eoy2024 Benchmarks for a future article. AMD EPYC 4124P 4-Core testing with a Supermicro AS-3015A-I H13SAE-MF v1.00 (2.1 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2412201-NE-EOY20246700&grs .
eoy2024 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b AMD EPYC 4564P 16-Core @ 5.88GHz (16 Cores / 32 Threads) Supermicro AS-3015A-I H13SAE-MF v1.00 (2.1 BIOS) AMD Device 14d8 2 x 32GB DRAM-4800MT/s Micron MTC20C2085S1EC48BA1 BC 3201GB Micron_7450_MTFDKCC3T2TFS + 960GB SAMSUNG MZ1L2960HCJR-00A07 ASPEED AMD Rembrandt Radeon HD Audio VA2431 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 1024x768 AMD EPYC 4484PX 12-Core @ 5.66GHz (12 Cores / 24 Threads) 6.12.2-061202-generic (x86_64) AMD EPYC 4464P 12-Core @ 5.48GHz (12 Cores / 24 Threads) AMD EPYC 4364P 8-Core @ 5.57GHz (8 Cores / 16 Threads) AMD EPYC 4584PX 16-Core @ 5.76GHz (16 Cores / 32 Threads) AMD EPYC 4124P 4-Core @ 5.17GHz (4 Cores / 8 Threads) 960GB SAMSUNG MZ1L2960HCJR-00A07 + 3201GB Micron_7450_MTFDKCC3T2TFS 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 Processor Details - a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601209 - 4484PX: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - px: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 4464p: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 4464p epyc: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 4364P: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 4584PX: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - EPYC 4584PX amd: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 45: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 41: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 - 41 b: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xa601209 Java Details - OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2) Python Details - Python 3.12.3 Security Details - a: 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: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 4484PX: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - px: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 4464p: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 4464p epyc: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 4364P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 4584PX: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4584PX amd: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 45: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 41: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 41 b: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
eoy2024 relion: Basic - CPU stockfish: Chess Benchmark byte: System Call litert: NASNet Mobile mt-dgemm: Sustained Floating-Point Rate byte: Pipe stockfish: Chess Benchmark ospray: gravity_spheres_volume/dim_512/ao/real_time blender: Barbershop - CPU-Only rustls: handshake - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 openssl: AES-128-GCM byte: Whetstone Double cassandra: Writes openssl: AES-256-GCM blender: Pabellon Barcelona - CPU-Only blender: BMW27 - CPU-Only astcenc: Thorough ospray: gravity_spheres_volume/dim_512/scivis/real_time astcenc: Medium blender: Junkshop - CPU-Only astcenc: Fast astcenc: Exhaustive ospray: particle_volume/ao/real_time astcenc: Very Thorough ospray: gravity_spheres_volume/dim_512/pathtracer/real_time blender: Fishy Cat - CPU-Only ospray: particle_volume/scivis/real_time blender: Classroom - CPU-Only byte: Dhrystone 2 openssl: ChaCha20 primesieve: 1e12 openssl: ChaCha20-Poly1305 primesieve: 1e13 compress-7zip: Decompression Rating povray: Trace Time etcpak: Multi-Threaded - ETC2 onednn: Recurrent Neural Network Inference - CPU rustls: handshake - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 onednn: Recurrent Neural Network Training - CPU rustls: handshake - TLS13_CHACHA20_POLY1305_SHA256 svt-av1: Preset 3 - Bosphorus 4K onednn: IP Shapes 1D - CPU onnx: ResNet101_DUC_HDC-12 - CPU - Standard build2: Time To Compile quantlib: XXS svt-av1: Preset 3 - Beauty 4K 10-bit namd: ATPase with 327,506 Atoms svt-av1: Preset 5 - Bosphorus 4K compress-7zip: Compression Rating quantlib: S onnx: fcn-resnet101-11 - CPU - Standard onednn: Deconvolution Batch shapes_3d - CPU cp2k: H20-64 xnnpack: FP16MobileNetV1 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024 rustls: handshake-ticket - TLS13_CHACHA20_POLY1305_SHA256 svt-av1: Preset 5 - Beauty 4K 10-bit x265: Bosphorus 4K xnnpack: FP32MobileNetV3Small svt-av1: Preset 8 - Beauty 4K 10-bit rustls: handshake-resume - TLS13_CHACHA20_POLY1305_SHA256 svt-av1: Preset 8 - Bosphorus 4K llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048 svt-av1: Preset 3 - Bosphorus 1080p llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024 namd: STMV with 1,066,628 Atoms svt-av1: Preset 8 - Bosphorus 1080p llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048 svt-av1: Preset 5 - Bosphorus 1080p gromacs: water_GMX50_bare llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512 rustls: handshake-resume - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 rustls: handshake-ticket - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 whisper-cpp: ggml-medium.en - 2016 State of the Union build-eigen: Time To Compile svt-av1: Preset 13 - Bosphorus 4K whisper-cpp: ggml-small.en - 2016 State of the Union litert: Inception V4 cp2k: H20-256 onednn: Deconvolution Batch shapes_1d - CPU litert: Mobilenet Quant xnnpack: FP32MobileNetV3Large litert: Inception ResNet V2 y-cruncher: 1B svt-av1: Preset 13 - Beauty 4K 10-bit litert: DeepLab V3 xnnpack: FP32MobileNetV1 onednn: Convolution Batch Shapes Auto - CPU y-cruncher: 500M svt-av1: Preset 13 - Bosphorus 1080p whisper-cpp: ggml-base.en - 2016 State of the Union onnx: super-resolution-10 - CPU - Standard cp2k: Fayalite-FIST ospray: particle_volume/pathtracer/real_time xnnpack: FP32MobileNetV2 xnnpack: QS8MobileNetV2 litert: Mobilenet Float litert: Quantized COCO SSD MobileNet v1 onnx: CaffeNet 12-int8 - CPU - Standard x265: Bosphorus 1080p xnnpack: FP16MobileNetV3Small whisperfile: Small whisperfile: Medium xnnpack: FP16MobileNetV2 onnx: ResNet50 v1-12-int8 - CPU - Standard litert: SqueezeNet xnnpack: FP16MobileNetV3Large onnx: bertsquad-12 - CPU - Standard whisperfile: Tiny onnx: yolov4 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onednn: IP Shapes 3D - CPU rustls: handshake-resume - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 rustls: handshake-ticket - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 renaissance: ALS Movie Lens renaissance: Finagle HTTP Requests onnx: ZFNet-512 - CPU - Standard financebench: Repo OpenMP onnx: T5 Encoder - CPU - Standard couchdb: 300 - 1000 - 30 financebench: Bonds OpenMP couchdb: 500 - 1000 - 30 renaissance: Genetic Algorithm Using Jenetics + Futures couchdb: 300 - 3000 - 30 couchdb: 100 - 1000 - 30 couchdb: 500 - 3000 - 30 couchdb: 100 - 3000 - 30 pyperformance: async_tree_io onnx: GPT-2 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard openvino-genai: Gemma-7b-int4-ov - CPU renaissance: Rand Forest pyperformance: asyncio_tcp_ssl renaissance: Apache Spark Bayes renaissance: Scala Dotty renaissance: Gaussian Mixture Model renaissance: In-Memory Database Shootout simdjson: DistinctUserID simdjson: PartialTweets simdjson: TopTweet openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU pyperformance: python_startup renaissance: Akka Unbalanced Cobwebbed Tree numpy: openvino-genai: Falcon-7b-instruct-int4-ov - CPU renaissance: Apache Spark PageRank renaissance: Savina Reactors.IO gcrypt: simdjson: Kostya llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 128 pyperformance: float llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128 llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 16 pyperformance: gc_collect llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128 simdjson: LargeRand pyperformance: pathlib llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128 llamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 16 pyperformance: asyncio_websockets pyperformance: regex_compile llamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 128 pyperformance: crypto_pyaes pyperformance: nbody pyperformance: xml_etree pyperformance: django_template pyperformance: json_loads llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 128 pyperformance: go llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 16 pyperformance: pickle_pure_python pyperformance: chaos llamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 128 pyperformance: raytrace llamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 16 llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 2048 llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 1024 llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 512 llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 256 llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 2048 llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 1024 llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 512 llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 256 llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 2048 llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 1024 llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 512 llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 256 llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 2048 llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 1024 llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 512 llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 256 openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Token openvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Token openvino-genai: Gemma-7b-int4-ov - CPU - Time To First Token onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: ResNet101_DUC_HDC-12 - CPU - Standard onnx: super-resolution-10 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: T5 Encoder - CPU - Standard onnx: ZFNet-512 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: GPT-2 - CPU - Standard renaissance: Apache Spark ALS a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 944.27 54752796 49140426.6 16936 1141.194104 48806257.1 46507038 7.63944 506.2 423535.68 104784522170 343491.9 271333 97172751700 166.12 53.55 20.3025 7.58789 156.2217 73.56 396.6495 1.6844 9.00917 2.741 8.82093 71.35 8.98486 143.36 1866536062.7 130588495050 6.347 92393529340 78.498 165916 18.542 577.817 700.859 80462.6 1372.03 76454.45 9.59 1.12573 1.54196 92.053 13.432 1.422 2.79632 34.538 163859 12.7476 3.2167 2.41294 58.191 1143 355.09 404263.45 6.504 32.57 979 12.468 388077.69 102.005 70.85 68.4 70.76 63.09 29.573 62.97 69.26 0.75656 339.023 279.04 101.971 1.692 327.3 1820810.21 1553632.14 700.91 58.655 212.52 245.07838 21477.8 592.857 2.97612 823.17 1810 19530.2 18.485 18.588 3579.67 1252 6.67287 8.772 842.558 87.48973 141.117 94.032 236.245 1495 844 1211.48 2129.52 636.318 114.45 920 195.41642 534.919 1190 390.597 1794.11 1498 15.5899 41.70935 11.0552 42.4537 4.058 3563852.57 2620332 9805.7 2319.4 102.331 21418.445312 156.453 106.13 33061.21875 148.049 732.8 367.83 69.929 511.775 232.188 755 134.596 47.0691 9.83 414.4 645 490.0 477.0 3399.5 3256.1 10.46 9.76 10.46 19.28 5.77 4403.8 775.75 12.93 2412.2 3506.4 162.125 5.97 26.28 50.7 47.72 24.59 677 6.88 1.83 14.2 7.24 1.78 315 69.8 1.99 41.7 59 35.8 20.7 12.1 10.47 77.8 10.22 165 38.2 20.13 175 19.03 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 51.86 55.93 77.34 86.06 101.72 106.62 21.2429 648.522 7.08601 2.55898 23.553 310.875 1.57084 64.141 6.39112 9.76985 90.4523 7.42776 729.4 45267546 30761218.9 8057.56 842.730642 33443359.2 33702298 5.63122 679.34 306153.2 76496336760 244075.3 174960 71160291870 226.34 74.08 14.17 5.54888 109.0265 97.01 278.2445 1.1887 6.52776 1.9412 6.41198 96.67 6.44913 197.2 1346521770.3 97105235690 9.116 68816544020 110.608 125698 25.264 410.726 965.015 59308.75 1898.36 57716.64 7.684 1.93806 1.17627 111.651 12.1169 1.188 2.38124 29.094 141263 11.8647 2.81093 3.5084 53.005 1383 232.26 344296.24 5.602 27.16 809 10.967 333882.92 85.201 66.57 68.2 69.11 63.8 25.446 63.61 66.85 0.65119 287.047 222.75 88.415 1.577 243.14 1586292.42 1329363.1 809.78969 67.364 198.112 268.23891 22083.3 628.104 3.40293 848.943 1515 19477.8 18.379 17.406 2343.38 1257 4.11551 8.688 776.115 92.70933 125.172 92.21 199.023 1365 717 1244.7 1420.15 941.401 101.37 779 173.38197 473.55091 1217 356.409 1809.18 1467 14.5122 37.13462 10.7338 37.3832 2.73072 3035330.21 2282729.64 9378.8 2492.2 110.94 22320.332031 208.174 117.566 34600.773438 164.468 904.0 406.12 75.901 559.346 253.99 666 159.71 40.0935 10.23 422.0 590 513.2 428.6 3860.6 3241.5 10.76 10.1 10.82 20.28 6.08 4038.4 745.59 13.4 2138.1 3655.8 171.023 6.11 27.59 51.3 52.3 25.86 699 7.11 1.84 14.4 7.41 1.83 321 71.7 2.05 43.1 59.5 36.8 21 12.4 10.91 78.6 10.45 169 39.7 20.39 182 19.49 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 49.31 58.91 74.65 93.01 97.79 121.48 24.9402 850.141 7.98873 2.80544 26.7478 355.751 1.06188 68.9051 4.80287 9.01322 93.1605 6.25815 733.02 42973396 30701622.8 7931.64 842.012831 33381363.1 33871595 5.71084 678.4 304060.28 76184405610 244131 173946 70902656480 224.64 73.16 14.1464 5.6147 108.8588 97.1 277.2994 1.1862 6.52206 1.9391 6.4074 97.09 6.52304 197.53 1340340196.6 97019897450 9.147 68678955550 110.709 125605 25.328 409.875 966.013 59206.34 1895.68 57688.08 7.646 1.93913 1.1705 113.78 12.1057 1.184 2.35379 28.824 142213 11.839 2.79638 3.51243 52.724 1386 244.77 342775.29 5.551 26.94 837 10.855 333574.3 84.998 66.35 68.81 67.95 63.79 25.447 63.41 66.52 0.65448 286.962 208.99 88.27 1.575 232.86 1572010.68 1340712.85 809.489 67.076 194.024 266.81425 22752.4 631.31 3.40628 849.209 1574 19490.7 18.365 17.355 2359.99 1272 4.13321 8.623 769.818 93.45463 125.076 94.896 197.2 1368 723 1244.51 1417.35 937.778 101.25 798 167.89219 475.51084 1248 356.194 1821.35 1527 14.5747 38.71828 10.7127 37.1048 2.72942 3038723.48 2292879.44 9275.7 2483.1 110.892 22318.738281 206.091 119.349 34896.835938 164.812 920.7 408.483 76.389 560.7 254.733 656 157.893 43.362 10.24 453.2 590 474.9 436.2 3815.2 3175.6 8.97 8.35 10.51 20.29 6.09 4002.3 831.42 13.41 2229.7 3676.0 163.839 5.45 27.8 50.8 52.37 25.94 706 7.12 1.84 14.4 7.44 1.84 322 72.5 2.05 43.3 59.2 36.5 21.2 12.5 10.93 79.4 10.45 168 39.4 20.51 182 19.5 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 49.28 58.86 74.54 93 97.61 122.3 23.0604 854.334 7.99486 2.80695 26.9485 357.602 1.066 68.6104 4.85142 9.01687 93.3441 6.33034 937.33 43158853 29969810.9 7759.69 818.678141 32471450.7 30315972 5.47043 739.91 301017.23 72709954220 242679 173633 67431535960 243.35 79.19 13.523 5.35756 103.8089 104.7 263.5475 1.1365 6.28807 1.8546 6.17399 105.45 6.29615 212.3 1272938788 93956743710 9.701 66548747470 118.664 118569 26.609 388.404 1009.58 57954.19 1911.44 56047.38 7.252 1.88731 1.14581 121.737 10.5788 1.129 2.21645 27.36 135033 10.2873 2.58688 3.38958 58.397 1418 235.01 336267.09 5.445 26.09 799 10.914 328877.92 82.525 63.71 65.24 64.96 60.68 24.854 60.47 64.15 0.61452 282.008 213.02 86.96 1.398 235.94 1543373.12 1297646.72 838.18425 69.379 192.171 280.03419 23141.4 676.742 3.43287 859.757 1473 20123.5 19.364 18.002 2272.28 1267 6.36475 9.041 752.155 97.94408 134.941 100.486 199.512 1357 703 1248.12 1431.19 724.533 101.23 759 178.32917 491.98412 1208 360.354 1820.34 1429 14.6885 40.847 10.4982 36.1205 3.75003 3061522.26 2283083.54 9243.0 2650.9 101.413 21588.90625 168.036 118.161 33551.523438 164.358 924.5 401.989 76.696 551.346 259.196 738 136.299 46.3543 10.17 415.3 626 515.3 424.6 3647.2 3288.5 10.54 9.8 10.66 19.82 5.8 4084.6 781.66 13.34 2366.1 3523.1 156.343 5.78 27.36 49.7 50.5 25.77 671 7.09 1.81 14.1 7.42 1.83 315 69.5 2.05 41.8 57.2 35.3 20.6 12 10.93 78.3 10.48 164 39 20.48 177 19.47 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 50.45 59.87 74.94 93 98.33 124.38 21.5708 872.742 7.41037 2.77422 27.6828 386.563 1.3797 68.0775 5.95035 9.85896 95.2507 7.33331 946.43 42042951 29923094.4 7640.81 812.147089 32439611.6 29940074 5.47057 731.39 301217.61 72667527300 242340.5 174025 67396254380 245.12 79.24 13.5139 5.36189 103.6744 104.01 263.3662 1.1368 6.29211 1.8559 6.17624 105.24 6.27188 211.4 1263644317.8 93907572870 9.705 66497739430 118.848 118587 26.595 388.128 1012.19 58056.01 1913.86 56176.9 7.232 1.88919 1.15632 117.067 10.5616 1.132 2.20728 27.564 133804 10.2531 2.59025 3.38823 58.864 1414 227.71 335411.96 5.422 25.85 791 10.885 326342.42 82.164 63.5 64.68 64.43 60.8 24.805 60.3 62.84 0.61093 281.892 212.3 86.386 1.393 242.1 1532788.04 1300937.3 839.98575 69.578 190.343 280.47206 22928.3 678.676 3.42547 857.489 1542 20503.5 19.278 17.944 2289.58 1246 6.3715 9.067 748.147 97.54562 134.517 97.446 199.546 1327 703 1248.6 1415.11 748.66 101.33 766 177.87 492.69519 1210 361.297 1822.7 1427 14.685 38.57843 10.4865 36.3968 3.74578 3082657.5 2304145.79 8980.8 2708.1 101.618 21612.042969 166.512 116.417 33538.269531 163.363 884.0 405.448 76.577 551.6 259.055 742 135.718 46.0921 10.2 412.9 628 513.3 442.9 3703.2 3275.5 10.28 9.63 10.69 19.82 5.81 4098.5 783.43 13.32 2373.0 3688.6 156.712 6.02 27.35 49.7 50.43 25.78 671 7.1 1.73 14.1 7.44 1.83 316 70 2.06 42 58.6 35.6 20.6 12 10.91 76 10.45 164 