AMD EPYC 7543 32-Core testing with a TYAN S8036GM2NE-LE (V2.00.B21 BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.
EPPYC 7543 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
2 Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 21.04, Kernel: 5.11.0-18-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server + Wayland, OpenGL: 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits), Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
7543 EPYC Ubuntu 21.04 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution EPPYC 7543 2 AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads) TYAN S8036GM2NE-LE (V2.00.B21 BIOS) AMD Starship/Matisse 64GB 1000GB Western Digital WD_BLACK SN850 1TB ASPEED VE228 2 x Broadcom NetXtreme BCM5720 2-port PCIe Ubuntu 21.04 5.11.0-18-generic (x86_64) GNOME Shell 3.38.4 X Server + Wayland 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits) GCC 10.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119 Python Details - Python 3.9.5 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPPYC 7543 vs. 2 Comparison Phoronix Test Suite Baseline +6% +6% +12% +12% +18% +18% 24% 10% 5.9% 5.5% 3.8% 3.3% 2.8% 2.8% 2.5% 2.3% 2.3% 2.1% 2% FT.C 19 - Compression Speed VMAF Optimized - Bosphorus 1080p 8.9% vklBenchmarkStructuredVolume Speed 8 Realtime - Bosphorus 1080p 7 - Bosphorus 1080p 4.3% vklBenchmarkVdbVolume CG.C vklBenchmark 3.1% 19, Long Mode - Compression Speed 3, Long Mode - Compression Speed 10 2.7% R.C.a.P - CPU TBB MG.C EP.C 2.3% Speed 6 Realtime - Bosphorus 1080p 2.2% RTLightmap.hdr.4096x4096 Wownero - 1M 8, Long Mode - D.S 2% NAS Parallel Benchmarks Zstd Compression SVT-VP9 OpenVKL AOM AV1 SVT-HEVC OpenVKL NAS Parallel Benchmarks OpenVKL Zstd Compression Zstd Compression libavif avifenc LuxCoreRender toyBrot Fractal Generator NAS Parallel Benchmarks NAS Parallel Benchmarks AOM AV1 Intel Open Image Denoise Xmrig Zstd Compression EPPYC 7543 2
7543 EPYC Ubuntu 21.04 toybrot: TBB toybrot: OpenMP toybrot: C++ Tasks toybrot: C++ Threads brl-cad: VGR Performance Metric astcenc: Medium astcenc: Thorough astcenc: Exhaustive draco: Lion draco: Church Facade toktx: UASTC 3 toktx: Zstd Compression 9 toktx: Zstd Compression 19 toktx: UASTC 3 + Zstd Compression 19 toktx: UASTC 4 + Zstd Compression 19 synthmark: VoiceMark_100 securemark: SecureMark-TLS xmrig: Monero - 1M xmrig: Wownero - 1M gromacs: MPI CPU - water_GMX50_bare npb: BT.C npb: CG.C npb: EP.C npb: EP.D npb: FT.C npb: IS.D npb: LU.C npb: MG.C npb: SP.B npb: SP.C namd: ATPase Simulation - 327,506 Atoms pennant: sedovbig pennant: leblancbig incompact3d: input.i3d 129 Cells Per Direction incompact3d: input.i3d 193 Cells Per Direction build-ffmpeg: Time To Compile build-gdb: Time To Compile build-llvm: Ninja build-llvm: Unix Makefiles compress-zstd: 3 - Compression Speed compress-zstd: 3 - Decompression Speed compress-zstd: 8 - Compression Speed compress-zstd: 8 - Decompression Speed compress-zstd: 19 - Compression Speed compress-zstd: 19 - Decompression Speed compress-zstd: 3, Long Mode - Compression Speed compress-zstd: 3, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed build-linux-kernel: Time To Compile aom-av1: Speed 0 Two-Pass - Bosphorus 4K aom-av1: Speed 4 Two-Pass - Bosphorus 4K aom-av1: Speed 6 Realtime - Bosphorus 4K aom-av1: Speed 6 Two-Pass - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 9 Realtime - Bosphorus 4K aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 4 Two-Pass - Bosphorus 1080p aom-av1: