Sapphire Rapids launch day benchmarks by Michael Larabel for a future article.
Xeon Platinum 8490H Processor: Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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 -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads)Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB INTEL SSDSC2KG96Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
Intel Xeon Platinum 8490H 1P vs. 2P Benchmarks Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution Xeon Platinum 8490H Xeon Platinum 8490H 2P Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 512GB 3841GB Micron_9300_MTFDHAL3T8TDP ASPEED VGA HDMI 4 x Intel E810-C for QSFP Ubuntu 22.10 6.0.0-060000rc3daily20220904-generic (x86_64) GNOME Shell X Server 1.21.1.3 1.3.211 GCC 12.2.0 ext4 1920x1080 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) 1008GB 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB INTEL SSDSC2KG96 4 x Intel E810-C for QSFP + 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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 - Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0 Java Details - OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1) Python Details - Python 3.10.6 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8490H vs. Xeon Platinum 8490H 2P Comparison Phoronix Test Suite Baseline +106.9% +106.9% +213.8% +213.8% +320.7% +320.7% 427.6% 189.9% 180.3% 180.3% 170.3% 149.7% 117.4% 110.9% 106.1% 106% 104% 103.5% 102.6% 100.9% 100.8% 99.9% 98.9% 98.8% 98.2% 98% 96.6% 96.4% 95.9% 95.9% 95.5% 94.9% 94.8% 94.6% 94.3% 94.2% 94.1% 93.9% 93.3% 93.1% 92.7% 92.5% 92.4% 91.2% 90.5% 89% 88.7% 88.7% 88.5% 88.5% 88.5% 88.4% 87.9% 87.9% 87.3% 87% 86.3% 86.3% 85.9% 85.3% 85% 84.9% 84.7% 83.8% 83.5% 81.6% 81% 80.6% 80.2% 78.6% 77.4% 77.3% 77% 76.3% 75.7% 73.9% 73.6% 71.7% 71.3% 68.7% 68.1% 67.8% 66% 61% 60.8% 60.8% 60.6% 60.5% 60.3% 59.2% 57.1% 57% 56.8% 56.8% 55.4% 53% 49.6% 48.9% 48.3% 47.5% 47.4% 47.2% 47.1% 46.1% 46.1% 45.7% 44.3% 43.1% 39.6% 37.8% 37.2% 36.5% 34.3% 33.2% 29.4% 28.2% 25.9% 25.6% 24.8% 22.5% 20.7% 19.7% 15.9% 14.9% 13.9% 13.7% 12.5% 9.5% 8.3% 6.7% 6.3% 5.8% 3% 2.6% 2.4% V.P.M W.P.D.F - CPU F.D.F - CPU F.D.F - CPU W.P.D.F.I - CPU F.D.F.I - CPU d.M.M.S - Execution Time SP.C 3 - 4K - 32 - Path Tracer P.V.B.D.F - CPU S.F.P.R i.i.1.C.P.D leblancbig V.D.F - CPU V.D.F - CPU CPU MG.C CoreMark Size 666 - I.P.S C.B.S.A - u8s8f32 - CPU Exhaustive EP.D tConvolve MPI - Gridding tConvolve MPI - Degridding N.T.C.D.m - A.M.S N.T.C.B.b.u.S - A.M.S N.D.C.o.b.u.o.I - A.M.S C.C.R.5.I - A.M.S LU.C SHA256 N.T.C.B.b.u.c - A.M.S RSA4096 Total Time Time To Solve RSA4096 Total Time - 4.1.R.P.P Basic - CPU D.R N.Q.A.B.b.u.S.1.P - A.M.S Pabellon Barcelona - CPU-Only 3 - 4K - 16 - Path Tracer Classroom - CPU-Only 2 - 4K - 16 - Path Tracer 1 - 4K - 16 - Path Tracer 2 - 4K - 32 - Path Tracer Thorough 1 - 4K - 32 - Path Tracer 3 - 4K - 1 - Path Tracer 1 - 4K - 1 - Path Tracer BT.C C.D.Y.C - A.M.S gravity_spheres_volume/dim_512/ao/real_time 2 - 4K - 1 - Path Tracer 256 - 256 - 57 V.D.F.I - CPU Barbershop - CPU-Only C.B.S.A - u8s8f32 - CPU A.G.R.R.0.F - CPU BMW27 - CPU-Only 128 - 256 - 57 conus 2.5km Fishy Cat - CPU-Only X.b.i.i EP.C 1.H.M.2.D MPI CPU - water_GMX50_bare gravity_spheres_volume/dim_512/pathtracer/real_time CG.C Wownero - 1M Medium allmodconfig Monero - 1M Sharpen SP.B RT.ldr_alb_nrm.3840x2160 OpenMP LavaMD RTLightmap.hdr.4096x4096 M.T.E.T.D.F - CPU RT.hdr_alb_nrm.3840x2160 M.T.E.T.D.F - CPU FT.C P.D.F - CPU P.D.F - CPU P.D.F - CPU P.D.F - CPU Enhanced Pathtracer - Asian Dragon C.B.S.A - f32 - CPU D.B.s - f32 - CPU Pathtracer - Crown Ninja Trace Time Compression Rating Pathtracer ISPC - Asian Dragon d.S.M.S - Execution Time C.B.S.A - f32 - CPU W.P.D.F - CPU sedovbig Pathtracer ISPC - Crown A.G.R.R.0.F.I - CPU 42.1% Time To Compile A.G.R.R.0.F - CPU W.P.D.F.I - CPU I.a.F.S.I.D.C defconfig A.G.R.R.0.F.I - CPU Orange Juice - CPU IS.D C.D.Y.C - S.S.S 27.6% C.D.Y.C - S.S.S 27.6% 64 - 256 - 57 Time To Compile F.D.F.I - CPU DLSC - CPU C.P.D.T Unix Makefiles 26 Time To Compile Eigen 26 ATPase Simulation - 327,506 Atoms 9.6% Time To Compile B.S.o.W 8.8% Time To Compile V.D.F.I - CPU 8.2% C.D.Y.C - A.M.S 7.2% C.B.S.A - bf16bf16bf16 - CPU Time To Compile Multi-Threaded - ETC2 19, Long Mode - D.S 5.7% N.Q.A.B.b.u.S.1.P - A.M.S 5.6% N.T.C.B.b.u.c - S.S.S 5.4% N.T.C.B.b.u.c - S.S.S 5.4% 19 - D.S 5.3% d.M.M.S - Mesh Time 4.5% Jython 4.2% N.D.C.o.b.u.o.I - S.S.S 4.2% N.D.C.o.b.u.o.I - S.S.S 4.2% d.S.M.S - Mesh Time 3.5% P.V.B.D.F - CPU N.T.C.B.b.u.c - A.M.S 2.9% C.C.R.5.I - A.M.S 2.6% 19, Long Mode - Compression Speed 2.6% N.D.C.o.b.u.o.I - A.M.S 2.6% 19 - Compression Speed C240 Buckyball N.T.C.B.b.u.S - S.S.S 2.3% N.T.C.B.b.u.S - S.S.S 