Benchmarks preparing for a future article by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2405244-NE-EPYC4004108 AMD EPYC 4364P EPYC 4564P Intel Xeon E-2488 Benchmarks - Phoronix Test Suite AMD EPYC 4364P EPYC 4564P Intel Xeon E-2488 Benchmarks Benchmarks preparing for a future article by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2405244-NE-EPYC4004108&grs&sor .
AMD EPYC 4364P EPYC 4564P Intel Xeon E-2488 Benchmarks Processor Motherboard Chipset Memory Disk Graphics Network Audio OS Kernel Desktop Display Server Compiler File-System Screen Resolution Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Intel Xeon E E-2488 @ 3.20GHz (8 Cores / 16 Threads) Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS) Intel Raptor Lake-S PCH 2 x 32GB DRAM-4800MT/s Micron MTC20C2085S1EC48BA1 3201GB Micron_7450_MTFDKCC3T2TFS + 960GB Micron_7450_MTFDKBA960TFR ASPEED 2 x Intel I210 Ubuntu 24.04 6.8.0-11-generic (x86_64) GNOME Shell 45.3 X Server 1.21.1.11 GCC 13.2.0 ext4 1920x1080 AMD EPYC 4364P 8-Core @ 5.57GHz (8 Cores / 16 Threads) Supermicro AS-3015A-I H13SAE-MF v1.00 (1.1 BIOS) AMD Device 14d8 AMD Rembrandt Radeon HD Audio 2 x 32GB DRAM-5200MT/s AMD EPYC 4564P 16-Core @ 5.88GHz (16 Cores / 32 Threads) 2 x 32GB DRAM-4800MT/s Micron MTC20C2085S1EC48BA1 2 x 32GB DRAM-5200MT/s OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-fxIygj/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-fxIygj/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - Xeon E-2488 @ DDR5-4800, EPYC 4364P @ DDR5-4800: NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096 Processor Details - Xeon E-2488 @ DDR5-4800: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x122 - Thermald 2.5.6 - EPYC 4364P @ DDR5-4800: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203 - EPYC 4364P @ DDR5-5200: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203 - EPYC 4564P @ DDR5-4800: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203 - EPYC 4564P @ DDR5-5200: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203 Java Details - OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2) Python Details - Python 3.12.2 Security Details - Xeon E-2488 @ DDR5-4800: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4364P @ DDR5-4800: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4364P @ DDR5-5200: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4564P @ DDR5-4800: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4564P @ DDR5-5200: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC 4364P EPYC 4564P Intel Xeon E-2488 Benchmarks john-the-ripper: WPA PSK openvino: Weld Porosity Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openssl: RSA4096 openvino: Person Re-Identification Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU john-the-ripper: MD5 john-the-ripper: HMAC-SHA512 openvino: Face Detection Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU srsran: PDSCH Processor Benchmark, Throughput Total namd: ATPase with 327,506 Atoms openvino: Machine Translation EN To DE FP16 - CPU openvino: Face Detection Retail FP16 - CPU minibude: OpenMP - BM1 minibude: OpenMP - BM1 minibude: OpenMP - BM2 minibude: OpenMP - BM2 openvino: Person Vehicle Bike Detection FP16 - CPU openssl: AES-128-GCM openssl: ChaCha20-Poly1305 openssl: AES-256-GCM openssl: ChaCha20 namd: STMV with 1,066,628 Atoms openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU primesieve: 1e12 openvino: Road Segmentation ADAS FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU primesieve: 1e13 openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU pgbench: 100 - 800 - Read Only - Average Latency pgbench: 100 - 800 - Read Only luxcorerender: Danish Mood - CPU openvino: Vehicle Detection FP16 - CPU ospray: gravity_spheres_volume/dim_512/scivis/real_time compress-7zip: Decompression Rating rocksdb: Rand Read openssl: SHA256 luxcorerender: LuxCore Benchmark - CPU openvino: Weld Porosity Detection FP16 - CPU ospray: gravity_spheres_volume/dim_512/ao/real_time openvino: Face Detection FP16 - CPU cpuminer-opt: LBC, LBRY Credits openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 500 - Read Only blender: Barbershop - CPU-Only petsc: Streams stockfish: Chess Benchmark m-queens: Time To Solve openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Handwritten English Recognition FP16 - CPU aircrack-ng: cpuminer-opt: scrypt onednn: IP Shapes 1D - CPU svt-hevc: 1 - Bosphorus 4K cpuminer-opt: Deepcoin cpuminer-opt: Blake-2 S openvino: Face Detection FP16-INT8 - CPU svt-hevc: 1 - Bosphorus 1080p cpuminer-opt: Triple SHA-256, Onecoin openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU cpuminer-opt: Skeincoin openssl: SHA512 blender: Pabellon Barcelona - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only cpuminer-opt: Ringcoin openvino: Machine Translation EN To DE FP16 - CPU stress-ng: CPU Cache ospray-studio: 2 - 1080p - 16 - Path Tracer - CPU ospray-studio: 1 - 1080p - 16 - Path Tracer - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU ospray-studio: 3 - 1080p - 16 - Path Tracer - CPU uvg266: Bosphorus 4K - Medium blender: Junkshop - CPU-Only kvazaar: Bosphorus 4K - Medium ospray: gravity_spheres_volume/dim_512/pathtracer/real_time cpuminer-opt: Garlicoin luxcorerender: DLSC - CPU speedb: Rand Read embree: Pathtracer ISPC - Crown john-the-ripper: bcrypt john-the-ripper: Blowfish blender: BMW27 - CPU-Only cpuminer-opt: Magi cpuminer-opt: Quad SHA-256, Pyrite java-scimark2: Fast Fourier Transform uvg266: Bosphorus 4K - Super Fast onednn: Deconvolution Batch shapes_1d - CPU ospray-studio: 2 - 1080p - 1 - Path Tracer - CPU stress-ng: AVX-512 VNNI ospray-studio: 1 - 1080p - 1 - Path Tracer - CPU ospray-studio: 3 - 1080p - 1 - Path Tracer - CPU rocksdb: Read While Writing uvg266: Bosphorus 4K - Very Fast quantlib: Multi-Threaded coremark: CoreMark Size 666 - Iterations Per Second openvino: Road Segmentation ADAS FP16 - CPU tensorflow: CPU - 512 - AlexNet uvg266: Bosphorus 4K - Ultra Fast onednn: Recurrent Neural Network Inference - CPU helsing: 14 digit v-ray: CPU kvazaar: Bosphorus 4K - Super Fast onednn: Recurrent Neural Network Training - CPU build-nodejs: Time To Compile openvino: Road Segmentation ADAS FP16-INT8 - CPU tensorflow: CPU - 256 - AlexNet ospray-studio: 2 - 1080p - 32 - Path Tracer - CPU ospray-studio: 3 - 1080p - 32 - Path Tracer - CPU luxcorerender: Orange Juice - CPU ospray-studio: 1 - 1080p - 32 - Path Tracer - CPU appleseed: Emily build-linux-kernel: allmodconfig openvkl: vklBenchmarkCPU ISPC kvazaar: Bosphorus 4K - Very Fast openvino: Person Vehicle Bike Detection FP16 - CPU svt-hevc: 7 - Bosphorus 4K easywave: e2Asean Grid + BengkuluSept2007 Source - 240 rocksdb: Rand Fill Sync kvazaar: Bosphorus 4K - Ultra Fast appleseed: Disney Material oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only stress-ng: Vector Floating Point brl-cad: VGR Performance Metric java-jmh: Throughput jpegxl: PNG - 100 helsing: 12 digit speedb: Read While Writing jpegxl: JPEG - 100 svt-av1: Preset 8 - Bosphorus 4K compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression stress-ng: x86_64 RdRand npb: BT.C dacapobench: Apache Tomcat askap: tConvolve OpenMP - Gridding build-ffmpeg: Time To Compile graphics-magick: Rotate x265: Bosphorus 4K build-llvm: Ninja ospray: particle_volume/ao/real_time onednn: IP Shapes 3D - CPU oidn: RTLightmap.hdr.4096x4096 - CPU-Only ospray: particle_volume/scivis/real_time embree: Pathtracer ISPC - Asian Dragon astcenc: Medium stress-ng: Floating Point graphics-magick: Sharpen build-godot: Time To Compile stress-ng: Vector Shuffle xmrig: GhostRider - 1M astcenc: Fast openssl: RSA4096 stress-ng: Fused Multiply-Add graphics-magick: Swirl astcenc: Very Thorough graphics-magick: Enhanced astcenc: Exhaustive openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Vehicle Detection FP16 - CPU stress-ng: Wide Vector Math uvg266: Bosphorus 1080p - Super Fast build-linux-kernel: defconfig embree: Pathtracer ISPC - Asian Dragon Obj uvg266: Bosphorus 1080p - Very Fast build-mesa: Time To Compile y-cruncher: 1B build-llvm: Unix Makefiles tensorflow: CPU - 64 - AlexNet svt-hevc: 7 - Bosphorus 1080p avifenc: 0 openvino: Person Detection FP32 - CPU openvino: Person Detection FP16 - CPU liquid-dsp: 16 - 256 - 512 avifenc: 6 memcached: 1:100 luxcorerender: Rainbow Colors and Prism - CPU openradioss: INIVOL and Fluid Structure Interaction Drop Container kvazaar: Bosphorus 1080p - Very Fast svt-av1: Preset 4 - Bosphorus 4K java-scimark2: Monte Carlo onnx: ResNet50 v1-12-int8 - CPU - Parallel compress-7zip: Compression Rating tensorflow: CPU - 512 - ResNet-50 gromacs: MPI CPU - water_GMX50_bare tensorflow: CPU - 256 - ResNet-50 speedb: Rand Fill Sync uvg266: Bosphorus 1080p - Ultra Fast onnx: super-resolution-10 - CPU - Parallel specfem3d: Tomographic Model uvg266: Bosphorus 1080p - Medium npb: SP.B kvazaar: Bosphorus 1080p - Medium tensorflow: CPU - 512 - GoogLeNet tensorflow: CPU - 64 - ResNet-50 y-cruncher: 500M tensorflow: CPU - 32 - ResNet-50 specfem3d: Layered Halfspace tensorflow: CPU - 256 - GoogLeNet memcached: 1:10 tensorflow: CPU - 32 - GoogLeNet nginx: 500 build-gem5: Time To Compile tensorflow: CPU - 64 - GoogLeNet nginx: 1000 avifenc: 2 graphics-magick: Noise-Gaussian openfoam: drivaerFastback, Small Mesh Size - Execution Time appleseed: Material Tester svt-vp9: VMAF Optimized - Bosphorus 1080p specfem3d: Homogeneous Halfspace askap: tConvolve MT - Degridding svt-vp9: Visual Quality Optimized - Bosphorus 4K svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p dacapobench: Avrora AVR Simulation Framework nginx: 200 compress-zstd: 8 - Compression Speed openvino: Face Detection Retail FP16-INT8 - CPU svt-av1: Preset 12 - Bosphorus 4K scylladb: Writes specfem3d: Mount St. Helens dacapobench: Jython specfem3d: Water-layered Halfspace compress-zstd: 8, Long Mode - Compression Speed svt-av1: Preset 8 - Bosphorus 1080p vvenc: Bosphorus 4K - Fast svt-hevc: 10 - Bosphorus 1080p svt-hevc: 10 - Bosphorus 4K cockroach: KV, 50% Reads - 128 pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 800 - Read Write dragonflydb: 10 - 1:100 jpegxl: PNG - 90 onnx: CaffeNet 12-int8 - CPU - Standard avifenc: 6, Lossless svt-av1: Preset 4 - Bosphorus 1080p tensorflow: CPU - 32 - AlexNet askap: tConvolve OpenMP - Degridding cockroach: KV, 60% Reads - 128 srsran: PUSCH Processor Benchmark, Throughput Total java-scimark2: Dense LU Matrix Factorization vvenc: Bosphorus 1080p - Fast apache: 1000 speedb: Update Rand onnx: CaffeNet 12-int8 - CPU - Parallel jpegxl: JPEG - 90 rocksdb: Update Rand vvenc: Bosphorus 4K - Faster svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K rocksdb: Read Rand Write Rand svt-vp9: VMAF Optimized - Bosphorus 4K pennant: sedovbig askap: tConvolve MT - Gridding cockroach: KV, 95% Reads - 128 stress-ng: Matrix 3D Math onnx: yolov4 - CPU - Parallel stress-ng: System V Message Passing rocksdb: Overwrite pgbench: 100 - 500 - Read Write pgbench: 100 - 500 - Read Write - Average Latency openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU rocksdb: Rand Fill dragonflydb: 10 - 1:10 apache: 500 openfoam: drivaerFastback, Small Mesh Size - Mesh Time x265: Bosphorus 1080p ospray: particle_volume/pathtracer/real_time openvino: Weld Porosity Detection FP16-INT8 - CPU graphics-magick: Resizing cloverleaf: clover_bm renaissance: Finagle HTTP Requests npb: SP.C onnx: bertsquad-12 - CPU - Parallel incompact3d: input.i3d 129 Cells Per Direction build-php: Time To Compile minife: Small openvino: Face Detection FP16-INT8 - CPU dacapobench: Spring Boot srsran: PDSCH Processor Benchmark, Throughput Thread apache-iotdb: 800 - 100 - 800 - 100 apache-iotdb: 800 - 100 - 800 - 100 mariadb: oltp_write_only - 64 npb: IS.D apache-iotdb: 800 - 100 - 800 - 400 openfoam: drivaerFastback, Medium Mesh Size - Mesh Time z3: 2.smt2 speedb: Read Rand Write Rand apache-iotdb: 800 - 100 - 800 - 400 apache-iotdb: 500 - 100 - 800 - 100 build-wasmer: Time To Compile openfoam: drivaerFastback, Medium Mesh Size - Execution Time amg: cloverleaf: clover_bm64_short dacapobench: Tradesoap pybench: Total For Average Test Times graphics-magick: HWB Color Space onednn: Convolution Batch Shapes Auto - CPU tensorflow: CPU - 1 - AlexNet onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel llama-cpp: llama-2-70b-chat.Q5_0.gguf llama-cpp: llama-2-7b.Q4_0.gguf java-scimark2: Composite llama-cpp: llama-2-13b.Q4_0.gguf tensorflow: CPU - 1 - ResNet-50 apache-iotdb: 800 - 100 - 500 - 100 llamafile: llava-v1.5-7b-q4 - CPU vvenc: Bosphorus 1080p - Faster apache-iotdb: 500 - 100 - 800 - 100 llamafile: mistral-7b-instruct-v0.2.Q8_0 - CPU apache-iotdb: 800 - 100 - 500 - 100 easywave: e2Asean Grid + BengkuluSept2007 Source - 1200 dacapobench: Apache Xalan XSLT apache-iotdb: 800 - 100 - 500 - 400 duckdb: IMDB apache-iotdb: 800 - 100 - 500 - 400 liquid-dsp: 2 - 256 - 32 liquid-dsp: 4 - 256 - 32 incompact3d: input.i3d 193 Cells Per Direction dacapobench: Tradebeans apache-iotdb: 500 - 100 - 500 - 100 tensorflow: CPU - 1 - GoogLeNet apache-iotdb: 500 - 100 - 500 - 100 svt-av1: Preset 12 - Bosphorus 1080p renaissance: Savina Reactors.IO onnx: T5 Encoder - CPU - Standard hadoop: Create - 100 - 100000 apache-iotdb: 500 - 100 - 800 - 400 llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPU apache-iotdb: 500 - 100 - 500 - 400 liquid-dsp: 1 - 256 - 32 numpy: mariadb: oltp_read_write - 64 compress-zstd: 19 - Compression Speed apache-iotdb: 500 - 100 - 500 - 400 dacapobench: BioJava Biological Data Framework build-python: Default apache-iotdb: 500 - 100 - 800 - 400 openradioss: Chrysler Neon 1M ffmpeg: libx265 - Video On Demand ffmpeg: libx265 - Platform ffmpeg: libx265 - Upload mariadb: oltp_update_non_index - 64 liquid-dsp: 8 - 256 - 512 speedb: Rand Fill dacapobench: H2 Database Engine node-web-tooling: mariadb: oltp_read_write - 32 mariadb: oltp_write_only - 32 rnnoise: 26 Minute Long Talking Sample octave-benchmark: onnx: T5 Encoder - CPU - Parallel hpcg: 104 104 104 - 60 quantlib: Single-Threaded mariadb: oltp_update_non_index - 32 mariadb: oltp_update_index - 64 webp: Quality 100, Highest Compression webp: Default liquid-dsp: 16 - 256 - 32 z3: 1.smt2 clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache avifenc: 10, Lossless draco: Church Facade clickhouse: 100M Rows Hits Dataset, Second Run hadoop: Create - 500 - 100000 clickhouse: 100M Rows Hits Dataset, Third Run rawtherapee: Total Benchmark Time dacapobench: Apache Lucene Search Index liquid-dsp: 8 - 256 - 32 dacapobench: PMD Source Code Analyzer dacapobench: Eclipse java-scimark2: Jacobi Successive Over-Relaxation renaissance: Genetic Algorithm Using Jenetics + Futures dacapobench: GraphChi dacapobench: Batik SVG Toolkit webp: Quality 100 onnx: GPT-2 - CPU - Standard webp: Quality 100, Lossless, Highest Compression mysqlslap: 128 dacapobench: FOP Print Formatter mariadb: oltp_update_index - 32 compress-zstd: 8 - Decompression Speed liquid-dsp: 2 - 256 - 512 draco: Lion mysqlslap: 64 dolfyn: Computational Fluid Dynamics build-python: Released Build, PGO + LTO Optimized ffmpeg: libx265 - Live compress-zstd: 19 - Decompression Speed webp: Quality 100, Lossless compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 12 - Decompression Speed liquid-dsp: 4 - 256 - 512 onnx: GPT-2 - CPU - Parallel securemark: SecureMark-TLS dacapobench: Apache Kafka dacapobench: jMonkeyEngine dacapobench: Zxing 1D/2D Barcode Image Processing dacapobench: Apache Lucene Search Engine cpuminer-opt: Myriad-Groestl onnx: T5 Encoder - CPU - Parallel onnx: T5 Encoder - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Standard onednn: Deconvolution Batch shapes_3d - CPU pytorch: CPU - 64 - ResNet-50 pytorch: CPU - 1 - ResNet-50 srsran: PUSCH Processor Benchmark, Throughput Thread liquid-dsp: 1 - 256 - 512 astcenc: Thorough kvazaar: Bosphorus 1080p - Ultra Fast kvazaar: Bosphorus 1080p - Super Fast svt-vp9: Visual Quality Optimized - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 1080p compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 12 - Compression Speed openradioss: Bumper Beam openradioss: Cell Phone Drop Test openradioss: Rubber O-Ring Seal Installation openradioss: Bird Strike on Windshield npb: CG.C npb: MG.C npb: LU.C npb: EP.C pennant: leblancbig gpaw: Carbon Nanotube qmcpack: simple-H2O heffte: r2c - FFTW - double - 128 heffte: r2c - FFTW - float - 128 askap: tConvolve MPI - Gridding askap: tConvolve MPI - Degridding lammps: 20k Atoms lammps: Rhodopsin Protein lulesh: mt-dgemm: Sustained Floating-Point Rate redis: SET - 500 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 29560 265.83 2.65 150.64 3000.2 18.22 7499.47 174.92 919791 40721000 9.76 437.96 2908.5 0.65977 33.74 816.17 12.452 311.310 313.737 12.550 401.42 64812725680 23800263020 56193249190 34651855800 0.20565 15.95 500.86 21.095 101.21 1559.06 523.02 245.674 29.83 29.71 1.852 431962 1.45 249.02 2.63851 61527 47512260 12336557263 1.69 30.05 2.73496 1506.63 6037.26 18507.31 0.899 555873 1281.54 69652.7320 16898291 72.852 1022.10 53.07 35441.707 119.86 2.91408 2.26 3294.49 56160 10.41 9.16 38847 36.35 1.00 13933 4429397160 411.15 