80.29 41.85
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Barbershop - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 70 140 210 280 350 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 1.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.42, N = 3 SE +/- 0.69, N = 3 SE +/- 0.21, N = 3 320.11 169.44 290.56 156.70 261.97 141.54 236.73 125.87
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 41.93 42.16 59.69 64.91 100.39 45.78 39.62 43.41 MIN: 27.14 / MAX: 54.05 MIN: 32.47 / MAX: 70.84 MIN: 42.86 / MAX: 84.25 MIN: 49.88 / MAX: 107.03 MIN: 41.76 / MAX: 139.86 MIN: 33.94 / MAX: 85.21 MIN: 26.71 / MAX: 62.24 MIN: 27.3 / MAX: 82.85 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1200 2400 3600 4800 6000 SE +/- 0.09, N = 3 SE +/- 26.47, N = 3 SE +/- 18.30, N = 3 SE +/- 0.15, N = 3 SE +/- 18.43, N = 3 SE +/- 47.68, N = 6 SE +/- 18.09, N = 3 SE +/- 0.12, N = 3 2170.7 3787.0 2514.0 4386.6 2616.9 4853.6 3088.7 5493.4 MIN: 1388.2 / MAX: 2170.8 MIN: 2545.7 / MAX: 3839.9 MIN: 1550.4 / MAX: 2532.5 MIN: 2970.2 / MAX: 4386.9 MIN: 1591.7 / MAX: 2653.8 MIN: 3181.8 / MAX: 4929.4 MIN: 1852.6 / MAX: 3124.9 MIN: 3703.4 / MAX: 5493.6 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.67, N = 3 SE +/- 0.00, N = 3 SE +/- 1.67, N = 3 114 199 130 227 157 265 167 284 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100 200 300 400 500 SE +/- 3.95, N = 15 SE +/- 1.31, N = 3 SE +/- 0.51, N = 3 SE +/- 0.89, N = 3 SE +/- 0.84, N = 3 SE +/- 0.26, N = 3 SE +/- 1.00, N = 3 SE +/- 3.01, N = 3 219.53 199.08 215.13 185.46 357.36 288.47 460.78 356.76 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: BMW27 - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 3 SE +/- 0.08, N = 4 SE +/- 0.15, N = 3 SE +/- 0.08, N = 4 SE +/- 0.04, N = 3 SE +/- 0.03, N = 4 31.66 16.55 28.49 15.29 25.89 13.74 23.72 12.76
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Fishy Cat - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 42.78 23.17 38.48 21.45 34.83 19.13 31.91 17.29
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.019, N = 3 SE +/- 0.025, N = 3 SE +/- 0.007, N = 3 SE +/- 0.032, N = 3 SE +/- 0.010, N = 3 SE +/- 0.019, N = 3 SE +/- 0.009, N = 3 SE +/- 0.046, N = 3 7.545 13.392 8.282 14.127 8.762 15.450 10.477 18.540 1. (CXX) g++ options: -O3 -lm
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 19.91 35.93 22.36 39.34 24.64 42.82 27.10 48.76
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20K 40K 60K 80K 100K SE +/- 41.33, N = 3 SE +/- 155.80, N = 3 SE +/- 65.97, N = 3 SE +/- 141.04, N = 3 SE +/- 58.68, N = 3 SE +/- 125.33, N = 3 SE +/- 162.52, N = 3 SE +/- 47.16, N = 3 80742 45211 73366 41971 68006 38813 59522 33391
Liquid-DSP Threads: 256 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400M 800M 1200M 1600M 2000M SE +/- 569766.03, N = 3 SE +/- 4238841.56, N = 3 SE +/- 740202.67, N = 3 SE +/- 6728628.72, N = 3 SE +/- 1722723.94, N = 3 SE +/- 5630373.98, N = 3 SE +/- 240370.09, N = 3 SE +/- 14465476.14, N = 3 838530000 1444066667 944550000 1518933333 1020833333 1616966667 1178766667 2027000000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 87.89, N = 12 SE +/- 23.56, N = 3 SE +/- 32.87, N = 12 SE +/- 195.28, N = 8 SE +/- 4.15, N = 3 SE +/- 75.19, N = 5 SE +/- 54.27, N = 5 SE +/- 60.72, N = 3 3375.32 3347.93 3406.96 4382.97 8088.11 7630.06 5062.07 6038.92 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.12, N = 7 SE +/- 0.07, N = 15 SE +/- 0.06, N = 4 SE +/- 0.03, N = 3 SE +/- 0.05, N = 4 SE +/- 0.10, N = 15 SE +/- 0.15, N = 4 SE +/- 0.04, N = 3 12.80 9.64 12.97 6.51 13.54 5.96 14.28 7.22 MIN: 11.39 / MAX: 13.21 MIN: 8.98 / MAX: 10.13 MIN: 12.11 / MAX: 13.11 MIN: 6.27 / MAX: 6.67 MIN: 13.42 / MAX: 13.68 MIN: 5.5 / MAX: 7.04 MIN: 12.85 / MAX: 14.54 MIN: 7.13 / MAX: 7.4
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 90 180 270 360 450 SE +/- 1.25, N = 3 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 SE +/- 0.01, N = 3 SE +/- 3.88, N = 4 SE +/- 0.05, N = 3 SE +/- 2.51, N = 3 SE +/- 0.37, N = 3 407.59 189.69 351.64 187.22 357.01 196.81 323.25 171.38 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
WRF Input: conus 2.5km OpenBenchmarking.org Seconds, Fewer Is Better WRF 4.2.2 Input: conus 2.5km Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3K 6K 9K 12K 15K 13273.69 7157.96 12410.29 6840.06 11980.81 6674.12 10602.41 5601.10 1. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Blender Blend File: Junkshop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Junkshop - Compute: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 42.85 24.99 39.17 23.45 35.96 21.15 32.08 18.31
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 80 160 240 320 400 SE +/- 0.00, N = 3 SE +/- 2.60, N = 3 SE +/- 0.00, N = 3 SE +/- 1.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 1.15, N = 3 160 269 181 301 216 342 228 374 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40K 80K 120K 160K 200K SE +/- 383.22, N = 3 SE +/- 18.38, N = 3 SE +/- 1761.33, N = 3 SE +/- 1422.88, N = 15 SE +/- 75.30, N = 3 SE +/- 2494.14, N = 3 SE +/- 988.12, N = 3 SE +/- 1158.60, N = 3 135075.07 174862.56 140144.01 176900.32 115106.30 189893.31 81279.79 128566.81 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 4 17.52 26.00 18.24 28.96 20.23 31.24 24.23 40.92 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.34, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 28.73 29.98 38.50 41.57 62.46 37.58 26.85 28.17 MIN: 19.52 / MAX: 209.26 MIN: 20.48 / MAX: 222.7 MIN: 25.18 / MAX: 161.13 MIN: 28.11 / MAX: 155.06 MIN: 46.12 / MAX: 79.06 MIN: 20.58 / MAX: 347.67 MIN: 20.18 / MAX: 307.38 MIN: 20.12 / MAX: 261.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.27, N = 4 18.13 26.69 18.84 29.62 20.97 32.04 24.80 41.58 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 16K 32K 48K 64K 80K SE +/- 95.84, N = 3 SE +/- 195.77, N = 3 SE +/- 143.25, N = 3 SE +/- 440.63, N = 3 SE +/- 78.02, N = 3 SE +/- 137.82, N = 3 SE +/- 198.41, N = 3 SE +/- 106.16, N = 3 69969 58952 72225 60046 71227 67315 75396 33110 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 14.29 16.96 13.85 16.66 14.04 14.86 13.26 30.20 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 800M 1600M 2400M 3200M 4000M SE +/- 3359086.30, N = 3 SE +/- 7233468.75, N = 3 SE +/- 1778769.08, N = 3 SE +/- 9164253.67, N = 3 SE +/- 468935.32, N = 3 SE +/- 2438223.49, N = 3 SE +/- 4000850.45, N = 3 SE +/- 9014927.20, N = 3 1588496667 3156261667 1597993333 3205161000 1605097000 3124402667 1814760000 3609646333 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 90 180 270 360 450 SE +/- 0.61, N = 3 SE +/- 0.56, N = 3 SE +/- 0.67, N = 3 SE +/- 0.73, N = 3 SE +/- 0.80, N = 3 SE +/- 0.86, N = 3 SE +/- 0.72, N = 3 SE +/- 0.56, N = 3 428.39 246.94 384.06 231.03 362.45 218.57 316.90 189.74
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1453 2.2906 3.4359 4.5812 5.7265 SE +/- 0.00, N = 4 SE +/- 0.02, N = 5 SE +/- 0.00, N = 4 SE +/- 0.02, N = 5 SE +/- 0.00, N = 4 SE +/- 0.01, N = 6 SE +/- 0.00, N = 5 SE +/- 0.03, N = 6 2.27 3.49 2.39 3.66 2.71 4.48 3.32 5.09
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1318 2.2636 3.3954 4.5272 5.659 SE +/- 0.00, N = 4 SE +/- 0.01, N = 5 SE +/- 0.00, N = 4 SE +/- 0.04, N = 5 SE +/- 0.00, N = 4 SE +/- 0.03, N = 6 SE +/- 0.00, N = 5 SE +/- 0.03, N = 6 2.26 3.51 2.38 3.65 2.71 4.41 3.31 5.03
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 15.13, N = 3 SE +/- 37.79, N = 3 SE +/- 7.60, N = 3 SE +/- 28.98, N = 3 SE +/- 1.87, N = 3 SE +/- 13.31, N = 3 SE +/- 10.14, N = 3 SE +/- 24.76, N = 3 4208.49 5565.23 4386.48 5933.65 4209.10 7356.63 6757.26 9360.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Medium Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 120 240 360 480 600 SE +/- 0.03, N = 6 SE +/- 0.52, N = 6 SE +/- 0.08, N = 6 SE +/- 0.77, N = 6 SE +/- 0.16, N = 6 SE +/- 2.79, N = 6 SE +/- 1.17, N = 6 SE +/- 1.56, N = 7 247.30 441.65 284.33 483.10 333.99 484.55 327.78 550.02 1. (CXX) g++ options: -O3 -flto -pthread
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.54 1.08 1.62 2.16 2.7 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 1.08 1.72 1.14 1.74 1.29 2.18 1.58 2.40