2.3% N.T.C.B.b.u.S - A.M.S 2.2% N.T.C.D.m - A.M.S 2% BRL-CAD OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO OpenFOAM NAS Parallel Benchmarks OSPRay Studio OpenVINO ACES DGEMM Xcompact3d Incompact3d Pennant OpenVINO OpenVINO Sysbench NAS Parallel Benchmarks Coremark oneDNN ASTC Encoder NAS Parallel Benchmarks ASKAP ASKAP Neural Magic DeepSparse Neural Magic DeepSparse Neural Magic DeepSparse Neural Magic DeepSparse NAS Parallel Benchmarks OpenSSL Neural Magic DeepSparse OpenSSL Tachyon m-queens OpenSSL C-Ray High Performance Conjugate Gradient RELION 7-Zip Compression Algebraic Multi-Grid Benchmark Neural Magic DeepSparse Blender OSPRay Studio Blender OSPRay Studio OSPRay Studio OSPRay Studio ASTC Encoder OSPRay Studio OSPRay Studio OSPRay Studio NAS Parallel Benchmarks Neural Magic DeepSparse OSPRay OSPRay Studio Liquid-DSP OpenVINO Blender oneDNN OpenVINO Blender Liquid-DSP WRF Blender Xcompact3d Incompact3d NAS Parallel Benchmarks LULESH asmFish GROMACS OSPRay NAS Parallel Benchmarks Xmrig ebizzy ASTC Encoder Timed Linux Kernel Compilation Xmrig GraphicsMagick NAS Parallel Benchmarks Intel Open Image Denoise Rodinia Intel Open Image Denoise OpenVINO Intel Open Image Denoise OpenVINO NAS Parallel Benchmarks OpenVINO OpenVINO OpenVINO OpenVINO GraphicsMagick Embree oneDNN oneDNN Embree Timed LLVM Compilation POV-Ray 7-Zip Compression Embree OpenFOAM oneDNN OpenVINO Pennant Embree OpenVINO Timed Node.js Compilation OpenVINO OpenVINO OpenRadioss Timed Linux Kernel Compilation OpenVINO LuxCoreRender NAS Parallel Benchmarks Neural Magic DeepSparse Neural Magic DeepSparse Liquid-DSP Timed MPlayer Compilation OpenVINO LuxCoreRender OpenRadioss Timed LLVM Compilation Graph500 Timed Godot Game Engine Compilation LeelaChessZero Graph500 NAMD Node.js Express HTTP Load Test Build2 OpenRadioss Timed Mesa Compilation OpenVINO Neural Magic DeepSparse oneDNN Timed Gem5 Compilation Etcpak Zstd Compression Neural Magic DeepSparse Neural Magic DeepSparse Neural Magic DeepSparse Zstd Compression OpenFOAM DaCapo Benchmark Neural Magic DeepSparse Neural Magic DeepSparse OpenFOAM OpenVINO Neural Magic DeepSparse Neural Magic DeepSparse Zstd Compression Neural Magic DeepSparse Zstd Compression NWChem Neural Magic DeepSparse Neural Magic DeepSparse Neural Magic DeepSparse Neural Magic DeepSparse Xeon Platinum 8490H Xeon Platinum 8490H 2P
Intel Xeon Platinum 8490H 1P vs. 2P Benchmarks gromacs: MPI CPU - water_GMX50_bare namd: ATPase Simulation - 327,506 Atoms graph500: 26 graph500: 26 graph500: 26 graph500: 26 hpcg: wrf: conus 2.5km relion: Basic - CPU amg: incompact3d: input.i3d 193 Cells Per Direction incompact3d: X3D-benchmarking input.i3d lulesh: pennant: leblancbig pennant: sedovbig mt-dgemm: Sustained Floating-Point Rate nwchem: C240 Buckyball npb: BT.C npb: EP.C npb: EP.D npb: FT.C npb: LU.C npb: SP.B npb: SP.C npb: IS.D npb: MG.C npb: CG.C rodinia: OpenMP LavaMD openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding lczero: Eigen onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU build-llvm: Ninja build-llvm: Unix Makefiles build-gem5: Time To Compile build-godot: Time To Compile build-linux-kernel: defconfig build-linux-kernel: allmodconfig build-mesa: Time To Compile build-mplayer: Time To Compile build-nodejs: Time To Compile build2: Time To Compile dacapobench: Jython compress-7zip: Compression Rating compress-7zip: Decompression Rating compress-zstd: 19 - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Pabellon Barcelona - CPU-Only blender: Barbershop - CPU-Only c-ray: Total Time - 4K, 16 Rays Per Pixel povray: Trace Time embree: Pathtracer - Asian Dragon embree: Pathtracer - Crown embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Crown oidn: RT.hdr_alb_nrm.3840x2160 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RTLightmap.hdr.4096x4096 ospray: gravity_spheres_volume/dim_512/ao/real_time ospray: gravity_spheres_volume/dim_512/pathtracer/real_time ospray-studio: 1 - 4K - 1 - Path Tracer ospray-studio: 1 - 4K - 16 - Path Tracer ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 2 - 4K - 1 - Path Tracer ospray-studio: 2 - 4K - 16 - Path Tracer ospray-studio: 2 - 4K - 32 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 16 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer luxcorerender: DLSC - CPU luxcorerender: Orange Juice - CPU graphics-magick: Enhanced graphics-magick: Sharpen astcenc: Medium astcenc: Thorough astcenc: Exhaustive etcpak: Multi-Threaded - ETC2 ebizzy: node-express-loadtest: simdjson: PartialTweets simdjson: LargeRand simdjson: Kostya simdjson: DistinctUserID simdjson: TopTweet brl-cad: VGR Performance Metric pybench: Total For Average Test Times pyperformance: crypto_pyaes pyperformance: django_template