336.94 165.00 1437.47 118.45 4023464.53 42275 41514 45.70 48929 6.62 173.17 9.28 3.79539 1356.31 2.13 57824426 13.3883 18787 18841 123.51 278.09 26527 1023.23 20.17 6.85318 2474 1125583.01 2441 2884 1942760 18.97 37214.4 430017.460583 39.48 192.28 24.69 1548.71 437.414 20060 28.64 2931.95 915.937 219.86 189.14 82403 95447 3.58 81236 323.270593 1508.042 288 23.05 9.94 47.98 6.278 201594 39.59 174.948967 0.42 0.42 28846.06 194127 36765943472.268 13.650 4.080 2548837 13.484 36.140 6.612486 81538.34 28326.36 6687 2556.22 50.051 317 19.48 697.937 5.93161 7.59695 0.21 5.88640 16.5757 89.1400 4740.28 36 364.422 9138.29 1742.9 205.9321 195618.8 29762395.57 130 1.4639 49 0.8741 15.21 16.04 576480.15 96.33 108.338 14.5499 89.31 32.515 33.891 719.392 173.78 168.39 133.567 134.54 133.99 159270000 6.260 3048853.56 9.35 538.42 103.04 4.348 1426.11 214.547 94990 22.98 1.434 23.07 225607 115.40 75.8803 52.893781663 36.59 12750.97 50.47 76.13 23.10 14.926 23.19 144.539537175 76.84 3072373.87 78.79 92582.29 468.378 78.17 87132.22 61.843 70 242.94479 173.408541 289.26 67.114929508 3033.56 59.56 295.69 1451 98692.95 485.6 5.07 105.280 104832 53.287162292 2433 135.416735242 504.1 120.533 4.975 383.64 101.83 59866.6 23.198 34486 4604951.36 31.814 587.732 8.969 15.918 160.52 4282.18 63021.4 1068.9 11976.06 15.463 113097.85 828184 557.408 32.506 908300 11.768 83.19 1976533 79.85 55.89647 2260.82 83987.5 2778.89 8.09421 17858353.80 1653489 42412 11.791 0.4 1647988 4522560.58 125745.61 35.18608 84.33 157.969 7.78 244 64.58 1668.7 11387.05 11.5372 19.7521490 54.449 9869.74 384.09 1220 809.6 137.92 56035278 296034 1604.85 524.13 225.95491 63.076 2120915 56494499 119.49 38.134 2260.9881 453703880 138.32 1914 415 315 6.38053 18.50 41.0093 1.36 16.07 4311.80 8.38 13.71 77.24 13.32 40.067 62558098 7.91 61842388 145.992 408 62655549 99.575 290.14 127376667 253450000 73.7203613 3410 80.56 51.33 57028398 548.042 3695.4 169.620 88992 64886364 2.20 57760197 63236667 675.48 186418 16.3 275.14 3708 16.85 382.48 983.54 58.75 58.75 28.89 220068 130002500 876130 2128 23.30 180020 304169 6.400 6.462 161.313 7.58350 5019.2 253110 187089 4.73 23.93 711050000 18.660 234.39 4.162 5607 249.50 76956 249.90 42.659 2296 439150000 1122 6943 2667.90 886.6 2675 897 15.37 126.674 0.88 574 426 210974 2375.6 40821333 3830 1128 10.421 197.921 178.15 1972.1 2.17 2375.4 2377.0 79553667 123.284 426706 4984 6827 1053 3113 4843.72 6.19876 5.90786 24.3858 23.6106 42.3505 1.79347 1.70107 4.66040 4.46170 224.106 43.3967 23.0436 8.10864 7.89080 86.6873 91.5188 10.9265 13.1792 960.856 1.042812 123.593 127.667 7.83432 4.94792 32.25 61.49 153.6 20255000 12.2307 197.51 139.72 221.33 104.614 649.426 1906.1 8.91 170.6 153.90 93.26 177.74 259.88 9750.34 24688.58 40491.56 1470.81 32.86765 228.899 24.057 26.4787 85.0062 6199.09 5146.33 7.579 7.236 8126.3211 4.204110 3327348.65 85712 728.18 7.19 392.93 7692.3 3.85 18754.59 422.62 2230333 117065667 2.2 1036.33 7792.6 1.73454 82.32 1791.06 26.365 659.131 662.344 26.494 834.18 132890512590 48632082067 113843625530 68362354417 0.49007 4.52 882.75 12.416 221.52 2522.56 980.84 152.679 54.11 54.23 2.077 385411 2.06 465.15 3.82321 87804 69366631 17965660883 2.41 10.97 3.87827 556.14 8437.93 26465.33 0.940 532015 928.10 39918.9683 22631087 53.082 1427.32 20.34 48802.996 163.88 1.98773 3.04 4405.85 74883 14.07 12.31 51370 14.59 0.4 18060 5813555230 316.02 259.85 127.12 1868.89 48.55 5854131.56 38010 37677 18.90 44013 8.62 139.94 12.48 4.65305 1691.29 2.74 72087947 16.3264 23271 23174 101.52 332.40 32010 470.91 26.73 3.87665 2171 1376354.00 2143 2539 2476441 25.32 44058.2 505633.419425 18.02 240.74 32.09 1329.68 372.103 23056 38.85 2496.65 737.286 273.50 237.76 72906 84611 4.42 72067 264.550473 1312.351 327 31.05 4.78 56.95 6.166 98054 52.25 156.370961 0.48 0.48 30715.14 229365 38717919571.114 16.689 3.753 3212276 16.578 46.837 6.176853 4400145.01 22551.09 6467 2703.36 42.474 169 17.73 643.223 4.58353 4.61211 0.23 4.64920 18.3544 80.5260 4283.48 31 329.179 8606.94 1690.9 204.8423 193565.9 30389834.82 138 1.4109 50 0.8633 8.03 8.57 416118.50 120.30 97.918 15.5714 112.05 28.195 25.242 670.269 205.32 178.68 107.789 73.71 73.87 212960000 5.301 2124192.99 11.89 582.32 129.55 5.711 2570.60 325.209 101849 30.41 1.526 30.33 128855 143.28 93.1564 46.576508103 45.75 10661.66 64.80 91.07 30.22 11.555 30.52 130.528009050 90.98 2217988.24 92.82 91505.24 436.048 91.42 84772.31 51.377 76 311.36104 143.379959 240.66 57.793286206 1791.99 61.45 249.86 2430 100527.89 513.9 3.13 123.638 94899 49.543042397 3790 129.551632196 518.5 147.312 5.681 358.54 107.65 64458.4 24.761 32316 4818585.25 36.035 674.506 8.140 19.962 171.11 3429.45 67444.0 1517.4 18030.92 18.902 87686.63 556040 680.951 36.320 609510 13.083 74.93 2137892 70.29 61.27547 1550.64 84052.3 1953.52 9.32307 12527831.36 1155121 40163 12.454 0.28 1154716 4759359.71 96630.23 41.677148 89.23 168.642 5.59 251 89.36 1925.0 9707.08 12.2597 22.5346236 53.091 7278.87 283.71 1159 1082.7 123.74 62420035 265093 1228.58 460.21 276.70864 48.122 2144575 64354682 106.44 36.548 2926.9791 350656750 177.83 1964 532 244 8.23220 14.53 51.7236 1.09 12.73 5519.55 6.70 16.77 69.05 10.57 44.584 69450850 6.34 68672756 159.043 448 68897602 101.939 267.99 107140000 212860000 90.6922328 2775 72.28 62.02 63627945 539.872 3036.5 142.061 90476 69856949 1.84 63296864 53661333 812.16 168388 17.9 248.62 4347 16.499 359.26 1060.53 65.27 65.45 32.03 200246 151906667 1011788 2000 21.89 159448 310088 7.028 5.668 142.816 6.67485 4518.4 224636 177842 5.30 26.78 740166667 20.501 211.59 4.202 5163 226.35 76371 228.79 46.732 2407 411290000 1142 6483 2487.93 819.5 2535 927 16.59 128.008 0.84 587 423 198305 2313.4 39693000 3922 1132 10.634 202.772 179.98 2026.0 2.16 2324.5 2394.8 77811000 120.909 437475 5031 6804 1016 2404 6023.38 7.00331 7.03702 19.3345 19.1025 52.3449 1.46770 1.48191 3.07441 3.05542 327.525 36.2481 27.7125 8.26788 7.81820 81.5676 85.1150 11.7495 10.7379 889.170 1.12597 107.5081 100.0271 10.46448 3.79890 45.20 68.30 183.5 20106667 10.3241 226.69 168.47 201.53 121.437 621.633 1836.4 10.3 168.4 140.26 100.19 175.46 276.24 7857.53 19566.67 37048.80 1101.23 43.80306 217.495 21.449 22.4741 74.1317 3975.69 3349.85 8.031 6.848 6454.6726 5.160364 3656582.35 85532 723.13 7.14 392.23 7697.3 3.87 18615.12 417.64 2234333 116770333 2.21 1029.88 7530.0 1.73764 82.80 1781.62 26.294 657.345 658.931 26.357 833.73 133134074673 48542739663 113941258877 68366108810 0.49345 4.53 879.50 12.506 224.43 2495.55 991.32 153.598 55.11 54.98 2.051 390018 2.10 472.57 3.82138 88945 69408254 17876358337 2.41 11.05 3.91070 560.14 8389.15 26230.85 0.961 520502 925.38 26545.7101 23143858 53.501 1417.33 20.37 48527.815 162.88 1.99986 3.04 4377.74 74513 13.97 12.28 51087 14.48 0.4 17983 5794405307 315.13 259.46 127.01 1851.25 48.26 5997921.20 37900 37458 19.13 43830 8.61 139.48 12.49 4.66757 1674.99 2.75 71648683 16.4625 23235 23243 101.72 330.62 31903 450.10 26.65 3.91089 2156 1371242.64 2133 2526 2519594 25.25 43490.7 499103.502905 17.79 240.23 31.86 1337.47 375.915 23078 38.82 2491.14 739.343 275.72 237.57 72250 84209 4.42 71530 263.511098 1310.962 331 31.04 4.78 57.23 5.990 99746 52.30 156.069532 0.48 0.48 30936.50 226198 38776376503.465 16.661 3.828 3194971 16.519 47.285 6.154460 4374980.16 22935.27 6482 2739.34 42.195 168 17.61 636.832 4.63828 4.67840 0.23 4.61871 18.4511 79.6040 4251.39 30 326.162 8556.72 1699.3 203.1039 194210.3 29927440.69 139 1.3979 50 0.8557 7.95 8.44 413926.82 119.83 97.405 15.6889 111.78 28.263 25.455 662.522 206.40 178.20 108.654 72.70 72.52 211670000 5.338 2104490.55 11.93 585.75 129.02 5.742 2541.20 322.610 103571 30.70 1.546 30.63 127955 142.97 91.5855 49.576470688 45.63 11152.31 64.68 91.90 30.53 11.589 30.79 133.309044185 91.77 2195688.49 93.71 94947.75 432.221 92.37 85990.12 51.942 76 296.60098 142.936958 242.58 63.865203042 1806.71 61.90 251.44 2415 101214.88 520.3 3.16 125.277 94217 51.286977035 3762 129.332051612 527.9 148.336 5.693 361.05 109.03 64052.7 24.498 32657 4762998.42 36.024 676.652 8.147 19.891 172.89 3426.03 67506.7 1470.5 17934.59 18.773 87708.39 553791 677.583 37.180 618187 13.141 76.06 2131122 71.48 61.96916 1619.82 83155.8 2029.45 9.29179 12445240.76 1152820 40473 12.355 0.28 1159865 4729191.29 96508.30 38.173004 89.12 170.390 5.63 255 86.82 1963.8 10027.11 12.5483 21.8746431 53.755 7325.10 285.97 1162 1061.5 122.55 62951458 265119 1269.37 462.14 296.21094 48.676 2138776 64182563 105.58 36.902 2827.8789 352361775 172.36 1979 527 255 8.16800 15.01 50.5310 1.06 12.54 5476.91 6.57 17.47 68.16 10.48 45.144 70305285 6.28 69561449 152.786 450 69144164 100.627 268.42 107146667 209743333 87.7703425 2815 70.70 62.99 64781285 546.706 3042.0 139.477 90938 71338740 1.82 64655502 53659000 808.62 168593 18.0 243.61 4327 16.576 347.97 1003.59 65.35 65.26 31.95 201401 150576667 1005973 1977 22.14 158499 306926 7.184 5.587 141.629 6.73761 4457.8 224118 177579 5.28 26.81 735566667 20.432 222.47 4.205 5083 236.47 77585 232.47 46.659 2390 409386667 1113 6410 2489.61 821.7 2561 930 16.54 123.952 0.84 580 414 198779 2322.3 39094333 3891 1124 10.727 200.978 179.99 2066.7 2.17 2352.5 2404.2 77508667 120.280 430421 5027 6802 1019 2409 5972.09 7.06097 7.16751 19.7910 19.2609 51.9129 1.47531 1.47738 3.09905 3.09150 323.381 37.0025 27.0247 8.31107 8.06389 79.7037 70.8263 15.2174 10.9182 864.561 1.16054 107.793 97.1235 10.70547 3.83412 45.11 67.48 183.6 19611667 10.2089 226.13 168.08 203.16 122.908 633.291 1926.9 10.2 171.0 145.32 95.48 162.03 266.65 7898.41 20265.52 37149.88 1169.68 42.93941 205.874 23.119 23.7179 77.5196 4256.28 3635.69 8.215 6.826 6744.8566 5.330500 3684418.98 160805 1359.29 13.46 726.61 14222.8 4.11 34850.47 794.33 4066667 178283333 2.37 1938.68 12647.5 2.74999 133.65 3283.98 49.812 1245.304 1248.077 49.923 1551.75 250497225070 91743101110 214525919597 129320991313 0.74072 4.83 1648.32 6.669 302.45 4743.73 1544.55 82.116 86.56 87.50 0.709 1128893 4.14 680.56 7.31921 168957 131218639 33924881420 4.62 11.75 7.45782 592.59 16317 49580.07 0.360 1388157 484.46 39471.0714 42791247 27.823 2669.64 21.99 92030.349 310.84 1.13203 5.74 8421.15 143480 26.44 22.86 97753 17.22 0.41 34753 11004843967 166.82 136.92 67.34 3541.50 59.77 2537425.46 17491 17247 20.11 20461 15.70 73.73 21.80 8.92149 3196.42 4.96 135603493 30.7908 43512 42924 53.56 644.74 61347 453.05 45.87 2.98654 1090 2572055.58 1078 1275 4368397 42.20 83133.5 954988.728979 26.38 422.88 54.07 703.750 199.825 43567 62.23 1354.12 427.637 462.96 405.64 38454 44561 7.70 37984 153.372731 717.711 596 47.67 5.13 97.70 3.164 170735 80.50 85.934505 0.85 0.85 59053.01 394575 75186159786.823 27.555 2.011 5146187 26.958 71.140 3.325543 8497821.55 43371.78 3367 4886.94 25.541 161 34.13 360.463 8.81078 4.07056 0.40 8.81722 31.5835 153.7016 8242.96 57 191.082 16537.83 3239.4 388.6309 372775.0 57429956.15 246 2.6608 93 1.6262 10.18 11.72 781906.97 180.54 57.927 26.8839 165.55 17.730 18.803 395.186 316.11 307.89 72.424 91.34 92.38 286960000 3.447 3850014.66 16.94 349.91 184.98 7.831 2456.47 386.409 167186 39.73 2.468 39.37 170365 201.92 132.293 30.487643606 63.89 18360.82 87.51 129.06 39.07 8.920 38.96 85.995981541 128.54 3775389.09 131.79 156935.63 277.725 129.59 144355.05 36.335 116 199.88007 102.744509 398.58 39.915238393 2291.85 97.12 408.36 2393 162256.48 778.5 3.32 164.852 151849 34.795020293 3795 87.856011578 778.8 187.537 7.746 545.31 153.78 90528.3 16.102 49683 7046043.06 47.231 894.660 5.932 23.944 236.71 5023.7 93864.1 1611.5 17230.85 22.997 130637.70 624743 833.520 46.773 703294 17.321 107.37 2912747 99.84 44.42709 1917.67 119084.9 1924.70 11.6777 16207347.12 1229747 57520 8.696 0.29 1229256 6406922.86 136714.05 29.739379 117.25 219.737 5.96 332 75.55 2288.1 12630.55 15.8484 17.1065413 40.847 7330.07 301.83 1554 1027.8 106.72 71922519 349473 1223.22 415.04 245.10431 48.997 2770899 71135797 95.72 29.890 2445.681 362574433 178.81 2439 536 269 6.72536 14.37 51.7844 1.16 13.12 5321.50 6.98 14.78 62.09 10.90 50.414 76780782 6.53 75706552 132.128 508 75893047 83.005 238.34 103326667 206306667 79.6040472 3359 67.07 57.21 68166248 649.204 3270.6 157.010 74946 77609975 1.94 67794681 52493000 800.78 201579 19.5 235.20 4413 14.149 322.24 915.82 69.52 69.24 34.06 234051 147935000 869816 1872 20.06 184015 352931 7.291 5.754 152.044 6.94846 4425.0 239542 200156 5.15 25.78 787633333 20.778 222.80 3.804 5237 240.37 71080 241.90 42.791 2517 404010000 1074 6627 2464.14 887.0 2521 969 15.84 131.438 0.82 614 403 206240 2279.9 38605667 4049 1182 10.927 193.585 186.71 1998.3 2.08 2278.0 2308.6 76415667 118.910 435859 5030 6808 597 2083 11228.13 6.57601 6.36984 19.3166 16.7849 60.0604 1.19855 1.11712 2.58704 2.49599 401.349 27.3493 36.5624 8.40671 7.60699 63.1072 65.4802 15.2718 7.55840 567.021 1.76384 85.6348 96.9943 10.3104 2.46164 45.76 66.63 183.6 19299333 19.6781 299.12 245.56 355.84 160.654 711.526 1890.5 11.5 207.5 107.17 68.68 101.62 177.58 8784.83 20223.60 46710.34 2117.29 30.23603 166.513 25.619 35.0651 125.536 7317.33 6613.59 14.471 12.449 8006.3547 9.536711 3827317.96 160664 1362.00 13.52 729.84 14289.7 4.11 34815.39 795.05 4118000 181331000 2.37 1938.32 12852.6 2.78846 136.73 3269.12 49.953 1248.810 1249.619 49.985 1556.07 251224402513 92129622150 215336847677 129853526473 0.75646 4.82 1653.69 6.691 317.25 4734.27 1587.74 82.473 88.84 88.32 0.722 1108243 4.18 701.84 7.36909 170373 130693063 33989652273 4.65 11.72 7.46649 590.80 16120 49485.35 0.361 1384166 481.15 41077.6339 44270858 27.914 2672.51 21.89 92259.953 308.21 1.13000 5.80 8356.74 142753 26.46 23.10 97340 16.73 0.41 34640 11041579923 165.35 136.11 66.78 3500.13 58.43 2446936.66 17285 17116 20.09 20283 15.92 72.75 22.02 8.97813 3179.32 5.00 134971626 31.3658 43695 43795 53.25 633.44 61360 443.49 46.41 3.00636 1080 2571394.82 1069 1265 4294631 42.60 83365.1 951674.506461 25.15 425.47 54.54 706.645 200.768 43879 62.56 1348.37 421.430 476.63 409.96 38192 44247 7.72 37923 152.301783 714.384 603 48.11 5.12 99.61 3.037 171199 81.23 85.317922 0.86 0.86 59037.14 397138 75134161573.042 27.748 2.016 5119891 27.223 72.744 3.299879 8469095.71 44844.13 3370 5073.23 25.301 167 34.65 354.764 8.98399 3.88685 0.41 8.98195 32.2209 154.7202 8199.65 58 188.525 16452.47 3266.9 392.2377 373632.3 56410032.25 250 2.6841 94 1.6391 9.90 11.36 778238.33 181.83 57.472 27.3873 166.81 17.464 18.211 387.011 322.53 311.95 72.106 90.49 89.98 292390000 3.421 3844031.28 16.98 322.67 186.56 7.838 2529.18 380.818 170888 41.02 2.543 40.68 171623 203.39 133.322 30.132231580 64.16 18660.90 88.30 132.62 40.24 8.652 39.99 83.970385886 132.13 3761626.61 135.30 154835.06 273.493 133.21 136360.72 36.331 119 183.23451 102.152381 408.42 39.561071375 2387.89 100.00 419.26 2359 162348.33 793.8 3.33 170.214 151729 33.126776518 3871 85.254370260 797.0 189.413 7.818 560.81 158.94 92195.2 16.157 49522 6289782.08 48.525 895.773 5.890 24.171 242.49 5172.44 95084.8 1611.5 17774.36 23.190 131437.32 623366 829.194 48.588 700416 17.435 111.01 2915758 103.52 42.22565 1977.00 121061.7 2011.17 11.5199 16150369.04 1225361 56517 8.850 0.29 1225921 6266297.87 133534.11 30.765271 118.06 220.907 5.96 338 72.88 2300.7 13374.35 15.5560 16.5884685 40.110 7673.66 301.79 1554 1049.1 103.37 74075244 348099 1278.44 399.56 226.01104 48.877 2770195 73716025 92.08 29.443 2351.5135 378697000 171.30 2474 533 278 6.40719 14.96 52.7214 1.21 13.82 5441.20 7.32 14.93 60.66 11.37 50.914 79315319 6.79 77605627 127.024 506 77658914 82.377 235.16 103696667 205890000 73.8836784 3329 65.63 57.34 69857519 660.336 3265.2 162.329 75381 78454316 2.01 69731166 53018667 803.04 201182 18.8 230.41 4425 14.134 321.29 891.84 69.81 69.80 34.21 233313 149903333 866759 1826 20.81 181519 346114 7.414 5.780 156.773 7.22104 4425.2 239192 198538 5.10 26.25 795966667 20.325 227.39 3.841 5224 248.89 70436 251.80 42.550 2471 404976667 1053 6587 2518.58 882.7 2472 936 16.11 133.168 0.82 612 399 207212 2245.7 38712667 3878 1183 10.963 193.465 186.42 2010.8 2.09 2299.7 2314.7 76809000 122.627 429779 5055 6806 589 2080 11337 6.37806 6.16145 18.9664 18.6633 53.5757 1.20504 1.11577 2.62524 2.38299 422.417 26.8284 37.2714 8.15155 7.51744 64.2827 66.0282 15.1443 7.50080 567.065 1.76349 86.8403 97.9358 10.2115 2.46159 43.38 65.69 183.5 18964400 19.9038 301.57 248.39 364.90 165.285 728.577 1908.3 10.7 220.9 108.64 67.71 110.05 183.64 9036.65 20961.35 47556.69 2123.37 29.55297 154.989 25.252 37.2403 127.931 7477.19 6642.94 13.691 12.481 8106.1545 9.577753 3419833.50 OpenBenchmarking.org