Liquid-DSP Threads: 256 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1300M 2600M 3900M 5200M 6500M SE +/- 4088330.28, N = 3 SE +/- 17558125.69, N = 3 SE +/- 1976810.00, N = 3 SE +/- 28453880.81, N = 3 SE +/- 5292237.50, N = 3 SE +/- 2331189.49, N = 3 SE +/- 3555434.03, N = 3 SE +/- 61971606.40, N = 3 2848933333 4825133333 3222533333 5036000000 3500833333 5361266667 3806833333 6284300000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.28, N = 3 SE +/- 0.38, N = 8 SE +/- 0.36, N = 3 SE +/- 0.44, N = 3 SE +/- 0.03, N = 3 SE +/- 0.49, N = 3 SE +/- 0.16, N = 3 SE +/- 0.52, N = 3 50.99 46.49 48.59 35.46 51.46 35.53 77.52 45.69 MIN: 11.73 / MAX: 59.01 MIN: 15.6 / MAX: 50.65 MIN: 4.58 / MAX: 55.2 MIN: 0.7 / MAX: 41 MIN: 35.78 / MAX: 55.29 MIN: 16.36 / MAX: 38.41 MIN: 36.51 / MAX: 79.65 MIN: 13.24 / MAX: 48.92
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 140K 280K 420K 560K 700K SE +/- 1836.55, N = 3 SE +/- 5127.15, N = 3 SE +/- 2258.81, N = 3 SE +/- 3924.87, N = 3 SE +/- 1535.53, N = 3 SE +/- 4200.62, N = 3 SE +/- 1982.97, N = 3 SE +/- 709.87, N = 3 314716 491729 342363 525514 388190 592729 441636 674239 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Tradebeans Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3K 6K 9K 12K 15K SE +/- 51.68, N = 15 SE +/- 66.27, N = 3 SE +/- 54.76, N = 15 SE +/- 10.41, N = 3 SE +/- 79.99, N = 3 SE +/- 64.94, N = 3 SE +/- 226.65, N = 15 SE +/- 16.01, N = 3 6130 6681 5994 6672 7270 8050 11004 12713
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.001847, N = 3 SE +/- 0.003237, N = 4 SE +/- 0.013353, N = 3 SE +/- 0.003253, N = 4 SE +/- 0.002987, N = 3 SE +/- 0.016400, N = 4 SE +/- 0.002400, N = 3 SE +/- 0.018471, N = 4 21.021120 13.211250 19.882460 12.106900 16.030800 11.284380 16.969100 9.964526 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 70 140 210 280 350 SE +/- 1.74, N = 3 SE +/- 0.47, N = 3 SE +/- 2.72, N = 3 SE +/- 0.73, N = 3 SE +/- 0.53, N = 3 SE +/- 0.73, N = 3 SE +/- 2.50, N = 3 SE +/- 1.63, N = 3 319.04 166.49 301.14 153.41 313.10 156.46 308.80 153.92 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.28, N = 3 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.27, N = 3 SE +/- 0.27, N = 3 40.73 32.81 42.27 29.20 46.85 29.15 60.41 31.46 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 136.49 243.24 134.39 239.73 126.15 225.35 118.78 210.82
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 70 140 210 280 350 SE +/- 2.40, N = 3 SE +/- 2.72, N = 15 SE +/- 3.31, N = 5 SE +/- 1.78, N = 3 SE +/- 1.80, N = 3 SE +/- 1.01, N = 3 SE +/- 2.52, N = 3 SE +/- 0.40, N = 3 330.10 174.68 296.80 161.89 315.41 177.76 314.06 171.23 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 2.01, N = 15 SE +/- 0.58, N = 3 SE +/- 1.88, N = 3 SE +/- 1.08, N = 3 SE +/- 1.50, N = 3 SE +/- 1.05, N = 3 SE +/- 1.19, N = 3 SE +/- 8.14, N = 15 176.33 141.95 168.86 132.71 222.03 180.03 270.33 236.65 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
uvg266 Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.36 19.75 13.89 22.14 15.71 24.71 16.06 27.11
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.2844 0.5688 0.8532 1.1376 1.422 SE +/- 0.000508, N = 9 SE +/- 0.000806, N = 9 SE +/- 0.000927, N = 9 SE +/- 0.001240, N = 9 SE +/- 0.000805, N = 9 SE +/- 0.001274, N = 9 SE +/- 0.000392, N = 9 SE +/- 0.000902, N = 9 1.264070 0.945075 1.196430 0.864358 1.077430 0.736170 0.907161 0.624250 MIN: 1.21 MIN: 0.9 MIN: 1.16 MIN: 0.81 MIN: 1.06 MIN: 0.66 MIN: 0.87 MIN: 0.58 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.05, N = 11 SE +/- 0.11, N = 9 SE +/- 0.04, N = 11 SE +/- 0.09, N = 8 SE +/- 0.36, N = 15 SE +/- 0.33, N = 8 SE +/- 0.29, N = 15 SE +/- 0.97, N = 15 27.63 47.51 30.84 52.24 28.72 42.28 34.30 55.50 1. (CXX) g++ options: -O3 -lm -ldl
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 15.17 22.25 15.68 24.65 17.85 27.65 16.64 30.37
Speedb Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4M 8M 12M 16M 20M SE +/- 88257.34, N = 3 SE +/- 171807.74, N = 3 SE +/- 93731.24, N = 7 SE +/- 197596.27, N = 3 SE +/- 62510.72, N = 3 SE +/- 239363.92, N = 3 SE +/- 143570.67, N = 4 SE +/- 195912.00, N = 15 8795408 13859254 9988176 15354400 10695360 17297027 12168413 17585737 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13 26 39 52 65 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 28.28 46.71 32.16 51.82 34.89 50.52 37.46 56.40 1. (CXX) g++ options: -O3 -lm -ldl
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 11.37 17.15 12.72 18.72 13.95 15.96 9.40 13.15 MIN: 9.17 / MAX: 32.12 MIN: 10.81 / MAX: 59.34 MIN: 9.56 / MAX: 30.66 MIN: 12.15 / MAX: 64.81 MIN: 8.67 / MAX: 65.92 MIN: 10.38 / MAX: 43.64 MIN: 7.66 / MAX: 25.07 MIN: 7.28 / MAX: 47.97 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.36, N = 3 SE +/- 0.79, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 212.48 134.42 197.84 128.07 187.02 122.31 165.05 106.82
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.1762 0.3524 0.5286 0.7048 0.881 SE +/- 0.001869, N = 4 SE +/- 0.004822, N = 4 SE +/- 0.000666, N = 4 SE +/- 0.003500, N = 4 SE +/- 0.000915, N = 4 SE +/- 0.004208, N = 4 SE +/- 0.000767, N = 4 SE +/- 0.004443, N = 4 0.725974 0.662387 0.617190 0.759434 0.539467 0.783180 0.398446 0.580664 MIN: 0.67 MIN: 0.58 MIN: 0.55 MIN: 0.67 MIN: 0.5 MIN: 0.69 MIN: 0.37 MIN: 0.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.69, N = 15 SE +/- 0.34, N = 3 SE +/- 0.59, N = 3 SE +/- 0.21, N = 3 SE +/- 0.16, N = 3 SE +/- 0.48, N = 3 SE +/- 0.82, N = 3 SE +/- 0.51, N = 13 47.27 40.57 42.27 33.96 52.82 36.25 66.52 38.42 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 8.4.0 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.015, N = 6 SE +/- 0.096, N = 5 SE +/- 0.024, N = 6 SE +/- 0.082, N = 5 SE +/- 0.015, N = 6 SE +/- 0.019, N = 6 SE +/- 0.020, N = 6 SE +/- 0.019, N = 6 7.622 12.617 7.748 12.578 7.532 8.036 6.458 6.856
OpenFOAM Input: drivaerFastback, Small Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 45.95 28.99 41.75 27.58 42.22 28.56 33.07 23.56 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: AlexNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400 800 1200 1600 2000 SE +/- 3.89, N = 3 SE +/- 17.88, N = 4 SE +/- 5.13, N = 3 SE +/- 8.55, N = 3 SE +/- 0.51, N = 3 SE +/- 18.52, N = 3 SE +/- 1.84, N = 3 SE +/- 19.23, N = 3 1047.96 1604.11 1108.95 1677.62 1278.45 1899.64 1486.12 2039.63
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Tradesoap Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1600 3200 4800 6400 8000 SE +/- 36.36, N = 15 SE +/- 48.92, N = 14 SE +/- 40.72, N = 15 SE +/- 48.60, N = 15 SE +/- 29.41, N = 3 SE +/- 31.29, N = 3 SE +/- 57.43, N = 15 SE +/- 52.55, N = 15 3887 4199 3884 4069 4115 4215 7321 7492
CloverLeaf Input: clover_bm16 OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm16 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 90 180 270 360 450 SE +/- 1.43, N = 3 SE +/- 1.56, N = 3 SE +/- 2.03, N = 3 SE +/- 2.11, N = 9 SE +/- 0.13, N = 3 SE +/- 0.74, N = 3 SE +/- 0.54, N = 3 SE +/- 2.02, N = 3 351.29 263.33 357.57 269.20 328.47 214.80 410.59 378.05 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100 200 300 400 500 SE +/- 3.48, N = 15 SE +/- 2.44, N = 3 SE +/- 1.74, N = 3 SE +/- 1.67, N = 15 SE +/- 0.86, N = 3 SE +/- 2.94, N = 3 SE +/- 3.84, N = 3 SE +/- 1.73, N = 3 337.00 246.68 346.21 252.67 326.14 246.34 462.86 354.75 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300M 600M 900M 1200M 1500M SE +/- 681281.47, N = 3 SE +/- 11560043.25, N = 5 SE +/- 1345523.44, N = 3 SE +/- 2123152.79, N = 3 SE +/- 1740596.96, N = 3 SE +/- 6842108.19, N = 3 SE +/- 2313246.88, N = 3 SE +/- 4790383.89, N = 3 800186667 1091460000 882200000 1206066667 918566667 1126466667 1152933333 1493833333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 21.7.2 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 0.53, N = 3 SE +/- 0.84, N = 3 SE +/- 0.74, N = 3 SE +/- 0.52, N = 3 SE +/- 0.71, N = 3 SE +/- 0.48, N = 3 SE +/- 0.52, N = 3 SE +/- 0.12, N = 3 270.38 175.63 252.65 171.17 254.00 172.99 214.43 145.41
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.26, N = 3 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 8 SE +/- 0.09, N = 3 SE +/- 0.16, N = 4 SE +/- 0.08, N = 3 SE +/- 0.19, N = 5 19.99 17.91 18.07 14.86 19.41 15.77 27.21 17.57 MIN: 0.34 / MAX: 23.05 MIN: 5.47 / MAX: 18.9 MIN: 0.27 / MAX: 21.93 MIN: 0.53 / MAX: 17.18 MIN: 14.68 / MAX: 22.3 MIN: 8.33 / MAX: 16.91 MIN: 13.91 / MAX: 28.31 MIN: 5.14 / MAX: 18.58