pyperformance: json_loads pyperformance: regex_compile numpy: phpbench: PHP Benchmark Suite srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: OFDM_Test liquid-dsp: 32 - 256 - 57 liquid-dsp: 64 - 256 - 57 liquid-dsp: 128 - 256 - 57 liquid-dsp: 256 - 256 - 57 pjsip: OPTIONS, Stateless quantlib: openssl: RSA4096 openssl: RSA4096 openssl: SHA256 xmrig: Monero - 1M xmrig: Wownero - 1M sysbench: CPU m-queens: Time To Solve coremark: CoreMark Size 666 - Iterations Per Second asmfish: 1024 Hash Memory, 26 Depth tachyon: Total Time openfoam: drivaerFastback, Small Mesh Size - Mesh Time openfoam: drivaerFastback, Small Mesh Size - Execution Time openfoam: drivaerFastback, Medium Mesh Size - Mesh Time openfoam: drivaerFastback, Medium Mesh Size - Execution Time onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream openradioss: Bird Strike on Windshield openradioss: Cell Phone Drop Test openradioss: Bumper Beam openradioss: INIVOL and Fluid Structure Interaction Drop Container openvino: Face Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU compress-zstd: 19 - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream Xeon Platinum 8490H Xeon Platinum 8490H 2P 8.581 0.29076 1040570000 1073660000 323231000 450856000 32.0770 11881.128 402.132 1616971667 12.8350466 352.794106 25990.516 5.206269 16.30634 22.411594 3851.6 179308.21 6988.76 7832.08 68514.71 135606.00 111530.94 71661.25 2812.20 84251.85 33480.76 42.640 70.58 424.67 150.87 82929.06 0.62 91377.53 0.57 25.55 1167.83 25.53 1169.15 16703.64 7839.51 7.52 3266.12 1892.85 15.83 3656.94 16.37 448.59 66.66 17623.9 21469.3 10513 0.636394 0.492516 1.10812 155.921 216.613 174.416 42.133 31.646 263.288 24.627 11.745 174.867 59.714 2557 378741 291248 89.9 3003.5 25.52 67.68 36.05 88.96 277.99 10.667 9.809 69.4593 57.2665 83.2084 63.8175 2.63 2.64 1.25 19.6102 24.1169 1603 25685 51326 1627 26095 52081 1931 30888 67518 8.46 12.89 1132 692 287.8179 42.0275 4.0722 6573.673 2951024 11902 5.60 1.30 3.49 6.53 6.77 829046 771 79.0 34.9 18.7 132 458.09 947570 144.1 152.1 132.4 144.9 132.3 88.3 160700000 2254333333 3398700000 3468033333 3583066667 34041 3167.9 14735.9 979532.1 62964771377 27397.8 35200.5 155262.70 14.785 2162643.678448 130447170 25.8262 31.758106 42.688031 149.14298 418.90255 0.645779 0.519451 0.281812 53.8314 18.5696 218.3873 137.3177 103.8217 9.6255 447.9605 66.9457 279.4595 3.5734 769.7793 38.9415 27.7133 36.0775 47.4454 84.5439 11.8188 192.9925 155.4013 121.2521 8.2415 318.9325 93.9986 27.6650 36.1400 47.2877 130.17 32.38 81.34 152.91 396.76 3.58 18.35 2857.4 51.9 373.0 405.0 365.2 403.8 629.5855 630.2258 15.127 0.25849 1022520000 1065690000 374656000 512610000 61.7522 6577.818 209.010 3080070333 6.30612000 197.567332 46081.222 2.569535 11.29827 45.713815 3760.7 334076.76 12397.43 15397.23 109091.04 263945.03 185110.02 151124.55 3606.51 167584.28 58234.49 26.516 197.81 151.49 376.67 152169.33 0.45 121729.47 0.81 40.14 744.65 40.08 745.86 45149.75 22725.25 5.16 6038.49 3801.48 7.88 7533.49 15.90 719.22 41.51 34531.1 42175.0 11976 0.435654 0.267939 0.744021 105.732 181.016 164.021 36.658 23.566 156.114 22.750 9.350 125.270 54.545 2664 557682 556755 92.2 2841.4 14.05 35.90 20.01 47.14 150.54 5.535 6.655 106.2493 84.9362 122.3683 91.3075 4.22 4.25 2.01 36.4481 42.3755 857 13628 27316 878 13844 27651 1031 16373 32759 10.36 16.68 1759 1161 492.9382 78.9763 8.0629 6955.483 5066751 10861 5.68 1.28 3.49 6.53 6.80 4374145 770 78.8 34.7 18.7 132 455.27 951782 144.4 152.4 133.7 145.4 132.8 88.4 160366667 2234066667 4279900000 6276200000 6629166667 34282 3167.8 28605.0 1891795.0 122314003620 46050.4 61104.8 310297.60 7.648 4299941.229128 230901090 13.3176 32.865265 29.21841 155.85613 192.68966 0.431788 0.262114 0.264160 52.6003 19.0029 426.8408 140.3803 103.2446 9.6785 877.3715 68.3153 281.8155 3.5434 1499.5004 39.9661 26.2827 38.0429 92.1557 82.9492 12.0464 364.7952 164.1788 95.0413 10.5177 594.0229 100.7650 26.5549 37.6495 92.1671 141.67 26.82 81.73 112.02 318.00 2.61 19.85 2713.4 50.6 371.4 407.4 364.7 402.7 647.8241 646.4008 OpenBenchmarking.org
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Platinum 8490H 2P Xeon Platinum 8490H 4 8 12 16 20 SE +/- 0.045, N = 3 SE +/- 0.006, N = 3 15.127 8.581 1. (CXX) g++ options: -O3
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.0654 0.1308 0.1962 0.2616 0.327 SE +/- 0.00249, N = 3 SE +/- 0.00022, N = 3 0.25849 0.29076
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8490H 2P Xeon Platinum 8490H 200M 400M 600M 800M 1000M 1022520000 1040570000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8490H 2P Xeon Platinum 8490H 200M 400M 600M 800M 1000M 1065690000 1073660000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8490H 2P Xeon Platinum 8490H 80M 160M 240M 320M 400M 374656000 323231000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8490H 2P Xeon Platinum 8490H 110M 220M 330M 440M 550M 512610000 450856000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