John The Ripper Test: WPA PSK OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 573.94, N = 3 SE +/- 425.10, N = 3 SE +/- 245.32, N = 3 SE +/- 221.78, N = 3 SE +/- 135.70, N = 3 160805 160664 85712 85532 29560 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 1.37, N = 3 SE +/- 1.41, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.54, N = 3 1362.00 1359.29 728.18 723.13 265.83 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.52 13.46 7.19 7.14 2.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 160 320 480 640 800 SE +/- 3.18, N = 3 SE +/- 1.88, N = 3 SE +/- 1.21, N = 3 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 729.84 726.61 392.93 392.23 150.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 3K 6K 9K 12K 15K SE +/- 5.90, N = 3 SE +/- 10.46, N = 3 SE +/- 2.36, N = 3 SE +/- 6.93, N = 3 SE +/- 28.09, N = 3 14289.7 14222.8 7697.3 7692.3 3000.2 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.11, N = 3 3.85 3.87 4.11 4.11 18.22 MIN: 2.35 / MAX: 15.38 MIN: 2.38 / MAX: 13.89 MIN: 2.52 / MAX: 16.5 MIN: 2.45 / MAX: 41.27 MIN: 10.36 / MAX: 177.58 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 7K 14K 21K 28K 35K SE +/- 30.10, N = 3 SE +/- 16.51, N = 3 SE +/- 3.66, N = 3 SE +/- 8.32, N = 3 SE +/- 31.71, N = 3 34850.47 34815.39 18754.59 18615.12 7499.47 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 1.22, N = 3 SE +/- 0.92, N = 3 SE +/- 0.13, N = 3 SE +/- 0.59, N = 3 SE +/- 0.45, N = 3 795.05 794.33 422.62 417.64 174.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: MD5 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 900K 1800K 2700K 3600K 4500K SE +/- 11590.23, N = 3 SE +/- 19341.95, N = 3 SE +/- 7423.69, N = 3 SE +/- 10837.18, N = 3 SE +/- 2504.83, N = 3 4118000 4066667 2234333 2230333 919791 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
John The Ripper Test: HMAC-SHA512 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: HMAC-SHA512 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 40M 80M 120M 160M 200M SE +/- 580393.26, N = 3 SE +/- 877445.98, N = 3 SE +/- 719862.56, N = 3 SE +/- 411753.30, N = 3 SE +/- 518797.01, N = 3 181331000 178283333 117065667 116770333 40721000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 2.20 2.21 2.37 2.37 9.76 MIN: 1.23 / MAX: 12.5 MIN: 1.23 / MAX: 13.12 MIN: 1.26 / MAX: 11.94 MIN: 1.27 / MAX: 12.75 MIN: 4.34 / MAX: 46.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 400 800 1200 1600 2000 SE +/- 0.55, N = 3 SE +/- 0.22, N = 3 SE +/- 0.54, N = 3 SE +/- 0.99, N = 3 SE +/- 2.58, N = 3 1938.68 1938.32 1036.33 1029.88 437.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3K 6K 9K 12K 15K SE +/- 51.53, N = 6 SE +/- 66.74, N = 6 SE +/- 8.66, N = 7 SE +/- 38.56, N = 7 SE +/- 5.11, N = 5 12852.6 12647.5 7792.6 7530.0 2908.5 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
NAMD Input: ATPase with 327,506 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.6274 1.2548 1.8822 2.5096 3.137 SE +/- 0.03311, N = 4 SE +/- 0.01282, N = 3 SE +/- 0.00212, N = 3 SE +/- 0.00243, N = 3 SE +/- 0.00164, N = 3 2.78846 2.74999 1.73764 1.73454 0.65977
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.25, N = 3 SE +/- 0.02, N = 3 136.73 133.65 82.80 82.32 33.74 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 6.99, N = 3 SE +/- 6.25, N = 3 SE +/- 1.03, N = 3 SE +/- 0.66, N = 3 SE +/- 1.96, N = 3 3283.98 3269.12 1791.06 1781.62 816.17 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.03, N = 4 SE +/- 0.17, N = 4 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 49.95 49.81 26.37 26.29 12.45 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 0.84, N = 4 SE +/- 4.15, N = 4 SE +/- 2.35, N = 3 SE +/- 2.56, N = 3 SE +/- 1.56, N = 3 1248.81 1245.30 659.13 657.35 311.31 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 1.54, N = 3 SE +/- 0.90, N = 3 SE +/- 0.43, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 1249.62 1248.08 662.34 658.93 313.74 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 49.99 49.92 26.49 26.36 12.55 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 2.52, N = 3 SE +/- 4.59, N = 3 SE +/- 2.43, N = 3 SE +/- 0.80, N = 3 SE +/- 0.87, N = 3 1556.07 1551.75 834.18 833.73 401.42 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50000M 100000M 150000M 200000M 250000M SE +/- 197196146.33, N = 3 SE +/- 105284888.52, N = 3 SE +/- 48206635.82, N = 3 SE +/- 53677368.01, N = 3 SE +/- 45687236.99, N = 3 251224402513 250497225070 133134074673 132890512590 64812725680 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20000M 40000M 60000M 80000M 100000M SE +/- 63328398.60, N = 3 SE +/- 14328313.13, N = 3 SE +/- 17581304.10, N = 3 SE +/- 11858939.41, N = 3 SE +/- 5622113.45, N = 3 92129622150 91743101110 48632082067 48542739663 23800263020 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50000M 100000M 150000M 200000M 250000M SE +/- 27189836.88, N = 3 SE +/- 47970633.04, N = 3 SE +/- 101608115.02, N = 3 SE +/- 93170961.59, N = 3 SE +/- 5611535.27, N = 3 215336847677 214525919597 113941258877 113843625530 56193249190 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30000M 60000M 90000M 120000M 150000M SE +/- 13732325.68, N = 3 SE +/- 23437434.86, N = 3 SE +/- 32786296.71, N = 3 SE +/- 85172787.78, N = 3 SE +/- 7700475.42, N = 3 129853526473 129320991313 68366108810 68362354417 34651855800 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
NAMD Input: STMV with 1,066,628 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.1702 0.3404 0.5106 0.6808 0.851 SE +/- 0.00230, N = 3 SE +/- 0.00230, N = 3 SE +/- 0.00059, N = 3 SE +/- 0.00121, N = 3 SE +/- 0.00016, N = 3 0.75646 0.74072 0.49345 0.49007 0.20565
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 4.52 4.53 4.82 4.83 15.95 MIN: 2.64 / MAX: 15.69 MIN: 2.65 / MAX: 17.47 MIN: 2.78 / MAX: 17.83 MIN: 2.79 / MAX: 19.86 MIN: 9.85 / MAX: 70.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 400 800 1200 1600 2000 SE +/- 1.19, N = 3 SE +/- 0.97, N = 3 SE +/- 0.30, N = 3 SE +/- 0.43, N = 3 SE +/- 1.52, N = 3 1653.69 1648.32 882.75 879.50 500.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 5 10 15 20 25 SE +/- 0.008, N = 6 SE +/- 0.007, N = 6 SE +/- 0.018, N = 4 SE +/- 0.007, N = 4 SE +/- 0.302, N = 3 6.669 6.691 12.416 12.506 21.095 1. (CXX) g++ options: -O3
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 0.46, N = 3 SE +/- 0.60, N = 3 SE +/- 1.10, N = 3 SE +/- 1.23, N = 3 SE +/- 0.22, N = 3 317.25 302.45 224.43 221.52 101.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1000 2000 3000 4000 5000 SE +/- 5.85, N = 3 SE +/- 1.99, N = 3 SE +/- 5.39, N = 3 SE +/- 1.63, N = 3 SE +/- 3.53, N = 3 4743.73 4734.27 2522.56 2495.55 1559.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 1.23, N = 3 SE +/- 1.94, N = 3 SE +/- 0.86, N = 3 SE +/- 0.72, N = 3 SE +/- 1.17, N = 3 1587.74 1544.55 991.32 980.84 523.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 82.12 82.47 152.68 153.60 245.67 1. (CXX) g++ options: -O3
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.98, N = 3 SE +/- 0.92, N = 5 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.16, N = 3 88.84 86.56 55.11 54.11 29.83 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.47, N = 3 SE +/- 0.61, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 88.32 87.50 54.98 54.23 29.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 0.4673 0.9346 1.4019 1.8692 2.3365 SE +/- 0.009, N = 3 SE +/- 0.006, N = 3 SE +/- 0.005, N = 3 SE +/- 0.023, N = 3 SE +/- 0.030, N = 3 0.709 0.722 1.852 2.051 2.077 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Only EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 200K 400K 600K 800K 1000K SE +/- 14172.11, N = 3 SE +/- 8757.92, N = 3 SE +/- 1154.98, N = 3 SE +/- 4300.20, N = 3 SE +/- 5557.21, N = 3 1128893 1108243 431962 390018 385411 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
LuxCoreRender Scene: Danish Mood - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 11 SE +/- 0.02, N = 3 SE +/- 0.01, N = 15 4.18 4.14 2.10 2.06 1.45 MIN: 1.81 / MAX: 4.75 MIN: 1.71 / MAX: 4.75 MIN: 0.64 / MAX: 2.54 MIN: 0.66 / MAX: 2.48 MIN: 0.39 / MAX: 1.82
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 150 300 450 600 750 SE +/- 2.53, N = 3 SE +/- 3.49, N = 3 SE +/- 1.08, N = 3 SE +/- 0.22, N = 3 SE +/- 0.14, N = 3 701.84 680.56 472.57 465.15 249.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.02548, N = 3 SE +/- 0.00203, N = 3 SE +/- 0.01059, N = 3 SE +/- 0.00260, N = 3 SE +/- 0.00622, N = 3 7.36909 7.31921 3.82321 3.82138 2.63851
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40K 80K 120K 160K 200K SE +/- 369.09, N = 3 SE +/- 110.28, N = 3 SE +/- 299.70, N = 3 SE +/- 835.95, N = 3 SE +/- 900.25, N = 3 170373 168957 88945 87804 61527 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30M 60M 90M 120M 150M SE +/- 342858.26, N = 3 SE +/- 780691.20, N = 3 SE +/- 144351.01, N = 3 SE +/- 112684.33, N = 3 SE +/- 236765.68, N = 3 131218639 130693063 69408254 69366631 47512260 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 7000M 14000M 21000M 28000M 35000M SE +/- 7892274.19, N = 3 SE +/- 8523911.43, N = 3 SE +/- 18056187.30, N = 3 SE +/- 8102567.82, N = 3 SE +/- 27097230.48, N = 3 33989652273 33924881420 17965660883 17876358337 12336557263 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1.0463 2.0926 3.1389 4.1852 5.2315 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 4.65 4.62 2.41 2.41 1.69 MIN: 2.03 / MAX: 5.27 MIN: 2 / MAX: 5.24 MIN: 0.82 / MAX: 2.85 MIN: 0.83 / MAX: 2.84 MIN: 0.51 / MAX: 2.04
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 10.97 11.05 11.72 11.75 30.05 MIN: 5.79 / MAX: 25.09 MIN: 5.83 / MAX: 23.56 MIN: 6 / MAX: 26.83 MIN: 5.98 / MAX: 26.57 MIN: 17.38 / MAX: 87.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/ao/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.00259, N = 3 SE +/- 0.01707, N = 3 SE +/- 0.00682, N = 3 SE +/- 0.01340, N = 3 SE +/- 0.00479, N = 3 7.46649 7.45782 3.91070 3.87827 2.73496
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 0.34, N = 3 SE +/- 0.52, N = 3 SE +/- 1.73, N = 3 SE +/- 1.15, N = 3 SE +/- 8.08, N = 3 556.14 560.14 590.80 592.59 1506.63 MIN: 444.24 / MAX: 578.41 MIN: 538 / MAX: 581.72 MIN: 555.5 / MAX: 623.22 MIN: 531.26 / MAX: 631.27 MIN: 1180.01 / MAX: 1642.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: LBC, LBRY Credits EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3K 6K 9K 12K 15K SE +/- 47.02, N = 3 SE +/- 5.77, N = 3 SE +/- 4.08, N = 3 SE +/- 7.26, N = 3 SE +/- 15.18, N = 3 16317.00 16120.00 8437.93 8389.15 6037.26 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11K 22K 33K 44K 55K SE +/- 49.45, N = 3 SE +/- 47.80, N = 3 SE +/- 67.36, N = 3 SE +/- 19.90, N = 3 SE +/- 38.88, N = 3 49580.07 49485.35 26465.33 26230.85 18507.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.2162 0.4324 0.6486 0.8648 1.081 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.010, N = 3 SE +/- 0.012, N = 3 0.360 0.361 0.899 0.940 0.961 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 500 - Mode: Read Only EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 300K 600K 900K 1200K 1500K SE +/- 3056.15, N = 3 SE +/- 3948.07, N = 3 SE +/- 1617.01, N = 3 SE +/- 5499.26, N = 3 SE +/- 6448.13, N = 3 1388157 1384166 555873 532015 520502 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Barbershop - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 0.46, N = 3 SE +/- 0.08, N = 3 SE +/- 0.87, N = 3 SE +/- 0.87, N = 3 SE +/- 4.06, N = 3 481.15 484.46 925.38 928.10 1281.54
PETSc Test: Streams OpenBenchmarking.org MB/s, More Is Better PETSc 3.19 Test: Streams Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 15K 30K 45K 60K 75K SE +/- 12.95, N = 3 SE +/- 23.59, N = 3 SE +/- 40.69, N = 3 SE +/- 31.25, N = 3 SE +/- 249.54, N = 3 69652.73 41077.63 39918.97 39471.07 26545.71 1. (CC) gcc options: -fPIC -O3 -O2 -lpthread -ludev -lpciaccess -lm
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9M 18M 27M 36M 45M SE +/- 574948.55, N = 15 SE +/- 511472.18, N = 4 SE +/- 160295.89, N = 3 SE +/- 150504.97, N = 15 SE +/- 121681.53, N = 15 44270858 42791247 23143858 22631087 16898291 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 16 32 48 64 80 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.62, N = 3 27.82 27.91 53.08 53.50 72.85 1. (CXX) g++ options: -fopenmp -O2 -march=native
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 4.11, N = 3 SE +/- 3.06, N = 3 SE +/- 0.44, N = 3 SE +/- 0.60, N = 3 SE +/- 2.31, N = 3 2672.51 2669.64 1427.32 1417.33 1022.10 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 20.34 20.37 21.89 21.99 53.07 MIN: 13.65 / MAX: 36.45 MIN: 14.74 / MAX: 35.54 MIN: 14.64 / MAX: 40.37 MIN: 14.99 / MAX: 41.87 MIN: 35.4 / MAX: 130.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 153.97, N = 3 SE +/- 194.99, N = 3 SE +/- 65.97, N = 3 SE +/- 45.75, N = 3 SE +/- 17.95, N = 3 92259.95 92030.35 48803.00 48527.82 35441.71 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: scrypt EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 1.89, N = 3 SE +/- 1.34, N = 3 SE +/- 0.23, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 310.84 308.21 163.88 162.88 119.86 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 0.6557 1.3114 1.9671 2.6228 3.2785 SE +/- 0.00269, N = 4 SE +/- 0.00498, N = 4 SE +/- 0.00306, N = 4 SE +/- 0.00536, N = 4 SE +/- 0.01544, N = 4 1.13000 1.13203 1.98773 1.99986 2.91408 MIN: 1.03 MIN: 1.03 MIN: 1.84 MIN: 1.85 MIN: 2.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-HEVC Tuning: 1 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1.305 2.61 3.915 5.22 6.525 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.80 5.74 3.04 3.04 2.26 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Deepcoin EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2K 4K 6K 8K 10K SE +/- 3.98, N = 3 SE +/- 5.77, N = 3 SE +/- 3.81, N = 3 SE +/- 3.02, N = 3 SE +/- 36.27, N = 3 8421.15 8356.74 4405.85 4377.74 3294.49 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Blake-2 S EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 125.03, N = 3 SE +/- 99.39, N = 3 SE +/- 74.24, N = 3 SE +/- 29.06, N = 3 SE +/- 460.90, N = 3 143480 142753 74883 74513 56160 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 26.46 26.44 14.07 13.97 10.41 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 23.10 22.86 12.31 12.28 9.16 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Triple SHA-256, Onecoin EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 73.33, N = 3 SE +/- 146.40, N = 3 SE +/- 5.77, N = 3 SE +/- 8.82, N = 3 SE +/- 3.33, N = 3 97753 97340 51370 51087 38847 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 14.48 14.59 16.73 17.22 36.35 MIN: 8.91 / MAX: 26.44 MIN: 9.42 / MAX: 26.08 MIN: 9.66 / MAX: 30.96 MIN: 10.01 / MAX: 28.19 MIN: 24.38 / MAX: 96.4 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 0.225 0.45 0.675 0.9 1.125 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.40 0.40 0.41 0.41 1.00 MIN: 0.2 / MAX: 8.52 MIN: 0.2 / MAX: 7.69 MIN: 0.21 / MAX: 10.47 MIN: 0.21 / MAX: 10.02 MIN: 0.4 / MAX: 10.73 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Skeincoin EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 7K 14K 21K 28K 35K SE +/- 17.64, N = 3 SE +/- 11.55, N = 3 SE +/- 5.77, N = 3 SE +/- 39.30, N = 3 SE +/- 139.08, N = 3 34753 34640 18060 17983 13933 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenSSL Algorithm: SHA512 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2000M 4000M 6000M 8000M 10000M SE +/- 2951460.39, N = 3 SE +/- 1453158.01, N = 3 SE +/- 1105217.67, N = 3 SE +/- 749962.39, N = 3 SE +/- 2787035.99, N = 3 11041579923 11004843967 5813555230 5794405307 4429397160 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Pabellon Barcelona - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.40, N = 3 SE +/- 0.09, N = 3 SE +/- 1.05, N = 3 165.35 166.82 315.13 316.02 411.15
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Classroom - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 SE +/- 0.38, N = 3 SE +/- 1.57, N = 3 136.11 136.92 259.46 259.85 336.94
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Fishy Cat - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.39, N = 3 SE +/- 0.38, N = 3 SE +/- 0.24, N = 3 66.78 67.34 127.01 127.12 165.00
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Ringcoin EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 800 1600 2400 3200 4000 SE +/- 37.02, N = 5 SE +/- 20.59, N = 3 SE +/- 11.68, N = 3 SE +/- 4.79, N = 3 SE +/- 3.73, N = 3 3541.50 3500.13 1868.89 1851.25 1437.47 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 48.26 48.55 58.43 59.77 118.45 MIN: 29.16 / MAX: 69.56 MIN: 29.96 / MAX: 68.41 MIN: 31.85 / MAX: 94.55 MIN: 40 / MAX: 88.32 MIN: 68.57 / MAX: 244.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 27236.78, N = 3 SE +/- 44904.06, N = 10 SE +/- 59300.10, N = 15 SE +/- 29190.39, N = 3 SE +/- 18366.37, N = 3 5997921.20 5854131.56 4023464.53 2537425.46 2446936.66 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9K 18K 27K 36K 45K SE +/- 19.75, N = 3 SE +/- 24.89, N = 3 SE +/- 127.68, N = 3 SE +/- 82.83, N = 3 SE +/- 172.31, N = 3 17285 17491 37900 38010 42275
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9K 18K 27K 36K 45K SE +/- 33.74, N = 3 SE +/- 11.15, N = 3 SE +/- 43.80, N = 3 SE +/- 115.78, N = 3 SE +/- 112.38, N = 3 17116 17247 37458 37677 41514
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 18.90 19.13 20.09 20.11 45.70 MIN: 13.12 / MAX: 33.09 MIN: 12.57 / MAX: 34 MIN: 13.66 / MAX: 38.02 MIN: 14.53 / MAX: 37.6 MIN: 32.92 / MAX: 117.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 10K 20K 30K 40K 50K SE +/- 29.87, N = 3 SE +/- 13.61, N = 3 SE +/- 62.68, N = 3 SE +/- 61.68, N = 3 SE +/- 115.84, N = 3 20283 20461 43830 44013 48929