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 1.04, N = 3 SE +/- 1.53, N = 3 SE +/- 2.63, N = 3 SE +/- 0.26, N = 3 SE +/- 0.53, N = 3 SE +/- 0.78, N = 3 SE +/- 0.27, N = 3 SE +/- 0.81, N = 3 191.11 135.98 188.93 136.69 191.56 144.64 248.68 195.45 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.06, N = 4 SE +/- 0.33, N = 4 SE +/- 0.08, N = 4 SE +/- 0.29, N = 4 SE +/- 0.08, N = 4 SE +/- 0.45, N = 5 SE +/- 0.04, N = 4 SE +/- 0.36, N = 5 40.23 51.91 41.34 52.23 50.03 67.64 38.02 65.38 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.12, N = 5 SE +/- 0.49, N = 5 SE +/- 0.20, N = 5 SE +/- 0.49, N = 15 SE +/- 0.07, N = 5 SE +/- 0.50, N = 5 SE +/- 0.09, N = 4 SE +/- 0.21, N = 5 53.13 52.63 54.47 54.19 66.74 69.05 39.20 66.78 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400 800 1200 1600 2000 SE +/- 1.21, N = 3 SE +/- 1.15, N = 3 SE +/- 6.82, N = 3 SE +/- 5.81, N = 3 SE +/- 0.54, N = 3 SE +/- 5.06, N = 3 SE +/- 4.27, N = 3 SE +/- 1.86, N = 3 986.04 1479.53 1058.99 1528.41 1205.30 1730.25 1277.46 1681.44
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.1103 0.2206 0.3309 0.4412 0.5515 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.33 0.28 0.37 0.30 0.43 0.29 0.49 0.46 MIN: 0.26 / MAX: 19.2 MIN: 0.25 / MAX: 41.4 MIN: 0.28 / MAX: 40.85 MIN: 0.26 / MAX: 42.1 MIN: 0.23 / MAX: 17.03 MIN: 0.24 / MAX: 39.69 MIN: 0.18 / MAX: 16.07 MIN: 0.18 / MAX: 22.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Swirl Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 150 300 450 600 750 SE +/- 0.58, N = 3 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.15, N = 3 SE +/- 1.76, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 394 509 432 558 502 617 529 689 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 4.16, N = 3 SE +/- 1.77, N = 3 SE +/- 4.87, N = 3 SE +/- 1.98, N = 3 SE +/- 5.72, N = 3 SE +/- 4.81, N = 3 SE +/- 10.06, N = 4 SE +/- 2.57, N = 3 687.67 492.89 678.48 478.47 784.30 566.38 830.73 605.59 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CockroachDB Workload: KV, 50% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20K 40K 60K 80K 100K SE +/- 297.86, N = 3 SE +/- 833.19, N = 3 SE +/- 1352.20, N = 3 SE +/- 556.62, N = 3 SE +/- 1037.18, N = 15 SE +/- 639.27, N = 15 SE +/- 1659.04, N = 15 SE +/- 325.76, N = 3 103089.8 69221.4 112265.3 66816.9 108953.6 68524.7 115715.8 77327.1
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.71, N = 3 SE +/- 0.51, N = 3 SE +/- 0.62, N = 3 SE +/- 0.46, N = 4 SE +/- 0.24, N = 3 SE +/- 0.50, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 51.55 42.35 51.35 38.30 56.01 37.08 63.06 40.77 MIN: 37.49 / MAX: 54.33 MIN: 36.76 / MAX: 44.4 MIN: 41.6 / MAX: 53.81 MIN: 27.11 / MAX: 40.39 MIN: 51.84 / MAX: 59.12 MIN: 26.46 / MAX: 40.15 MIN: 33.2 / MAX: 65.54 MIN: 16.88 / MAX: 42.06
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.76, N = 3 SE +/- 0.52, N = 3 SE +/- 0.62, N = 3 SE +/- 0.45, N = 3 SE +/- 0.52, N = 3 SE +/- 0.49, N = 3 SE +/- 0.64, N = 3 SE +/- 0.29, N = 3 52.97 41.68 51.56 37.91 54.84 37.44 63.60 41.45 MIN: 33.28 / MAX: 55.78 MIN: 37.38 / MAX: 44.02 MIN: 30.49 / MAX: 54.7 MIN: 16.15 / MAX: 40.53 MIN: 46.5 / MAX: 58.5 MIN: 26.88 / MAX: 41.26 MIN: 37.79 / MAX: 65.67 MIN: 38.42 / MAX: 42.93
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.72, N = 3 SE +/- 0.26, N = 3 SE +/- 0.43, N = 15 SE +/- 0.34, N = 15 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 SE +/- 0.19, N = 3 SE +/- 0.30, N = 15 51.05 41.65 51.86 37.84 56.44 37.55 63.30 40.83 MIN: 40.71 / MAX: 53.89 MIN: 31.6 / MAX: 43.65 MIN: 30.55 / MAX: 55.87 MIN: 19.63 / MAX: 40.77 MIN: 48.09 / MAX: 58.6 MIN: 24.5 / MAX: 40.69 MIN: 48.94 / MAX: 65.25 MIN: 15.4 / MAX: 43.41
LuxCoreRender Scene: Orange Juice - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.16, N = 15 SE +/- 0.04, N = 3 SE +/- 0.28, N = 15 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.30, N = 15 11.86 16.91 12.50 16.64 13.46 18.70 14.74 19.91 MIN: 9.93 / MAX: 13.28 MIN: 12.9 / MAX: 23.07 MIN: 10.38 / MAX: 14.93 MIN: 12.39 / MAX: 24.93 MIN: 11.09 / MAX: 16.56 MIN: 16.22 / MAX: 25.05 MIN: 12.17 / MAX: 18.21 MIN: 15 / MAX: 30.59
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.59, N = 3 SE +/- 0.40, N = 4 SE +/- 0.57, N = 3 SE +/- 0.31, N = 5 SE +/- 0.55, N = 3 SE +/- 0.43, N = 3 SE +/- 0.39, N = 4 SE +/- 0.23, N = 7 43.42 32.14 40.50 30.53 39.45 29.98 34.59 25.87
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.19, N = 5 SE +/- 0.21, N = 3 SE +/- 0.17, N = 12 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.17, N = 3 SE +/- 0.34, N = 3 SE +/- 0.15, N = 12 19.01 15.84 19.24 14.96 20.13 14.03 23.49 16.25 MIN: 11.15 / MAX: 20.08 MIN: 6.82 / MAX: 16.51 MIN: 10.95 / MAX: 20.39 MIN: 10.89 / MAX: 15.42 MIN: 17.06 / MAX: 21.01 MIN: 8.98 / MAX: 15.41 MIN: 19.73 / MAX: 24.56 MIN: 6.19 / MAX: 17.5
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1000M 2000M 3000M 4000M 5000M SE +/- 2030052.00, N = 3 SE +/- 25888414.40, N = 3 SE +/- 3119294.79, N = 3 SE +/- 14772609.79, N = 3 SE +/- 3116800.35, N = 3 SE +/- 13655808.69, N = 3 SE +/- 5260228.13, N = 3 SE +/- 51282832.98, N = 4 2670033333 3596400000 2972400000 3896500000 3181266667 3723666667 3503200000 4450525000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 16.17 13.09 16.39 12.60 18.14 12.75 20.88 14.20 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 1B Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.045, N = 5 SE +/- 0.122, N = 15 SE +/- 0.026, N = 5 SE +/- 0.142, N = 12 SE +/- 0.005, N = 5 SE +/- 0.007, N = 6 SE +/- 0.030, N = 5 SE +/- 0.010, N = 6 8.300 6.334 7.959 6.266 7.047 5.008 6.701 5.110
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 4 SE +/- 0.08, N = 3 SE +/- 0.13, N = 7 SE +/- 0.29, N = 3 SE +/- 0.16, N = 3 19.20 16.30 19.58 14.92 20.25 14.08 23.33 16.00 MIN: 10.93 / MAX: 20 MIN: 11.86 / MAX: 16.95 MIN: 13.13 / MAX: 20.27 MIN: 8.28 / MAX: 15.85 MIN: 17.03 / MAX: 21.21 MIN: 6.98 / MAX: 15.46 MIN: 19.78 / MAX: 24.54 MIN: 11.43 / MAX: 16.66
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 23.12 24.00 24.94 25.72 36.20 25.12 21.87 22.96 MIN: 18.74 / MAX: 31.08 MIN: 19.19 / MAX: 45.88 MIN: 19.75 / MAX: 33.18 MIN: 20.7 / MAX: 44.98 MIN: 20.73 / MAX: 45.28 MIN: 19.86 / MAX: 59.96 MIN: 20.16 / MAX: 32.36 MIN: 20.8 / MAX: 34.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Rubber O-Ring Seal Installation Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.60, N = 3 SE +/- 0.02, N = 3 SE +/- 0.32, N = 3 SE +/- 0.51, N = 15 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.34, N = 3 SE +/- 0.72, N = 8 59.58 70.73 59.32 81.65 59.91 88.39 54.14 86.85
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.30, N = 3 160.56 114.29 146.03 110.56 140.43 107.36 128.74 100.00
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.18, N = 7 SE +/- 0.09, N = 3 SE +/- 0.18, N = 7 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.18, N = 3 19.47 16.68 19.29 14.74 20.46 14.59 23.41 16.17 MIN: 11.79 / MAX: 20.53 MIN: 7.02 / MAX: 17.07 MIN: 10.66 / MAX: 20.07 MIN: 10.63 / MAX: 15.36 MIN: 17.25 / MAX: 21.16 MIN: 10.11 / MAX: 16.06 MIN: 22.41 / MAX: 24.3 MIN: 11.54 / MAX: 16.69
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 500M Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.8507 1.7014 2.5521 3.4028 4.2535 SE +/- 0.010, N = 7 SE +/- 0.064, N = 15 SE +/- 0.023, N = 15 SE +/- 0.074, N = 15 SE +/- 0.003, N = 7 SE +/- 0.002, N = 8 SE +/- 0.008, N = 7 SE +/- 0.004, N = 7 3.781 3.110 3.704 2.961 3.267 2.364 3.391 2.659
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.17, N = 15 SE +/- 0.29, N = 15 SE +/- 0.15, N = 15 SE +/- 0.10, N = 14 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 18.22 14.48 16.92 14.46 19.86 15.56 22.97 16.97 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CloverLeaf Input: clover_bm64_short OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm64_short Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10 20 30 40 50 SE +/- 0.15, N = 3 SE +/- 0.31, N = 15 SE +/- 0.17, N = 3 SE +/- 0.40, N = 4 SE +/- 0.02, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.45, N = 3 41.43 32.25 42.22 32.44 39.48 26.58 39.38 31.90 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 80 160 240 320 400 SE +/- 0.15, N = 3 SE +/- 0.40, N = 3 SE +/- 0.47, N = 3 SE +/- 0.35, N = 3 SE +/- 0.28, N = 3 SE +/- 0.00, N = 3 SE +/- 0.69, N = 3 SE +/- 0.33, N = 3 236.52 256.63 257.50 278.52 356.38 283.11 224.64 234.24 MIN: 172.47 / MAX: 265.77 MIN: 191.95 / MAX: 301.21 MIN: 187.62 / MAX: 295.06 MIN: 196.58 / MAX: 401.59 MIN: 109.11 / MAX: 395.69 MIN: 203.37 / MAX: 332.08 MIN: 153.29 / MAX: 553.64 MIN: 148.68 / MAX: 448.54 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.13, N = 5 SE +/- 0.55, N = 5 SE +/- 0.32, N = 5 SE +/- 0.56, N = 5 SE +/- 0.75, N = 15 SE +/- 0.54, N = 6 SE +/- 0.17, N = 4 SE +/- 0.39, N = 6 63.10 54.98 63.99 58.14 74.57 72.01 47.07 73.81 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 16.33 17.19 19.44 20.24 17.84 21.73 13.73 14.67 MIN: 13.49 / MAX: 26.98 MIN: 13.16 / MAX: 42.02 MIN: 15.1 / MAX: 32.19 MIN: 13.69 / MAX: 36.9 MIN: 9.08 / MAX: 37.11 MIN: 15.08 / MAX: 39.82 MIN: 12.23 / MAX: 23.01 MIN: 12.73 / MAX: 41.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.7444 1.4888 2.2332 2.9776 3.722 SE +/- 0.01189, N = 3 SE +/- 0.02702, N = 13 SE +/- 0.01517, N = 3 SE +/- 0.02652, N = 3 SE +/- 0.00871, N = 3 SE +/- 0.00768, N = 3 SE +/- 0.00805, N = 3 SE +/- 0.03826, N = 3 2.62544 2.17463 2.61721 2.10480 3.03922 2.83498 3.30836 3.05085 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.12, N = 4 SE +/- 0.39, N = 4 SE +/- 0.02, N = 4 SE +/- 0.38, N = 9 SE +/- 0.01, N = 4 SE +/- 0.50, N = 5 SE +/- 0.08, N = 3 SE +/- 0.16, N = 5 39.56 44.75 40.82 46.25 49.42 54.88 35.10 53.66