38.6 20.5 176 19.53 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 50.46 59.86 75.06 94.77 98.03 124.52 21.6933 864.81 7.43372 2.76714 27.4729 386.061 1.33516 68.0934 6.0047 9.83893 95.3576 7.36544 1369.225 31514937 21559197 3808.8 629.16512 23448988.5 24017024 3.91749 978.03 225379.66 53755663700 174760.6 139110 49930945600 320.59 103.97 10.3392 3.83152 80.3686 141.99 205.0144 0.8612 4.63965 1.4052 4.52318 136.51 4.62423 276.44 966576789.4 68048329660 12.273 48278109930 150.668 88229 34.917 304.244 1270.76 45095.35 2422.83 43571.86 5.373 1.90686 0.916317 154.429 8.19153 0.872 1.74038 19.85 101872 8.02696 2.05211 3.78008 68.171 1578 185.97 265949.2 3.802 18.85 335 6.458 272035.68 65.194 59.27 61.09 60.87 55.95 18.744 56.05 59.54 0.49771 215.213 171.68 65.318 1.104 204.06 1298373.66 1187839.34 966.00638 84.477 156.598 314.47722 24502.1 740.089 3.78629 935.994 753 21153.5 23.886 9.188 1569.75 1056 7.87367 10.954 652.965 103.71549 157.078 108.436 177.118 708 400 1044.53 1494.51 762.248 88.71 455 193.93664 528.33262 1088 376.531 1654.65 1067 19.8127 41.29562 13.2372 39.0828 4.45096 2874011.56 2353677.96 5993.4 1705.5 97.2268 21121.613281 141.568 118.317 32715.808594 163.915 749.9 398.386 73.237 545.967 239.078 726 125.52 44.8002 9.52 381.6 610 483.4 464.5 3397.0 3244.8 10.85 10.04 10.86 19 6.34 3720.1 813.31 12.59 2506.8 3349.5 154.317 6.06 25.52 48.2 51.86 24.27 649 6.64 1.81 13.5 7.02 1.76 308 68.1 1.93 40.7 56.8 34.7 20.1 11.8 10.32 75.3 9.92 162 38.3 19.6 174 18.83 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 52.64 71.58 79.41 115.73 105.09 154.83 22.3192 1091.32 6.36564 2.65482 25.5845 487.301 1.31121 50.4698 7.06075 10.2835 75.5414 7.96069 551.722 57247763 40531084 9311.77 1091.011509 44169926.7 44446458 7.3876 514.7 435194.2 100450008810 329601.4 235893 93168087590 171.82 55.26 18.7075 7.32353 144.4782 73.87 368.5451 1.5697 8.51573 2.5634 8.43752 73.96 8.49097 149.37 1765175324.6 127793294810 6.926 90711447140 84.489 164581 19.55 556.043 672.506 74468.49 1320.99 72793.26 9.329 1.12465 1.53619 91.724 14.624 1.426 2.83913 34.164 170361 14.0171 3.38658 2.67219 43.167 1200 290.1 393408.85 6.327 32.59 933 12.086 379874.32 101.332 90.01 93.24 92.89 86.17 29.067 86.56 91.12 0.75987 320.184 289.41 98.789 1.817 316.8 1863395.07 1559859.89 686.87944 58.818 217.908 233.68441 20102.8 517.664 3.07219 734.352 1760 18224 17.343 17.845 2185.78 1194 4.03808 8.173 842.344 84.68398 122.168 84.802 218.181 1484 809 1165.5 1337.78 1005.5 113.37 877 155.13923 425.50969 1224 383.134 1769.56 1527 15.0106 35.91499 11.3551 43.8436 2.74699 3397871.03 2528614.52 9891.4 2627.3 112.671 21948.935547 203.947 116.241 34053.0625 163.805 1050.3 397.426 75.893 553.805 252.825 653 166.047 48.2636 10.11 420.7 582 477.0 441.9 3806.5 3232.8 11.05 9.85 11.25 19.67 6.01 4384.0 806.83 13.32 2182.5 3582.4 150.639 6.07 27.2 51.1 49.9 25.32 682 7 1.82 14.1 7.32 1.82 315 71.4 2.03 42.7 59 36.1 20.8 12.5 10.81 78.4 10.3 166 39.2 20.23 176 19.27 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 50.84 56.06 75.06 86.04 98.91 105.36 20.7183 650.96 8.18519 2.60974 22.8062 295.281 0.994193 66.6172 4.90285 8.87444 88.0632 6.02069 553.782 58676636 40718581.6 9231.97 1093.097867 44323920 45724794 7.44575 513.66 436101.34 100666591640 331202 238227 93555991350 171.25 55.74 18.7499 7.32284 144.6262 73.55 368.5734 1.5743 8.57146 2.5694 8.47727 73.86 8.51233 148.97 1771958344.7 128265416980 6.903 90927418030 84.263 165934 20.325 556.412 670.234 74683.74 1320.37 72508.13 9.4 1.12801 1.54365 92.021 14.6973 1.433 2.85485 34.414 169750 14.0472 3.39064 2.66429 42.51 1196 324.04 394570 6.391 32.22 931 11.897 382691.63 101.537 91.31 93.49 93.91 86.47 29.205 86.44 90.48 0.75645 327.264 289.04 99.445 1.808 326.16 1874050.7 1569308.65 684.38662 58.692 218.529 233.05316 19859.4 517.918 3.06341 742.029 1756 18412.3 17.567 17.863 2200.93 1192 4.04877 8.279 845.584 84.02813 122.205 84.211 220.799 1477 807 1175.5 1339.69 999.973 113.16 871 155.9745 424.94666 1222 382.771 1765.39 1542 14.9427 35.4262 11.3166 44.051 2.77727 3431395.73 2558621.38 9969.8 2571.2 113.294 21848.070312 203.491 116.617 33913.464844 161.089 959.3 400.399 76.669 554.397 253.493 651 165.769 47.885 10.14 402.2 586 515.6 411.9 3773.1 3442.9 11.14 9.98 9.19 19.73 6.01 4344.8 754.41 13.24 2227.9 3641.9 159.247 6.04 27.19 51 49.76 25.3 686 7 1.83 14.1 7.37 1.83 317 69.8 2.03 42.7 58.8 36.2 21 12.2 10.85 79.6 10.37 165 39.1 20.26 176 19.24 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 50.68 55.47 75.51 86.2 98.64 104.38 20.8816 647.814 8.18265 2.61221 22.6984 294.927 0.999701 66.9202 4.91381 8.82581 88.3622 6.03024 549.8 55762702 40711986.9 9245.76 1092.088495 44309550.9 48797079 7.46399 513.54 435926.4 100742301290 331193.7 236826 93614594180 170.09 55.18 18.7661 7.31594 144.6131 73.69 369.0274 1.5767 8.54878 2.5696 8.49646 73.48 8.54395 149.37 1766450267.1 128278766110 6.937 91025092880 84.315 166180 19.521 556.865 670.7 74672.57 1320.23 72140.75 9.345 1.13012 1.54988 91.017 14.6226 1.427 2.83798 34.66 169373 14.0431 3.40178 2.66296 42.469 1195 291.02 395112.39 6.322 32.23 929 12.112 382067.3 101.522 90.96 94.08 91.71 86.68 29.179 86.91 91.17 0.76227 325.945 273.67 98.905 1.811 337.06 1862938 1569479.7 684.13056 57.18 217.957 232.58353 19686 517.502 3.05918 730.167 1754 17824.6 17.364 17.836 2152.48 1189 4.0355 8.119 835.45 84.11276 122.219 84.072 220.728 1478 801 1178.94 1343.22 1013.19 113.31 898 154.43658 424.57459 1223 380.801 1763.22 1547 14.8837 35.11036 11.3105 43.4886 2.77835 3379343.72 2559245.2 9972.0 2570.5 113.171 22060.152344 203.934 116.222 33906.6875 161.473 891.2 399.261 76.662 552.209 253.279 633 166.168 47.6721 10.17 407.7 581 500.0 455.6 3829.9 3408.4 9.15 10.32 9.4 19.71 6.03 4359.3 833.64 13.36 2179.0 3589.4 167.631 5.54 27.21 50.7 50.33 25.38 689 7 1.83 14.2 7.37 1.86 314 70.4 2.03 42.4 59.6 36.1 20.9 12.3 10.82 78.1 10.34 163 38.8 20.29 179 19.16 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 50.74 55.67 74.86 87.34 98.31 104.87 20.9753 645.208 8.18175 2.62573 22.9923 293.961 0.986643 67.1849 4.90313 8.83524 88.4104 6.01631 2771.778 12630264 10707715 5153.49 259.146491 11669425.7 12024682 1.84407 2077.69 106833.78 25376123290 84017.4 66243 23845653160 667.71 215.53 5.0655 1.90804 39.3205 292.14 100.3659 0.4244 2.30223 0.6923 2.23851 280.26 2.29544 560.89 478992410.7 33280835860 24.723 23701092760 301.596 43781 70.064 155.441 2415.25 22255.23 4726.08 21499.73 2.808 3.83117 0.464723 300.72 4.47643 0.443 0.88895 10.869 54079 4.43021 1.07903 7.53655 123.656 3512 132265.65 2.178 10.91 412 4.334 135362.96 35.849 10.578 0.27352 123.792 37.171 0.664 732992.32 596141.19 145.21 85.948 581.27325 49048.8 1281.082 7.26738 1781.6 1342 41844 40.562 8.007 2950.8 2367 9.18658 18.165 380.633 187.28645 73.2707 177.144 112.72 1425 623 2193.88 2736.98 495.836 56.61 714 2131 207.605 3173.55 2018 10.5186 7.16015 23.8412 4.94689 2105346.65 1656876.39 7465.1 1664.4 73.8845 32271.666016 141.955 153.029 47198.941406 212.829 806.4 515.495 96.744 695.352 314.485 855 124.166 36.107 439.9 723 566.2 506.5 3087.0 2951.1 9.92 9.32 10.02 6.93 4474.8 705.99 2267.1 3745.8 165.547 5.7 52.8 702 1.7 14.6 330 72.6 43 60.4 36.7 21.2 12.4 78.4 171 39.9 182 27.6891 2151.82 13.6457 4.8153 41.9418 926.756 2.01609 95.0664 7.04122 13.5323 139.659 8.04835 3046.805 14943737 10629944.8 5034.38 263.204392 11518844.2 11607502 1.90481 2095.98 105324.92 25582374640 83540.7 66519 23760535010 671.42 214.89 5.0448 1.89469 39.0377 294.04 99.3999 0.4223 2.26612 0.6906 2.22318 282.19 2.27718 563.14 475486444.1 33289542860 24.821 23701138360 302.737 43210 70.774 154.248 2441.27 22201.03 4752.85 21444.09 2.793 3.82885 0.464485 294.951 4.46411 0.441 0.89241 10.805 53425 4.43091 1.07829 7.55315 130.813 3508 115.67 132025.36 2.172 10.89 414 4.332 135016.23 35.641 31.91 32.94 32.97 30.93 10.554 31.04 32.59 0.27320 122.921 105.1 37.07 0.661 122.8 690282.02 602002.02 1797.8625 146.655 85.603 583.2045 49101.9 1282.66 7.28139 1785.4 1359 41757.9 39.245 7.984 2994.59 2407 9.16956 18.29 377.791 186.22906 73.8364 179.122 111.483 1443 623 2190.79 2741.68 495.078 56.03 720 310.38181 845.17 2097 202.118 3179.55 1998 10.6241 66.11323 7.15712 23.9108 4.95867 2103587.5 1571309.62 7147.4 1669.9 73.0047 32477.349609 140.034 154.041 46851.421875 212.528 801.4 513.583 96.554 698.074 316.459 858 123.269 38.5294 8.05 485.4 737 600.1 515.8 3130.4 3681.9 10.16 9.3 9.97 16.65 6.97 4457.1 700.76 11.38 2292.2 3818.5 169.141 5.68 25.09 52.9 51.5 23.8 704 6.55 1.71 14.6 6.9 1.73 331 72.7 1.93 43.1 60 36.6 21.3 12.4 10.46 78.7 9.99 171 40.2 20.08 180 19.17 12288 6144 3072 1536 32768 16384 8192 4096 32768 16384 8192 4096 32768 16384 8192 4096 60.07 130.47 87.9 217.85 124.24 288.64 25.9499 2152.92 13.5417 4.94636 41.8199 927.388 2.01913 94.1216 7.13857 13.6955 139.718 8.10767 OpenBenchmarking.org