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 15.92 15.70 8.62 8.61 6.62
Blender Blend File: Junkshop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Junkshop - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.43, N = 3 SE +/- 0.19, N = 3 SE +/- 0.02, N = 3 72.75 73.73 139.48 139.94 173.17
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 22.02 21.80 12.49 12.48 9.28 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.00353, N = 3 SE +/- 0.00685, N = 3 SE +/- 0.00236, N = 3 SE +/- 0.00132, N = 3 SE +/- 0.00822, N = 3 8.97813 8.92149 4.66757 4.65305 3.79539
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Garlicoin EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 1.95, N = 3 SE +/- 4.61, N = 3 SE +/- 4.36, N = 3 SE +/- 1.43, N = 3 SE +/- 4.51, N = 3 3196.42 3179.32 1691.29 1674.99 1356.31 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
LuxCoreRender Scene: DLSC - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1.125 2.25 3.375 4.5 5.625 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.00 4.96 2.75 2.74 2.13 MIN: 4.85 / MAX: 5.35 MIN: 4.84 / MAX: 5.29 MIN: 2.66 / MAX: 2.86 MIN: 2.66 / MAX: 2.85 MIN: 2.03 / MAX: 2.65
Speedb Test: Random Read OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30M 60M 90M 120M 150M SE +/- 185772.57, N = 3 SE +/- 286737.26, N = 3 SE +/- 103627.09, N = 3 SE +/- 34435.41, N = 3 SE +/- 170759.02, N = 3 135603493 134971626 72087947 71648683 57824426 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 31.37 30.79 16.46 16.33 13.39 MIN: 30.96 / MAX: 32.3 MIN: 30.28 / MAX: 31.99 MIN: 16.24 / MAX: 16.97 MIN: 16.12 / MAX: 16.74 MIN: 13.27 / MAX: 16.49
John The Ripper Test: bcrypt OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 9K 18K 27K 36K 45K SE +/- 104.20, N = 3 SE +/- 61.43, N = 3 SE +/- 45.41, N = 3 SE +/- 43.32, N = 3 SE +/- 127.68, N = 3 43695 43512 23271 23235 18787 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9K 18K 27K 36K 45K SE +/- 39.87, N = 3 SE +/- 344.23, N = 3 SE +/- 44.47, N = 3 SE +/- 121.86, N = 3 SE +/- 68.54, N = 3 43795 42924 23243 23174 18841 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: BMW27 - Compute: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 0.33, N = 3 SE +/- 0.18, N = 3 53.25 53.56 101.52 101.72 123.51
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Magi EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 140 280 420 560 700 SE +/- 7.55, N = 4 SE +/- 0.26, N = 3 SE +/- 0.10, N = 3 SE +/- 0.30, N = 3 SE +/- 0.39, N = 3 644.74 633.44 332.40 330.62 278.09 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Quad SHA-256, Pyrite EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 13K 26K 39K 52K 65K SE +/- 331.71, N = 3 SE +/- 297.56, N = 3 SE +/- 5.77, N = 3 SE +/- 78.81, N = 3 SE +/- 3.33, N = 3 61360 61347 32010 31903 26527 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Java SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Fast Fourier Transform Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 200 400 600 800 1000 SE +/- 8.67, N = 3 SE +/- 0.60, N = 3 SE +/- 3.44, N = 3 SE +/- 0.41, N = 3 SE +/- 0.73, N = 3 1023.23 470.91 453.05 450.10 443.49
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.07, N = 4 SE +/- 0.05, N = 4 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 46.41 45.87 26.73 26.65 20.17
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.00488, N = 3 SE +/- 0.01295, N = 3 SE +/- 0.01491, N = 3 SE +/- 0.00421, N = 3 SE +/- 0.02381, N = 3 2.98654 3.00636 3.87665 3.91089 6.85318 MIN: 2.41 MIN: 2.4 MIN: 3.48 MIN: 3.5 MIN: 3.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 2.08, N = 3 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 2.73, N = 3 SE +/- 2.33, N = 3 1080 1090 2156 2171 2474
Stress-NG Test: AVX-512 VNNI OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVX-512 VNNI EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 600K 1200K 1800K 2400K 3000K SE +/- 3334.21, N = 3 SE +/- 2539.18, N = 3 SE +/- 1569.35, N = 3 SE +/- 1225.91, N = 3 SE +/- 5501.16, N = 3 2572055.58 2571394.82 1376354.00 1371242.64 1125583.01 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 1.00, N = 3 SE +/- 1.15, N = 3 SE +/- 1.76, N = 3 SE +/- 2.19, N = 3 SE +/- 0.88, N = 3 1069 1078 2133 2143 2441
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 0.33, N = 3 SE +/- 1.53, N = 3 SE +/- 4.04, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 1265 1275 2526 2539 2884
RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 900K 1800K 2700K 3600K 4500K SE +/- 13356.72, N = 3 SE +/- 7045.87, N = 3 SE +/- 22460.23, N = 3 SE +/- 15255.97, N = 3 SE +/- 3646.67, N = 3 4368397 4294631 2519594 2476441 1942760 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 10 20 30 40 50 SE +/- 0.08, N = 4 SE +/- 0.07, N = 4 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 42.60 42.20 25.32 25.25 18.97
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 169.22, N = 3 SE +/- 103.02, N = 3 SE +/- 56.56, N = 3 SE +/- 49.82, N = 3 SE +/- 294.52, N = 3 83365.1 83133.5 44058.2 43490.7 37214.4 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200K 400K 600K 800K 1000K SE +/- 2950.54, N = 3 SE +/- 9073.63, N = 3 SE +/- 1288.71, N = 3 SE +/- 1076.82, N = 3 SE +/- 3256.58, N = 15 954988.73 951674.51 505633.42 499103.50 430017.46 1. (CC) gcc options: -O2 -lrt" -lrt
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 17.79 18.02 25.15 26.38 39.48 MIN: 9.38 / MAX: 30.36 MIN: 11.1 / MAX: 33.13 MIN: 11.63 / MAX: 50.5 MIN: 13.08 / MAX: 46.13 MIN: 22.02 / MAX: 90.7 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: AlexNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 1.74, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.55, N = 3 SE +/- 0.02, N = 3 425.47 422.88 240.74 240.23 192.28
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.08, N = 5 SE +/- 0.03, N = 5 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 54.54 54.07 32.09 31.86 24.69
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 2.19, N = 3 SE +/- 1.91, N = 3 SE +/- 2.00, N = 3 SE +/- 7.18, N = 3 SE +/- 6.38, N = 3 703.75 706.65 1329.68 1337.47 1548.71 MIN: 675.7 MIN: 679.48 MIN: 1297.27 MIN: 1299.81 MIN: 1512.56 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Helsing Digit Range: 14 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 0.45, N = 3 SE +/- 0.37, N = 3 SE +/- 0.35, N = 3 SE +/- 0.18, N = 3 SE +/- 0.23, N = 3 199.83 200.77 372.10 375.92 437.41 1. (CC) gcc options: -O2 -pthread
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 6.0 Mode: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9K 18K 27K 36K 45K SE +/- 204.38, N = 3 SE +/- 38.48, N = 3 SE +/- 11.00, N = 3 SE +/- 57.13, N = 3 SE +/- 16.84, N = 3 43879 43567 23078 23056 20060
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 14 28 42 56 70 SE +/- 0.07, N = 5 SE +/- 0.07, N = 5 SE +/- 0.02, N = 4 SE +/- 0.05, N = 4 SE +/- 0.31, N = 4 62.56 62.23 38.85 38.82 28.64 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 1.43, N = 3 SE +/- 3.18, N = 3 SE +/- 1.64, N = 3 SE +/- 3.90, N = 3 SE +/- 9.27, N = 3 1348.37 1354.12 2491.14 2496.65 2931.95 MIN: 1314.05 MIN: 1317.27 MIN: 2459.9 MIN: 2449.87 MIN: 2882.15 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 21.7.2 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 0.68, N = 3 SE +/- 0.94, N = 3 SE +/- 0.37, N = 3 SE +/- 0.38, N = 3 SE +/- 1.08, N = 3 421.43 427.64 737.29 739.34 915.94
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 100 200 300 400 500 SE +/- 1.94, N = 3 SE +/- 1.58, N = 3 SE +/- 0.50, N = 3 SE +/- 1.13, N = 3 SE +/- 0.28, N = 3 476.63 462.96 275.72 273.50 219.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 409.96 405.64 237.76 237.57 189.14
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 61.02, N = 3 SE +/- 126.32, N = 3 SE +/- 152.10, N = 3 SE +/- 128.55, N = 3 SE +/- 34.91, N = 3 38192 38454 72250 72906 82403
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 101.69, N = 3 SE +/- 146.12, N = 3 SE +/- 273.73, N = 3 SE +/- 59.04, N = 3 SE +/- 76.92, N = 3 44247 44561 84209 84611 95447
LuxCoreRender Scene: Orange Juice - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 7.72 7.70 4.42 4.42 3.58 MIN: 6.87 / MAX: 8.15 MIN: 6.73 / MAX: 8.14 MIN: 4.32 / MAX: 4.49 MIN: 4.35 / MAX: 4.49 MIN: 3.44 / MAX: 4.42
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 168.15, N = 3 SE +/- 192.07, N = 3 SE +/- 145.56, N = 3 SE +/- 135.51, N = 3 SE +/- 135.20, N = 3 37923 37984 71530 72067 81236
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 152.30 153.37 263.51 264.55 323.27
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 0.38, N = 3 SE +/- 0.17, N = 3 SE +/- 0.32, N = 3 SE +/- 0.19, N = 3 SE +/- 0.63, N = 3 714.38 717.71 1310.96 1312.35 1508.04
OpenVKL Benchmark: vklBenchmarkCPU ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 130 260 390 520 650 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 2.52, N = 3 SE +/- 0.33, N = 3 603 596 331 327 288 MIN: 48 / MAX: 8450 MIN: 47 / MAX: 8430 MIN: 25 / MAX: 4820 MIN: 25 / MAX: 4775 MIN: 20 / MAX: 4338
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.09, N = 4 SE +/- 0.06, N = 4 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 48.11 47.67 31.05 31.04 23.05 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 4.78 4.78 5.12 5.13 9.94 MIN: 3.25 / MAX: 16.12 MIN: 3.18 / MAX: 16.31 MIN: 3.61 / MAX: 15.43 MIN: 3.4 / MAX: 14.3 MIN: 6.2 / MAX: 41.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-HEVC Tuning: 7 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.06, N = 6 SE +/- 0.08, N = 6 SE +/- 0.04, N = 5 SE +/- 0.07, N = 5 SE +/- 0.08, N = 4 99.61 97.70 57.23 56.95 47.98 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.010, N = 9 SE +/- 0.008, N = 8 SE +/- 0.030, N = 6 SE +/- 0.009, N = 6 SE +/- 0.089, N = 15 3.037 3.164 5.990 6.166 6.278 1. (CXX) g++ options: -O3 -fopenmp
RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Fill Sync Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 40K 80K 120K 160K 200K SE +/- 710.34, N = 3 SE +/- 270.54, N = 3 SE +/- 414.30, N = 3 SE +/- 48.85, N = 3 SE +/- 196.51, N = 3 201594 171199 170735 99746 98054 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.07, N = 6 SE +/- 0.08, N = 6 SE +/- 0.04, N = 4 SE +/- 0.05, N = 4 SE +/- 0.30, N = 10 81.23 80.50 52.30 52.25 39.59 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 85.32 85.93 156.07 156.37 174.95
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.1935 0.387 0.5805 0.774 0.9675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.86 0.85 0.48 0.48 0.42
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.1935 0.387 0.5805 0.774 0.9675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.86 0.85 0.48 0.48 0.42
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 13K 26K 39K 52K 65K SE +/- 131.10, N = 3 SE +/- 261.75, N = 3 SE +/- 415.80, N = 3 SE +/- 404.29, N = 3 SE +/- 378.33, N = 3 59053.01 59037.14 30936.50 30715.14 28846.06 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.38.2 VGR Performance Metric EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90K 180K 270K 360K 450K 397138 394575 229365 226198 194127 1. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6
Java JMH Throughput OpenBenchmarking.org Ops/s, More Is Better Java JMH Throughput EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 16000M 32000M 48000M 64000M 80000M 75186159786.82 75134161573.04 38776376503.47 38717919571.11 36765943472.27
JPEG-XL libjxl Input: PNG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 27.75 27.56 16.69 16.66 13.65 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
Helsing Digit Range: 12 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 12 digit EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 0.918 1.836 2.754 3.672 4.59 SE +/- 0.002, N = 10 SE +/- 0.003, N = 11 SE +/- 0.004, N = 8 SE +/- 0.004, N = 8 SE +/- 0.028, N = 15 2.011 2.016 3.753 3.828 4.080 1. (CC) gcc options: -O2 -pthread
Speedb Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 22040.69, N = 3 SE +/- 26941.48, N = 3 SE +/- 13925.00, N = 3 SE +/- 14207.26, N = 3 SE +/- 20209.24, N = 3 5146187 5119891 3212276 3194971 2548837 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
JPEG-XL libjxl Input: JPEG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 27.22 26.96 16.58 16.52 13.48 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 16 32 48 64 80 SE +/- 0.15, N = 5 SE +/- 0.25, N = 5 SE +/- 0.10, N = 4 SE +/- 0.02, N = 4 SE +/- 0.30, N = 3 72.74 71.14 47.29 46.84 36.14 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.025811, N = 10 SE +/- 0.023270, N = 9 SE +/- 0.045809, N = 15 SE +/- 0.045334, N = 15 SE +/- 0.044479, N = 6 3.299879 3.325543 6.154460 6.176853 6.612486 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: x86_64 RdRand EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2M 4M 6M 8M 10M SE +/- 980.70, N = 3 SE +/- 6736.08, N = 3 SE +/- 1009.93, N = 3 SE +/- 788.85, N = 3 SE +/- 7.65, N = 3 8497821.55 8469095.71 4400145.01 4374980.16 81538.34 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 10K 20K 30K 40K 50K SE +/- 110.88, N = 3 SE +/- 553.44, N = 3 SE +/- 96.46, N = 3 SE +/- 14.25, N = 3 SE +/- 21.68, N = 3 44844.13 43371.78 28326.36 22935.27 22551.09 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
DaCapo Benchmark Java Test: Apache Tomcat OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Tomcat EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1400 2800 4200 5600 7000 SE +/- 4.40, N = 4 SE +/- 2.95, N = 4 SE +/- 2.73, N = 3 SE +/- 9.21, N = 3 SE +/- 14.71, N = 3 3367 3370 6467 6482 6687
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1100 2200 3300 4400 5500 SE +/- 41.40, N = 6 SE +/- 38.41, N = 6 SE +/- 24.04, N = 8 SE +/- 11.75, N = 6 SE +/- 25.17, N = 5 5073.23 4886.94 2739.34 2703.36 2556.22 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 6.1 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.33, N = 3 25.30 25.54 42.20 42.47 50.05
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Rotate Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 70 140 210 280 350 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.53, N = 3 SE +/- 0.67, N = 3 317 169 168 167 161 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 SE +/- 0.21, N = 4 SE +/- 0.15, N = 15 34.65 34.13 19.48 17.73 17.61 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 150 300 450 600 750 SE +/- 0.24, N = 3 SE +/- 0.22, N = 3 SE +/- 0.77, N = 3 SE +/- 0.50, N = 3 SE +/- 0.51, N = 3 354.76 360.46 636.83 643.22 697.94
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 3 6 9 12 15 SE +/- 0.00600, N = 3 SE +/- 0.00268, N = 3 SE +/- 0.00839, N = 3 SE +/- 0.00129, N = 3 SE +/- 0.05544, N = 4 8.98399 8.81078 5.93161 4.63828 4.58353
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.00611, N = 5 SE +/- 0.00590, N = 5 SE +/- 0.02020, N = 5 SE +/- 0.00833, N = 5 SE +/- 0.01930, N = 5 3.88685 4.07056 4.61211 4.67840 7.59695 MIN: 3.57 MIN: 3.76 MIN: 4.4 MIN: 4.46 MIN: 7.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.0923 0.1846 0.2769 0.3692 0.4615 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.41 0.40 0.23 0.23 0.21
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 3 6 9 12 15 SE +/- 0.00296, N = 3 SE +/- 0.00801, N = 3 SE +/- 0.00749, N = 3 SE +/- 0.00354, N = 3 SE +/- 0.00347, N = 3 8.98195 8.81722 5.88640 4.64920 4.61871
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 32.22 31.58 18.45 18.35 16.58 MIN: 31.88 / MAX: 33.23 MIN: 31.27 / MAX: 32.45 MIN: 18.3 / MAX: 18.87 MIN: 18.21 / MAX: 18.8 MIN: 16.29 / MAX: 19.34
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Medium EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 30 60 90 120 150 SE +/- 0.18, N = 5 SE +/- 0.09, N = 5 SE +/- 0.00, N = 3 SE +/- 0.05, N = 4 SE +/- 0.04, N = 4 154.72 153.70 89.14 80.53 79.60 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Test: Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Floating Point EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 2K 4K 6K 8K 10K SE +/- 8.60, N = 3 SE +/- 15.20, N = 3 SE +/- 7.41, N = 3 SE +/- 2.36, N = 3 SE +/- 6.00, N = 3 8242.96 8199.65 4740.28 4283.48 4251.39 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 13 26 39 52 65 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 58 57 36 31 30 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 80 160 240 320 400 SE +/- 0.40, N = 3 SE +/- 0.56, N = 3 SE +/- 0.15, N = 3 SE +/- 0.20, N = 3 SE +/- 0.34, N = 3 188.53 191.08 326.16 329.18 364.42