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.15, N = 4 SE +/- 0.43, N = 4 SE +/- 0.15, N = 4 SE +/- 0.41, N = 7 SE +/- 0.05, N = 5 SE +/- 0.16, N = 5 SE +/- 0.07, N = 3 SE +/- 0.21, N = 5 44.05 45.09 45.32 44.40 55.54 55.40 35.56 54.95
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 12.91, N = 15 SE +/- 1.83, N = 3 SE +/- 7.34, N = 3 SE +/- 6.21, N = 5 SE +/- 11.46, N = 3 SE +/- 6.50, N = 15 SE +/- 2.43, N = 3 SE +/- 8.88, N = 3 728.47 604.76 705.61 581.77 852.33 696.98 908.19 754.81 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.06, N = 4 SE +/- 0.50, N = 5 SE +/- 0.13, N = 4 SE +/- 0.36, N = 15 SE +/- 0.07, N = 5 SE +/- 0.58, N = 5 SE +/- 0.04, N = 4 SE +/- 0.17, N = 5 48.91 46.13 50.09 45.79 60.87 55.26 39.31 57.13
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 7.0 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 26.46 20.79 24.84 20.01 24.06 19.51 21.36 17.39
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.20, N = 3 SE +/- 0.19, N = 3 SE +/- 0.09, N = 3 SE +/- 0.35, N = 15 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 3 21.17 16.64 20.01 17.99 20.15 16.57 25.16 22.43 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.8055 1.611 2.4165 3.222 4.0275 SE +/- 0.03, N = 4 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.50 2.53 2.67 2.79 3.58 2.50 2.36 2.48 MIN: 2.22 / MAX: 27.89 MIN: 2.23 / MAX: 31.44 MIN: 2.39 / MAX: 34.22 MIN: 2.44 / MAX: 34.21 MIN: 1.4 / MAX: 12.71 MIN: 2.28 / MAX: 40.8 MIN: 2.02 / MAX: 21.33 MIN: 1.98 / MAX: 34.01 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 800M 1600M 2400M 3200M 4000M SE +/- 400000.00, N = 3 SE +/- 4598671.31, N = 3 SE +/- 1342054.81, N = 3 SE +/- 2403700.85, N = 3 SE +/- 1858314.65, N = 3 SE +/- 26633124.74, N = 3 SE +/- 2236316.42, N = 3 SE +/- 13813198.20, N = 3 2351900000 3254033333 2739633333 3337066667 3200600000 3558600000 3148233333 3520766667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: GoogLeNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 120 240 360 480 600 SE +/- 0.41, N = 3 SE +/- 1.14, N = 3 SE +/- 0.37, N = 3 SE +/- 2.46, N = 3 SE +/- 0.34, N = 3 SE +/- 2.62, N = 3 SE +/- 3.68, N = 3 SE +/- 1.52, N = 3 383.57 467.91 398.40 477.33 461.23 576.08 462.78 577.76
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1500 3000 4500 6000 7500 SE +/- 7.18, N = 6 SE +/- 7.99, N = 6 SE +/- 9.53, N = 6 SE +/- 22.13, N = 6 SE +/- 14.74, N = 6 SE +/- 18.12, N = 6 SE +/- 30.70, N = 7 SE +/- 20.74, N = 7 6707 6821 6693 6777 5670 5672 4565 4693 1. (CXX) g++ options: -O3
TensorFlow Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 1.17, N = 3 SE +/- 0.79, N = 3 SE +/- 0.61, N = 3 SE +/- 1.80, N = 3 SE +/- 0.01, N = 3 SE +/- 1.39, N = 3 SE +/- 0.48, N = 3 SE +/- 0.61, N = 3 117.53 145.29 125.14 138.39 148.45 174.95 140.53 169.75
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: HWB Color Space Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 2.40, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 286 193 277 207 265 236 285 256 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 12.54 13.34 13.59 14.42 16.50 15.04 11.17 11.69 MIN: 9.17 / MAX: 21.01 MIN: 9.67 / MAX: 39.84 MIN: 9.53 / MAX: 21.61 MIN: 9.74 / MAX: 43.95 MIN: 11.95 / MAX: 28.87 MIN: 12.32 / MAX: 32.87 MIN: 10.18 / MAX: 19.36 MIN: 10.28 / MAX: 42.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1000K 2000K 3000K 4000K 5000K SE +/- 21428.06, N = 3 SE +/- 26891.33, N = 3 SE +/- 52575.97, N = 3 SE +/- 24083.78, N = 3 SE +/- 25335.31, N = 3 SE +/- 50660.01, N = 15 SE +/- 35182.67, N = 3 SE +/- 35300.21, N = 3 4384040.52 3373323.92 4315467.17 3392842.38 4481667.95 3245908.40 4752673.79 3780240.56 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 7.13 7.32 7.76 7.97 9.79 7.72 6.72 6.95 MIN: 6.64 / MAX: 12.22 MIN: 6.78 / MAX: 18.72 MIN: 6.86 / MAX: 12.92 MIN: 7.04 / MAX: 21.51 MIN: 4.37 / MAX: 18.18 MIN: 7.16 / MAX: 18.31 MIN: 6.22 / MAX: 11.15 MIN: 6.28 / MAX: 20.42 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.61, N = 7 SE +/- 0.83, N = 5 SE +/- 0.40, N = 7 SE +/- 0.97, N = 6 SE +/- 0.41, N = 7 SE +/- 0.25, N = 7 SE +/- 0.20, N = 7 SE +/- 0.42, N = 7 146.10 122.09 151.72 127.55 164.25 156.52 177.86 165.50 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 3 SE +/- 0.03, N = 3 16.33 13.74 15.74 13.52 16.10 14.53 19.68 15.43 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.26, N = 4 SE +/- 0.58, N = 5 SE +/- 0.29, N = 4 SE +/- 0.44, N = 15 SE +/- 0.20, N = 5 SE +/- 0.46, N = 4 SE +/- 0.22, N = 5 SE +/- 0.79, N = 5 62.75 54.82 65.36 55.98 70.91 65.22 79.44 70.43 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.18, N = 3 SE +/- 0.56, N = 3 SE +/- 0.32, N = 3 SE +/- 1.69, N = 3 SE +/- 0.76, N = 3 SE +/- 0.56, N = 3 SE +/- 0.91, N = 3 SE +/- 0.29, N = 3 149.38 123.88 143.81 122.70 140.23 118.57 122.72 103.38
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.6 Video Input: Bosphorus 4K Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.39, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 4 SE +/- 0.20, N = 4 SE +/- 0.06, N = 4 SE +/- 0.09, N = 4 29.05 27.26 31.40 27.90 37.86 37.04 38.93 39.31 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.27, N = 3 SE +/- 0.24, N = 3 SE +/- 0.55, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 54.38 42.87 48.49 43.91 47.78 41.56 43.05 38.05 1. (CC) gcc options: -shared -lxc -lblas -lmpi
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/pathtracer/real_time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.09, N = 3 SE +/- 0.42, N = 3 SE +/- 0.29, N = 3 SE +/- 0.81, N = 3 SE +/- 0.17, N = 3 SE +/- 0.49, N = 3 SE +/- 0.25, N = 3 SE +/- 0.89, N = 3 144.48 137.50 143.48 135.44 160.24 149.09 193.14 176.40
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 1.44, N = 15 SE +/- 1.63, N = 15 SE +/- 1.62, N = 15 SE +/- 1.67, N = 15 SE +/- 2.31, N = 15 SE +/- 2.18, N = 15 SE +/- 2.83, N = 15 SE +/- 2.84, N = 15 144.70 122.62 150.00 124.26 162.47 154.50 174.83 162.98 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Rotate Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.93, N = 6 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 197 148 194 143 196 172 203 182 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 500 1000 1500 2000 2500 2530.5 1785.0 2245.2 1873.1 2070.3 1960.9 1878.3 1809.7 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 110 220 330 440 550 SE +/- 1.67, N = 3 SE +/- 2.29, N = 3 SE +/- 1.91, N = 3 SE +/- 4.80, N = 3 SE +/- 0.24, N = 3 SE +/- 4.87, N = 3 SE +/- 2.30, N = 3 SE +/- 2.68, N = 3 375.73 447.50 386.00 449.91 448.46 528.93 423.59 501.39
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 2.59, N = 4 SE +/- 1.72, N = 3 SE +/- 2.11, N = 6 SE +/- 1.01, N = 3 SE +/- 0.92, N = 3 SE +/- 0.58, N = 3 SE +/- 2.17, N = 3 SE +/- 0.89, N = 3 220.57 184.30 215.50 181.63 210.93 178.28 187.51 157.36
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.15, N = 4 SE +/- 0.11, N = 4 SE +/- 0.06, N = 4 SE +/- 0.07, N = 4 SE +/- 0.10, N = 4 SE +/- 0.13, N = 4 SE +/- 0.10, N = 4 SE +/- 0.03, N = 4 16.08 14.40 15.38 14.09 14.72 13.26 12.60 11.49
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200M 400M 600M 800M 1000M SE +/- 1611276.24, N = 3 SE +/- 4432294.36, N = 3 SE +/- 1289603.73, N = 3 SE +/- 6141471.96, N = 3 SE +/- 940265.92, N = 3 SE +/- 3717554.45, N = 3 SE +/- 1515552.70, N = 3 SE +/- 7562646.32, N = 8 632396667 732560000 689003333 757176667 744410000 799496667 783770000 883701250 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