RELION Test: Basic - Device: CPU OpenBenchmarking.org Seconds, Fewer Is Better RELION 5.0 Test: Basic - Device: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 700 1400 2100 2800 3500 944.27 729.40 733.02 937.33 946.43 1369.23 551.72 553.78 549.80 2771.78 3046.81 1. (CXX) g++ options: -fPIC -std=c++14 -fopenmp -O3 -rdynamic -lfftw3f -lfftw3 -ldl -ltiff -lpng -ljpeg -lmpi_cxx -lmpi
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 17 Chess Benchmark a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 13M 26M 39M 52M 65M 54752796 45267546 42973396 43158853 42042951 31514937 57247763 58676636 55762702 12630264 14943737 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
BYTE Unix Benchmark Computational Test: System Call OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: System Call a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 11M 22M 33M 44M 55M 49140426.6 30761218.9 30701622.8 29969810.9 29923094.4 21559197.0 40531084.0 40718581.6 40711986.9 10707715.0 10629944.8 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
LiteRT Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: NASNet Mobile a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4K 8K 12K 16K 20K 16936.00 8057.56 7931.64 7759.69 7640.81 3808.80 9311.77 9231.97 9245.76 5153.49 5034.38
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 1141.19 842.73 842.01 818.68 812.15 629.17 1091.01 1093.10 1092.09 259.15 263.20 1. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas
BYTE Unix Benchmark Computational Test: Pipe OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: Pipe a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10M 20M 30M 40M 50M 48806257.1 33443359.2 33381363.1 32471450.7 32439611.6 23448988.5 44169926.7 44323920.0 44309550.9 11669425.7 11518844.2 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish Chess Benchmark a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10M 20M 30M 40M 50M 46507038 33702298 33871595 30315972 29940074 24017024 44446458 45724794 48797079 12024682 11607502 1. Stockfish 16 by the Stockfish developers (see AUTHORS file)
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/ao/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 7.63944 5.63122 5.71084 5.47043 5.47057 3.91749 7.38760 7.44575 7.46399 1.84407 1.90481
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Barbershop - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400 800 1200 1600 2000 506.20 679.34 678.40 739.91 731.39 978.03 514.70 513.66 513.54 2077.69 2095.98
Rustls Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 90K 180K 270K 360K 450K 423535.68 306153.20 304060.28 301017.23 301217.61 225379.66 435194.20 436101.34 435926.40 106833.78 105324.92 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-128-GCM a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20000M 40000M 60000M 80000M 100000M 104784522170 76496336760 76184405610 72709954220 72667527300 53755663700 100450008810 100666591640 100742301290 25376123290 25582374640 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8
BYTE Unix Benchmark Computational Test: Whetstone Double OpenBenchmarking.org MWIPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: Whetstone Double a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70K 140K 210K 280K 350K 343491.9 244075.3 244131.0 242679.0 242340.5 174760.6 329601.4 331202.0 331193.7 84017.4 83540.7 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 5.0 Test: Writes a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 60K 120K 180K 240K 300K 271333 174960 173946 173633 174025 139110 235893 238227 236826 66243 66519
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-256-GCM a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20000M 40000M 60000M 80000M 100000M 97172751700 71160291870 70902656480 67431535960 67396254380 49930945600 93168087590 93555991350 93614594180 23845653160 23760535010 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 140 280 420 560 700 166.12 226.34 224.64 243.35 245.12 320.59 171.82 171.25 170.09 667.71 671.42
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: BMW27 - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 50 100 150 200 250 53.55 74.08 73.16 79.19 79.24 103.97 55.26 55.74 55.18 215.53 214.89
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 5.0 Preset: Thorough a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 5 10 15 20 25 20.3025 14.1700 14.1464 13.5230 13.5139 10.3392 18.7075 18.7499 18.7661 5.0655 5.0448 1. (CXX) g++ options: -O3 -flto -pthread
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 7.58789 5.54888 5.61470 5.35756 5.36189 3.83152 7.32353 7.32284 7.31594 1.90804 1.89469
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 5.0 Preset: Medium a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 156.22 109.03 108.86 103.81 103.67 80.37 144.48 144.63 144.61 39.32 39.04 1. (CXX) g++ options: -O3 -flto -pthread
Blender Blend File: Junkshop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Junkshop - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 60 120 180 240 300 73.56 97.01 97.10 104.70 104.01 141.99 73.87 73.55 73.69 292.14 294.04
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 5.0 Preset: Fast a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 90 180 270 360 450 396.65 278.24 277.30 263.55 263.37 205.01 368.55 368.57 369.03 100.37 99.40 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 5.0 Preset: Exhaustive a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.379 0.758 1.137 1.516 1.895 1.6844 1.1887 1.1862 1.1365 1.1368 0.8612 1.5697 1.5743 1.5767 0.4244 0.4223 1. (CXX) g++ options: -O3 -flto -pthread
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: particle_volume/ao/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 9.00917 6.52776 6.52206 6.28807 6.29211 4.63965 8.51573 8.57146 8.54878 2.30223 2.26612
ASTC Encoder Preset: Very Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 5.0 Preset: Very Thorough a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.6167 1.2334 1.8501 2.4668 3.0835 2.7410 1.9412 1.9391 1.8546 1.8559 1.4052 2.5634 2.5694 2.5696 0.6923 0.6906 1. (CXX) g++ options: -O3 -flto -pthread
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 8.82093 6.41198 6.40740 6.17399 6.17624 4.52318 8.43752 8.47727 8.49646 2.23851 2.22318
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 60 120 180 240 300 71.35 96.67 97.09 105.45 105.24 136.51 73.96 73.86 73.48 280.26 282.19
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: particle_volume/scivis/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 8.98486 6.44913 6.52304 6.29615 6.27188 4.62423 8.49097 8.51233 8.54395 2.29544 2.27718
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Classroom - Compute: CPU-Only a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 120 240 360 480 600 143.36 197.20 197.53 212.30 211.40 276.44 149.37 148.97 149.37 560.89 563.14
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 5.1.3-git Computational Test: Dhrystone 2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400M 800M 1200M 1600M 2000M 1866536062.7 1346521770.3 1340340196.6 1272938788.0 1263644317.8 966576789.4 1765175324.6 1771958344.7 1766450267.1 478992410.7 475486444.1 1. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30000M 60000M 90000M 120000M 150000M 130588495050 97105235690 97019897450 93956743710 93907572870 68048329660 127793294810 128265416980 128278766110 33280835860 33289542860 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.6 Length: 1e12 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 6 12 18 24 30 6.347 9.116 9.147 9.701 9.705 12.273 6.926 6.903 6.937 24.723 24.821 1. (CXX) g++ options: -O3
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20-Poly1305 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20000M 40000M 60000M 80000M 100000M 92393529340 68816544020 68678955550 66548747470 66497739430 48278109930 90711447140 90927418030 91025092880 23701092760 23701138360 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.6 Length: 1e13 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70 140 210 280 350 78.50 110.61 110.71 118.66 118.85 150.67 84.49 84.26 84.32 301.60 302.74 1. (CXX) g++ options: -O3
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression Test: Decompression Rating a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40K 80K 120K 160K 200K 165916 125698 125605 118569 118587 88229 164581 165934 166180 43781 43210 1. 7-Zip 23.01 (x64) : Copyright (c) 1999-2023 Igor Pavlov : 2023-06-20