WRF WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WRF 4.2.2 Input: conus 2.5km Xeon Platinum 8490H 2P Xeon Platinum 8490H 3K 6K 9K 12K 15K 6577.82 11881.13 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
RELION RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RELION 3.1.1 Test: Basic - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 1.79, N = 8 SE +/- 4.31, N = 3 209.01 402.13 1. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi
Algebraic Multi-Grid Benchmark AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 Xeon Platinum 8490H 2P Xeon Platinum 8490H 700M 1400M 2100M 2800M 3500M SE +/- 2176637.03, N = 3 SE +/- 775406.63, N = 3 3080070333 1616971667 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.01534019, N = 6 SE +/- 0.00718141, N = 4 6.30612000 12.83504660 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
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d Xeon Platinum 8490H 2P Xeon Platinum 8490H 80 160 240 320 400 SE +/- 2.44, N = 3 SE +/- 4.13, N = 4 197.57 352.79 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
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Xeon Platinum 8490H 2P Xeon Platinum 8490H 4 8 12 16 20 SE +/- 0.01, N = 4 SE +/- 0.02, N = 3 11.30 16.31 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
NWChem NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball Xeon Platinum 8490H 2P Xeon Platinum 8490H 800 1600 2400 3200 4000 3760.7 3851.6 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
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 70K 140K 210K 280K 350K SE +/- 231.33, N = 5 SE +/- 335.77, N = 3 334076.76 179308.21 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 3K 6K 9K 12K 15K SE +/- 70.37, N = 12 SE +/- 62.59, N = 15 12397.43 6988.76 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Platinum 8490H 2P Xeon Platinum 8490H 3K 6K 9K 12K 15K SE +/- 28.18, N = 5 SE +/- 26.92, N = 3 15397.23 7832.08 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 20K 40K 60K 80K 100K SE +/- 969.11, N = 15 SE +/- 518.21, N = 6 109091.04 68514.71 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 60K 120K 180K 240K 300K SE +/- 192.74, N = 5 SE +/- 179.86, N = 4 263945.03 135606.00 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Xeon Platinum 8490H 2P Xeon Platinum 8490H 40K 80K 120K 160K 200K SE +/- 740.00, N = 10 SE +/- 226.33, N = 8 185110.02 111530.94 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 30K 60K 90K 120K 150K SE +/- 391.00, N = 5 SE +/- 179.87, N = 3 151124.55 71661.25 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Platinum 8490H 2P Xeon Platinum 8490H 800 1600 2400 3200 4000 SE +/- 33.07, N = 7 SE +/- 19.69, N = 4 3606.51 2812.20 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 40K 80K 120K 160K 200K SE +/- 1087.50, N = 15 SE +/- 121.29, N = 10 167584.28 84251.85 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 4.1.4
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon Platinum 8490H 2P Xeon Platinum 8490H 12K 24K 36K 48K 60K SE +/- 173.40, N = 9 SE +/- 132.41, N = 7 58234.49 33480.76 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 4.1.4
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Xeon Platinum 8490H 2P Xeon Platinum 8490H 10 20 30 40 50 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 26.52 42.64 1. (CXX) g++ options: -O2 -lOpenCL
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 40 80 120 160 200 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 197.81 70.58 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 0.09, N = 3 SE +/- 0.29, N = 3 151.49 424.67 MIN: 123.14 / MAX: 273.7 MIN: 324.89 / MAX: 491.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 80 160 240 320 400 SE +/- 0.66, N = 3 SE +/- 0.45, N = 3 376.67 150.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 30K 60K 90K 120K 150K SE +/- 667.44, N = 3 SE +/- 111.96, N = 3 152169.33 82929.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1395 0.279 0.4185 0.558 0.6975 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.45 0.62 MIN: 0.33 / MAX: 78.34 MIN: 0.31 / MAX: 23.57 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 30K 60K 90K 120K 150K SE +/- 1999.64, N = 12 SE +/- 1248.62, N = 13 121729.47 91377.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1823 0.3646 0.5469 0.7292 0.9115 SE +/- 0.03, N = 12 SE +/- 0.01, N = 13 0.81 0.57 MIN: 0.29 / MAX: 40.45 MIN: 0.27 / MAX: 25.17 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 9 18 27 36 45 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 40.14 25.