JPEG-XL libjxl Input: JPEG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 11 22 33 44 55 SE +/- 0.34, N = 8 SE +/- 0.01, N = 3 SE +/- 0.21, N = 3 SE +/- 0.36, N = 5 SE +/- 0.35, N = 3 SE +/- 0.06, N = 3 SE +/- 0.53, N = 15 SE +/- 0.67, N = 12 39.10 39.59 43.63 34.63 43.20 42.04 48.36 42.97 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
JPEG-XL libjxl Input: PNG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.32, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.49, N = 14 SE +/- 0.50, N = 3 43.36 34.83 40.35 33.27 42.91 40.08 46.32 39.52 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1100 2200 3300 4400 5500 SE +/- 21.44, N = 6 SE +/- 18.24, N = 6 SE +/- 15.47, N = 6 SE +/- 25.38, N = 6 SE +/- 23.47, N = 7 SE +/- 25.25, N = 7 SE +/- 22.92, N = 8 SE +/- 21.09, N = 7 5217 5342 5188 5322 4731 4733 3861 3894 1. (CXX) g++ options: -O3
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50 100 150 200 250 SE +/- 0.98, N = 3 SE +/- 1.17, N = 3 SE +/- 0.61, N = 3 SE +/- 0.62, N = 3 SE +/- 2.34, N = 3 SE +/- 0.74, N = 3 SE +/- 1.98, N = 3 SE +/- 1.38, N = 3 195.71 173.91 190.06 169.85 205.53 188.89 234.54 214.81 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.15, N = 3 SE +/- 0.09, N = 15 SE +/- 0.11, N = 15 SE +/- 0.13, N = 15 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.21, N = 4 SE +/- 0.03, N = 3 14.4 13.8 14.5 13.3 14.6 15.2 18.0 17.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.34, N = 3 SE +/- 0.07, N = 3 SE +/- 0.19, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 28.52 24.73 28.48 24.68 32.34 30.04 33.38 31.71 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.8496 1.6992 2.5488 3.3984 4.248 SE +/- 0.017, N = 9 SE +/- 0.029, N = 8 SE +/- 0.011, N = 9 SE +/- 0.022, N = 9 SE +/- 0.022, N = 9 SE +/- 0.008, N = 9 SE +/- 0.016, N = 9 SE +/- 0.009, N = 10 3.730 3.776 3.550 3.738 3.169 3.044 2.971 2.805 1. (CXX) g++ options: -O3 -fPIC -lm
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.14, N = 3 SE +/- 1.40, N = 3 SE +/- 0.63, N = 3 SE +/- 1.04, N = 12 SE +/- 0.03, N = 3 SE +/- 1.57, N = 3 SE +/- 0.58, N = 3 SE +/- 0.21, N = 3 119.73 141.95 123.69 135.28 143.67 161.06 129.02 150.33
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 14.10 11.90 14.36 11.97 15.06 12.54 15.97 13.26 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13 26 39 52 65 58.38 51.25 56.40 49.14 53.49 48.56 48.43 43.70
DuckDB Benchmark: IMDB OpenBenchmarking.org Seconds, Fewer Is Better DuckDB 0.9.1 Benchmark: IMDB Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.23, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.41, N = 3 SE +/- 0.10, N = 3 SE +/- 0.67, N = 3 SE +/- 0.59, N = 3 SE +/- 0.30, N = 3 100.09 127.70 99.62 131.80 99.49 125.88 99.18 127.57 1. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13 26 39 52 65 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 46.96 55.44 47.09 56.78 46.76 53.76 42.78 52.69 1. RawTherapee, version 5.10, command line.
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.39, N = 3 SE +/- 0.93, N = 3 SE +/- 1.28, N = 3 SE +/- 0.04, N = 3 SE +/- 1.12, N = 3 SE +/- 0.50, N = 3 SE +/- 0.70, N = 3 104.23 111.71 103.56 107.30 120.93 115.47 91.51 94.66
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.027, N = 3 SE +/- 0.015, N = 3 SE +/- 0.047, N = 3 SE +/- 0.042, N = 3 SE +/- 0.030, N = 3 SE +/- 0.049, N = 3 SE +/- 0.005, N = 3 SE +/- 0.044, N = 3 6.490 5.991 6.572 6.052 7.061 6.698 7.876 7.360 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 15 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 7.76 7.62 7.72 7.46 7.94 8.16 9.80 9.67 1. (CC) gcc options: -O3 -pthread -lz -llzma
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 500M 1000M 1500M 2000M 2500M SE +/- 688799.28, N = 3 SE +/- 2206304.10, N = 3 SE +/- 692820.32, N = 3 SE +/- 3017909.50, N = 3 SE +/- 3167192.94, N = 3 SE +/- 3300505.01, N = 3 SE +/- 27191440.65, N = 3 SE +/- 17236814.61, N = 3 1640266667 1963233333 1679700000 2090466667 1890566667 2025000000 1927766667 2154633333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: GoogLeNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 80 160 240 320 400 SE +/- 1.94, N = 3 SE +/- 3.52, N = 5 SE +/- 0.83, N = 3 SE +/- 2.38, N = 3 SE +/- 1.62, N = 3 SE +/- 2.37, N = 3 SE +/- 1.12, N = 3 SE +/- 0.21, N = 3 333.73 341.51 335.58 308.95 380.14 331.76 319.76 291.37
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 0.09, N = 3 SE +/- 2.30, N = 4 SE +/- 0.25, N = 3 SE +/- 1.02, N = 3 SE +/- 0.16, N = 3 SE +/- 4.15, N = 15 SE +/- 0.03, N = 3 SE +/- 3.39, N = 3 217.88 205.89 213.99 199.90 227.42 212.92 259.19 251.31 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.15, N = 3 SE +/- 0.00, N = 3 SE +/- 0.88, N = 3 150 150 158 164 158 182 171 194 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.29, N = 3 SE +/- 0.22, N = 3 SE +/- 0.32, N = 3 SE +/- 0.32, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 76.92 69.65 73.06 68.44 69.93 67.38 64.48 60.53 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.045, N = 6 SE +/- 0.027, N = 6 SE +/- 0.033, N = 6 SE +/- 0.035, N = 6 SE +/- 0.013, N = 7 SE +/- 0.022, N = 7 SE +/- 0.025, N = 7 SE +/- 0.031, N = 7 6.836 7.121 6.605 7.038 6.278 6.172 5.784 5.613 1. (CXX) g++ options: -O3 -fPIC -lm
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300 600 900 1200 1500 SE +/- 2.12, N = 3 SE +/- 0.66, N = 15 SE +/- 1.08, N = 15 SE +/- 0.65, N = 15 SE +/- 4.45, N = 3 SE +/- 4.96, N = 3 SE +/- 3.01, N = 4 SE +/- 1.88, N = 3 1126.4 1040.2 1127.5 1039.2 1032.0 963.6 1221.8 1165.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Cell Phone Drop Test Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.32, N = 3 33.75 27.51 31.92 27.63 31.49 28.22 27.90 26.88
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.31, N = 3 SE +/- 0.27, N = 3 SE +/- 0.26, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 30.00 27.61 29.43 27.78 34.00 33.61 34.46 34.66 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300 600 900 1200 1500 SE +/- 0.56, N = 3 SE +/- 1.00, N = 3 SE +/- 1.45, N = 3 SE +/- 1.78, N = 15 SE +/- 0.43, N = 3 SE +/- 3.69, N = 3 SE +/- 0.84, N = 3 SE +/- 1.60, N = 3 1131.1 1041.8 1133.3 1046.0 1069.1 992.1 1242.6 1189.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 24.0 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.17, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 4 20.18 18.47 19.65 18.14 19.23 18.29 17.26 16.18
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 600M 1200M 1800M 2400M 3000M SE +/- 2629533.12, N = 3 SE +/- 28812627.44, N = 4 SE +/- 5493127.02, N = 3 SE +/- 27382304.50, N = 5 SE +/- 7076957.92, N = 3 SE +/- 28500058.48, N = 3 SE +/- 11426868.92, N = 3 SE +/- 32405829.38, N = 3 2138766667 2494050000 2308966667 2491340000 2539200000 2655500000 2475500000 2620066667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.27 5.55 5.77 6.02 6.43 5.72 5.19 5.18 MIN: 4.98 / MAX: 13.16 MIN: 5.12 / MAX: 24.99 MIN: 5.26 / MAX: 13.86 MIN: 5.37 / MAX: 27.77 MIN: 3.84 / MAX: 15.83 MIN: 5.1 / MAX: 17.93 MIN: 4.72 / MAX: 11.02 MIN: 4.74 / MAX: 26.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
QMCPACK Input: Li2_STO_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: Li2_STO_ae Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 1.04, N = 3 SE +/- 1.11, N = 5 SE +/- 0.89, N = 3 SE +/- 1.11, N = 3 SE +/- 1.03, N = 3 SE +/- 0.93, N = 3 121.19 102.12 117.81 106.27 109.30 101.63 105.98 97.91 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
Graph500 Scale: 26 OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 140M 280M 420M 560M 700M 539613000 667365000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenFOAM Input: drivaerFastback, Small Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 31.78 32.48 32.00 28.84 31.38 35.60 31.70 29.33 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Fast Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.010, N = 3 SE +/- 0.081, N = 3 SE +/- 0.033, N = 3 SE +/- 0.043, N = 15 SE +/- 0.022, N = 3 SE +/- 0.047, N = 3 SE +/- 0.023, N = 3 SE +/- 0.038, N = 3 6.324 6.023 6.501 6.077 6.719 6.480 7.392 6.960 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.21, N = 3 SE +/- 0.22, N = 3 SE +/- 0.31, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 41.13 38.65 39.88 38.14 37.75 37.31 34.79 33.65 1. (CXX) g++ options: -O3 -fPIC -lm
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: AlexNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 1.95, N = 5 SE +/- 6.39, N = 13 SE +/- 2.31, N = 5 SE +/- 7.35, N = 5 SE +/- 0.51, N = 5 SE +/- 7.98, N = 5 SE +/- 6.22, N = 5 SE +/- 2.22, N = 5 841.68 932.59 852.36 940.40 969.62 996.47 819.89 858.84