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray Trace Time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 16 32 48 64 80 18.54 25.26 25.33 26.61 26.60 34.92 19.55 20.33 19.52 70.06 70.77 1. POV-Ray 3.7.0.10.unofficial
Etcpak Benchmark: Multi-Threaded - Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 2.0 Benchmark: Multi-Threaded - Configuration: ETC2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 120 240 360 480 600 577.82 410.73 409.88 388.40 388.13 304.24 556.04 556.41 556.87 155.44 154.25 1. (CXX) g++ options: -flto -pthread
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 700.86 965.02 966.01 1009.58 1012.19 1270.76 672.51 670.23 670.70 2415.25 2441.27 MIN: 679.89 MIN: 963.27 MIN: 963.43 MIN: 994.85 MIN: 999.17 MIN: 1266.25 MIN: 665.03 MIN: 663.39 MIN: 662.66 MIN: 2406.21 MIN: 2435.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Rustls Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20K 40K 60K 80K 100K 80462.60 59308.75 59206.34 57954.19 58056.01 45095.35 74468.49 74683.74 74672.57 22255.23 22201.03 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 1000 2000 3000 4000 5000 1372.03 1898.36 1895.68 1911.44 1913.86 2422.83 1320.99 1320.37 1320.23 4726.08 4752.85 MIN: 1342.06 MIN: 1894.26 MIN: 1892.59 MIN: 1895 MIN: 1899.63 MIN: 2416.25 MIN: 1308.56 MIN: 1301.96 MIN: 1302.81 MIN: 4716.28 MIN: 4746.78 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Rustls Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 16K 32K 48K 64K 80K 76454.45 57716.64 57688.08 56047.38 56176.90 43571.86 72793.26 72508.13 72140.75 21499.73 21444.09 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 4K a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 9.590 7.684 7.646 7.252 7.232 5.373 9.329 9.400 9.345 2.808 2.793 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.862 1.724 2.586 3.448 4.31 1.12573 1.93806 1.93913 1.88731 1.88919 1.90686 1.12465 1.12801 1.13012 3.83117 3.82885 MIN: 1.03 MIN: 1.92 MIN: 1.91 MIN: 1.83 MIN: 1.83 MIN: 1.86 MIN: 1.09 MIN: 1.1 MIN: 1.1 MIN: 3.77 MIN: 3.77 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.3487 0.6974 1.0461 1.3948 1.7435 1.541960 1.176270 1.170500 1.145810 1.156320 0.916317 1.536190 1.543650 1.549880 0.464723 0.464485 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.17 Time To Compile a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70 140 210 280 350 92.05 111.65 113.78 121.74 117.07 154.43 91.72 92.02 91.02 300.72 294.95
QuantLib Size: XXS OpenBenchmarking.org tasks/s, More Is Better QuantLib 1.35-dev Size: XXS a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4 8 12 16 20 13.43200 12.11690 12.10570 10.57880 10.56160 8.19153 14.62400 14.69730 14.62260 4.47643 4.46411 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
SVT-AV1 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.3224 0.6448 0.9672 1.2896 1.612 1.422 1.188 1.184 1.129 1.132 0.872 1.426 1.433 1.427 0.443 0.441 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
NAMD Input: ATPase with 327,506 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: ATPase with 327,506 Atoms a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.6423 1.2846 1.9269 2.5692 3.2115 2.79632 2.38124 2.35379 2.21645 2.20728 1.74038 2.83913 2.85485 2.83798 0.88895 0.89241
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 4K a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 8 16 24 32 40 34.54 29.09 28.82 27.36 27.56 19.85 34.16 34.41 34.66 10.87 10.81 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression Test: Compression Rating a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40K 80K 120K 160K 200K 163859 141263 142213 135033 133804 101872 170361 169750 169373 54079 53425 1. 7-Zip 23.01 (x64) : Copyright (c) 1999-2023 Igor Pavlov : 2023-06-20
QuantLib Size: S OpenBenchmarking.org tasks/s, More Is Better QuantLib 1.35-dev Size: S a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4 8 12 16 20 12.74760 11.86470 11.83900 10.28730 10.25310 8.02696 14.01710 14.04720 14.04310 4.43021 4.43091 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.7654 1.5308 2.2962 3.0616 3.827 3.21670 2.81093 2.79638 2.58688 2.59025 2.05211 3.38658 3.39064 3.40178 1.07903 1.07829 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 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 2.41294 3.50840 3.51243 3.38958 3.38823 3.78008 2.67219 2.66429 2.66296 7.53655 7.55315 MIN: 2.34 MIN: 3.46 MIN: 3.47 MIN: 3.28 MIN: 3.28 MIN: 3.64 MIN: 2.62 MIN: 2.62 MIN: 2.62 MIN: 7.53 MIN: 7.52 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
CP2K Molecular Dynamics Input: H20-64 OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 2024.3 Input: H20-64 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 58.19 53.01 52.72 58.40 58.86 68.17 43.17 42.51 42.47 123.66 130.81 1. (F9X) gfortran options: -fopenmp -march=native -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kgrid -lcp2kgriddgemm -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kdbx -lcp2kdbm -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -l:libhdf5_fortran.a -l:libhdf5.a -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -llibgrpp -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -l:libopenblas.a -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm
XNNPACK Model: FP16MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV1 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800 1600 2400 3200 4000 1143 1383 1386 1418 1414 1578 1200 1196 1195 3512 3508 1. (CXX) g++ options: -O3 -lrt -lm
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 80 160 240 320 400 355.09 232.26 244.77 235.01 227.71 185.97 290.10 324.04 291.02 115.67 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Rustls Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 90K 180K 270K 360K 450K 404263.45 344296.24 342775.29 336267.09 335411.96 265949.20 393408.85 394570.00 395112.39 132265.65 132025.36 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
SVT-AV1 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 6.504 5.602 5.551 5.445 5.422 3.802 6.327 6.391 6.322 2.178 2.172 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 Video Input: Bosphorus 4K a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 8 16 24 32 40 32.57 27.16 26.94 26.09 25.85 18.85 32.59 32.22 32.23 10.91 10.89 1. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Small a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 979 809 837 799 791 335 934 931 929 412 414 1. (CXX) g++ options: -O3 -lrt -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 12.468 10.967 10.855 10.914 10.885 6.458 12.086 11.897 12.112 4.334 4.332 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Rustls Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 80K 160K 240K 320K 400K 388077.69 333882.92 333574.30 328877.92 326342.42 272035.68 379874.32 382691.63 382067.30 135362.96 135016.23 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 4K a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20 40 60 80 100 102.01 85.20 85.00 82.53 82.16 65.19 101.33 101.54 101.52 35.85 35.64 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 70.85 66.57 66.35 63.71 63.50 59.27 90.01 91.31 90.96 31.91 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 68.40 68.20 68.81 65.24 64.68 61.09 93.24 93.49 94.08 32.94 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 70.76 69.11 67.95 64.96 64.43 60.87 92.89 93.91 91.71 32.97 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 63.09 63.80 63.79 60.68 60.80 55.95 86.17 86.47 86.68 30.93 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 1080p a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 7 14 21 28 35 29.57 25.45 25.45 24.85 24.81 18.74 29.07 29.21 29.18 10.58 10.55 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 62.97 63.61 63.41 60.47 60.30 56.05 86.56 86.44 86.91 31.04 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 69.26 66.85 66.52 64.15 62.84 59.54 91.12 90.48 91.17 32.59 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
NAMD Input: STMV with 1,066,628 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: STMV with 1,066,628 Atoms a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.1715 0.343 0.5145 0.686 0.8575 0.75656 0.65119 0.65448 0.61452 0.61093 0.49771 0.75987 0.75645 0.76227 0.27352 0.27320