Speed 6 Realtime - Bosphorus 1080p aom-av1: Speed 6 Two-Pass - Bosphorus 1080p aom-av1: Speed 8 Realtime - Bosphorus 1080p aom-av1: Speed 9 Realtime - Bosphorus 1080p svt-vp9: VMAF Optimized - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p dav1d: Chimera 1080p dav1d: Summer Nature 4K dav1d: Summer Nature 1080p dav1d: Chimera 1080p 10-bit svt-hevc: 1 - Bosphorus 1080p svt-hevc: 7 - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only avifenc: 0 avifenc: 2 avifenc: 6 avifenc: 10 avifenc: 6, Lossless avifenc: 10, Lossless build-godot: Time To Compile embree: Pathtracer - Crown embree: Pathtracer ISPC - Crown embree: Pathtracer - Asian Dragon embree: Pathtracer - Asian Dragon Obj embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Asian Dragon Obj oidn: RT.hdr_alb_nrm.3840x2160 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RTLightmap.hdr.4096x4096 openvkl: vklBenchmark openvkl: vklBenchmarkVdbVolume openvkl: vklBenchmarkStructuredVolume openvkl: vklBenchmarkUnstructuredVolume luxcorerender: DLSC - CPU luxcorerender: Danish Mood - CPU luxcorerender: Orange Juice - CPU luxcorerender: LuxCore Benchmark - CPU luxcorerender: Rainbow Colors and Prism - CPU build-mesa: Time To Compile build-nodejs: Time To Compile EPPYC 7543 2 12854 12815 12926 12640 416402 4.1204 6.9969 23.5757 5182 6688 5.575 2.807 19.123 10.895 103.961 820.855 249608 21806.8 22663.5 3.658 86655.83 29176.28 2909.24 2961.89 38990.23 1894.03 103956.09 48142.19 67812.87 32836.66 0.68178 15.75069 9.611897 6.14532347 27.8616452 22.021 40.427 209.155 253.624 5107.7 3490.6 2760.5 3589.6 60.2 3198.0 581.6 3782.5 763.6 3906.7 39.2 3177.8 31.793 0.2 3.92 10.58 7.04 31.34 44.78 0.51 6.69 25.51 19.00 74.52 102.77 274.08 252.38 240.01 548.48 407.08 538.66 409.34 24.56 295.83 480.50 53.50 147.72 70.16 197.71 165.27 50.124 27.520 10.933 3.757 30.348 6.354 54.427 36.1780 33.3181 41.1863 36.8465 36.8038 32.9763 0.95 0.95 0.47 300 16681805 75601852 1792476 5.42 4.34 8.28 4.71 16.35 20.894 139.812 12561 12810 12951 12603 416828 4.1136 7.0010 23.5825 5191 6745 5.553 2.782 18.851 10.894 103.988 819.662 252200 21864.8 23112.9 3.675 87479.51 30145.53 2843.82 2968.94 48349.23 1894.77 103990.12 49253.78 67720.83 33317.56 0.67718 15.75626 9.725950 6.07545233 28.2131564 22.014 40.570 207.719 251.473 5026.0 3454.5 2767.2 3647.6 66.2 3208.4 597.8 3732.9 767.8 3831.4 40.3 3177.6 31.822 0.2 3.90 10.48 7.15 31.62 44.48 0.51 6.65 24.97 18.84 78.63 102.06 251.78 248.30 238.48 546.34 406.30 537.46 408.70 24.57 283.61 478.08 53.52 148.29 70.18 197.93 165.75 50.253 27.550 10.840 3.857 30.515 6.305 54.431 36.3189 33.3017 41.2382 36.2914 36.7191 32.8729 0.95 0.96 0.48 291 17308328 80062311 1789270 5.45 4.33 8.24 4.67 16.76 20.918 139.656 OpenBenchmarking.org
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 7.32.2 VGR Performance Metric 2 EPPYC 7543 90K 180K 270K 360K 450K 416828 416402 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 -pthread -ldl -lm
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 Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Medium 2 EPPYC 7543 0.9271 1.8542 2.7813 3.7084 4.6355 SE +/- 0.0008, N = 3 SE +/- 0.0061, N = 3 4.1136 4.1204 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Thorough 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.0103, N = 3 SE +/- 0.0041, N = 3 7.0010 6.9969 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Exhaustive 2 EPPYC 7543 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 23.58 23.58 1. (CXX) g++ options: -O3 -flto -pthread