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 300 600 900 1200 1500 SE +/- 2.09, N = 3 SE +/- 2.53, N = 3 744.65 1167.83 MIN: 515.46 / MAX: 1463.52 MIN: 600.36 / MAX: 1656.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 9 18 27 36 45 SE +/- 0.45, N = 3 SE +/- 0.01, N = 3 40.08 25.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 300 600 900 1200 1500 SE +/- 8.26, N = 3 SE +/- 0.26, N = 3 745.86 1169.15 MIN: 475.57 / MAX: 1408.18 MIN: 870.58 / MAX: 1651.76 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 10K 20K 30K 40K 50K SE +/- 54.08, N = 3 SE +/- 9.01, N = 3 45149.75 16703.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 5K 10K 15K 20K 25K SE +/- 252.27, N = 4 SE +/- 60.72, N = 10 22725.25 7839.51 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 2 4 6 8 10 SE +/- 0.05, N = 4 SE +/- 0.05, N = 10 5.16 7.52 MIN: 4.27 / MAX: 91.31 MIN: 2.66 / MAX: 31.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 1300 2600 3900 5200 6500 SE +/- 6.74, N = 3 SE +/- 3.43, N = 3 6038.49 3266.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 800 1600 2400 3200 4000 SE +/- 2.04, N = 3 SE +/- 1.95, N = 3 3801.48 1892.85 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 7.88 15.83 MIN: 7.12 / MAX: 60.06 MIN: 7.8 / MAX: 50.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 1600 3200 4800 6400 8000 SE +/- 17.07, N = 3 SE +/- 5.03, N = 3 7533.49 3656.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 15.90 16.37 MIN: 13.66 / MAX: 82.27 MIN: 9.29 / MAX: 49.62 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 160 320 480 640 800 SE +/- 2.72, N = 3 SE +/- 0.03, N = 3 719.22 448.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 41.51 66.66 MIN: 27.82 / MAX: 338.88 MIN: 23.93 / MAX: 106.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Xeon Platinum 8490H 2P Xeon Platinum 8490H 7K 14K 21K 28K 35K SE +/- 305.60, N = 3 SE +/- 52.77, N = 3 34531.1 17623.9 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Xeon Platinum 8490H 2P Xeon Platinum 8490H 9K 18K 27K 36K 45K SE +/- 303.43, N = 3 SE +/- 78.37, N = 3 42175.0 21469.3 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen Xeon Platinum 8490H 2P Xeon Platinum 8490H 3K 6K 9K 12K 15K SE +/- 76.29, N = 3 SE +/- 64.57, N = 3 11976 10513 1. (CXX) g++ options: -flto -pthread
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1432 0.2864 0.4296 0.5728 0.716 SE +/- 0.002329, N = 7 SE +/- 0.000967, N = 7 0.435654 0.636394 MIN: 0.38 MIN: 0.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1108 0.2216 0.3324 0.4432 0.554 SE +/- 0.001562, N = 7 SE +/- 0.000571, N = 7 0.267939 0.492516 MIN: 0.2 MIN: 0.42 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.2493 0.4986 0.7479 0.9972 1.2465 SE +/- 0.001670, N = 9 SE +/- 0.000893, N = 9 0.744021 1.108120 MIN: 0.67 MIN: 1.08 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Timed Mesa Compilation This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile Xeon Platinum 8490H 2P Xeon Platinum 8490H 6 12 18 24 30 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 22.75 24.63
Build2 This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Xeon Platinum 8490H 2P Xeon Platinum 8490H 13 26 39 52 65 SE +/- 0.14, N = 3 SE +/- 0.14, N = 3 54.55 59.71
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Xeon Platinum 8490H 2P Xeon Platinum 8490H 120K 240K 360K 480K 600K SE +/- 925.70, N = 3 SE +/- 197.90, N = 3 556755 291248 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.51, N = 3 SE +/- 0.13, N = 3 92.2 89.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Xeon Platinum 8490H 2P Xeon Platinum 8490H 600 1200 1800 2400 3000 SE +/- 2.47, N = 15 SE +/- 7.21, N = 3 2841.4 3003.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: BMW27 - Compute: CPU-Only Xeon Platinum 8490H 2P Xeon Platinum 8490H 6 12 18 24 30 SE +/- 0.06, N = 4 SE +/- 0.03, N = 3 14.05 25.52
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Classroom - Compute: CPU-Only Xeon Platinum 8490H 2P Xeon Platinum 8490H 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 35.90 67.68
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Fishy Cat - Compute: CPU-Only Xeon Platinum 8490H 2P Xeon Platinum 8490H 8 16 24 32 40 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 20.01 36.05
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Pabellon Barcelona - Compute: CPU-Only Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 47.14 88.96
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Barbershop - Compute: CPU-Only Xeon Platinum 8490H 2P Xeon Platinum 8490H 60 120 180 240 300 SE +/- 0.47, N = 3 SE +/- 1.33, N = 3 150.54 277.99
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.009, N = 7 SE +/- 0.002, N = 5 5.535 10.667 1. (CC) gcc options: -lm -lpthread -O3