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70 140 210 280 350 339.02 287.05 286.96 282.01 281.89 215.21 320.18 327.26 325.95 123.79 122.92 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 60 120 180 240 300 279.04 222.75 208.99 213.02 212.30 171.68 289.41 289.04 273.67 105.10 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 1080p a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20 40 60 80 100 101.97 88.42 88.27 86.96 86.39 65.32 98.79 99.45 98.91 37.17 37.07 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
GROMACS Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS Input: water_GMX50_bare a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.4088 0.8176 1.2264 1.6352 2.044 1.692 1.577 1.575 1.398 1.393 1.104 1.817 1.808 1.811 0.664 0.661 1. GROMACS version: 2023.3-Ubuntu_2023.3_1ubuntu3
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 70 140 210 280 350 327.30 243.14 232.86 235.94 242.10 204.06 316.80 326.16 337.06 122.80 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Rustls Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400K 800K 1200K 1600K 2000K 1820810.21 1586292.42 1572010.68 1543373.12 1532788.04 1298373.66 1863395.07 1874050.70 1862938.00 732992.32 690282.02 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Rustls Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 300K 600K 900K 1200K 1500K 1553632.14 1329363.10 1340712.85 1297646.72 1300937.30 1187839.34 1559859.89 1569308.65 1569479.70 596141.19 602002.02 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Whisper.cpp Model: ggml-medium.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-medium.en - Input: 2016 State of the Union a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 400 800 1200 1600 2000 700.91 809.79 809.49 838.18 839.99 966.01 686.88 684.39 684.13 1797.86 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.4.0 Time To Compile a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 58.66 67.36 67.08 69.38 69.58 84.48 58.82 58.69 57.18 145.21 146.66
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 4K a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 50 100 150 200 250 212.52 198.11 194.02 192.17 190.34 156.60 217.91 218.53 217.96 85.95 85.60 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Whisper.cpp Model: ggml-small.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-small.en - Input: 2016 State of the Union a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 130 260 390 520 650 245.08 268.24 266.81 280.03 280.47 314.48 233.68 233.05 232.58 581.27 583.20 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
LiteRT Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception V4 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 11K 22K 33K 44K 55K 21477.8 22083.3 22752.4 23141.4 22928.3 24502.1 20102.8 19859.4 19686.0 49048.8 49101.9
CP2K Molecular Dynamics Input: H20-256 OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 2024.3 Input: H20-256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 300 600 900 1200 1500 592.86 628.10 631.31 676.74 678.68 740.09 517.66 517.92 517.50 1281.08 1282.66 1. (F9X) gfortran options: -fopenmp -march=native -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kgrid -lcp2kgriddgemm -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kdbx -lcp2kdbm -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -l:libhdf5_fortran.a -l:libhdf5.a -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -llibgrpp -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -l:libopenblas.a -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 2.97612 3.40293 3.40628 3.43287 3.42547 3.78629 3.07219 3.06341 3.05918 7.26738 7.28139 MIN: 2.42 MIN: 3.03 MIN: 3.03 MIN: 2.96 MIN: 2.9 MIN: 3.55 MIN: 2.59 MIN: 2.58 MIN: 2.56 MIN: 6.92 MIN: 6.94 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
LiteRT Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Quant a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400 800 1200 1600 2000 823.17 848.94 849.21 859.76 857.49 935.99 734.35 742.03 730.17 1781.60 1785.40
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Large a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400 800 1200 1600 2000 1810 1515 1574 1473 1542 753 1749 1756 1754 1342 1359 1. (CXX) g++ options: -O3 -lrt -lm
LiteRT Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception ResNet V2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 9K 18K 27K 36K 45K 19530.2 19477.8 19490.7 20123.5 20503.5 21153.5 18224.0 18412.3 17824.6 41844.0 41757.9
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 1B a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 9 18 27 36 45 18.49 18.38 18.37 19.36 19.28 23.89 17.34 17.57 17.36 40.56 39.25
SVT-AV1 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 5 10 15 20 25 18.588 17.406 17.355 18.002 17.944 9.188 17.845 17.863 17.836 8.007 7.984 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
LiteRT Model: DeepLab V3 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: DeepLab V3 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800 1600 2400 3200 4000 3579.67 2343.38 2359.99 2272.28 2289.58 1569.75 2185.78 2200.93 2152.48 2950.80 2994.59
XNNPACK Model: FP32MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV1 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 1252 1257 1272 1267 1246 1056 1191 1192 1189 2367 2407 1. (CXX) g++ options: -O3 -lrt -lm
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 6.67287 4.11551 4.13321 6.36475 6.37150 7.87367 4.03808 4.04877 4.03550 9.18658 9.16956 MIN: 6.2 MIN: 4.05 MIN: 4.07 MIN: 6.28 MIN: 6.28 MIN: 7.77 MIN: 3.98 MIN: 3.99 MIN: 3.98 MIN: 9.06 MIN: 9.03 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 500M a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 5 10 15 20 25 8.772 8.688 8.623 9.041 9.067 10.954 8.173 8.279 8.119 18.165 18.290
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 842.56 776.12 769.82 752.16 748.15 652.97 842.34 845.58 835.45 380.63 377.79 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-base.en - Input: 2016 State of the Union a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 87.49 92.71 93.45 97.94 97.55 103.72 84.68 84.03 84.11 187.29 186.23 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 141.12 125.17 125.08 134.94 134.52 157.08 122.17 122.21 122.22 73.27 73.84 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CP2K Molecular Dynamics Input: Fayalite-FIST OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 2024.3 Input: Fayalite-FIST a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 94.03 92.21 94.90 100.49 97.45 108.44 84.80 84.21 84.07 177.14 179.12 1. (F9X) gfortran options: -fopenmp -march=native -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kgrid -lcp2kgriddgemm -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kdbx -lcp2kdbm -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -l:libhdf5_fortran.a -l:libhdf5.a -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -llibgrpp -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -l:libopenblas.a -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.2 Benchmark: particle_volume/pathtracer/real_time a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 50 100 150 200 250 236.25 199.02 197.20 199.51 199.55 177.12 218.18 220.80 220.73 112.72 111.48
XNNPACK Model: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 300 600 900 1200 1500 1495 1365 1368 1357 1327 708 1481 1477 1478 1425 1443 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QS8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: QS8MobileNetV2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 844 717 723 703 703 400 814 807 801 623 623 1. (CXX) g++ options: -O3 -lrt -lm
LiteRT Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Float a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 1211.48 1244.70 1244.51 1248.12 1248.60 1044.53 1165.50 1175.50 1178.94 2193.88 2190.79
LiteRT Model: Quantized COCO SSD MobileNet v1 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 600 1200 1800 2400 3000 2129.52 1420.15 1417.35 1431.19 1415.11 1494.51 1337.78 1339.69 1343.22 2736.98 2741.68
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 636.32 941.40 937.78 724.53 748.66 762.25 1005.50 999.97 1013.19 495.84 495.08 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 Video Input: Bosphorus 1080p a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 114.45 101.37 101.25 101.23 101.33 88.71 113.37 113.16 113.31 56.61 56.03 1. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Small a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 920 779 798 759 766 455 882 871 898 714 720 1. (CXX) g++ options: -O3 -lrt -lm
Whisperfile Model Size: Small OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Small a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 70 140 210 280 350 195.42 173.38 167.89 178.33 177.87 193.94 155.14 155.97 154.44 310.38