Google Draco Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Lion 2 EPPYC 7543 1100 2200 3300 4400 5500 SE +/- 53.15, N = 15 SE +/- 40.84, N = 15 5191 5182 1. (CXX) g++ options: -O3
KTX-Software toktx This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 2 EPPYC 7543 1.2544 2.5088 3.7632 5.0176 6.272 SE +/- 0.008, N = 3 SE +/- 0.017, N = 3 5.553 5.575
Google SynthMark SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 2 EPPYC 7543 200 400 600 800 1000 SE +/- 0.61, N = 3 SE +/- 0.64, N = 3 819.66 820.86 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
SecureMark SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS 2 EPPYC 7543 50K 100K 150K 200K 250K SE +/- 53.58, N = 3 SE +/- 1702.10, N = 3 252200 249608 1. (CC) gcc options: -pedantic -O3
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 2 EPPYC 7543 5K 10K 15K 20K 25K SE +/- 26.85, N = 3 SE +/- 95.80, N = 3 21864.8 21806.8 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 2 EPPYC 7543 5K 10K 15K 20K 25K SE +/- 57.29, N = 3 SE +/- 26.05, N = 3 23112.9 22663.5 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
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 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare 2 EPPYC 7543 0.8269 1.6538 2.4807 3.3076 4.1345 SE +/- 0.006, N = 3 SE +/- 0.011, N = 3 3.675 3.658 1. (CXX) g++ options: -O3 -pthread
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 2 EPPYC 7543 20K 40K 60K 80K 100K SE +/- 140.25, N = 3 SE +/- 77.14, N = 3 87479.51 86655.83 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C 2 EPPYC 7543 6K 12K 18K 24K 30K SE +/- 343.31, N = 4 SE +/- 280.47, N = 3 30145.53 29176.28 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C 2 EPPYC 7543 600 1200 1800 2400 3000 SE +/- 48.45, N = 12 SE +/- 35.86, N = 3 2843.82 2909.24 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D 2 EPPYC 7543 600 1200 1800 2400 3000 SE +/- 13.25, N = 3 SE +/- 20.75, N = 3 2968.94 2961.89 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C 2 EPPYC 7543 10K 20K 30K 40K 50K SE +/- 142.64, N = 3 SE +/- 552.14, N = 3 48349.23 38990.23 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D 2 EPPYC 7543 400 800 1200 1600 2000 SE +/- 16.57, N = 3 SE +/- 23.36, N = 15 1894.77 1894.03 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C 2 EPPYC 7543 20K 40K 60K 80K 100K SE +/- 330.37, N = 3 SE +/- 452.49, N = 3 103990.12 103956.09 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C 2 EPPYC 7543 11K 22K 33K 44K 55K SE +/- 40.90, N = 3 SE +/- 48.32, N = 3 49253.78 48142.19 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 2 EPPYC 7543 15K 30K 45K 60K 75K SE +/- 70.66, N = 3 SE +/- 191.18, N = 3 67720.83 67812.87 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C 2 EPPYC 7543 7K 14K 21K 28K 35K SE +/- 52.82, N = 3 SE +/- 45.27, N = 3 33317.56 32836.66 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
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 2 EPPYC 7543 0.1534 0.3068 0.4602 0.6136 0.767 SE +/- 0.00408, N = 3 SE +/- 0.00564, N = 3 0.67718 0.68178
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.034359, N = 3 SE +/- 0.032408, N = 3 9.725950 9.611897 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -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 129 Cells Per Direction 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.02628751, N = 3 SE +/- 0.03902719, N = 15 6.07545233 6.14532347 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction 2 EPPYC 7543 7 14 21 28 35 SE +/- 0.38, N = 3 SE +/- 0.32, N = 4 28.21 27.86 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