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.045, N = 5 SE +/- 0.055, N = 4 6.655 9.809 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lSDL -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.75, N = 6 SE +/- 0.32, N = 5 106.25 69.46 MIN: 81.97 / MAX: 143.97 MIN: 62.46 / MAX: 82.23
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.51, N = 5 SE +/- 0.11, N = 4 84.94 57.27 MIN: 71.38 / MAX: 118.61 MIN: 53.31 / MAX: 67.51
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.50, N = 6 SE +/- 0.68, N = 6 122.37 83.21 MIN: 88.61 / MAX: 170.97 MIN: 73.06 / MAX: 101.5
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.53, N = 6 SE +/- 0.13, N = 5 91.31 63.82 MIN: 75.79 / MAX: 138.07 MIN: 59.5 / MAX: 75.6
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon Platinum 8490H 2P Xeon Platinum 8490H 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 36.45 19.61
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Platinum 8490H 2P Xeon Platinum 8490H 10 20 30 40 50 SE +/- 0.40, N = 6 SE +/- 0.02, N = 3 42.38 24.12
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 300 600 900 1200 1500 SE +/- 1.45, N = 3 SE +/- 1.00, N = 3 857 1603 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 6K 12K 18K 24K 30K SE +/- 14.17, N = 3 SE +/- 33.98, N = 3 13628 25685 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 11K 22K 33K 44K 55K SE +/- 43.66, N = 3 SE +/- 73.00, N = 3 27316 51326 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 300 600 900 1200 1500 SE +/- 0.88, N = 3 SE +/- 1.33, N = 3 878 1627 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 6K 12K 18K 24K 30K SE +/- 18.15, N = 3 SE +/- 36.19, N = 3 13844 26095 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 11K 22K 33K 44K 55K SE +/- 10.53, N = 3 SE +/- 84.62, N = 3 27651 52081 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 400 800 1200 1600 2000 SE +/- 1.45, N = 3 SE +/- 2.33, N = 3 1031 1931 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 7K 14K 21K 28K 35K SE +/- 18.59, N = 3 SE +/- 47.70, N = 3 16373 30888 1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8490H 2P Xeon Platinum 8490H 14K 28K 42K 56K 70K SE +/- 30.66, N = 3 SE +/- 105.74, N = 3 32759 67518 1. (CXX) g++ options: -O3 -ldl
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.17, N = 15 SE +/- 0.01, N = 3 10.36 8.46 MIN: 8.3 / MAX: 16.8 MIN: 8.06 / MAX: 10.38
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 4 8 12 16 20 SE +/- 0.18, N = 3 SE +/- 0.11, N = 15 16.68 12.89 MIN: 12.85 / MAX: 25.49 MIN: 10.41 / MAX: 16.31
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced Xeon Platinum 8490H 2P Xeon Platinum 8490H 400 800 1200 1600 2000 SE +/- 4.26, N = 3 SE +/- 0.58, N = 3 1759 1132 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Xeon Platinum 8490H 2P Xeon Platinum 8490H 200 400 600 800 1000 SE +/- 0.88, N = 3 SE +/- 0.00, N = 3 1161 692 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Xeon Platinum 8490H 2P Xeon Platinum 8490H 110 220 330 440 550 SE +/- 0.43, N = 7 SE +/- 0.08, N = 7 492.94 287.82 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.02, N = 6 SE +/- 0.02, N = 5 78.98 42.03 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Xeon Platinum 8490H 2P Xeon Platinum 8490H 2 4 6 8 10 SE +/- 0.0085, N = 5 SE +/- 0.0010, N = 4 8.0629 4.0722 1. (CXX) g++ options: -O3 -flto -pthread
Etcpak Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 Xeon Platinum 8490H 2P Xeon Platinum 8490H 1500 3000 4500 6000 7500 SE +/- 53.37, N = 8 SE +/- 23.61, N = 9 6955.48 6573.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Xeon Platinum 8490H 2P Xeon Platinum 8490H 1.278 2.556 3.834 5.112 6.39 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.68 5.60 1. (CXX) g++ options: -O3
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.2925 0.585 0.8775 1.17 1.4625 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.28 1.30 1. (CXX) g++ options: -O3
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.7853 1.5706 2.3559 3.1412 3.9265 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.49 3.49 1. (CXX) g++ options: -O3
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Xeon Platinum 8490H 2P Xeon Platinum 8490H 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 6.53 6.53 1. (CXX) g++ options: -O3
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Xeon Platinum 8490H 2P Xeon Platinum 8490H 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.80 6.77 1. (CXX) g++ options: -O3
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric Xeon Platinum 8490H 2P Xeon Platinum 8490H 900K 1800K 2700K 3600K 4500K 4374145 829046 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon Platinum 8490H 2P Xeon Platinum 8490H 170 340 510 680 850 SE +/- 2.60, N = 3 SE +/- 2.96, N = 3 770 771