Whisperfile Model Size: Medium OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Medium a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 200 400 600 800 1000 534.92 473.55 475.51 491.98 492.70 528.33 425.51 424.95 424.57 845.17
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV2 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 1190 1217 1248 1208 1210 1088 1212 1222 1223 2131 2097 1. (CXX) g++ options: -O3 -lrt -lm
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 80 160 240 320 400 390.60 356.41 356.19 360.35 361.30 376.53 383.13 382.77 380.80 207.61 202.12 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
LiteRT Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: SqueezeNet a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 700 1400 2100 2800 3500 1794.11 1809.18 1821.35 1820.34 1822.70 1654.65 1769.56 1765.39 1763.22 3173.55 3179.55
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Large a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 400 800 1200 1600 2000 1498 1467 1527 1429 1427 1067 1532 1542 1547 2018 1998 1. (CXX) g++ options: -O3 -lrt -lm
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 5 10 15 20 25 15.59 14.51 14.57 14.69 14.69 19.81 15.01 14.94 14.88 10.52 10.62 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Whisperfile Model Size: Tiny OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Tiny a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 15 30 45 60 75 41.71 37.13 38.72 40.85 38.58 41.30 35.91 35.43 35.11 66.11
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 11.05520 10.73380 10.71270 10.49820 10.48650 13.23720 11.35510 11.31660 11.31050 7.16015 7.15712 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10 20 30 40 50 42.45 37.38 37.10 36.12 36.40 39.08 43.84 44.05 43.49 23.84 23.91 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 1.1157 2.2314 3.3471 4.4628 5.5785 4.05800 2.73072 2.72942 3.75003 3.74578 4.45096 2.74699 2.77727 2.77835 4.94689 4.95867 MIN: 3.75 MIN: 2.7 MIN: 2.7 MIN: 3.71 MIN: 3.71 MIN: 4.38 MIN: 2.72 MIN: 2.75 MIN: 2.74 MIN: 4.85 MIN: 4.87 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Rustls Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800K 1600K 2400K 3200K 4000K 3563852.57 3035330.21 3038723.48 3061522.26 3082657.50 2874011.56 3397871.03 3431395.73 3379343.72 2105346.65 2103587.50 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Rustls Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 600K 1200K 1800K 2400K 3000K 2620332.00 2282729.64 2292879.44 2283083.54 2304145.79 2353677.96 2528614.52 2558621.38 2559245.20 1656876.39 1571309.62 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: ALS Movie Lens a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2K 4K 6K 8K 10K 9805.7 9378.8 9275.7 9243.0 8980.8 5993.4 9891.4 9969.8 9972.0 7465.1 7147.4 MIN: 9253.4 / MAX: 10057.61 MIN: 8718.36 / MAX: 9413.7 MIN: 8821.09 / MAX: 9495.91 MIN: 8920.42 / MAX: 9406.46 MIN: 8480.95 / MAX: 9113.57 MIN: 5836.57 / MAX: 6535.35 MIN: 9364.27 / MAX: 10037.94 MIN: 9680.91 / MAX: 9983.16 MIN: 9479.38 / MAX: 10040.33 MIN: 6716.72 / MAX: 7815.35 MIN: 6653.82 / MAX: 7863.42
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Finagle HTTP Requests a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 600 1200 1800 2400 3000 2319.4 2492.2 2483.1 2650.9 2708.1 1705.5 2627.3 2571.2 2570.5 1664.4 1669.9 MIN: 1832.84 MIN: 1947.63 MIN: 1933.43 MIN: 2066.79 MIN: 2074.84 / MAX: 2708.11 MIN: 1676.49 / MAX: 1730.57 MIN: 2034.59 / MAX: 2627.31 MIN: 1999.64 MIN: 1960.33 / MAX: 2570.51 MIN: 1625.17 / MAX: 1776.68 MIN: 1612.75 / MAX: 1713.57
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 102.33 110.94 110.89 101.41 101.62 97.23 112.67 113.29 113.17 73.88 73.00 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
FinanceBench Benchmark: Repo OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Repo OpenMP a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 7K 14K 21K 28K 35K 21418.45 22320.33 22318.74 21588.91 21612.04 21121.61 21948.94 21848.07 22060.15 32271.67 32477.35 1. (CXX) g++ options: -O3 -march=native -fopenmp
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 50 100 150 200 250 156.45 208.17 206.09 168.04 166.51 141.57 203.95 203.49 203.93 141.96 140.03 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Apache CouchDB Bulk Size: 300 - Inserts: 1000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 300 - Inserts: 1000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 106.13 117.57 119.35 118.16 116.42 118.32 116.24 116.62 116.22 153.03 154.04 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
FinanceBench Benchmark: Bonds OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Bonds OpenMP a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10K 20K 30K 40K 50K 33061.22 34600.77 34896.84 33551.52 33538.27 32715.81 34053.06 33913.46 33906.69 47198.94 46851.42 1. (CXX) g++ options: -O3 -march=native -fopenmp
Apache CouchDB Bulk Size: 500 - Inserts: 1000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 500 - Inserts: 1000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 50 100 150 200 250 148.05 164.47 164.81 164.36 163.36 163.92 163.81 161.09 161.47 212.83 212.53 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 732.8 904.0 920.7 924.5 884.0 749.9 1050.3 959.3 891.2 806.4 801.4 MIN: 713.67 / MAX: 813.49 MIN: 886.83 / MAX: 919.31 MIN: 888.75 / MAX: 934.44 MIN: 821.03 MIN: 863.46 / MAX: 897.46 MIN: 737.7 / MAX: 777.92 MIN: 1016.46 / MAX: 1068.02 MIN: 844.95 MIN: 861.29 / MAX: 903.79 MIN: 786.25 / MAX: 832.34 MIN: 786.46 / MAX: 836.72
Apache CouchDB Bulk Size: 300 - Inserts: 3000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 300 - Inserts: 3000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 110 220 330 440 550 367.83 406.12 408.48 401.99 405.45 398.39 397.43 400.40 399.26 515.50 513.58 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
Apache CouchDB Bulk Size: 100 - Inserts: 1000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 100 - Inserts: 1000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20 40 60 80 100 69.93 75.90 76.39 76.70 76.58 73.24 75.89 76.67 76.66 96.74 96.55 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
Apache CouchDB Bulk Size: 500 - Inserts: 3000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 500 - Inserts: 3000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 150 300 450 600 750 511.78 559.35 560.70 551.35 551.60 545.97 553.81 554.40 552.21 695.35 698.07 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
Apache CouchDB Bulk Size: 100 - Inserts: 3000 - Rounds: 30 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.4.1 Bulk Size: 100 - Inserts: 3000 - Rounds: 30 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70 140 210 280 350 232.19 253.99 254.73 259.20 259.06 239.08 252.83 253.49 253.28 314.49 316.46 1. (CXX) g++ options: -flto -lstdc++ -shared -lei
PyPerformance Benchmark: async_tree_io OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: async_tree_io a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 755 666 656 738 742 726 653 651 633 855 858
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 134.60 159.71 157.89 136.30 135.72 125.52 166.05 165.77 166.17 124.17 123.27 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 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 11 22 33 44 55 47.07 40.09 43.36 46.35 46.09 44.80 48.26 47.89 47.67 36.11 38.53 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 3 6 9 12 15 9.83 10.23 10.24 10.17 10.20 9.52 10.11 10.14 10.17 8.05
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Random Forest a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 110 220 330 440 550 414.4 422.0 453.2 415.3 412.9 381.6 420.7 402.2 407.7 439.9 485.4 MIN: 322.79 / MAX: 466.1 MIN: 357.91 / MAX: 497.55 MIN: 352.31 / MAX: 513.31 MIN: 342.21 / MAX: 486.26 MIN: 342.95 / MAX: 473.15 MIN: 332.96 / MAX: 445.77 MIN: 339.2 / MAX: 478.26 MIN: 343.06 / MAX: 486.63 MIN: 337.66 / MAX: 471.92 MIN: 388.86 / MAX: 516.9 MIN: 403.24 / MAX: 525.59
PyPerformance Benchmark: asyncio_tcp_ssl OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: asyncio_tcp_ssl a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 160 320 480 640 800 645 590 590 626 628 610 582 586 581 723 737
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark Bayes a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 130 260 390 520 650 490.0 513.2 474.9 515.3 513.3 483.4 477.0 515.6 500.0 566.2 600.1 MIN: 459.29 / MAX: 580.9 MIN: 453.66 / MAX: 554.7 MIN: 454.77 / MAX: 514.32 MIN: 456.38 / MAX: 531.31 MIN: 455.04 / MAX: 535.53 MIN: 456.88 / MAX: 535.94 MIN: 460.78 / MAX: 515.59 MIN: 459.35 / MAX: 536.06 MIN: 457.03 / MAX: 581.14 MIN: 493.35 / MAX: 1029.04 MIN: 506.71 / MAX: 741.31