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: 3 - Compression Speed 2 EPPYC 7543 1100 2200 3300 4400 5500 SE +/- 51.22, N = 15 SE +/- 72.64, N = 15 5026.0 5107.7 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Decompression Speed 2 EPPYC 7543 700 1400 2100 2800 3500 SE +/- 43.19, N = 6 SE +/- 19.27, N = 6 3454.5 3490.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed 2 EPPYC 7543 600 1200 1800 2400 3000 SE +/- 21.43, N = 3 SE +/- 26.48, N = 3 2767.2 2760.5 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed 2 EPPYC 7543 800 1600 2400 3200 4000 SE +/- 11.01, N = 3 SE +/- 9.50, N = 2 3647.6 3589.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed 2 EPPYC 7543 700 1400 2100 2800 3500 SE +/- 11.55, N = 15 SE +/- 13.20, N = 15 3208.4 3198.0 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Compression Speed 2 EPPYC 7543 130 260 390 520 650 SE +/- 6.21, N = 15 SE +/- 3.42, N = 3 597.8 581.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Decompression Speed 2 EPPYC 7543 800 1600 2400 3200 4000 SE +/- 8.23, N = 15 SE +/- 23.62, N = 3 3732.9 3782.5 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Compression Speed 2 EPPYC 7543 170 340 510 680 850 SE +/- 8.79, N = 3 SE +/- 5.12, N = 3 767.8 763.6 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Decompression Speed 2 EPPYC 7543 800 1600 2400 3200 4000 SE +/- 23.76, N = 3 SE +/- 34.11, N = 3 3831.4 3906.7 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed 2 EPPYC 7543 9 18 27 36 45 SE +/- 0.47, N = 3 SE +/- 0.06, N = 3 40.3 39.2 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed 2 EPPYC 7543 700 1400 2100 2800 3500 SE +/- 7.23, N = 3 SE +/- 7.90, N = 3 3177.6 3177.8 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K 2 EPPYC 7543 0.882 1.764 2.646 3.528 4.41 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 3.90 3.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 10.48 10.58 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 7.15 7.04 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K 2 EPPYC 7543 7 14 21 28 35 SE +/- 0.24, N = 3 SE +/- 0.14, N = 3 31.62 31.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K 2 EPPYC 7543 10 20 30 40 50 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 44.48 44.78 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p 2 EPPYC 7543 0.1148 0.2296 0.3444 0.4592 0.574 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.51 0.51 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.08, N = 4 SE +/- 0.04, N = 3 6.65 6.69 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p 2 EPPYC 7543 6 12 18 24 30 SE +/- 0.28, N = 15 SE +/- 0.26, N = 3 24.97 25.51 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.20, N = 15 18.84 19.00 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p 2 EPPYC 7543 20 40 60 80 100 SE +/- 0.62, N = 3 SE +/- 0.92, N = 4 78.63 74.52 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p 2 EPPYC 7543 20 40 60 80 100 SE +/- 1.42, N = 15 SE +/- 0.86, N = 9 102.06 102.77 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p 2 EPPYC 7543 60 120 180 240 300 SE +/- 3.44, N = 15 SE +/- 12.03, N = 12 251.78 274.08 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p 2 EPPYC 7543 60 120 180 240 300 SE +/- 1.05, N = 3 SE +/- 2.74, N = 4 248.30 252.38 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p 2 EPPYC 7543 50 100 150 200 250 SE +/- 2.57, N = 3 SE +/- 0.99, N = 3 238.48 240.01 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Chimera 1080p 2 EPPYC 7543 120 240 360 480 600 SE +/- 0.95, N = 3 SE +/- 1.56, N = 3 546.34 548.48 MIN: 408.87 / MAX: 701.54 MIN: 410.53 / MAX: 707.35 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Summer Nature 4K 2 EPPYC 7543 90 180 270 360 450 SE +/- 1.47, N = 3 SE +/- 0.71, N = 3 406.30 407.08 MIN: 295.02 / MAX: 471.7 MIN: 283.42 / MAX: 478.16 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Summer Nature 1080p 2 EPPYC 7543 120 240 360 480 600 SE +/- 5.74, N = 3 SE +/- 5.60, N = 4 537.46 538.66 MIN: 403.3 / MAX: 635.04 MIN: 405.48 / MAX: 683.54 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Chimera 1080p 10-bit 2 EPPYC 7543 90 180 270 360 450 SE +/- 0.09, N = 3 SE +/- 0.71, N = 3 408.70 409.34 MIN: 298.7 / MAX: 566.67 MIN: 299.18 / MAX: 574.49 1. (CC) gcc options: -pthread -lm
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p 2 EPPYC 7543 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 24.57 24.56 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p 2 EPPYC 7543 60 120 180 240 300 SE +/- 1.18, N = 3 SE +/- 1.72, N = 3 283.61 295.83 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p 2 EPPYC 7543 100 200 300 400 500 SE +/- 9.83, N = 15 SE +/- 10.81, N = 12 478.08 480.50 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only 2 EPPYC 7543 12 24 36 48 60 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 53.52 53.50
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only 2 EPPYC 7543 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.20, N = 3 148.29 147.72
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CPU-Only 2 EPPYC 7543 16 32 48 64 80 SE +/- 0.11, N = 3 SE +/- 0.26, N = 3 70.18 70.16
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only 2 EPPYC 7543 40 80 120 160 200 SE +/- 0.60, N = 3 SE +/- 0.29, N = 3 197.93 197.71
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CPU-Only 2 EPPYC 7543 40 80 120 160 200 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 165.75 165.27
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 2 EPPYC 7543 0.8678 1.7356 2.6034 3.4712 4.339 SE +/- 0.026, N = 3 SE +/- 0.029, N = 15 3.857 3.757 1. (CXX) g++ options: -O3 -fPIC -lm
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: Crown 2 EPPYC 7543 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 36.32 36.18 MIN: 35.81 / MAX: 37.21 MIN: 35.58 / MAX: 37.38
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown 2 EPPYC 7543 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 33.30 33.32 MIN: 32.84 / MAX: 34.27 MIN: 32.78 / MAX: 34.22
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon 2 EPPYC 7543 9 18 27 36 45 SE +/- 0.24, N = 3 SE +/- 0.21, N = 3 41.24 41.19 MIN: 40.35 / MAX: 42.14 MIN: 40.33 / MAX: 42.19
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Obj 2 EPPYC 7543 8 16 24 32 40 SE +/- 0.39, N = 5 SE +/- 0.09, N = 3 36.29 36.85 MIN: 34 / MAX: 37.63 MIN: 36.38 / MAX: 37.66
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon 2 EPPYC 7543 8 16 24 32 40 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 36.72 36.80 MIN: 36.23 / MAX: 37.69 MIN: 36.35 / MAX: 37.67
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 2 EPPYC 7543 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 32.87 32.98 MIN: 32.44 / MAX: 33.45 MIN: 32.65 / MAX: 33.54
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkVdbVolume 2 EPPYC 7543 4M 8M 12M 16M 20M SE +/- 141817.63, N = 9 SE +/- 164621.89, N = 3 17308328 16681805 MIN: 895405 / MAX: 84960504 MIN: 892093 / MAX: 74712168