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Xeon Platinum 8490H 2P Xeon Platinum 8490H 200K 400K 600K 800K 1000K SE +/- 948.00, N = 3 SE +/- 2905.52, N = 3 951782 947570
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.20, N = 4 SE +/- 0.32, N = 4 144.4 144.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 0.41, N = 3 152.4 152.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.19, N = 3 133.7 132.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.38, N = 3 SE +/- 0.34, N = 3 145.4 144.9 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 0.77, N = 3 132.8 132.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 88.4 88.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test Xeon Platinum 8490H 2P Xeon Platinum 8490H 30M 60M 90M 120M 150M SE +/- 405517.50, N = 3 SE +/- 1504437.88, N = 3 160366667 160700000 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8490H 2P Xeon Platinum 8490H 500M 1000M 1500M 2000M 2500M SE +/- 3540872.46, N = 3 SE +/- 2794240.11, N = 3 2234066667 2254333333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8490H 2P Xeon Platinum 8490H 900M 1800M 2700M 3600M 4500M SE +/- 1040833.00, N = 3 SE +/- 3175426.48, N = 3 4279900000 3398700000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8490H 2P Xeon Platinum 8490H 1300M 2600M 3900M 5200M 6500M SE +/- 13313151.39, N = 3 SE +/- 2667291.59, N = 3 6276200000 3468033333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8490H 2P Xeon Platinum 8490H 1400M 2800M 4200M 5600M 7000M SE +/- 1192103.65, N = 3 SE +/- 7522484.81, N = 3 6629166667 3583066667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PJSIP PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Xeon Platinum 8490H 2P Xeon Platinum 8490H 7K 14K 21K 28K 35K SE +/- 299.91, N = 7 SE +/- 559.10, N = 15 34282 34041 1. (CC) gcc options: -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lopus -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.21 Xeon Platinum 8490H 2P Xeon Platinum 8490H 700 1400 2100 2800 3500 SE +/- 30.19, N = 3 SE +/- 25.54, N = 3 3167.8 3167.9 1. (CXX) g++ options: -O3 -march=native -rdynamic
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Xeon Platinum 8490H 2P Xeon Platinum 8490H 6K 12K 18K 24K 30K SE +/- 28.11, N = 3 SE +/- 22.62, N = 3 28605.0 14735.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Xeon Platinum 8490H 2P Xeon Platinum 8490H 400K 800K 1200K 1600K 2000K SE +/- 383.16, N = 3 SE +/- 461.15, N = 3 1891795.0 979532.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 Xeon Platinum 8490H 2P Xeon Platinum 8490H 30000M 60000M 90000M 120000M 150000M SE +/- 1169331279.81, N = 3 SE +/- 20153231.00, N = 3 122314003620 62964771377 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Xeon Platinum 8490H 2P Xeon Platinum 8490H 10K 20K 30K 40K 50K SE +/- 177.42, N = 3 SE +/- 7.76, N = 3 46050.4 27397.8 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M Xeon Platinum 8490H 2P Xeon Platinum 8490H 13K 26K 39K 52K 65K SE +/- 7.56, N = 3 SE +/- 13.52, N = 3 61104.8 35200.5 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Sysbench This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 70K 140K 210K 280K 350K SE +/- 9.45, N = 3 SE +/- 0.27, N = 3 310297.60 155262.70 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
Tachyon This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99.2 Total Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 6 12 18 24 30 SE +/- 0.03, N = 4 SE +/- 0.15, N = 3 13.32 25.83 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 8 16 24 32 40 32.87 31.76 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
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 10 20 30 40 50 29.22 42.69 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
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 155.86 149.14 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
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 192.69 418.90 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
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1453 0.2906 0.4359 0.5812 0.7265 SE +/- 0.002510, N = 7 SE +/- 0.000493, N = 7 0.431788 0.645779 MIN: 0.38 MIN: 0.55 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.1169 0.2338 0.3507 0.4676 0.5845 SE +/- 0.002009, N = 10 SE +/- 0.001949, N = 7 0.262114 0.519451 MIN: 0.2 MIN: 0.46 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.0634 0.1268 0.1902 0.2536 0.317 SE +/- 0.001768, N = 7 SE +/- 0.002592, N = 15 0.264160 0.281812 MIN: 0.22 MIN: 0.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 12 24 36 48 60 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 52.60 53.83
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 19.00 18.57