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 4K 8K 12K 16K 20K SE +/- 12.64, N = 3 SE +/- 12.57, N = 3 SE +/- 104.90, N = 3 SE +/- 3.63, N = 3 SE +/- 2.63, N = 3 16537.83 16452.47 9138.29 8606.94 8556.72 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Xmrig Variant: GhostRider - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 22.46, N = 3 SE +/- 4.40, N = 3 SE +/- 3.35, N = 3 SE +/- 10.83, N = 3 SE +/- 5.04, N = 3 3266.9 3239.4 1742.9 1699.3 1690.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 90 180 270 360 450 SE +/- 0.54, N = 4 SE +/- 0.65, N = 4 SE +/- 0.04, N = 3 SE +/- 0.35, N = 3 SE +/- 0.29, N = 3 392.24 388.63 205.93 204.84 203.10 1. (CXX) g++ options: -O3 -flto -pthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 80K 160K 240K 320K 400K SE +/- 143.01, N = 3 SE +/- 28.66, N = 3 SE +/- 1626.68, N = 3 SE +/- 20.61, N = 3 SE +/- 1102.39, N = 3 373632.3 372775.0 195618.8 194210.3 193565.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Stress-NG Test: Fused Multiply-Add OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Fused Multiply-Add EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12M 24M 36M 48M 60M SE +/- 59842.82, N = 3 SE +/- 500794.58, N = 3 SE +/- 28572.99, N = 3 SE +/- 252666.10, N = 3 SE +/- 267691.10, N = 3 57429956.15 56410032.25 30389834.82 29927440.69 29762395.57 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Swirl EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 250 246 139 138 130 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
ASTC Encoder Preset: Very Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Very Thorough EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.6039 1.2078 1.8117 2.4156 3.0195 SE +/- 0.0093, N = 3 SE +/- 0.0070, N = 3 SE +/- 0.0116, N = 3 SE +/- 0.0023, N = 3 SE +/- 0.0010, N = 3 2.6841 2.6608 1.4639 1.4109 1.3979 1. (CXX) g++ options: -O3 -flto -pthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 94 93 50 50 49 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Exhaustive EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.3688 0.7376 1.1064 1.4752 1.844 SE +/- 0.0020, N = 3 SE +/- 0.0018, N = 3 SE +/- 0.0051, N = 3 SE +/- 0.0007, N = 3 SE +/- 0.0000, N = 3 1.6391 1.6262 0.8741 0.8633 0.8557 1. (CXX) g++ options: -O3 -flto -pthread
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 7.95 8.03 9.90 10.18 15.21 MIN: 5 / MAX: 23.85 MIN: 5.57 / MAX: 23.51 MIN: 6.53 / MAX: 37.69 MIN: 5.82 / MAX: 38.39 MIN: 10.08 / MAX: 64.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 8.44 8.57 11.36 11.72 16.04 MIN: 4.55 / MAX: 19.23 MIN: 3.77 / MAX: 23.35 MIN: 4.12 / MAX: 36.81 MIN: 4.13 / MAX: 31.49 MIN: 9.49 / MAX: 56.98 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 200K 400K 600K 800K 1000K SE +/- 1012.30, N = 3 SE +/- 1811.04, N = 3 SE +/- 373.64, N = 3 SE +/- 313.30, N = 3 SE +/- 205.90, N = 3 781906.97 778238.33 576480.15 416118.50 413926.82 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
uvg266 Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.16, N = 9 SE +/- 0.19, N = 9 SE +/- 0.07, N = 7 SE +/- 0.08, N = 7 SE +/- 0.97, N = 15 181.83 180.54 120.30 119.83 96.33
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.36, N = 3 SE +/- 0.42, N = 3 SE +/- 0.32, N = 3 SE +/- 0.32, N = 3 SE +/- 0.45, N = 3 57.47 57.93 97.41 97.92 108.34
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 27.39 26.88 15.69 15.57 14.55 MIN: 27.11 / MAX: 28.25 MIN: 26.58 / MAX: 27.83 MIN: 15.56 / MAX: 16.03 MIN: 15.43 / MAX: 15.99 MIN: 14.14 / MAX: 16.68
uvg266 Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.11, N = 9 SE +/- 0.14, N = 9 SE +/- 0.05, N = 7 SE +/- 0.14, N = 7 SE +/- 0.95, N = 15 166.81 165.55 112.05 111.78 89.31
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 24.0 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 8 16 24 32 40 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 17.46 17.73 28.20 28.26 32.52
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 1B EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.21, N = 3 18.21 18.80 25.24 25.46 33.89
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Unix Makefiles EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 160 320 480 640 800 SE +/- 1.00, N = 3 SE +/- 1.22, N = 3 SE +/- 0.38, N = 3 SE +/- 0.98, N = 3 SE +/- 0.50, N = 3 387.01 395.19 662.52 670.27 719.39
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: AlexNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 0.34, N = 3 SE +/- 0.14, N = 3 SE +/- 0.21, N = 3 SE +/- 0.21, N = 3 SE +/- 0.21, N = 3 322.53 316.11 206.40 205.32 173.78
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 0.26, N = 10 SE +/- 0.34, N = 10 SE +/- 0.16, N = 8 SE +/- 0.21, N = 8 SE +/- 2.05, N = 15 311.95 307.89 178.68 178.20 168.39 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.49, N = 3 72.11 72.42 107.79 108.65 133.57 1. (CXX) g++ options: -O3 -fPIC -lm
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.48, N = 3 SE +/- 0.63, N = 3 SE +/- 0.77, N = 3 72.70 73.71 90.49 91.34 134.54 MIN: 40.38 / MAX: 84.07 MIN: 31.23 / MAX: 89.7 MIN: 55.81 / MAX: 127.95 MIN: 68.51 / MAX: 134.9 MIN: 98.92 / MAX: 233.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 1.01, N = 3 SE +/- 1.00, N = 5 SE +/- 0.73, N = 3 72.52 73.87 89.98 92.38 133.99 MIN: 28.47 / MAX: 87.6 MIN: 36.14 / MAX: 99.53 MIN: 63.39 / MAX: 124.53 MIN: 31.8 / MAX: 128.67 MIN: 103.21 / MAX: 233.72 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 60M 120M 180M 240M 300M SE +/- 520000.00, N = 3 SE +/- 2047567.66, N = 3 SE +/- 176162.80, N = 3 SE +/- 75055.53, N = 3 SE +/- 1245404.89, N = 3 292390000 286960000 212960000 211670000 159270000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.010, N = 9 SE +/- 0.018, N = 9 SE +/- 0.007, N = 7 SE +/- 0.014, N = 7 SE +/- 0.088, N = 15 3.421 3.447 5.301 5.338 6.260 1. (CXX) g++ options: -O3 -fPIC -lm
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 800K 1600K 2400K 3200K 4000K SE +/- 3096.61, N = 3 SE +/- 5665.65, N = 3 SE +/- 11523.53, N = 3 SE +/- 1526.11, N = 3 SE +/- 1471.26, N = 3 3850014.66 3844031.28 3048853.56 2124192.99 2104490.55 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.06, N = 5 SE +/- 0.11, N = 5 SE +/- 0.04, N = 4 SE +/- 0.01, N = 4 SE +/- 0.03, N = 3 16.98 16.94 11.93 11.89 9.35 MIN: 15.46 / MAX: 17.3 MIN: 15.4 / MAX: 17.31 MIN: 11.1 / MAX: 12.12 MIN: 11.05 / MAX: 12 MIN: 8.52 / MAX: 10.72
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 130 260 390 520 650 SE +/- 2.52, N = 3 SE +/- 4.48, N = 9 SE +/- 8.95, N = 9 SE +/- 10.02, N = 7 SE +/- 5.87, N = 9 322.67 349.91 538.42 582.32 585.75
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.25, N = 9 SE +/- 0.24, N = 9 SE +/- 0.08, N = 8 SE +/- 0.10, N = 8 SE +/- 0.87, N = 7 186.56 184.98 129.55 129.02 103.04 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.009, N = 3 SE +/- 0.016, N = 3 SE +/- 0.016, N = 3 SE +/- 0.014, N = 3 SE +/- 0.024, N = 3 7.838 7.831 5.742 5.711 4.348 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Java SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Monte Carlo EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 32.12, N = 3 SE +/- 19.82, N = 3 SE +/- 17.64, N = 3 SE +/- 26.32, N = 3 SE +/- 0.88, N = 3 2570.60 2541.20 2529.18 2456.47 1426.11
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 80 160 240 320 400 SE +/- 0.69, N = 3 SE +/- 3.68, N = 3 SE +/- 1.58, N = 3 SE +/- 0.89, N = 3 SE +/- 1.45, N = 3 386.41 380.82 325.21 322.61 214.55 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40K 80K 120K 160K 200K SE +/- 313.05, N = 3 SE +/- 227.16, N = 3 SE +/- 195.02, N = 3 SE +/- 118.34, N = 3 SE +/- 436.66, N = 3 170888 167186 103571 101849 94990 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
TensorFlow Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 41.02 39.73 30.70 30.41 22.98
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.5722 1.1444 1.7166 2.2888 2.861 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 2.543 2.468 1.546 1.526 1.434 1. (CXX) g++ options: -O3 -lm
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 40.68 39.37 30.63 30.33 23.07
Speedb Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Fill Sync Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 50K 100K 150K 200K 250K SE +/- 573.89, N = 3 SE +/- 238.71, N = 3 SE +/- 490.37, N = 3 SE +/- 257.69, N = 3 SE +/- 468.76, N = 3 225607 171623 170365 128855 127955 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
uvg266 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.20, N = 9 SE +/- 0.15, N = 9 SE +/- 0.14, N = 8 SE +/- 0.06, N = 8 SE +/- 1.21, N = 15 203.39 201.92 143.28 142.97 115.40
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 1.10, N = 3 SE +/- 0.42, N = 3 SE +/- 1.26, N = 3 SE +/- 0.18, N = 3 SE +/- 0.57, N = 3 133.32 132.29 93.16 91.59 75.88 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
SPECFEM3D Model: Tomographic Model OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Tomographic Model EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.20, N = 15 SE +/- 0.37, N = 3 SE +/- 0.38, N = 3 SE +/- 0.48, N = 3 SE +/- 0.06, N = 3 30.13 30.49 46.58 49.58 52.89 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
uvg266 Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 14 28 42 56 70 SE +/- 0.07, N = 5 SE +/- 0.05, N = 5 SE +/- 0.07, N = 4 SE +/- 0.03, N = 4 SE +/- 0.14, N = 4 64.16 63.89 45.75 45.63 36.59
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 4K 8K 12K 16K 20K SE +/- 253.63, N = 3 SE +/- 211.58, N = 3 SE +/- 44.80, N = 3 SE +/- 12.84, N = 3 SE +/- 48.58, N = 3 18660.90 18360.82 12750.97 11152.31 10661.66 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.08, N = 6 SE +/- 0.15, N = 6 SE +/- 0.04, N = 5 SE +/- 0.04, N = 5 SE +/- 0.37, N = 4 88.30 87.51 64.80 64.68 50.47 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: GoogLeNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 132.62 129.06 91.90 91.07 76.13
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 40.24 39.07 30.53 30.22 23.10
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 500M EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.010, N = 5 SE +/- 0.013, N = 5 SE +/- 0.040, N = 4 SE +/- 0.036, N = 4 SE +/- 0.124, N = 4 8.652 8.920 11.555 11.589 14.926
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 39.99 38.96 30.79 30.52 23.19
SPECFEM3D Model: Layered Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Layered Halfspace EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 SE +/- 0.89, N = 3 SE +/- 0.49, N = 3 SE +/- 1.26, N = 3 83.97 86.00 130.53 133.31 144.54 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 132.13 128.54 91.77 90.98 76.84
Memcached Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 800K 1600K 2400K 3200K 4000K SE +/- 5916.60, N = 3 SE +/- 5303.54, N = 3 SE +/- 7388.22, N = 3 SE +/- 1626.82, N = 3 SE +/- 2761.61, N = 3 3775389.09 3761626.61 3072373.87 2217988.24 2195688.49 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: GoogLeNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 135.30 131.79 93.71 92.82 78.79
nginx Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 126.64, N = 3 SE +/- 288.60, N = 3 SE +/- 191.32, N = 3 SE +/- 173.47, N = 3 SE +/- 239.98, N = 3 156935.63 154835.06 94947.75 92582.29 91505.24 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 100 200 300 400 500 SE +/- 0.80, N = 3 SE +/- 0.46, N = 3 SE +/- 0.34, N = 3 SE +/- 0.18, N = 3 SE +/- 0.89, N = 3 273.49 277.73 432.22 436.05 468.38
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: GoogLeNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 133.21 129.59 92.37 91.42 78.17
nginx Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 536.64, N = 3 SE +/- 301.50, N = 3 SE +/- 46.60, N = 3 SE +/- 98.21, N = 3 SE +/- 52.64, N = 3 144355.05 136360.72 87132.22 85990.12 84772.31 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 36.33 36.34 51.38 51.94 61.84 1. (CXX) g++ options: -O3 -fPIC -lm
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 119 116 76 76 70 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenFOAM Input: drivaerFastback, Small Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 70 140 210 280 350 183.23 199.88 242.94 296.60 311.36 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 102.15 102.74 142.94 143.38 173.41
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 90 180 270 360 450 SE +/- 0.58, N = 11 SE +/- 0.22, N = 11 SE +/- 0.18, N = 10 SE +/- 0.20, N = 10 SE +/- 0.20, N = 10 408.42 398.58 289.26 242.58 240.66 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SPECFEM3D Model: Homogeneous Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Homogeneous Halfspace EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 15 30 45 60 75 SE +/- 0.28, N = 3 SE +/- 0.10, N = 3 SE +/- 0.66, N = 3 SE +/- 0.35, N = 3 SE +/- 0.41, N = 3 39.56 39.92 57.79 63.87 67.11 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 6.39, N = 3 SE +/- 14.04, N = 3 SE +/- 6.45, N = 3 SE +/- 6.80, N = 3 SE +/- 4.57, N = 3 3033.56 2387.89 2291.85 1806.71 1791.99 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 1.42, N = 15 SE +/- 1.37, N = 15 SE +/- 0.56, N = 5 SE +/- 0.50, N = 5 SE +/- 0.47, N = 15 100.00 97.12 61.90 61.45 59.56 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 90 180 270 360 450 SE +/- 0.42, N = 11 SE +/- 0.27, N = 11 SE +/- 0.53, N = 10 SE +/- 0.28, N = 10 SE +/- 0.36, N = 10 419.26 408.36 295.69 251.44 249.86 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
DaCapo Benchmark Java Test: Avrora AVR Simulation Framework OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Avrora AVR Simulation Framework Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 2.49, N = 8 SE +/- 20.96, N = 6 SE +/- 21.04, N = 8 SE +/- 3.26, N = 6 SE +/- 3.46, N = 6 1451 2359 2393 2415 2430
nginx Connections: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 150.85, N = 3 SE +/- 223.05, N = 3 SE +/- 127.61, N = 3 SE +/- 204.87, N = 3 SE +/- 231.66, N = 3 162348.33 162256.48 101214.88 100527.89 98692.95 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 6.27, N = 9 SE +/- 6.44, N = 9 SE +/- 1.88, N = 3 SE +/- 1.37, N = 3 SE +/- 3.15, N = 3 793.8 778.5 520.3 513.9 485.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.1408 2.2816 3.4224 4.5632 5.704 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 3.13 3.16 3.32 3.33 5.07 MIN: 1.79 / MAX: 14.78 MIN: 1.77 / MAX: 13.91 MIN: 1.82 / MAX: 16.13 MIN: 1.88 / MAX: 15.67 MIN: 2.36 / MAX: 27.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.33, N = 8 SE +/- 0.69, N = 8 SE +/- 0.14, N = 7 SE +/- 0.15, N = 7 SE +/- 1.00, N = 15 170.21 164.85 125.28 123.64 105.28 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ScyllaDB Test: Writes OpenBenchmarking.org Op/s, More Is Better ScyllaDB 5.2.9 Test: Writes EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 30K 60K 90K 120K 150K SE +/- 78.75, N = 3 SE +/- 255.51, N = 3 SE +/- 395.91, N = 3 SE +/- 446.24, N = 3 SE +/- 60.93, N = 3 151849 151729 104832 94899 94217
SPECFEM3D Model: Mount St. Helens OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Mount St. Helens EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.29, N = 15 SE +/- 0.33, N = 3 SE +/- 0.33, N = 15 SE +/- 0.25, N = 3 SE +/- 0.34, N = 3 33.13 34.80 49.54 51.29 53.29 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Jython Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 800 1600 2400 3200 4000 SE +/- 14.73, N = 5 SE +/- 16.55, N = 4 SE +/- 14.78, N = 4 SE +/- 15.77, N = 4 SE +/- 34.16, N = 4 2433 3762 3790 3795 3871
SPECFEM3D Model: Water-layered Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Water-layered Halfspace EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.26, N = 3 SE +/- 0.42, N = 3 SE +/- 0.40, N = 3 SE +/- 0.21, N = 3 85.25 87.86 129.33 129.55 135.42 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 3.49, N = 3 SE +/- 3.67, N = 3 SE +/- 0.95, N = 3 SE +/- 0.67, N = 3 SE +/- 1.12, N = 3 797.0 778.8 527.9 518.5 504.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.29, N = 9 SE +/- 0.22, N = 9 SE +/- 0.13, N = 8 SE +/- 0.12, N = 8 SE +/- 1.11, N = 15 189.41 187.54 148.34 147.31 120.53 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.058, N = 3 SE +/- 0.061, N = 3 SE +/- 0.021, N = 3 SE +/- 0.024, N = 3 SE +/- 0.018, N = 3 7.818 7.746 5.693 5.681 4.975 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 120 240 360 480 600 SE +/- 1.04, N = 12 SE +/- 1.05, N = 12 SE +/- 4.53, N = 15 SE +/- 0.24, N = 11 SE +/- 0.26, N = 11 560.81 545.31 383.64 361.05 358.54 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.14, N = 8 SE +/- 0.15, N = 8 SE +/- 0.12, N = 6 SE +/- 0.10, N = 6 SE +/- 1.10, N = 15 158.94 153.78 109.03 107.65 101.83 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
CockroachDB Workload: KV, 50% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 831.25, N = 3 SE +/- 764.38, N = 3 SE +/- 103.24, N = 3 SE +/- 264.18, N = 3 SE +/- 189.35, N = 3 92195.2 90528.3 64458.4 64052.7 59866.6
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.26, N = 3 16.10 16.16 23.20 24.50 24.76 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Write EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 11K 22K 33K 44K 55K SE +/- 155.76, N = 3 SE +/- 481.81, N = 3 SE +/- 85.58, N = 3 SE +/- 123.75, N = 3 SE +/- 337.25, N = 3 49683 49522 34486 32657 32316 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Dragonflydb Clients Per Thread: 10 - Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.5M 3M 4.5M 6M 7.5M SE +/- 57648.71, N = 9 SE +/- 34452.25, N = 3 SE +/- 16892.77, N = 3 SE +/- 6458.55, N = 3 SE +/- 43112.16, N = 3 7046043.06 6289782.08 4818585.25 4762998.42 4604951.36 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