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 8.3.4 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.31, N = 3 SE +/- 0.09, N = 3 48.71 46.87 47.95 46.57 48.01 46.64 41.85 40.38
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Upload Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 23.33 22.34 23.77 23.30 24.97 24.56 26.93 26.80 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 153.12 134.78 150.67 159.31 160.73 162.03 148.40 139.62 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4 8 12 16 20 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 15.59 14.99 15.62 14.51 15.76 15.49 17.42 17.02
JPEG-XL libjxl Input: JPEG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 4 SE +/- 0.07, N = 4 26.86 27.33 27.75 27.26 28.75 28.16 32.24 31.61 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 35.66 36.20 35.20 35.70 34.93 35.46 30.17 30.47 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20M 40M 60M 80M 100M SE +/- 662950.65, N = 3 SE +/- 565297.90, N = 12 SE +/- 1037167.36, N = 3 SE +/- 574699.97, N = 12 SE +/- 308756.34, N = 3 SE +/- 692701.79, N = 8 SE +/- 746822.47, N = 3 SE +/- 761276.42, N = 12 82455664 77501248 83475645 78057728 87797206 80169620 92709751 89231850
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 110 220 330 440 550 SE +/- 0.60, N = 3 SE +/- 1.13, N = 3 SE +/- 0.79, N = 3 SE +/- 1.30, N = 3 SE +/- 0.33, N = 3 SE +/- 0.26, N = 3 SE +/- 1.84, N = 3 SE +/- 1.42, N = 3 461.61 435.21 464.72 439.84 455.57 456.18 520.22 519.89
JPEG-XL libjxl Input: PNG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 4 SE +/- 0.08, N = 4 26.25 26.84 27.09 26.99 28.10 27.66 31.35 30.97 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1963 2.3926 3.5889 4.7852 5.9815 SE +/- 0.005, N = 7 SE +/- 0.019, N = 7 SE +/- 0.015, N = 7 SE +/- 0.028, N = 7 SE +/- 0.006, N = 7 SE +/- 0.014, N = 7 SE +/- 0.008, N = 8 SE +/- 0.015, N = 8 4.916 5.317 4.867 5.311 4.923 5.074 4.456 4.579 1. (CXX) g++ options: -O3 -fPIC -lm
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Video On Demand Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.10, N = 3 SE +/- 0.43, N = 3 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 47.34 45.29 48.14 46.79 49.84 48.77 53.99 53.29 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
DuckDB Benchmark: TPC-H Parquet OpenBenchmarking.org Seconds, Fewer Is Better DuckDB 0.9.1 Benchmark: TPC-H Parquet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.57, N = 3 SE +/- 0.58, N = 3 SE +/- 0.95, N = 3 SE +/- 0.12, N = 3 SE +/- 0.55, N = 3 SE +/- 0.34, N = 3 SE +/- 0.44, N = 3 146.87 156.14 145.24 158.31 145.57 155.73 132.87 144.26 1. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.05, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.28, N = 3 55.74 56.71 62.53 62.11 55.99 65.02 55.07 57.13 MIN: 44.83 / MAX: 69.99 MIN: 45.43 / MAX: 89.46 MIN: 48.23 / MAX: 78.43 MIN: 47.82 / MAX: 101.26 MIN: 27.63 / MAX: 76.45 MIN: 55.15 / MAX: 104.43 MIN: 46.78 / MAX: 80.73 MIN: 39.58 / MAX: 104.91 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20M 40M 60M 80M 100M SE +/- 435900.66, N = 3 SE +/- 594234.55, N = 3 SE +/- 782176.98, N = 3 SE +/- 872659.60, N = 4 SE +/- 276414.35, N = 3 SE +/- 928557.10, N = 3 SE +/- 739343.51, N = 3 SE +/- 862582.24, N = 7 85744542 80770465 86354518 80139566 90871770 83651785 94616807 92771639
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.135 0.27 0.405 0.54 0.675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.55 0.54 0.55 0.54 0.52 0.51 0.60 0.59 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Platform Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.27, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 47.32 45.95 48.35 46.59 49.79 48.76 53.92 53.22 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 70 140 210 280 350 SE +/- 5.15, N = 3 SE +/- 2.59, N = 12 SE +/- 5.07, N = 3 SE +/- 3.74, N = 12 SE +/- 2.20, N = 3 SE +/- 3.79, N = 8 SE +/- 3.41, N = 3 SE +/- 3.40, N = 12 314.44 328.41 309.03 325.97 294.33 317.36 280.26 286.78 MAX: 27244.84 MAX: 29309.84 MAX: 26720.06 MAX: 30042.47 MAX: 27740.38 MAX: 32341.07 MAX: 27450.82 MAX: 28496.67
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.48, N = 3 SE +/- 1.01, N = 3 SE +/- 0.87, N = 3 SE +/- 1.11, N = 4 SE +/- 0.15, N = 3 SE +/- 1.18, N = 3 SE +/- 0.68, N = 3 SE +/- 0.80, N = 7 90.02 94.84 89.53 95.39 85.16 92.23 81.73 82.73 MAX: 23857.34 MAX: 23842.98 MAX: 23819.37 MAX: 23846.38 MAX: 23810.86 MAX: 23842.9 MAX: 24081.78 MAX: 24148.34
Graph500 Scale: 26 OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100M 200M 300M 400M 500M 416523000 484977000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 110 220 330 440 550 SE +/- 2.85, N = 3 SE +/- 1.35, N = 3 SE +/- 5.88, N = 3 SE +/- 3.85, N = 12 SE +/- 3.41, N = 3 SE +/- 4.37, N = 3 SE +/- 4.18, N = 6 SE +/- 4.12, N = 5 446.40 491.89 461.62 460.66 465.50 485.63 437.20 423.30 MIN: 32.64 / MAX: 4615.38 MIN: 51.86 / MAX: 5454.55 MIN: 35.59 / MAX: 5454.55 MIN: 53.62 / MAX: 5454.55 MIN: 40.93 / MAX: 5454.55 MIN: 63.63 / MAX: 5000 MIN: 41.7 / MAX: 5454.55 MIN: 61.54 / MAX: 6000
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Thread Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 160 320 480 640 800 SE +/- 1.64, N = 8 SE +/- 3.86, N = 8 SE +/- 1.27, N = 8 SE +/- 5.02, N = 8 SE +/- 1.17, N = 8 SE +/- 2.57, N = 8 SE +/- 1.34, N = 8 SE +/- 1.89, N = 8 702.6 651.9 705.5 663.8 680.2 675.5 742.9 755.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.3375 0.675 1.0125 1.35 1.6875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 1.40 1.39 1.39 1.39 1.31 1.30 1.50 1.50 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bird Strike on Windshield Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.45, N = 3 SE +/- 0.69, N = 3 SE +/- 0.03, N = 3 SE +/- 0.38, N = 3 SE +/- 0.24, N = 3 SE +/- 0.29, N = 3 SE +/- 0.14, N = 3 SE +/- 0.83, N = 3 126.89 116.49 120.76 119.03 117.41 124.44 110.32 113.15
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 132.13 137.46 128.60 137.00 120.75 130.62 119.80 129.96
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Jython Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 800 1600 2400 3200 4000 SE +/- 20.55, N = 4 SE +/- 28.30, N = 4 SE +/- 38.86, N = 5 SE +/- 24.34, N = 4 SE +/- 7.09, N = 4 SE +/- 24.09, N = 4 SE +/- 21.99, N = 4 SE +/- 9.71, N = 4 3785 3926 3707 3921 3801 3892 3424 3466
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 110 220 330 440 550 SE +/- 1.94, N = 3 SE +/- 0.19, N = 3 SE +/- 4.95, N = 3 SE +/- 3.17, N = 12 SE +/- 2.93, N = 3 SE +/- 3.26, N = 3 SE +/- 2.86, N = 6 SE +/- 3.10, N = 5 465.06 499.18 474.68 467.96 486.05 507.56 455.79 443.58 MIN: 32.59 / MAX: 5000 MIN: 54.2 / MAX: 4615.38 MIN: 36.43 / MAX: 6000 MIN: 52.36 / MAX: 6000 MIN: 40.43 / MAX: 6666.67 MIN: 66.45 / MAX: 5454.55 MIN: 42.19 / MAX: 6666.67 MIN: 62.43 / MAX: 6666.67
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 110 220 330 440 550 SE +/- 6.03, N = 3 SE +/- 3.08, N = 3 SE +/- 3.60, N = 3 SE +/- 3.54, N = 12 SE +/- 3.45, N = 3 SE +/- 2.55, N = 3 SE +/- 3.62, N = 6 SE +/- 5.39, N = 5 470.02 501.07 476.91 471.79 481.66 501.63 458.23 438.60 MIN: 32.59 / MAX: 5454.55 MIN: 54.25 / MAX: 5000 MIN: 36.01 / MAX: 5000 MIN: 53.43 / MAX: 6000 MIN: 40.16 / MAX: 5454.55 MIN: 64.45 / MAX: 6666.67 MIN: 42.16 / MAX: 6000 MIN: 58.2 / MAX: 6000
Timed CPython Compilation Build Configuration: Released Build, PGO + LTO Optimized OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Released Build, PGO + LTO Optimized Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 60 120 180 240 300 275.39 276.46 273.52 276.23 277.39 279.69 244.82 244.95
DaCapo Benchmark Java Test: Apache Lucene Search Index OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Lucene Search Index Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 800 1600 2400 3200 4000 SE +/- 33.41, N = 3 SE +/- 10.84, N = 3 SE +/- 42.24, N = 4 SE +/- 11.86, N = 3 SE +/- 11.79, N = 3 SE +/- 41.09, N = 5 SE +/- 18.19, N = 3 SE +/- 12.44, N = 3 3378 3643 3396 3537 3581 3689 3242 3345
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.00, N = 10 SE +/- 0.00, N = 10 SE +/- 0.00, N = 10 SE +/- 0.00, N = 10 SE +/- 0.01, N = 10 SE +/- 0.01, N = 10 SE +/- 0.00, N = 10 SE +/- 0.01, N = 10 10.13 10.01 10.13 10.03 10.11 10.05 11.36 11.31 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Timed CPython Compilation Build Configuration: Default OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Default Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 19.12 18.81 18.85 18.82 19.20 18.93 17.08 16.93