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 0.50, N = 3 SE +/- 0.26, N = 3 426.84 218.39
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 140.38 137.32
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 103.24 103.82
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.0003, N = 3 SE +/- 0.0079, N = 3 9.6785 9.6255
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 200 400 600 800 1000 SE +/- 2.47, N = 3 SE +/- 1.01, N = 3 877.37 447.96
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 15 30 45 60 75 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 68.32 66.95
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 60 120 180 240 300 SE +/- 0.80, N = 3 SE +/- 0.50, N = 3 281.82 279.46
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.804 1.608 2.412 3.216 4.02 SE +/- 0.0099, N = 3 SE +/- 0.0063, N = 3 3.5434 3.5734
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 300 600 900 1200 1500 SE +/- 2.06, N = 3 SE +/- 0.49, N = 3 1499.50 769.78
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 39.97 38.94
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 7 14 21 28 35 SE +/- 0.18, N = 3 SE +/- 0.00, N = 3 26.28 27.71
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 9 18 27 36 45 SE +/- 0.26, N = 3 SE +/- 0.00, N = 3 38.04 36.08
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 92.16 47.45
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.35, N = 3 82.95 84.54
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 12.05 11.82
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 80 160 240 320 400 SE +/- 2.04, N = 3 SE +/- 0.12, N = 3 364.80 192.99
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 40 80 120 160 200 SE +/- 0.87, N = 3 SE +/- 0.10, N = 3 164.18 155.40
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 1.07, N = 3 SE +/- 0.45, N = 3 95.04 121.25
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 3 6 9 12 15 SE +/- 0.1185, N = 3 SE +/- 0.0308, N = 3 10.5177 8.2415
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 130 260 390 520 650 SE +/- 0.43, N = 3 SE +/- 0.14, N = 3 594.02 318.93
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 100.77 94.00
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 26.55 27.67
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 9 18 27 36 45 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 37.65 36.14
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.15, N = 3 92.17 47.29
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.53, N = 3 SE +/- 0.72, N = 3 141.67 130.17
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 112.02 152.91
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 0.52, N = 3 SE +/- 1.06, N = 3 318.00 396.76 MIN: 225.29 / MAX: 493.46 MIN: 130.62 / MAX: 484.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 0.8055 1.611 2.4165 3.222 4.0275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.61 3.58 MIN: 2.11 / MAX: 28.5 MIN: 1.58 / MAX: 28.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Platinum 8490H 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 19.85 18.35 MIN: 13.53 / MAX: 111.05 MIN: 8.59 / MAX: 57.04 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Xeon Platinum 8490H 2P Xeon Platinum 8490H 600 1200 1800 2400 3000 SE +/- 8.11, N = 3 SE +/- 0.43, N = 3 2713.4 2857.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Xeon Platinum 8490H 2P Xeon Platinum 8490H 12 24 36 48 60 SE +/- 0.59, N = 15 SE +/- 0.03, N = 3 50.6 51.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 80 160 240 320 400 SE +/- 1.13, N = 4 SE +/- 0.85, N = 4 371.4 373.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 1.44, N = 3 SE +/- 1.19, N = 3 407.4 405.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 80 160 240 320 400 SE +/- 1.98, N = 3 SE +/- 0.84, N = 3 364.7 365.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8490H 2P Xeon Platinum 8490H 90 180 270 360 450 SE +/- 0.99, N = 3 SE +/- 0.61, N = 3 402.7 403.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -ldl -lpthread -lm
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 140 280 420 560 700 SE +/- 0.61, N = 3 SE +/- 1.35, N = 3 647.82 629.59
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Xeon Platinum 8490H 2P Xeon Platinum 8490H 140 280 420 560 700 SE +/- 1.63, N = 3 SE +/- 0.12, N = 3 646.40 630.23
Xeon Platinum 8490H Processor: Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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 -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 January 2023 19:53 by user phoronix.
Xeon Platinum 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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 -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 January 2023 03:00 by user phoronix.