JPEG-XL libjxl Input: PNG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.28, N = 3 SE +/- 0.68, N = 3 SE +/- 0.21, N = 3 SE +/- 0.36, N = 3 SE +/- 0.19, N = 3 48.53 47.23 36.04 36.02 31.81 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 4.41, N = 3 SE +/- 4.40, N = 3 SE +/- 3.70, N = 3 SE +/- 1.59, N = 3 SE +/- 4.53, N = 3 895.77 894.66 676.65 674.51 587.73 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.044, N = 7 SE +/- 0.018, N = 7 SE +/- 0.012, N = 6 SE +/- 0.021, N = 6 SE +/- 0.014, N = 5 5.890 5.932 8.140 8.147 8.969 1. (CXX) g++ options: -O3 -fPIC -lm
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.13, N = 6 SE +/- 0.05, N = 6 SE +/- 0.08, N = 5 SE +/- 0.07, N = 5 SE +/- 0.15, N = 5 24.17 23.94 19.96 19.89 15.92 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: AlexNet EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 0.14, N = 4 SE +/- 0.14, N = 4 SE +/- 0.23, N = 3 SE +/- 0.05, N = 3 SE +/- 1.37, N = 3 242.49 236.71 172.89 171.11 160.52
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 1100 2200 3300 4400 5500 SE +/- 49.85, N = 6 SE +/- 0.00, N = 6 SE +/- 41.03, N = 5 SE +/- 29.29, N = 6 SE +/- 27.18, N = 8 5172.44 5023.70 4282.18 3429.45 3426.03 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
CockroachDB Workload: KV, 60% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 156.58, N = 3 SE +/- 137.27, N = 3 SE +/- 47.09, N = 3 SE +/- 204.39, N = 3 SE +/- 198.29, N = 3 95084.8 93864.1 67506.7 67444.0 63021.4
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 300 600 900 1200 1500 SE +/- 0.05, N = 4 SE +/- 0.04, N = 4 SE +/- 17.52, N = 15 SE +/- 0.10, N = 6 SE +/- 9.26, N = 15 1611.5 1611.5 1517.4 1470.5 1068.9 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 1019.4 / MAX: 1611.6 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 1019.3 / MAX: 1611.6 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 849.7 / MAX: 1610.7 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 849.1 / MAX: 1470.7 MIN: 637.2 / MAX: 1111.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Java SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Dense LU Matrix Factorization EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4K 8K 12K 16K 20K SE +/- 217.22, N = 3 SE +/- 146.88, N = 3 SE +/- 115.98, N = 3 SE +/- 171.55, N = 3 SE +/- 8.09, N = 3 18030.92 17934.59 17774.36 17230.85 11976.06
VVenC Video Input: Bosphorus 1080p - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 1080p - Video Preset: Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 23.19 23.00 18.90 18.77 15.46 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
Apache HTTP Server Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 1000 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 30K 60K 90K 120K 150K SE +/- 797.39, N = 3 SE +/- 802.85, N = 3 SE +/- 873.03, N = 3 SE +/- 62.36, N = 3 SE +/- 59.58, N = 3 131437.32 130637.70 113097.85 87708.39 87686.63 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Speedb Test: Update Random OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Update Random Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 200K 400K 600K 800K 1000K SE +/- 1460.51, N = 3 SE +/- 726.71, N = 3 SE +/- 1173.38, N = 3 SE +/- 819.19, N = 3 SE +/- 1312.04, N = 3 828184 624743 623366 556040 553791 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 4.40, N = 3 SE +/- 8.14, N = 3 SE +/- 3.38, N = 3 SE +/- 7.12, N = 3 SE +/- 3.86, N = 3 833.52 829.19 680.95 677.58 557.41 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
JPEG-XL libjxl Input: JPEG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.37, N = 10 SE +/- 0.27, N = 3 SE +/- 0.30, N = 3 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 48.59 46.77 37.18 36.32 32.51 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Update Random Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 200K 400K 600K 800K 1000K SE +/- 2978.74, N = 3 SE +/- 818.39, N = 3 SE +/- 1578.78, N = 3 SE +/- 748.73, N = 3 SE +/- 1914.75, N = 3 908300 703294 700416 618187 609510 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 17.44 17.32 13.14 13.08 11.77 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 0.13, N = 6 SE +/- 0.14, N = 6 SE +/- 0.64, N = 10 SE +/- 0.08, N = 5 SE +/- 0.14, N = 5 111.01 107.37 83.19 76.06 74.93 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read Random Write Random EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 600K 1200K 1800K 2400K 3000K SE +/- 24549.22, N = 3 SE +/- 24632.94, N = 3 SE +/- 2242.91, N = 3 SE +/- 5891.62, N = 3 SE +/- 17144.87, N = 3 2915758 2912747 2137892 2131122 1976533 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 0.15, N = 6 SE +/- 0.05, N = 6 SE +/- 0.46, N = 15 SE +/- 0.09, N = 5 SE +/- 0.09, N = 5 103.52 99.84 79.85 71.48 70.29 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 14 28 42 56 70 SE +/- 0.35, N = 8 SE +/- 0.31, N = 15 SE +/- 0.67, N = 4 SE +/- 0.86, N = 15 SE +/- 0.59, N = 6 42.23 44.43 55.90 61.28 61.97 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 4.91, N = 3 SE +/- 1.46, N = 3 SE +/- 1.09, N = 3 SE +/- 3.42, N = 3 SE +/- 2.12, N = 3 2260.82 1977.00 1917.67 1619.82 1550.64 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
CockroachDB Workload: KV, 95% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 30K 60K 90K 120K 150K SE +/- 765.52, N = 3 SE +/- 716.09, N = 3 SE +/- 258.97, N = 3 SE +/- 237.27, N = 3 SE +/- 302.28, N = 3 121061.7 119084.9 84052.3 83987.5 83155.8
Stress-NG Test: Matrix 3D Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix 3D Math Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 0.40, N = 3 SE +/- 2.55, N = 3 SE +/- 0.58, N = 3 SE +/- 3.38, N = 3 SE +/- 1.97, N = 3 2778.89 2029.45 2011.17 1953.52 1924.70 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.06318, N = 3 SE +/- 0.13812, N = 4 SE +/- 0.12476, N = 15 SE +/- 0.10193, N = 15 SE +/- 0.11600, N = 3 11.67770 11.51990 9.32307 9.29179 8.09421 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 4M 8M 12M 16M 20M SE +/- 185878.60, N = 5 SE +/- 20135.83, N = 3 SE +/- 18408.29, N = 3 SE +/- 6257.32, N = 3 SE +/- 7976.77, N = 3 17858353.80 16207347.12 16150369.04 12527831.36 12445240.76 1. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
RocksDB Test: Overwrite OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Overwrite Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 400K 800K 1200K 1600K 2000K SE +/- 14969.35, N = 3 SE +/- 1384.95, N = 3 SE +/- 1555.52, N = 3 SE +/- 1933.24, N = 3 SE +/- 1465.82, N = 3 1653489 1229747 1225361 1155121 1152820 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 500 - Mode: Read Write EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 12K 24K 36K 48K 60K SE +/- 617.95, N = 4 SE +/- 699.92, N = 3 SE +/- 362.37, N = 3 SE +/- 256.18, N = 3 SE +/- 453.73, N = 4 57520 56517 42412 40473 40163 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 3 6 9 12 15 SE +/- 0.094, N = 4 SE +/- 0.109, N = 3 SE +/- 0.101, N = 3 SE +/- 0.078, N = 3 SE +/- 0.141, N = 4 8.696 8.850 11.791 12.355 12.454 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 0.09 0.18 0.27 0.36 0.45 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.28 0.28 0.29 0.29 0.40 MIN: 0.15 / MAX: 7.24 MIN: 0.15 / MAX: 7.71 MIN: 0.16 / MAX: 9.68 MIN: 0.16 / MAX: 8.63 MIN: 0.18 / MAX: 8.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Fill Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 400K 800K 1200K 1600K 2000K SE +/- 10692.91, N = 3 SE +/- 2055.67, N = 3 SE +/- 3781.08, N = 3 SE +/- 4512.41, N = 3 SE +/- 1270.91, N = 3 1647988 1229256 1225921 1159865 1154716 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Dragonflydb Clients Per Thread: 10 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.4M 2.8M 4.2M 5.6M 7M SE +/- 45878.41, N = 3 SE +/- 90168.82, N = 12 SE +/- 43642.69, N = 3 SE +/- 38431.66, N = 3 SE +/- 44122.15, N = 3 6406922.86 6266297.87 4759359.71 4729191.29 4522560.58 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Apache HTTP Server Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 500 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 30K 60K 90K 120K 150K SE +/- 667.30, N = 3 SE +/- 521.55, N = 3 SE +/- 774.43, N = 3 SE +/- 141.36, N = 3 SE +/- 152.51, N = 3 136714.05 133534.11 125745.61 96630.23 96508.30 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenFOAM Input: drivaerFastback, Small Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 10 20 30 40 50 29.74 30.77 35.19 38.17 41.68 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.21, N = 7 SE +/- 0.13, N = 7 SE +/- 0.38, N = 6 SE +/- 0.53, N = 6 SE +/- 0.77, N = 15 118.06 117.25 89.23 89.12 84.33 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/pathtracer/real_time EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 0.68, N = 3 SE +/- 0.83, N = 3 SE +/- 0.61, N = 3 SE +/- 0.86, N = 3 SE +/- 0.42, N = 3 220.91 219.74 170.39 168.64 157.97
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.59 5.63 5.96 5.96 7.78 MIN: 2.93 / MAX: 16.72 MIN: 2.98 / MAX: 16.09 MIN: 3.09 / MAX: 18.13 MIN: 3.08 / MAX: 18.52 MIN: 3.64 / MAX: 44.07 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Resizing EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.86, N = 3 338 332 255 251 244 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
CloverLeaf Input: clover_bm OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 0.27, N = 3 SE +/- 0.45, N = 3 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 64.58 72.88 75.55 86.82 89.36 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 500 1000 1500 2000 2500 SE +/- 25.68, N = 12 SE +/- 7.85, N = 3 SE +/- 22.75, N = 3 SE +/- 14.49, N = 3 SE +/- 15.93, N = 3 1668.7 1925.0 1963.8 2288.1 2300.7 MIN: 1155.42 / MAX: 1849.98 MIN: 1772.86 / MAX: 2146.59 MIN: 1776.88 / MAX: 2143.78 MIN: 2126.73 / MAX: 2373.63 MIN: 2117.57 / MAX: 2419.92
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 3K 6K 9K 12K 15K SE +/- 146.76, N = 5 SE +/- 175.17, N = 3 SE +/- 4.20, N = 3 SE +/- 1.44, N = 3 SE +/- 2.24, N = 3 13374.35 12630.55 11387.05 10027.11 9707.08 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 4.1.6
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 15.85 15.56 12.55 12.26 11.54 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 5 10 15 20 25 SE +/- 0.12, N = 15 SE +/- 0.21, N = 3 SE +/- 0.22, N = 3 SE +/- 0.18, N = 9 SE +/- 0.17, N = 15 16.59 17.11 19.75 21.87 22.53 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
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 8.3.4 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.18, N = 3 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 40.11 40.85 53.09 53.76 54.45
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 2K 4K 6K 8K 10K SE +/- 8.52, N = 3 SE +/- 8.13, N = 3 SE +/- 16.40, N = 3 SE +/- 3.31, N = 3 SE +/- 7.52, N = 3 9869.74 7673.66 7330.07 7325.10 7278.87 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 80 160 240 320 400 SE +/- 0.44, N = 3 SE +/- 0.15, N = 3 SE +/- 0.24, N = 3 SE +/- 0.18, N = 3 SE +/- 0.59, N = 3 283.71 285.97 301.79 301.83 384.09 MIN: 240.12 / MAX: 303.33 MIN: 150.08 / MAX: 303.22 MIN: 278.87 / MAX: 327.8 MIN: 264.12 / MAX: 322.86 MIN: 285.45 / MAX: 543.49 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
DaCapo Benchmark Java Test: Spring Boot OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Spring Boot EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 300 600 900 1200 1500 SE +/- 7.11, N = 5 SE +/- 6.93, N = 5 SE +/- 6.95, N = 5 SE +/- 10.62, N = 13 SE +/- 8.13, N = 5 1159 1162 1220 1554 1554
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Thread EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 5.66, N = 10 SE +/- 3.24, N = 10 SE +/- 5.92, N = 10 SE +/- 2.53, N = 9 SE +/- 5.58, N = 9 1082.7 1061.5 1049.1 1027.8 809.6 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.16, N = 3 SE +/- 0.48, N = 3 SE +/- 0.94, N = 3 SE +/- 0.51, N = 3 103.37 106.72 122.55 123.74 137.92 MAX: 23852.59 MAX: 23939.91 MAX: 23938.16 MAX: 23948.92 MAX: 23917.2
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 16M 32M 48M 64M 80M SE +/- 205604.00, N = 3 SE +/- 109473.22, N = 3 SE +/- 268932.10, N = 3 SE +/- 503428.59, N = 3 SE +/- 209117.79, N = 3 74075244 71922519 62951458 62420035 56035278
MariaDB Test: oltp_write_only - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_write_only - Threads: 64 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 70K 140K 210K 280K 350K SE +/- 559.43, N = 3 SE +/- 56.85, N = 3 SE +/- 798.38, N = 3 SE +/- 419.19, N = 3 SE +/- 526.67, N = 3 349473 348099 296034 265119 265093 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 300 600 900 1200 1500 SE +/- 16.64, N = 3 SE +/- 4.80, N = 3 SE +/- 16.77, N = 15 SE +/- 18.32, N = 12 SE +/- 10.32, N = 15 1604.85 1278.44 1269.37 1228.58 1223.22 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 110 220 330 440 550 SE +/- 4.31, N = 3 SE +/- 7.45, N = 3 SE +/- 4.57, N = 3 SE +/- 4.56, N = 3 SE +/- 1.92, N = 3 399.56 415.04 460.21 462.14 524.13 MAX: 27980.82 MAX: 27057.75 MAX: 27836.55 MAX: 27920.53 MAX: 26588.63
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 60 120 180 240 300 225.95 226.01 245.10 276.71 296.21 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Z3 Theorem Prover SMT File: 2.smt2 OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 14 28 42 56 70 SE +/- 0.21, N = 3 SE +/- 0.27, N = 3 SE +/- 0.53, N = 3 SE +/- 0.35, N = 3 SE +/- 0.51, N = 3 48.12 48.68 48.88 49.00 63.08 1. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
Speedb Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read Random Write Random EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 600K 1200K 1800K 2400K 3000K SE +/- 5448.80, N = 3 SE +/- 2327.92, N = 3 SE +/- 1481.36, N = 3 SE +/- 1406.43, N = 3 SE +/- 4914.43, N = 3 2770899 2770195 2144575 2138776 2120915 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 16M 32M 48M 64M 80M SE +/- 597457.28, N = 3 SE +/- 669845.56, N = 3 SE +/- 766998.72, N = 3 SE +/- 441409.11, N = 3 SE +/- 207001.08, N = 3 73716025 71135797 64354682 64182563 56494499
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.82, N = 3 SE +/- 0.76, N = 3 SE +/- 0.24, N = 3 SE +/- 0.47, N = 3 SE +/- 0.54, N = 3 92.08 95.72 105.58 106.44 119.49 MAX: 11356.99 MAX: 11335.36 MAX: 15103.61 MAX: 13870.13 MAX: 13845.12
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.23, N = 3 SE +/- 0.23, N = 3 29.44 29.89 36.55 36.90 38.13 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 600 1200 1800 2400 3000 2260.99 2351.51 2445.68 2827.88 2926.98 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 100M 200M 300M 400M 500M SE +/- 269181.94, N = 5 SE +/- 143363.91, N = 3 SE +/- 201300.38, N = 3 SE +/- 445215.93, N = 4 SE +/- 333950.91, N = 4 453703880 378697000 362574433 352361775 350656750 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
CloverLeaf Input: clover_bm64_short OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm64_short Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 40 80 120 160 200 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 138.32 171.30 172.36 177.83 178.81 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Tradesoap Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 500 1000 1500 2000 2500 SE +/- 16.67, N = 4 SE +/- 7.41, N = 4 SE +/- 20.46, N = 5 SE +/- 16.84, N = 13 SE +/- 17.19, N = 4 1914 1964 1979 2439 2474
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 120 240 360 480 600 SE +/- 2.82, N = 5 SE +/- 2.53, N = 4 SE +/- 1.38, N = 4 SE +/- 6.41, N = 4 SE +/- 2.65, N = 4 415 527 532 533 536
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: HWB Color Space Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 70 140 210 280 350 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 315 278 269 255 244 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 2 4 6 8 10 SE +/- 0.04485, N = 7 SE +/- 0.01415, N = 7 SE +/- 0.01136, N = 7 SE +/- 0.00717, N = 7 SE +/- 0.00879, N = 7 6.38053 6.40719 6.72536 8.16800 8.23220 MIN: 5.92 MIN: 5.93 MIN: 6.2 MIN: 7.7 MIN: 7.77 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
TensorFlow Device: CPU - Batch Size: 1 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: AlexNet Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 5 10 15 20 25 SE +/- 0.01, N = 6 SE +/- 0.00, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 5 18.50 15.01 14.96 14.53 14.37
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 12 24 36 48 60 SE +/- 0.21, N = 3 SE +/- 0.52, N = 5 SE +/- 0.43, N = 3 SE +/- 0.43, N = 3 SE +/- 0.30, N = 3 52.72 51.78 51.72 50.53 41.01 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Llama.cpp Model: llama-2-70b-chat.Q5_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-70b-chat.Q5_0.gguf Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.306 0.612 0.918 1.224 1.53 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.36 1.21 1.16 1.09 1.06 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Llama.cpp Model: llama-2-7b.Q4_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-7b.Q4_0.gguf Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 4 8 12 16 20 SE +/- 0.18, N = 4 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 6 SE +/- 0.11, N = 3 16.07 13.82 13.12 12.73 12.54 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Java SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Composite EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1200 2400 3600 4800 6000 SE +/- 56.78, N = 3 SE +/- 42.37, N = 3 SE +/- 35.75, N = 3 SE +/- 46.58, N = 8 SE +/- 52.94, N = 3 5519.55 5476.91 5441.20 5321.50 4311.80