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.7808 1.5616 2.3424 3.1232 3.904 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 3.10 3.09 3.10 3.09 3.08 3.07 3.47 3.46 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 70K 140K 210K 280K 350K SE +/- 256.85, N = 3 SE +/- 384.08, N = 3 SE +/- 670.43, N = 3 SE +/- 196.24, N = 3 SE +/- 625.56, N = 3 SE +/- 330.95, N = 3 SE +/- 209.97, N = 3 SE +/- 411.11, N = 3 277647 277589 277260 277298 277205 275472 309896 308434 1. (CC) gcc options: -pedantic -O3
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 SE +/- 0.24, N = 3 SE +/- 0.48, N = 3 SE +/- 0.22, N = 3 SE +/- 1.51, N = 3 SE +/- 0.13, N = 3 SE +/- 0.38, N = 3 711.10 710.92 712.01 712.09 711.38 712.70 799.72 799.49 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 800 1600 2400 3200 4000 SE +/- 22.17, N = 3 SE +/- 28.11, N = 3 SE +/- 25.35, N = 3 SE +/- 28.57, N = 3 SE +/- 28.42, N = 3 SE +/- 25.40, N = 3 SE +/- 33.58, N = 3 SE +/- 30.36, N = 12 3225.7 3207.0 3229.1 3222.8 3209.6 3210.1 3600.5 3586.3 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4M 8M 12M 16M 20M SE +/- 5238.74, N = 3 SE +/- 17457.89, N = 3 SE +/- 30179.10, N = 3 SE +/- 7571.88, N = 3 SE +/- 8685.88, N = 3 SE +/- 38670.98, N = 3 SE +/- 9492.69, N = 3 SE +/- 162096.41, N = 15 16906333 16904667 16885333 16884000 16882333 16843333 18774333 18200533 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 170 340 510 680 850 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 1.15, N = 3 SE +/- 0.41, N = 4 SE +/- 0.48, N = 4 763 763 762 763 765 767 691 692
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9M 18M 27M 36M 45M SE +/- 1666.67, N = 3 SE +/- 1201.85, N = 3 SE +/- 3000.00, N = 3 SE +/- 1452.97, N = 3 SE +/- 1527.53, N = 3 SE +/- 1154.70, N = 3 SE +/- 417042.80, N = 5 SE +/- 419600.12, N = 5 36537667 36497667 36539000 36521333 36506000 36461000 40244000 38950600 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 16M 32M 48M 64M 80M SE +/- 4910.31, N = 3 SE +/- 4163.33, N = 3 SE +/- 5364.49, N = 3 SE +/- 822374.71, N = 4 SE +/- 666.67, N = 3 SE +/- 3844.19, N = 3 SE +/- 599433.09, N = 9 SE +/- 68119.99, N = 3 67130333 67064000 67127667 66266000 67074667 66991333 73140667 70499000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
DaCapo Benchmark Java Test: Apache Kafka OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Kafka Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1200 2400 3600 4800 6000 SE +/- 6.44, N = 3 SE +/- 2.03, N = 3 SE +/- 3.51, N = 3 SE +/- 4.06, N = 3 SE +/- 1.20, N = 3 SE +/- 1.76, N = 3 SE +/- 31.50, N = 3 SE +/- 10.11, N = 3 5108 5101 5102 5088 5106 5113 5560 5611
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bumper Beam Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.23, N = 3 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 83.44 78.27 81.72 80.32 79.54 81.30 78.71 86.11
nginx Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 90K 180K 270K 360K 450K SE +/- 125.38, N = 3 SE +/- 142.71, N = 3 SE +/- 576.43, N = 2 367199.06 399698.78 381352.69 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Graph500 Scale: 26 OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300M 600M 900M 1200M 1500M 1244300000 1204520000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Graph500 Scale: 26 OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300M 600M 900M 1200M 1500M 1299170000 1267480000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 129.7 129.7 129.7 129.7 129.7 129.7 129.5 129.5 MIN: 105.9 MIN: 105.9 MIN: 105.9 MIN: 105.9 MIN: 105.9 MIN: 105.9 MIN: 105.7 MIN: 105.7 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P 3K 6K 9K 12K 15K SE +/- 150.41, N = 12 SE +/- 577.93, N = 3 SE +/- 228.53, N = 12 SE +/- 295.26, N = 8 8868.20 14665.00 9204.87 14463.40 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 50M 100M 150M 200M 250M SE +/- 1751369.24, N = 12 SE +/- 4344961.90, N = 10 SE +/- 629927.17, N = 3 SE +/- 2925715.37, N = 11 SE +/- 1304590.97, N = 3 SE +/- 2148606.38, N = 4 SE +/- 2966712.90, N = 9 SE +/- 2482737.87, N = 3 68019088 137977203 73592230 149409082 96887479 187761769 109766345 222610378 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
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.9132 1.8264 2.7396 3.6528 4.566 SE +/- 0.03338, N = 15 SE +/- 0.04072, N = 3 SE +/- 0.01443, N = 3 SE +/- 0.02633, N = 15 SE +/- 0.00807, N = 3 SE +/- 0.04801, N = 3 SE +/- 0.01801, N = 3 SE +/- 0.01381, N = 3 2.97094 4.05270 2.88734 3.95819 3.06500 4.05881 2.15980 2.81739 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.213 2.426 3.639 4.852 6.065 SE +/- 0.08827, N = 15 SE +/- 0.03283, N = 3 SE +/- 0.01103, N = 3 SE +/- 0.02608, N = 3 SE +/- 0.00659, N = 3 SE +/- 0.00316, N = 3 SE +/- 0.00472, N = 3 SE +/- 0.02371, N = 3 4.57581 5.02267 4.64757 5.39123 2.79694 3.46571 2.16966 2.80263 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.55, N = 3 SE +/- 0.08, N = 3 SE +/- 0.32, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 35.07 40.45 35.11 40.52 30.92 33.29 29.96 31.53 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.40, N = 3 SE +/- 0.31, N = 3 SE +/- 0.33, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 33.33 36.23 33.99 36.00 29.41 29.75 29.02 28.85 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.4698 0.9396 1.4094 1.8792 2.349 SE +/- 0.00884, N = 3 SE +/- 0.00720, N = 3 SE +/- 0.01053, N = 3 SE +/- 0.00871, N = 3 SE +/- 0.00936, N = 3 SE +/- 0.01492, N = 3 SE +/- 0.01491, N = 4 SE +/- 0.00701, N = 3 1.45280 2.02659 1.47249 2.08780 1.27368 1.76353 1.20298 1.64919 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.3867 0.7734 1.1601 1.5468 1.9335 SE +/- 0.02719, N = 15 SE +/- 0.00498, N = 3 SE +/- 0.01456, N = 3 SE +/- 0.01853, N = 5 SE +/- 0.01594, N = 3 SE +/- 0.01405, N = 15 SE +/- 0.00291, N = 3 SE +/- 0.01541, N = 3 1.37831 1.65270 1.41662 1.71875 1.17292 1.43573 1.10042 1.32454 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.01698, N = 3 SE +/- 0.01680, N = 3 SE +/- 0.03023, N = 3 SE +/- 0.03080, N = 3 SE +/- 0.00544, N = 3 SE +/- 0.02968, N = 3 SE +/- 0.02630, N = 3 SE +/- 0.06875, N = 3 3.13366 6.00525 3.32030 6.51744 3.19298 6.39031 3.23780 6.49693 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.02187, N = 3 SE +/- 0.09530, N = 15 SE +/- 0.03815, N = 5 SE +/- 0.06816, N = 3 SE +/- 0.01810, N = 3 SE +/- 0.03225, N = 3 SE +/- 0.02572, N = 3 SE +/- 0.01358, N = 3 3.02897 5.74491 3.37034 6.17796 3.17002 5.62517 3.18392 5.83954 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.28, N = 3 24.55 30.47 23.66 34.25 21.34 34.31 16.55 31.79 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7 14 21 28 35 SE +/- 0.32, N = 15 SE +/- 0.21, N = 3 SE +/- 0.33, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.36, N = 3 SE +/- 0.19, N = 3 SE +/- 0.39, N = 13 21.22 24.65 23.66 29.44 18.93 27.59 15.04 26.09 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.02823, N = 3 SE +/- 0.08283, N = 3 SE +/- 0.07483, N = 3 SE +/- 0.01417, N = 3 SE +/- 0.01428, N = 3 SE +/- 0.03717, N = 3 SE +/- 0.00434, N = 3 SE +/- 0.02114, N = 3 5.22781 7.34848 5.29027 7.30822 5.21520 6.90619 4.01687 5.10948 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.06596, N = 15 SE +/- 0.02902, N = 3 SE +/- 0.06620, N = 3 SE +/- 0.06105, N = 3 SE +/- 0.03075, N = 3 SE +/- 0.03218, N = 3 SE +/- 0.01631, N = 3 SE +/- 0.15083, N = 15 5.67700 7.04111 5.91961 7.53259 4.49976 5.55101 3.69649 4.29531 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 16 32 48 64 80 SE +/- 0.23, N = 3 SE +/- 0.50, N = 3 SE +/- 0.31, N = 3 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.57, N = 3 SE +/- 0.12, N = 3 61.25 72.80 63.54 73.97 62.13 68.83 50.83 64.79 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 14 28 42 56 70 SE +/- 0.44, N = 3 SE +/- 0.68, N = 3 SE +/- 0.23, N = 3 SE +/- 1.12, N = 15 SE +/- 0.17, N = 3 SE +/- 0.62, N = 3 SE +/- 0.04, N = 3 SE +/- 0.44, N = 3 47.24 60.11 49.97 55.90 49.64 60.36 39.75 44.60 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.3244 2.6488 3.9732 5.2976 6.622 SE +/- 0.02534, N = 3 SE +/- 0.03854, N = 3 SE +/- 0.01694, N = 3 SE +/- 0.02155, N = 3 SE +/- 0.05586, N = 3 SE +/- 0.02062, N = 3 SE +/- 0.03569, N = 3 SE +/- 0.02988, N = 3 5.10914 5.74921 5.26075 5.88628 4.86604 5.29287 4.26352 4.65431 