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkStructuredVolume 2 EPPYC 7543 20M 40M 60M 80M 100M SE +/- 730402.78, N = 15 SE +/- 926890.24, N = 4 80062311 75601852 MIN: 982196 / MAX: 788752152 MIN: 1000589 / MAX: 695480040
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkUnstructuredVolume 2 EPPYC 7543 400K 800K 1200K 1600K 2000K SE +/- 2751.58, N = 3 SE +/- 1820.12, N = 3 1789270 1792476 MIN: 21799 / MAX: 6539286 MIN: 21782 / MAX: 6520994
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 2.5 Scene: DLSC - Acceleration: CPU 2 EPPYC 7543 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.45 5.42 MIN: 5.33 / MAX: 5.78 MIN: 5.3 / MAX: 5.79
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: CPU 2 EPPYC 7543 0.9765 1.953 2.9295 3.906 4.8825 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 4.33 4.34 MIN: 1.78 / MAX: 5.03 MIN: 1.78 / MAX: 5.04
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: CPU 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 8.24 8.28 MIN: 7.35 / MAX: 8.7 MIN: 7.39 / MAX: 8.74
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: CPU 2 EPPYC 7543 1.0598 2.1196 3.1794 4.2392 5.299 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.67 4.71 MIN: 1.78 / MAX: 5.45 MIN: 1.79 / MAX: 5.49
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: CPU 2 EPPYC 7543 4 8 12 16 20 SE +/- 0.27, N = 15 SE +/- 0.25, N = 15 16.76 16.35 MIN: 14.94 / MAX: 18.21 MIN: 14.57 / MAX: 18.83
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 2 EPPYC 7543 0.5414 1.0828 1.6242 2.1656 2.707 SE +/- 0.026, N = 15 SE +/- 0.011, N = 3 2.391 2.406 MIN: 2.21 / MAX: 6.29 MIN: 2.33 / MAX: 4.36 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 2 EPPYC 7543 0.9653 1.9306 2.8959 3.8612 4.8265 SE +/- 0.036, N = 15 SE +/- 0.049, N = 3 4.186 4.290 MIN: 3.84 / MAX: 8.17 MIN: 4.08 / MAX: 11.4 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.13, N = 15 SE +/- 0.21, N = 3 21.27 21.19 MIN: 20.15 / MAX: 137.68 MIN: 20.42 / MAX: 124.32 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.062, N = 15 SE +/- 0.080, N = 3 6.672 6.777 MIN: 5.96 / MAX: 25.64 MIN: 6.12 / MAX: 18.62 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 2 EPPYC 7543 0.8402 1.6804 2.5206 3.3608 4.201 SE +/- 0.028, N = 15 SE +/- 0.032, N = 3 3.670 3.734 MIN: 3.34 / MAX: 9.53 MIN: 3.62 / MAX: 9.03 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 2 EPPYC 7543 0.7628 1.5256 2.2884 3.0512 3.814 SE +/- 0.066, N = 15 SE +/- 0.185, N = 3 3.390 3.269 MIN: 2.65 / MAX: 44.51 MIN: 2.6 / MAX: 36.26 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 2 EPPYC 7543 6 12 18 24 30 SE +/- 0.19, N = 15 SE +/- 1.39, N = 3 25.48 26.51 MIN: 23.35 / MAX: 110.59 MIN: 24.1 / MAX: 106.6 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: mobilenet 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 20.00 19.43 MIN: 17.93 / MAX: 66.88 MIN: 16.83 / MAX: 64.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU-v2-v2 - Model: mobilenet-v2 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.31, N = 3 SE +/- 0.37, N = 3 8.70 9.08 MIN: 7.04 / MAX: 54.12 MIN: 7.22 / MAX: 167.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU-v3-v3 - Model: mobilenet-v3 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.21, N = 3 SE +/- 0.15, N = 3 9.91 8.62 MIN: 7.09 / MAX: 382.75 MIN: 7.15 / MAX: 122.