Llama.cpp Model: llama-2-13b.Q4_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-13b.Q4_0.gguf Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 8.38 7.32 6.98 6.70 6.57 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
TensorFlow Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.01, N = 5 SE +/- 0.04, N = 5 SE +/- 0.03, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 17.47 16.77 14.93 14.78 13.71
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.29, N = 3 SE +/- 0.11, N = 3 SE +/- 0.29, N = 3 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 60.66 62.09 68.16 69.05 77.24 MAX: 23861.25 MAX: 23874.44 MAX: 23889.9 MAX: 23877.52 MAX: 23891.04
Llamafile Test: llava-v1.5-7b-q4 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: llava-v1.5-7b-q4 - Acceleration: CPU Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 13.32 11.37 10.90 10.57 10.48
VVenC Video Input: Bosphorus 1080p - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 1080p - Video Preset: Faster EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 11 22 33 44 55 SE +/- 0.11, N = 4 SE +/- 0.09, N = 4 SE +/- 0.04, N = 4 SE +/- 0.05, N = 4 SE +/- 0.25, N = 4 50.91 50.41 45.14 44.58 40.07 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20M 40M 60M 80M 100M SE +/- 368630.91, N = 3 SE +/- 224737.25, N = 3 SE +/- 282897.65, N = 3 SE +/- 351738.51, N = 3 SE +/- 262085.32, N = 3 79315319 76780782 70305285 69450850 62558098
Llamafile Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 7.91 6.79 6.53 6.34 6.28
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 17M 34M 51M 68M 85M SE +/- 390613.00, N = 3 SE +/- 113056.05, N = 3 SE +/- 296062.71, N = 3 SE +/- 75302.81, N = 3 SE +/- 232749.13, N = 3 77605627 75706552 69561449 68672756 61842388
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 40 80 120 160 200 SE +/- 0.25, N = 3 SE +/- 0.20, N = 3 SE +/- 0.20, N = 3 SE +/- 0.21, N = 3 SE +/- 0.14, N = 3 127.02 132.13 145.99 152.79 159.04 1. (CXX) g++ options: -O3 -fopenmp
DaCapo Benchmark Java Test: Apache Xalan XSLT OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Xalan XSLT Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 110 220 330 440 550 SE +/- 2.76, N = 11 SE +/- 2.21, N = 10 SE +/- 2.71, N = 10 SE +/- 3.47, N = 10 SE +/- 2.09, N = 10 408 448 450 506 508
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 17M 34M 51M 68M 85M SE +/- 360981.97, N = 3 SE +/- 362879.93, N = 3 SE +/- 261270.67, N = 3 SE +/- 239601.11, N = 3 SE +/- 787042.09, N = 3 77658914 75893047 69144164 68897602 62655549
DuckDB Benchmark: IMDB OpenBenchmarking.org Seconds, Fewer Is Better DuckDB 0.9.1 Benchmark: IMDB EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 82.38 83.01 99.58 100.63 101.94 1. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 60 120 180 240 300 SE +/- 2.35, N = 3 SE +/- 2.23, N = 3 SE +/- 1.83, N = 3 SE +/- 1.82, N = 3 SE +/- 4.53, N = 3 235.16 238.34 267.99 268.42 290.14 MAX: 26882.16 MAX: 26718.64 MAX: 27513.85 MAX: 27440.82 MAX: 26535.45
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 30M 60M 90M 120M 150M SE +/- 724829.48, N = 3 SE +/- 13333.33, N = 3 SE +/- 15275.25, N = 3 SE +/- 282921.27, N = 3 SE +/- 14529.66, N = 3 127376667 107146667 107140000 103696667 103326667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 50M 100M 150M 200M 250M SE +/- 17320.51, N = 3 SE +/- 1006495.57, N = 3 SE +/- 325695.84, N = 3 SE +/- 452413.28, N = 3 SE +/- 674487.46, N = 3 253450000 212860000 209743333 206306667 205890000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 0.87, N = 15 SE +/- 0.58, N = 10 SE +/- 1.01, N = 3 SE +/- 0.27, N = 3 SE +/- 0.76, N = 3 73.72 73.88 79.60 87.77 90.69 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
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Tradebeans EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 31.95, N = 4 SE +/- 22.67, N = 4 SE +/- 21.46, N = 4 SE +/- 38.01, N = 4 SE +/- 14.57, N = 4 2775 2815 3329 3359 3410
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.42, N = 3 SE +/- 0.31, N = 3 SE +/- 0.41, N = 3 SE +/- 0.51, N = 3 65.63 67.07 70.70 72.28 80.56 MAX: 12576.01 MAX: 12570.5 MAX: 13822.83 MAX: 13851.96 MAX: 15084.51
TensorFlow Device: CPU - Batch Size: 1 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: GoogLeNet EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 14 28 42 56 70 SE +/- 0.10, N = 9 SE +/- 0.11, N = 9 SE +/- 0.18, N = 8 SE +/- 0.05, N = 8 SE +/- 0.05, N = 8 62.99 62.02 57.34 57.21 51.33
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 15M 30M 45M 60M 75M SE +/- 41672.18, N = 3 SE +/- 313014.56, N = 3 SE +/- 42980.57, N = 3 SE +/- 161254.73, N = 3 SE +/- 205982.51, N = 3 69857519 68166248 64781285 63627945 57028398
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 140 280 420 560 700 SE +/- 1.66, N = 15 SE +/- 0.81, N = 12 SE +/- 0.76, N = 12 SE +/- 0.74, N = 12 SE +/- 0.68, N = 12 660.34 649.20 548.04 546.71 539.87 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Savina Reactors.IO EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 800 1600 2400 3200 4000 SE +/- 27.86, N = 3 SE +/- 28.17, N = 3 SE +/- 15.03, N = 3 SE +/- 33.81, N = 3 SE +/- 16.31, N = 3 3036.5 3042.0 3265.2 3270.6 3695.4 MIN: 2985.79 / MAX: 4135.64 MIN: 3011.87 / MAX: 4321.7 MIN: 3236.75 / MAX: 4741.82 MIN: 3216.47 / MAX: 4638.43 MIN: 3664.8 / MAX: 5363.87
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 40 80 120 160 200 SE +/- 2.25, N = 15 SE +/- 2.20, N = 3 SE +/- 2.01, N = 3 SE +/- 0.82, N = 3 SE +/- 0.71, N = 3 169.62 162.33 157.01 142.06 139.48 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Apache Hadoop Operation: Create - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 100 - Files: 100000 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 20K 40K 60K 80K 100K SE +/- 670.20, N = 11 SE +/- 496.20, N = 3 SE +/- 1027.34, N = 3 SE +/- 376.90, N = 3 SE +/- 292.68, N = 3 90938 90476 88992 75381 74946
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20M 40M 60M 80M 100M SE +/- 818556.17, N = 3 SE +/- 919852.08, N = 3 SE +/- 255843.12, N = 3 SE +/- 357039.39, N = 3 SE +/- 922667.78, N = 3 78454316 77609975 71338740 69856949 64886364
Llamafile Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.495 0.99 1.485 1.98 2.475 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.20 2.01 1.94 1.84 1.82
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 15M 30M 45M 60M 75M SE +/- 489754.87, N = 3 SE +/- 438509.29, N = 3 SE +/- 418677.10, N = 3 SE +/- 382550.66, N = 3 SE +/- 245819.57, N = 3 69731166 67794681 64655502 63296864 57760197
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 14M 28M 42M 56M 70M SE +/- 637003.49, N = 3 SE +/- 881.92, N = 3 SE +/- 2645.75, N = 3 SE +/- 318365.79, N = 3 SE +/- 469067.51, N = 3 63236667 53661333 53659000 53018667 52493000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 2.58, N = 3 SE +/- 3.59, N = 3 SE +/- 2.05, N = 3 SE +/- 3.29, N = 3 SE +/- 1.43, N = 3 812.16 808.62 803.04 800.78 675.48
MariaDB Test: oltp_read_write - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_read_write - Threads: 64 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 40K 80K 120K 160K 200K SE +/- 108.10, N = 3 SE +/- 389.87, N = 3 SE +/- 562.40, N = 3 SE +/- 211.83, N = 3 SE +/- 60.79, N = 3 201579 201182 186418 168593 168388 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 5 10 15 20 25 SE +/- 0.23, N = 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 19.5 18.8 18.0 17.9 16.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 60 120 180 240 300 SE +/- 3.67, N = 3 SE +/- 3.26, N = 3 SE +/- 2.74, N = 3 SE +/- 3.81, N = 3 SE +/- 1.91, N = 3 230.41 235.20 243.61 248.62 275.14 MAX: 26735.87 MAX: 26852.2 MAX: 26975.13 MAX: 26892.13 MAX: 27185.57
DaCapo Benchmark Java Test: BioJava Biological Data Framework OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: BioJava Biological Data Framework Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 900 1800 2700 3600 4500 SE +/- 25.22, N = 4 SE +/- 20.56, N = 4 SE +/- 19.50, N = 4 SE +/- 15.83, N = 4 SE +/- 33.62, N = 4 3708 4327 4347 4413 4425
Timed CPython Compilation Build Configuration: Default OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Default EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 14.13 14.15 16.50 16.58 16.85
Apache IoTDB Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 80 160 240 320 400 SE +/- 5.40, N = 3 SE +/- 8.45, N = 3 SE +/- 6.12, N = 3 SE +/- 1.80, N = 3 SE +/- 10.20, N = 3 321.29 322.24 347.97 359.26 382.48 MAX: 27126.33 MAX: 27055.68 MAX: 27085.8 MAX: 27346.14 MAX: 27376.22
OpenRadioss Model: Chrysler Neon 1M OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 200 400 600 800 1000 SE +/- 4.49, N = 3 SE +/- 5.48, N = 3 SE +/- 17.37, N = 7 SE +/- 10.68, N = 9 SE +/- 2.88, N = 3 891.84 915.82 983.54 1003.59 1060.53
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 6.1 Encoder: libx265 - Scenario: Video On Demand EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 16 32 48 64 80 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 69.81 69.52 65.35 65.27 58.75 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 6.1 Encoder: libx265 - Scenario: Platform EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 16 32 48 64 80 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 69.80 69.24 65.45 65.26 58.75 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 6.1 Encoder: libx265 - Scenario: Upload EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 34.21 34.06 32.03 31.95 28.89 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
MariaDB Test: oltp_update_non_index - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_update_non_index - Threads: 64 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 50K 100K 150K 200K 250K SE +/- 437.08, N = 3 SE +/- 290.99, N = 3 SE +/- 516.32, N = 3 SE +/- 295.88, N = 3 SE +/- 410.68, N = 3 234051 233313 220068 201401 200246 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30M 60M 90M 120M 150M SE +/- 368435.13, N = 3 SE +/- 612490.36, N = 3 SE +/- 292137.71, N = 3 SE +/- 1579485.68, N = 4 SE +/- 1116779.09, N = 8 151906667 150576667 149903333 147935000 130002500 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Speedb Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Fill EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 200K 400K 600K 800K 1000K SE +/- 738.85, N = 3 SE +/- 1877.58, N = 3 SE +/- 5918.01, N = 3 SE +/- 826.71, N = 3 SE +/- 1278.43, N = 3 1011788 1005973 876130 869816 866759 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
DaCapo Benchmark Java Test: H2 Database Engine OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: H2 Database Engine EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 13.96, N = 3 SE +/- 9.17, N = 3 SE +/- 7.51, N = 3 SE +/- 12.68, N = 3 SE +/- 23.84, N = 3 1826 1872 1977 2000 2128
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 23.30 22.14 21.89 20.81 20.06
MariaDB Test: oltp_read_write - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_read_write - Threads: 32 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 40K 80K 120K 160K 200K SE +/- 135.64, N = 3 SE +/- 158.42, N = 3 SE +/- 554.89, N = 3 SE +/- 199.70, N = 3 SE +/- 73.28, N = 3 184015 181519 180020 159448 158499 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
MariaDB Test: oltp_write_only - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_write_only - Threads: 32 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 80K 160K 240K 320K 400K SE +/- 101.24, N = 3 SE +/- 441.31, N = 3 SE +/- 133.55, N = 3 SE +/- 471.57, N = 3 SE +/- 574.53, N = 3 352931 346114 310088 306926 304169 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
RNNoise Input: 26 Minute Long Talking Sample OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 0.2 Input: 26 Minute Long Talking Sample Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 2 4 6 8 10 SE +/- 0.059, N = 7 SE +/- 0.016, N = 6 SE +/- 0.050, N = 6 SE +/- 0.063, N = 6 SE +/- 0.033, N = 6 6.400 7.028 7.184 7.291 7.414 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 8.4.0 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2 4 6 8 10 SE +/- 0.017, N = 7 SE +/- 0.016, N = 7 SE +/- 0.043, N = 7 SE +/- 0.021, N = 7 SE +/- 0.011, N = 6 5.587 5.668 5.754 5.780 6.462
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 40 80 120 160 200 SE +/- 0.97, N = 3 SE +/- 0.69, N = 3 SE +/- 0.25, N = 3 SE +/- 1.92, N = 3 SE +/- 1.35, N = 3 161.31 156.77 152.04 142.82 141.63 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
High Performance Conjugate Gradient X Y Z: 104 104 104 - RT: 60 OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 2 4 6 8 10 SE +/- 0.12782, N = 12 SE +/- 0.05325, N = 3 SE +/- 0.01035, N = 3 SE +/- 0.04118, N = 3 SE +/- 0.06329, N = 12 7.58350 7.22104 6.94846 6.73761 6.67485 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 1100 2200 3300 4400 5500 SE +/- 34.53, N = 4 SE +/- 43.08, N = 3 SE +/- 17.50, N = 3 SE +/- 46.95, N = 3 SE +/- 56.37, N = 3 5019.2 4518.4 4457.8 4425.2 4425.0 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
MariaDB Test: oltp_update_non_index - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_update_non_index - Threads: 32 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 50K 100K 150K 200K 250K SE +/- 223.46, N = 3 SE +/- 466.56, N = 3 SE +/- 861.02, N = 3 SE +/- 181.91, N = 3 SE +/- 399.51, N = 3 253110 239542 239192 224636 224118 -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl
MariaDB Test: oltp_update_index - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_update_index - Threads: 64 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 40K 80K 120K 160K 200K SE +/- 130.01, N = 3 SE +/- 282.52, N = 3 SE +/- 250.58, N = 3 SE +/- 125.38, N = 3 SE +/- 308.54, N = 3 200156 198538 187089 177842 177579 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.1925 2.385 3.5775 4.77 5.9625 SE +/- 0.03, N = 8 SE +/- 0.03, N = 8 SE +/- 0.03, N = 8 SE +/- 0.01, N = 8 SE +/- 0.02, N = 7 5.30 5.28 5.15 5.10 4.73 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
WebP Image Encode Encode Settings: Default OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Default EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.07, N = 13 SE +/- 0.10, N = 13 SE +/- 0.13, N = 13 SE +/- 0.08, N = 13 SE +/- 0.07, N = 13 26.81 26.78 26.25 25.78 23.93 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200M 400M 600M 800M 1000M SE +/- 67412.49, N = 3 SE +/- 1556216.92, N = 3 SE +/- 199192.82, N = 3 SE +/- 812656.82, N = 3 SE +/- 5153390.47, N = 3 795966667 787633333 740166667 735566667 711050000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Z3 Theorem Prover SMT File: 1.smt2 OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 1.smt2 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 18.66 20.33 20.43 20.50 20.78 1. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 50 100 150 200 250 SE +/- 1.98, N = 3 SE +/- 2.37, N = 5 SE +/- 2.08, N = 3 SE +/- 1.84, N = 3 SE +/- 2.84, N = 3 234.39 227.39 222.80 222.47 211.59 MIN: 9.14 / MAX: 12000 MIN: 13.31 / MAX: 10000 MIN: 12.9 / MAX: 7500 MIN: 10.49 / MAX: 12000 MIN: 10.43 / MAX: 10000
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 0.9461 1.8922 2.8383 3.7844 4.7305 SE +/- 0.020, N = 8 SE +/- 0.038, N = 15 SE +/- 0.011, N = 8 SE +/- 0.009, N = 8 SE +/- 0.025, N = 8 3.804 3.841 4.162 4.202 4.205 1. (CXX) g++ options: -O3 -fPIC -lm
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1200 2400 3600 4800 6000 SE +/- 10.00, N = 7 SE +/- 12.60, N = 6 SE +/- 29.27, N = 6 SE +/- 31.00, N = 6 SE +/- 17.70, N = 6 5083 5163 5224 5237 5607 1. (CXX) g++ options: -O3
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 50 100 150 200 250 SE +/- 3.87, N = 3 SE +/- 1.51, N = 5 SE +/- 1.60, N = 3 SE +/- 1.00, N = 3 SE +/- 1.92, N = 3 249.50 248.89 240.37 236.47 226.35 MIN: 9.27 / MAX: 12000 MIN: 15.92 / MAX: 8571.43 MIN: 15.16 / MAX: 10000 MIN: 10.66 / MAX: 10000 MIN: 10.69 / MAX: 10000
Apache Hadoop Operation: Create - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 500 - Files: 100000 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 17K 34K 51K 68K 85K SE +/- 465.56, N = 3 SE +/- 717.72, N = 3 SE +/- 761.92, N = 3 SE +/- 488.73, N = 3 SE +/- 682.82, N = 3 77585 76956 76371 71080 70436
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 60 120 180 240 300 SE +/- 2.29, N = 5 SE +/- 1.74, N = 3 SE +/- 1.20, N = 3 SE +/- 4.93, N = 3 SE +/- 1.72, N = 3 251.80 249.90 241.90 232.47 228.79 MIN: 15.75 / MAX: 10000 MIN: 9.25 / MAX: 12000 MIN: 15.08 / MAX: 7500 MIN: 10.67 / MAX: 12000 MIN: 10.54 / MAX: 10000
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 42.55 42.66 42.79 46.66 46.73 1. RawTherapee, version 5.10, command line.