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 1.1255 2.251 3.3765 4.502 5.6275 SE +/- 0.00187, N = 3 SE +/- 0.05347, N = 4 SE +/- 0.00532, N = 3 SE +/- 0.02558, N = 3 SE +/- 0.00313, N = 3 SE +/- 0.10855, N = 15 SE +/- 0.00044, N = 3 SE +/- 0.05342, N = 3 4.58912 4.85818 4.67269 5.00222 4.39649 4.72530 3.85774 3.98013 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 100 200 300 400 500 SE +/- 1.73, N = 3 SE +/- 5.57, N = 13 SE +/- 2.21, N = 3 SE +/- 6.06, N = 3 SE +/- 0.94, N = 3 SE +/- 0.96, N = 3 SE +/- 0.74, N = 3 SE +/- 4.07, N = 3 380.90 460.67 382.11 475.25 329.04 352.74 302.27 327.88 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 3.36, N = 15 SE +/- 5.82, N = 12 SE +/- 6.41, N = 15 SE +/- 2.59, N = 15 SE +/- 0.09, N = 3 SE +/- 0.69, N = 15 SE +/- 0.71, N = 3 SE +/- 0.44, N = 3 139.10 121.67 155.79 121.78 116.32 92.35 109.67 100.74 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.15651, N = 15 SE +/- 0.34632, N = 12 SE +/- 0.22869, N = 15 SE +/- 0.16487, N = 15 SE +/- 0.00664, N = 3 SE +/- 0.07619, N = 15 SE +/- 0.05824, N = 3 SE +/- 0.04271, N = 3 7.24187 8.39962 6.54965 8.26016 8.59719 10.83623 9.11885 9.92684 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.22, N = 3 SE +/- 0.74, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.30, N = 3 SE +/- 0.57, N = 3 61.83 76.42 61.01 79.38 55.12 78.40 47.90 70.44 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.55, N = 15 SE +/- 1.43, N = 15 SE +/- 0.55, N = 15 SE +/- 0.47, N = 14 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.10, N = 3 SE +/- 0.35, N = 3 54.96 69.45 59.18 69.20 50.35 64.29 43.54 58.94 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 300 600 900 1200 1500 SE +/- 21.06, N = 12 SE +/- 113.47, N = 12 SE +/- 20.21, N = 15 SE +/- 7.22, N = 3 SE +/- 0.29, N = 3 SE +/- 2.30, N = 3 SE +/- 2.24, N = 3 SE +/- 3.17, N = 3 734.80 1498.58 632.15 719.23 409.59 633.29 488.92 538.23 MIN: 546.95 MIN: 641.2 MIN: 459.4 MIN: 696.95 MIN: 390.22 MIN: 621.42 MIN: 457.65 MIN: 529.58 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
TensorFlow Device: CPU - Batch Size: 1 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: AlexNet Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 13 26 39 52 65 SE +/- 0.76, N = 15 SE +/- 0.57, N = 15 SE +/- 1.22, N = 15 SE +/- 0.52, N = 15 SE +/- 0.08, N = 8 SE +/- 0.44, N = 15 SE +/- 0.66, N = 15 SE +/- 0.45, N = 15 48.28 37.76 43.67 33.21 56.53 37.57 35.50 30.76
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 7K 14K 21K 28K 35K SE +/- 938.95, N = 15 SE +/- 175.78, N = 4 SE +/- 281.72, N = 15 SE +/- 490.54, N = 15 SE +/- 236.27, N = 4 SE +/- 312.17, N = 3 SE +/- 298.34, N = 15 SE +/- 356.81, N = 15 21286.6 30236.0 15081.0 11866.7 24688.5 30108.7 26378.1 30547.6 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.5922 1.1844 1.7766 2.3688 2.961 SE +/- 0.023295, N = 15 SE +/- 0.030907, N = 15 SE +/- 0.020941, N = 15 SE +/- 0.028863, N = 15 SE +/- 0.007749, N = 10 SE +/- 0.017240, N = 15 SE +/- 0.023842, N = 15 SE +/- 0.024402, N = 15 2.632077 1.982932 2.287766 1.711296 2.144857 1.469210 1.847537 1.432362 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
LuxCoreRender Scene: Danish Mood - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.22, N = 15 SE +/- 0.07, N = 15 SE +/- 0.20, N = 15 SE +/- 0.08, N = 3 SE +/- 0.18, N = 12 SE +/- 0.10, N = 12 SE +/- 0.11, N = 15 6.03 6.23 6.29 5.91 6.85 7.00 7.63 7.70 MIN: 2.52 / MAX: 7 MIN: 2.27 / MAX: 9.18 MIN: 2.44 / MAX: 7.56 MIN: 2.31 / MAX: 9.24 MIN: 3.05 / MAX: 8.02 MIN: 2.74 / MAX: 9.4 MIN: 3.26 / MAX: 9.01 MIN: 3.44 / MAX: 9.79
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.22, N = 12 SE +/- 0.05, N = 3 SE +/- 0.16, N = 15 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.17, N = 12 6.30 6.81 6.82 7.41 7.10 8.82 8.06 8.88 MIN: 2.53 / MAX: 7.3 MIN: 2.55 / MAX: 9.19 MIN: 2.81 / MAX: 7.94 MIN: 2.67 / MAX: 9.42 MIN: 3.06 / MAX: 8.2 MIN: 3.72 / MAX: 10.41 MIN: 3.62 / MAX: 9.37 MIN: 3.73 / MAX: 11.48
LuxCoreRender Scene: DLSC - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 15 SE +/- 0.06, N = 15 SE +/- 0.23, N = 15 SE +/- 0.02, N = 3 SE +/- 0.24, N = 15 7.46 10.17 8.00 10.44 8.72 11.12 9.38 12.74 MIN: 7.17 / MAX: 8.21 MIN: 9.34 / MAX: 14.75 MIN: 7.65 / MAX: 9.12 MIN: 8.86 / MAX: 16.08 MIN: 8.12 / MAX: 10.6 MIN: 9.18 / MAX: 17.51 MIN: 8.94 / MAX: 11.49 MIN: 10.69 / MAX: 19.19
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 12.12, N = 12 SE +/- 15.80, N = 12 SE +/- 5.17, N = 9 SE +/- 18.26, N = 12 SE +/- 0.67, N = 3 SE +/- 0.99, N = 12 SE +/- 0.96, N = 15 SE +/- 9.88, N = 12 173.01 182.12 145.24 173.55 119.84 126.39 75.73 102.13 1. (CXX) g++ options: -O3 -fopenmp
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 3.12, N = 12 SE +/- 4.11, N = 15 SE +/- 3.75, N = 15 SE +/- 3.75, N = 15 SE +/- 0.10, N = 3 SE +/- 0.24, N = 3 SE +/- 0.32, N = 4 SE +/- 0.23, N = 3 63.43 74.87 64.88 68.86 46.29 50.83 28.70 37.66 1. (CXX) g++ options: -O3 -fopenmp
NAMD Input: STMV with 1,066,628 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.5072 1.0144 1.5216 2.0288 2.536 SE +/- 0.05087, N = 15 SE +/- 0.05644, N = 12 SE +/- 0.05862, N = 15 SE +/- 0.05463, N = 15 SE +/- 0.01396, N = 15 SE +/- 0.04403, N = 15 SE +/- 0.02648, N = 15 SE +/- 0.08185, N = 13 1.45223 1.88679 1.50214 1.76778 1.05274 1.10900 1.43787 2.25422
NAMD Input: ATPase with 327,506 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 2 4 6 8 10 SE +/- 0.16058, N = 15 SE +/- 0.26203, N = 15 SE +/- 0.14537, N = 15 SE +/- 0.44989, N = 15 SE +/- 0.21567, N = 12 SE +/- 0.17435, N = 15 SE +/- 0.54361, N = 15 SE +/- 0.34017, N = 12 5.97130 7.30065 5.92501 2.56319 2.97021 2.21948 4.64814 5.85267
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 11K 22K 33K 44K 55K SE +/- 41.81, N = 5 SE +/- 0.00, N = 4 SE +/- 69.31, N = 5 SE +/- 955.08, N = 5 SE +/- 677.85, N = 15 SE +/- 948.80, N = 15 SE +/- 131.12, N = 15 SE +/- 1365.55, N = 15 6758.81 4437.60 7046.56 7304.58 30471.50 51476.20 16936.80 48686.80 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 10K 20K 30K 40K 50K SE +/- 601.03, N = 12 SE +/- 1097.75, N = 15 SE +/- 572.00, N = 12 SE +/- 283.44, N = 3 SE +/- 11.14, N = 4 SE +/- 467.78, N = 4 SE +/- 135.77, N = 4 SE +/- 1633.92, N = 15 20091.1 19876.5 18621.2 21583.2 35230.1 46877.5 31830.2 42114.6 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 3M 6M 9M 12M 15M SE +/- 83772.27, N = 13 SE +/- 218479.19, N = 15 SE +/- 26369.56, N = 3 SE +/- 254193.37, N = 15 SE +/- 61518.27, N = 10 SE +/- 343737.14, N = 15 SE +/- 28201.44, N = 3 SE +/- 215352.04, N = 15 7439663 9624417 7366500 11223329 7841738 12321300 8926893 12425519 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
CockroachDB Workload: KV, 60% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30K 60K 90K 120K 150K SE +/- 1362.07, N = 3 SE +/- 889.12, N = 15 SE +/- 1384.66, N = 15 SE +/- 970.10, N = 15 SE +/- 1885.96, N = 15 SE +/- 886.06, N = 15 SE +/- 2440.36, N = 12 SE +/- 1250.17, N = 13 110666.9 71680.5 109388.2 71696.5 116603.7 72110.1 121465.2 73640.9
CockroachDB Workload: KV, 95% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 30K 60K 90K 120K 150K SE +/- 2758.29, N = 15 SE +/- 1830.36, N = 15 SE +/- 2047.28, N = 12 SE +/- 1792.91, N = 12 SE +/- 3058.00, N = 15 SE +/- 1606.68, N = 15 SE +/- 2853.06, N = 12 SE +/- 1875.64, N = 15 128125.9 80804.7 120494.3 76524.7 131999.7 82341.2 135861.9 85613.1
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 0.2909 0.5818 0.8727 1.1636 1.4545 SE +/- 0.008, N = 12 SE +/- 0.017, N = 9 SE +/- 0.007, N = 3 SE +/- 0.038, N = 9 SE +/- 0.007, N = 3 SE +/- 0.030, N = 12 SE +/- 0.005, N = 12 SE +/- 0.040, N = 12 0.559 1.027 0.622 1.098 0.572 1.293 0.589 1.149 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 400K 800K 1200K 1600K 2000K SE +/- 24978.23, N = 12 SE +/- 16726.04, N = 9 SE +/- 17697.00, N = 3 SE +/- 36627.33, N = 9 SE +/- 20350.34, N = 3 SE +/- 18635.21, N = 12 SE +/- 13863.97, N = 12 SE +/- 30933.90, N = 12 1792636 976035 1607424 920725 1748146 778141 1699046 881881 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: MD5 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 4M 8M 12M 16M 20M SE +/- 54649.77, N = 15 SE +/- 601801.63, N = 12 SE +/- 5000.00, N = 3 SE +/- 695042.48, N = 12 SE +/- 3511.88, N = 3 SE +/- 22338.31, N = 3 SE +/- 1201.85, N = 3 SE +/- 317498.76, N = 15 7626333 12958000 8957000 14609417 9583000 18166000 10922667 18438600 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Phoronix Test Suite v10.8.4