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: shufflenet-v2 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 8.41 8.28 MIN: 7.41 / MAX: 20.58 MIN: 7.29 / MAX: 24.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: mnasnet 2 EPPYC 7543 2 4 6 8 10 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 7.92 7.70 MIN: 6.61 / MAX: 47.63 MIN: 6.62 / MAX: 17.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: efficientnet-b0 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.24, N = 3 10.34 10.47 MIN: 9.18 / MAX: 43.05 MIN: 8.88 / MAX: 181.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: blazeface 2 EPPYC 7543 0.864 1.728 2.592 3.456 4.32 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 3.82 3.84 MIN: 3.37 / MAX: 9.28 MIN: 3.4 / MAX: 5.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: googlenet 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.29, N = 3 SE +/- 0.65, N = 3 18.74 17.90 MIN: 15.94 / MAX: 401.3 MIN: 15.87 / MAX: 263.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: vgg16 2 EPPYC 7543 14 28 42 56 70 SE +/- 2.92, N = 3 SE +/- 2.31, N = 3 64.74 61.56 MIN: 37.06 / MAX: 691.85 MIN: 53.48 / MAX: 536.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: resnet18 2 EPPYC 7543 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 13.76 14.16 MIN: 12.22 / MAX: 26.08 MIN: 12.56 / MAX: 50.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: alexnet 2 EPPYC 7543 3 6 9 12 15 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 9.59 9.84 MIN: 8.47 / MAX: 11.91 MIN: 8.73 / MAX: 22.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: resnet50 2 EPPYC 7543 7 14 21 28 35 SE +/- 0.41, N = 3 SE +/- 2.65, N = 3 26.95 28.80 MIN: 24.94 / MAX: 167.32 MIN: 22.78 / MAX: 1760.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: yolov4-tiny 2 EPPYC 7543 7 14 21 28 35 SE +/- 1.18, N = 3 SE +/- 0.36, N = 3 28.48 28.47 MIN: 25.39 / MAX: 463.16 MIN: 26.82 / MAX: 42.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: squeezenet_ssd 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.24, N = 3 SE +/- 0.83, N = 3 20.73 21.31 MIN: 18.71 / MAX: 24.54 MIN: 18.64 / MAX: 147.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: regnety_400m 2 EPPYC 7543 5 10 15 20 25 SE +/- 0.26, N = 3 SE +/- 0.19, N = 3 21.85 21.39 MIN: 20.52 / MAX: 169.29 MIN: 20.53 / MAX: 35.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 2 EPPYC 7543 700 1400 2100 2800 3500 SE +/- 23.73, N = 3 SE +/- 22.81, N = 11 3077.06 3093.50 MIN: 2930.07 / MAX: 3675.48 MIN: 2921.34 / MAX: 3944.76 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 2 EPPYC 7543 70 140 210 280 350 SE +/- 2.88, N = 7 SE +/- 2.70, N = 3 308.51 309.89 MIN: 287.59 / MAX: 370.33 MIN: 287.03 / MAX: 356.5 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 2 EPPYC 7543 15 30 45 60 75 SE +/- 0.30, N = 3 SE +/- 0.13, N = 3 66.46 66.25 MIN: 65.72 / MAX: 69.75 MIN: 65.96 / MAX: 66.68 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 2 EPPYC 7543 60 120 180 240 300 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 277.04 276.66 MIN: 276.02 / MAX: 283.55 MIN: 276.23 / MAX: 284.68 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
EPPYC 7543 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 June 2021 12:40 by user phoronix.
2 Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 21.04, Kernel: 5.11.0-18-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server + Wayland, OpenGL: 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits), Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 June 2021 21:10 by user phoronix.