DaCapo Benchmark Java Test: Apache Lucene Search Index OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Lucene Search Index Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 19.22, N = 3 SE +/- 18.27, N = 3 SE +/- 17.23, N = 3 SE +/- 12.68, N = 3 SE +/- 11.06, N = 3 2296 2390 2407 2471 2517
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 90M 180M 270M 360M 450M SE +/- 2917967.33, N = 3 SE +/- 1727319.70, N = 3 SE +/- 388858.73, N = 3 SE +/- 2535286.53, N = 3 SE +/- 1946723.74, N = 3 439150000 411290000 409386667 404976667 404010000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
DaCapo Benchmark Java Test: PMD Source Code Analyzer OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: PMD Source Code Analyzer EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 200 400 600 800 1000 SE +/- 5.68, N = 7 SE +/- 10.09, N = 7 SE +/- 9.55, N = 7 SE +/- 8.96, N = 15 SE +/- 9.22, N = 15 1053 1074 1113 1122 1142
DaCapo Benchmark Java Test: Eclipse OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Eclipse EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1500 3000 4500 6000 7500 SE +/- 37.34, N = 3 SE +/- 12.50, N = 3 SE +/- 26.61, N = 3 SE +/- 28.45, N = 3 SE +/- 61.34, N = 8 6410 6483 6587 6627 6943
Java SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Jacobi Successive Over-Relaxation Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 2.05, N = 3 SE +/- 10.01, N = 3 SE +/- 22.65, N = 3 SE +/- 22.92, N = 3 SE +/- 18.83, N = 3 2667.90 2518.58 2489.61 2487.93 2464.14
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 200 400 600 800 1000 SE +/- 9.08, N = 3 SE +/- 5.89, N = 3 SE +/- 6.12, N = 15 SE +/- 9.79, N = 3 SE +/- 8.75, N = 3 819.5 821.7 882.7 886.6 887.0 MIN: 773.51 / MAX: 850.94 MIN: 782.09 / MAX: 843.31 MIN: 756.16 / MAX: 981 MIN: 844.84 / MAX: 942.25 MIN: 771.69 / MAX: 950.63
DaCapo Benchmark Java Test: GraphChi OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: GraphChi EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 600 1200 1800 2400 3000 SE +/- 14.73, N = 4 SE +/- 10.30, N = 4 SE +/- 18.46, N = 4 SE +/- 21.22, N = 4 SE +/- 18.95, N = 4 2472 2521 2535 2561 2675
DaCapo Benchmark Java Test: Batik SVG Toolkit OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Batik SVG Toolkit Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 200 400 600 800 1000 SE +/- 5.39, N = 8 SE +/- 6.28, N = 8 SE +/- 5.55, N = 8 SE +/- 3.65, N = 8 SE +/- 5.97, N = 8 897 927 930 936 969
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.04, N = 12 SE +/- 0.06, N = 12 SE +/- 0.10, N = 11 SE +/- 0.02, N = 11 SE +/- 0.05, N = 11 16.59 16.54 16.11 15.84 15.37 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 30 60 90 120 150 SE +/- 1.39, N = 15 SE +/- 1.70, N = 3 SE +/- 1.28, N = 15 SE +/- 0.39, N = 3 SE +/- 0.21, N = 3 133.17 131.44 128.01 126.67 123.95 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 0.198 0.396 0.594 0.792 0.99 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.88 0.84 0.84 0.82 0.82 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
MariaDB mariadb-slap Clients: 128 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB mariadb-slap 11.5 Clients: 128 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 130 260 390 520 650 SE +/- 0.55, N = 3 SE +/- 0.54, N = 3 SE +/- 0.57, N = 3 SE +/- 0.74, N = 3 SE +/- 1.05, N = 3 614 612 587 580 574 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
DaCapo Benchmark Java Test: FOP Print Formatter OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: FOP Print Formatter EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 5.40, N = 15 SE +/- 3.38, N = 15 SE +/- 5.35, N = 15 SE +/- 3.32, N = 15 SE +/- 6.07, N = 15 399 403 414 423 426
MariaDB Test: oltp_update_index - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.5 Test: oltp_update_index - Threads: 32 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 50K 100K 150K 200K 250K SE +/- 290.25, N = 3 SE +/- 307.26, N = 3 SE +/- 113.22, N = 3 SE +/- 331.57, N = 3 SE +/- 249.27, N = 3 210974 207212 206240 198779 198305 -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 500 1000 1500 2000 2500 SE +/- 2.75, N = 3 SE +/- 4.31, N = 3 SE +/- 3.55, N = 3 SE +/- 5.41, N = 9 SE +/- 24.36, N = 9 2375.6 2322.3 2313.4 2279.9 2245.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 9M 18M 27M 36M 45M SE +/- 14666.67, N = 3 SE +/- 267690.74, N = 3 SE +/- 368485.05, N = 12 SE +/- 254700.04, N = 3 SE +/- 184763.21, N = 3 40821333 39693000 39094333 38712667 38605667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 900 1800 2700 3600 4500 SE +/- 9.84, N = 7 SE +/- 17.41, N = 7 SE +/- 12.07, N = 7 SE +/- 5.99, N = 7 SE +/- 18.70, N = 7 3830 3878 3891 3922 4049 1. (CXX) g++ options: -O3
MariaDB mariadb-slap Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB mariadb-slap 11.5 Clients: 64 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 300 600 900 1200 1500 SE +/- 4.85, N = 3 SE +/- 5.34, N = 3 SE +/- 5.02, N = 3 SE +/- 4.64, N = 3 SE +/- 5.66, N = 3 1183 1182 1132 1128 1124 -shared -lrt -lstdc++ -shared -lrt -lstdc++ -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto -shared -lrt -lstdc++ 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -lpthread -lz -ldl -lm
Dolfyn Computational Fluid Dynamics OpenBenchmarking.org Seconds, Fewer Is Better Dolfyn 0.527 Computational Fluid Dynamics Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 3 6 9 12 15 SE +/- 0.03, N = 5 SE +/- 0.04, N = 5 SE +/- 0.02, N = 5 SE +/- 0.06, N = 5 SE +/- 0.11, N = 5 10.42 10.63 10.73 10.93 10.96
Timed CPython Compilation Build Configuration: Released Build, PGO + LTO Optimized OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Released Build, PGO + LTO Optimized EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 40 80 120 160 200 193.47 193.59 197.92 200.98 202.77
FFmpeg Encoder: libx265 - Scenario: Live OpenBenchmarking.org FPS, More Is Better FFmpeg 6.1 Encoder: libx265 - Scenario: Live EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.58, N = 3 SE +/- 0.71, N = 3 SE +/- 0.17, N = 3 SE +/- 0.16, N = 3 SE +/- 1.39, N = 3 186.71 186.42 179.99 179.98 178.15 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 400 800 1200 1600 2000 SE +/- 18.77, N = 3 SE +/- 20.68, N = 3 SE +/- 9.65, N = 3 SE +/- 7.95, N = 15 SE +/- 7.69, N = 3 2066.7 2026.0 2010.8 1998.3 1972.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 0.4883 0.9766 1.4649 1.9532 2.4415 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 4 SE +/- 0.01, N = 4 2.17 2.17 2.16 2.09 2.08 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 5.21, N = 3 SE +/- 7.19, N = 3 SE +/- 7.92, N = 3 SE +/- 6.24, N = 3 SE +/- 3.89, N = 3 2375.4 2352.5 2324.5 2299.7 2278.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 12 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 10.81, N = 3 SE +/- 7.37, N = 3 SE +/- 2.01, N = 3 SE +/- 25.03, N = 3 SE +/- 11.41, N = 12 2404.2 2394.8 2377.0 2314.7 2308.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 20M 40M 60M 80M 100M SE +/- 493083.61, N = 3 SE +/- 444695.78, N = 3 SE +/- 342214.52, N = 3 SE +/- 190528.21, N = 3 SE +/- 302227.47, N = 3 79553667 77811000 77508667 76809000 76415667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 30 60 90 120 150 SE +/- 0.46, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.41, N = 3 SE +/- 0.22, N = 3 123.28 122.63 120.91 120.28 118.91 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90K 180K 270K 360K 450K SE +/- 1137.99, N = 3 SE +/- 1244.71, N = 3 SE +/- 1282.82, N = 3 SE +/- 1954.24, N = 3 SE +/- 739.32, N = 3 437475 435859 430421 429779 426706 1. (CC) gcc options: -pedantic -O3
DaCapo Benchmark Java Test: Apache Kafka OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Kafka Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 1100 2200 3300 4400 5500 SE +/- 2.00, N = 3 SE +/- 29.67, N = 3 SE +/- 27.06, N = 3 SE +/- 29.48, N = 3 SE +/- 32.17, N = 3 4984 5027 5030 5031 5055
DaCapo Benchmark Java Test: jMonkeyEngine OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: jMonkeyEngine EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 1500 3000 4500 6000 7500 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 SE +/- 1.20, N = 3 SE +/- 4.67, N = 3 6802 6804 6806 6808 6827
DaCapo Benchmark Java Test: Zxing 1D/2D Barcode Image Processing OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Zxing 1D/2D Barcode Image Processing EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 4.09, N = 9 SE +/- 4.29, N = 9 SE +/- 3.37, N = 8 SE +/- 2.37, N = 8 SE +/- 30.56, N = 15 589 597 1016 1019 1053
DaCapo Benchmark Java Test: Apache Lucene Search Engine OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Lucene Search Engine EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 700 1400 2100 2800 3500 SE +/- 9.53, N = 5 SE +/- 9.20, N = 5 SE +/- 17.06, N = 5 SE +/- 18.64, N = 5 SE +/- 50.09, N = 15 2080 2083 2404 2409 3113
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Myriad-Groestl EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 2K 4K 6K 8K 10K SE +/- 13.33, N = 3 SE +/- 195.61, N = 12 SE +/- 0.86, N = 3 SE +/- 6.11, N = 3 SE +/- 30.23, N = 3 11337.00 11228.13 6023.38 5972.09 4843.72 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 2 4 6 8 10 SE +/- 0.03755, N = 3 SE +/- 0.02831, N = 3 SE +/- 0.01065, N = 3 SE +/- 0.09318, N = 3 SE +/- 0.06732, N = 3 6.19876 6.37806 6.57601 7.00331 7.06097 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 2 4 6 8 10 SE +/- 0.07186, N = 15 SE +/- 0.08220, N = 3 SE +/- 0.08219, N = 3 SE +/- 0.04051, N = 3 SE +/- 0.03666, N = 3 5.90786 6.16145 6.36984 7.03702 7.16751 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.19, N = 5 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 18.97 19.32 19.33 19.79 24.39 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 6 12 18 24 30 SE +/- 0.41, N = 15 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 16.78 18.66 19.10 19.26 23.61 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 13 26 39 52 65 SE +/- 1.44, N = 15 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 60.06 53.58 52.34 51.91 42.35 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 0.4035 0.807 1.2105 1.614 2.0175 SE +/- 0.00633, N = 3 SE +/- 0.01197, N = 3 SE +/- 0.00719, N = 3 SE +/- 0.01555, N = 3 SE +/- 0.01234, N = 3 1.19855 1.20504 1.46770 1.47531 1.79347 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.3827 0.7654 1.1481 1.5308 1.9135 SE +/- 0.00549, N = 3 SE +/- 0.00557, N = 3 SE +/- 0.00807, N = 3 SE +/- 0.00355, N = 3 SE +/- 0.01304, N = 3 1.11577 1.11712 1.47738 1.48191 1.70107 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.0486 2.0972 3.1458 4.1944 5.243 SE +/- 0.00459, N = 3 SE +/- 0.02511, N = 3 SE +/- 0.01507, N = 3 SE +/- 0.00856, N = 3 SE +/- 0.03176, N = 3 2.58704 2.62524 3.07441 3.09905 4.66040 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.0039 2.0078 3.0117 4.0156 5.0195 SE +/- 0.05300, N = 15 SE +/- 0.03044, N = 15 SE +/- 0.02531, N = 15 SE +/- 0.00310, N = 3 SE +/- 0.03583, N = 3 2.38299 2.49599 3.05542 3.09150 4.46170 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 90 180 270 360 450 SE +/- 9.29, N = 15 SE +/- 4.78, N = 15 SE +/- 2.89, N = 15 SE +/- 0.32, N = 3 SE +/- 1.81, N = 3 422.42 401.35 327.53 323.38 224.11 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.69, N = 12 SE +/- 0.15, N = 3 SE +/- 0.21, N = 3 26.83 27.35 36.25 37.00 43.40 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.60, N = 12 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 37.27 36.56 27.71 27.02 23.04 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 2 4 6 8 10 SE +/- 0.03060, N = 3 SE +/- 0.00809, N = 3 SE +/- 0.00562, N = 3 SE +/- 0.02822, N = 3 SE +/- 0.01596, N = 3 8.10864 8.15155 8.26788 8.31107 8.40671 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 2 4 6 8 10 SE +/- 0.08068, N = 15 SE +/- 0.09699, N = 3 SE +/- 0.07551, N = 15 SE +/- 0.02440, N = 3 SE +/- 0.01376, N = 3 7.51744 7.60699 7.81820 7.89080 8.06389 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.63, N = 3 SE +/- 0.22, N = 3 SE +/- 0.76, N = 3 SE +/- 0.35, N = 3 SE +/- 0.78, N = 3 63.11 64.28 79.70 81.57 86.69 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 20 40 60 80 100 SE +/- 0.32, N = 3 SE +/- 0.03, N = 3 SE +/- 4.77, N = 15 SE +/- 0.63, N = 3 SE +/- 0.14, N = 3 65.48 66.03 70.83 85.12 91.52 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 1.17, N = 15 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 15.27 15.22 15.14 11.75 10.93 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.06152, N = 3 SE +/- 0.02431, N = 3 SE +/- 0.14350, N = 3 SE +/- 0.02135, N = 3 SE +/- 0.09981, N = 3 7.50080 7.55840 10.73790 10.91820 13.17920 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 200 400 600 800 1000 SE +/- 4.73, N = 3 SE +/- 1.90, N = 3 SE +/- 12.91, N = 15 SE +/- 8.12, N = 15 SE +/- 11.74, N = 14 567.02 567.07 864.56 889.17 960.86 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 0.3969 0.7938 1.1907 1.5876 1.9845 SE +/- 0.014643, N = 3 SE +/- 0.005924, N = 3 SE +/- 0.018640, N = 15 SE +/- 0.010436, N = 15 SE +/- 0.013081, N = 14 1.763840 1.763490 1.160540 1.125970 1.042812 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.47, N = 3 SE +/- 1.04, N = 4 SE +/- 1.34, N = 15 SE +/- 1.14, N = 15 SE +/- 1.78, N = 3 85.63 86.84 107.51 107.79 123.59 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 0.60, N = 3 SE +/- 5.00, N = 15 SE +/- 0.70, N = 3 SE +/- 5.32, N = 15 SE +/- 1.27, N = 3 96.99 97.12 97.94 100.03 127.67 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.57269, N = 15 SE +/- 0.63014, N = 15 SE +/- 0.06449, N = 3 SE +/- 0.07376, N = 3 SE +/- 0.07886, N = 3 10.70547 10.46448 10.31040 10.21150 7.83432 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 1.1133 2.2266 3.3399 4.4532 5.5665 SE +/- 0.00405, N = 9 SE +/- 0.00342, N = 9 SE +/- 0.00353, N = 9 SE +/- 0.00661, N = 9 SE +/- 0.10597, N = 15 2.46159 2.46164 3.79890 3.83412 4.94792 MIN: 2.35 MIN: 2.35 MIN: 3.63 MIN: 3.58 MIN: 4.45 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 10 20 30 40 50 SE +/- 0.27, N = 3 SE +/- 0.35, N = 3 SE +/- 0.16, N = 3 SE +/- 0.94, N = 15 SE +/- 1.58, N = 15 45.76 45.20 45.11 43.38 32.25 MIN: 34.75 / MAX: 46.5 MIN: 29.05 / MAX: 46.24 MIN: 43.61 / MAX: 45.86 MIN: 34.95 / MAX: 46.71 MIN: 23.14 / MAX: 40.93
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 15 30 45 60 75 SE +/- 1.71, N = 12 SE +/- 1.84, N = 15 SE +/- 0.29, N = 3 SE +/- 0.90, N = 15 SE +/- 1.37, N = 12 68.30 67.48 66.63 65.69 61.49 MIN: 48 / MAX: 73.52 MIN: 46.76 / MAX: 74.15 MIN: 57.04 / MAX: 69.34 MIN: 53.12 / MAX: 69.76 MIN: 40.06 / MAX: 72.22
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 7.12, N = 15 183.6 183.6 183.5 183.5 153.6 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 106 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 106 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.9 -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.9 MIN: 105.1 / MAX: 182.1 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 4M 8M 12M 16M 20M SE +/- 13650.40, N = 3 SE +/- 17835.67, N = 3 SE +/- 250051.55, N = 3 SE +/- 154682.83, N = 3 SE +/- 410224.76, N = 15 20255000 20106667 19611667 19299333 18964400 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Thorough EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.32, N = 12 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 19.90 19.68 12.23 10.32 10.21 1. (CXX) g++ options: -O3 -flto -pthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 70 140 210 280 350 SE +/- 0.21, N = 11 SE +/- 0.21, N = 11 SE +/- 0.17, N = 10 SE +/- 0.14, N = 10 SE +/- 4.30, N = 15 301.57 299.12 226.69 226.13 197.51 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 0.26, N = 10 SE +/- 0.29, N = 10 SE +/- 0.11, N = 9 SE +/- 0.09, N = 9 SE +/- 2.29, N = 15 248.39 245.56 168.47 168.08 139.72 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 80 160 240 320 400 SE +/- 1.71, N = 15 SE +/- 1.84, N = 15 SE +/- 3.49, N = 15 SE +/- 0.76, N = 9 SE +/- 0.90, N = 9 364.90 355.84 221.33 203.16 201.53 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 4.27, N = 15 SE +/- 4.13, N = 15 SE +/- 2.01, N = 15 SE +/- 1.96, N = 15 SE +/- 0.99, N = 15 165.29 160.65 122.91 121.44 104.61 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 160 320 480 640 800 SE +/- 20.65, N = 15 SE +/- 20.45, N = 15 SE +/- 13.14, N = 15 SE +/- 15.50, N = 15 SE +/- 14.78, N = 15 728.58 711.53 649.43 633.29 621.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 400 800 1200 1600 2000 SE +/- 9.44, N = 3 SE +/- 20.05, N = 3 SE +/- 9.70, N = 3 SE +/- 6.90, N = 15 SE +/- 97.47, N = 3 1926.9 1908.3 1906.1 1890.5 1836.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.18, N = 15 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 11.50 10.70 10.30 10.20 8.91 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 12 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 50 100 150 200 250 SE +/- 2.97, N = 3 SE +/- 4.91, N = 12 SE +/- 0.92, N = 3 SE +/- 2.27, N = 3 SE +/- 1.44, N = 3 220.9 207.5 171.0 170.6 168.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bumper Beam EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 30 60 90 120 150 SE +/- 1.80, N = 15 SE +/- 1.49, N = 15 SE +/- 2.19, N = 12 SE +/- 3.91, N = 12 SE +/- 2.49, N = 12 107.17 108.64 140.26 145.32 153.90
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Cell Phone Drop Test EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 20 40 60 80 100 SE +/- 1.68, N = 12 SE +/- 1.27, N = 15 SE +/- 3.30, N = 15 SE +/- 3.06, N = 15 SE +/- 3.05, N = 12 67.71 68.68 93.26 95.48 100.19
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Rubber O-Ring Seal Installation EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 40 80 120 160 200 SE +/- 3.52, N = 15 SE +/- 1.00, N = 3 SE +/- 8.68, N = 9 SE +/- 9.50, N = 9 SE +/- 5.45, N = 12 101.62 110.05 162.03 175.46 177.74
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bird Strike on Windshield EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 60 120 180 240 300 SE +/- 2.98, N = 12 SE +/- 2.93, N = 12 SE +/- 3.59, N = 9 SE +/- 7.66, N = 9 SE +/- 6.27, N = 9 177.58 183.64 259.88 266.65 276.24
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 2K 4K 6K 8K 10K SE +/- 210.57, N = 15 SE +/- 89.79, N = 6 SE +/- 68.61, N = 9 SE +/- 92.49, N = 15 SE +/- 81.68, N = 15 9750.34 9036.65 8784.83 7898.41 7857.53 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-4800 5K 10K 15K 20K 25K SE +/- 532.70, N = 12 SE +/- 161.84, N = 5 SE +/- 213.35, N = 5 SE +/- 94.12, N = 5 SE +/- 158.41, N = 5 24688.58 20961.35 20265.52 20223.60 19566.67 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 10K 20K 30K 40K 50K SE +/- 521.71, N = 15 SE +/- 545.16, N = 15 SE +/- 714.33, N = 15 SE +/- 613.23, N = 15 SE +/- 662.65, N = 12 47556.69 46710.34 40491.56 37149.88 37048.80 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 500 1000 1500 2000 2500 SE +/- 13.01, N = 8 SE +/- 18.71, N = 8 SE +/- 55.41, N = 15 SE +/- 41.08, N = 15 SE +/- 4.34, N = 6 2123.37 2117.29 1470.81 1169.68 1101.23 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 10 20 30 40 50 SE +/- 0.27, N = 3 SE +/- 0.33, N = 5 SE +/- 1.09, N = 12 SE +/- 0.88, N = 15 SE +/- 0.82, N = 15 29.55 30.24 32.87 42.94 43.80 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 50 100 150 200 250 SE +/- 1.88, N = 3 SE +/- 2.33, N = 12 SE +/- 2.92, N = 3 SE +/- 4.83, N = 12 SE +/- 8.24, N = 12 154.99 166.51 205.87 217.50 228.90 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: simple-H2O EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 6 12 18 24 30 SE +/- 0.82, N = 15 SE +/- 0.73, N = 12 SE +/- 1.38, N = 12 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 21.45 23.12 24.06 25.25 25.62 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.4 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 9 18 27 36 45 SE +/- 0.58, N = 15 SE +/- 0.96, N = 15 SE +/- 0.39, N = 15 SE +/- 0.15, N = 15 SE +/- 0.17, N = 15 37.24 35.07 26.48 23.72 22.47 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.4 Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 30 60 90 120 150 SE +/- 1.14, N = 15 SE +/- 1.50, N = 15 SE +/- 3.73, N = 15 SE +/- 1.52, N = 15 SE +/- 0.33, N = 15 127.93 125.54 85.01 77.52 74.13 1. (CXX) g++ options: -O3
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 1600 3200 4800 6400 8000 SE +/- 298.02, N = 15 SE +/- 298.76, N = 15 SE +/- 48.43, N = 3 SE +/- 180.65, N = 12 SE +/- 0.00, N = 3 7477.19 7317.33 6199.09 4256.28 3975.69 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 1400 2800 4200 5600 7000 SE +/- 321.53, N = 15 SE +/- 328.86, N = 15 SE +/- 58.27, N = 3 SE +/- 192.19, N = 12 SE +/- 14.20, N = 3 6642.94 6613.59 5146.33 3635.69 3349.85 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms EPYC 4564P @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 4 8 12 16 20 SE +/- 0.342, N = 7 SE +/- 0.297, N = 9 SE +/- 0.174, N = 9 SE +/- 0.120, N = 9 SE +/- 0.177, N = 9 14.471 13.691 8.215 8.031 7.579 1. (CXX) g++ options: -O3 -lm -ldl
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 EPYC 4364P @ DDR5-4800 EPYC 4364P @ DDR5-5200 3 6 9 12 15 SE +/- 0.059, N = 11 SE +/- 0.084, N = 15 SE +/- 0.250, N = 15 SE +/- 0.032, N = 9 SE +/- 0.055, N = 9 12.481 12.449 7.236 6.848 6.826 1. (CXX) g++ options: -O3 -lm -ldl
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 Xeon E-2488 @ DDR5-4800 EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 2K 4K 6K 8K 10K SE +/- 210.25, N = 15 SE +/- 57.24, N = 12 SE +/- 15.60, N = 6 SE +/- 55.23, N = 6 SE +/- 39.33, N = 5 8126.32 8106.15 8006.35 6744.86 6454.67 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate EPYC 4564P @ DDR5-5200 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 Xeon E-2488 @ DDR5-4800 3 6 9 12 15 SE +/- 0.258971, N = 12 SE +/- 0.166167, N = 15 SE +/- 0.144416, N = 15 SE +/- 0.133403, N = 15 SE +/- 0.054700, N = 3 9.577753 9.536711 5.330500 5.160364 4.204110 1. (CC) gcc options: -O3 -march=native -fopenmp
Redis Test: SET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 EPYC 4564P @ DDR5-4800 EPYC 4364P @ DDR5-5200 EPYC 4364P @ DDR5-4800 EPYC 4564P @ DDR5-5200 Xeon E-2488 @ DDR5-4800 800K 1600K 2400K 3200K 4000K SE +/- 72840.48, N = 12 SE +/- 201571.91, N = 12 SE +/- 181123.85, N = 15 SE +/- 164667.68, N = 15 SE +/- 128040.11, N = 15 3827317.96 3684418.98 3656582.35 3419833.50 3327348.65 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Phoronix Test Suite v10.8.4