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Scala Dotty a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 110 220 330 440 550 477.0 428.6 436.2 424.6 442.9 464.5 441.9 411.9 455.6 506.5 515.8 MIN: 371.54 / MAX: 736.5 MIN: 378.22 / MAX: 628.77 MIN: 380.62 / MAX: 721.56 MIN: 376.26 / MAX: 659.55 MIN: 376.04 / MAX: 787.17 MIN: 358.07 / MAX: 790.35 MIN: 387.7 / MAX: 646.01 MIN: 362.36 / MAX: 713.71 MIN: 394.05 / MAX: 695.67 MIN: 420.76 / MAX: 1038.72 MIN: 426.08 / MAX: 1026.55
Renaissance Test: Gaussian Mixture Model OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Gaussian Mixture Model a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800 1600 2400 3200 4000 3399.5 3860.6 3815.2 3647.2 3703.2 3397.0 3806.5 3773.1 3829.9 3087.0 3130.4 MIN: 2471.52 MIN: 2758.89 / MAX: 3860.61 MIN: 2749.56 / MAX: 3815.24 MIN: 2576.86 / MAX: 3647.22 MIN: 2648.51 / MAX: 3703.23 MIN: 2497.54 / MAX: 3397.03 MIN: 2770.53 / MAX: 3806.52 MIN: 2755.26 / MAX: 3773.12 MIN: 2792.29 MIN: 2935.02 / MAX: 3439.02 MIN: 2997.45 / MAX: 3481.57
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: In-Memory Database Shootout a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800 1600 2400 3200 4000 3256.1 3241.5 3175.6 3288.5 3275.5 3244.8 3232.8 3442.9 3408.4 2951.1 3681.9 MIN: 3019.89 / MAX: 3599.5 MIN: 3037.03 / MAX: 3491.91 MIN: 2896.06 / MAX: 3367.44 MIN: 2991.78 / MAX: 3586.63 MIN: 3012.8 / MAX: 3533.02 MIN: 2350.89 MIN: 3057.86 / MAX: 3585.74 MIN: 3258.62 / MAX: 3709.4 MIN: 3187.55 / MAX: 3638.98 MIN: 2787.28 / MAX: 3070.94 MIN: 2559.5
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: DistinctUserID a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 10.46 10.76 8.97 10.54 10.28 10.85 11.05 11.14 9.15 9.92 10.16 1. (CXX) g++ options: -O3 -lrt
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: PartialTweets a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 9.76 10.10 8.35 9.80 9.63 10.04 9.85 9.98 10.32 9.32 9.30 1. (CXX) g++ options: -O3 -lrt
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: TopTweet a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 10.46 10.82 10.51 10.66 10.69 10.86 11.25 9.19 9.40 10.02 9.97 1. (CXX) g++ options: -O3 -lrt
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 5 10 15 20 25 19.28 20.28 20.29 19.82 19.82 19.00 19.67 19.73 19.71 16.65
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: python_startup a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 5.77 6.08 6.09 5.80 5.81 6.34 6.01 6.01 6.03 6.93 6.97
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 1000 2000 3000 4000 5000 4403.8 4038.4 4002.3 4084.6 4098.5 3720.1 4384.0 4344.8 4359.3 4474.8 4457.1 MAX: 5719.11 MIN: 4038.36 / MAX: 5089.28 MIN: 4002.27 / MAX: 4983.72 MAX: 5256.95 MIN: 4098.48 / MAX: 5163.21 MIN: 3720.09 / MAX: 4686.78 MIN: 4383.98 / MAX: 5691.67 MAX: 5622.35 MIN: 4359.25 / MAX: 5618.71 MIN: 4474.77 / MAX: 5751.45 MIN: 4457.08 / MAX: 5796.57
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 775.75 745.59 831.42 781.66 783.43 813.31 806.83 754.41 833.64 705.99 700.76
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 3 6 9 12 15 12.93 13.40 13.41 13.34 13.32 12.59 13.32 13.24 13.36 11.38
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark PageRank a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 2412.2 2138.1 2229.7 2366.1 2373.0 2506.8 2182.5 2227.9 2179.0 2267.1 2292.2 MIN: 1691.04 MIN: 1499.64 MIN: 1612.96 / MAX: 2229.74 MIN: 1667.92 / MAX: 2366.13 MIN: 1684.52 MIN: 1771.47 MIN: 1564.17 MIN: 1592.13 / MAX: 2227.91 MIN: 1591.55 / MAX: 2179.02 MIN: 2117.39 / MAX: 2335.98 MIN: 2106.39 / MAX: 2374.31
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Savina Reactors.IO a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 800 1600 2400 3200 4000 3506.4 3655.8 3676.0 3523.1 3688.6 3349.5 3582.4 3641.9 3589.4 3745.8 3818.5 MIN: 3506.38 / MAX: 4329.37 MIN: 3655.76 / MAX: 4484.97 MAX: 4536.84 MIN: 3523.09 / MAX: 4370.41 MAX: 4840.82 MIN: 3349.49 / MAX: 4130.17 MIN: 3582.35 / MAX: 4689.63 MAX: 4585.77 MAX: 4472.27 MIN: 3745.79 / MAX: 4547.1 MAX: 4702.95
Gcrypt Library OpenBenchmarking.org Seconds, Fewer Is Better Gcrypt Library 1.10.3 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 162.13 171.02 163.84 156.34 156.71 154.32 150.64 159.25 167.63 165.55 169.14 1. (CC) gcc options: -O2 -fvisibility=hidden
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: Kostya a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 5.97 6.11 5.45 5.78 6.02 6.06 6.07 6.04 5.54 5.70 5.68 1. (CXX) g++ options: -O3 -lrt
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 7 14 21 28 35 26.28 27.59 27.80 27.36 27.35 25.52 27.20 27.19 27.21 25.09
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: float a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 12 24 36 48 60 50.7 51.3 50.8 49.7 49.7 48.2 51.1 51.0 50.7 52.8 52.9
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 12 24 36 48 60 47.72 52.30 52.37 50.50 50.43 51.86 49.90 49.76 50.33 51.50 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 16 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 16 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 6 12 18 24 30 24.59 25.86 25.94 25.77 25.78 24.27 25.32 25.30 25.38 23.80
PyPerformance Benchmark: gc_collect OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: gc_collect a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 150 300 450 600 750 677 699 706 671 671 649 682 686 689 702 704
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 2 4 6 8 10 6.88 7.11 7.12 7.09 7.10 6.64 7.00 7.00 7.00 6.55 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: LargeRandom a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.414 0.828 1.242 1.656 2.07 1.83 1.84 1.84 1.81 1.73 1.81 1.82 1.83 1.83 1.70 1.71 1. (CXX) g++ options: -O3 -lrt
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: pathlib a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4 8 12 16 20 14.2 14.4 14.4 14.1 14.1 13.5 14.1 14.1 14.2 14.6 14.6
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 2 4 6 8 10 7.24 7.41 7.44 7.42 7.44 7.02 7.32 7.37 7.37 6.90 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 16 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 16 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 0.4185 0.837 1.2555 1.674 2.0925 1.78 1.83 1.84 1.83 1.83 1.76 1.82 1.83 1.86 1.73
PyPerformance Benchmark: asyncio_websockets OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: asyncio_websockets a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 70 140 210 280 350 315 321 322 315 316 308 315 317 314 330 331
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: regex_compile a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 16 32 48 64 80 69.8 71.7 72.5 69.5 70.0 68.1 71.4 69.8 70.4 72.6 72.7
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 0.4635 0.927 1.3905 1.854 2.3175 1.99 2.05 2.05 2.05 2.06 1.93 2.03 2.03 2.03 1.93
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: crypto_pyaes a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10 20 30 40 50 41.7 43.1 43.3 41.8 42.0 40.7 42.7 42.7 42.4 43.0 43.1
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: nbody a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 14 28 42 56 70 59.0 59.5 59.2 57.2 58.6 56.8 59.0 58.8 59.6 60.4 60.0
PyPerformance Benchmark: xml_etree OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: xml_etree a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 8 16 24 32 40 35.8 36.8 36.5 35.3 35.6 34.7 36.1 36.2 36.1 36.7 36.6
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: django_template a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 5 10 15 20 25 20.7 21.0 21.2 20.6 20.6 20.1 20.8 21.0 20.9 21.2 21.3
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: json_loads a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 3 6 9 12 15 12.1 12.4 12.5 12.0 12.0 11.8 12.5 12.2 12.3 12.4 12.4
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 3 6 9 12 15 10.47 10.91 10.93 10.93 10.91 10.32 10.81 10.85 10.82 10.46
PyPerformance Benchmark: go OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: go a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20 40 60 80 100 77.8 78.6 79.4 78.3 76.0 75.3 78.4 79.6 78.1 78.4 78.7
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 3 6 9 12 15 10.22 10.45 10.45 10.48 10.45 9.92 10.30 10.37 10.34 9.99
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: pickle_pure_python a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 165 169 168 164 164 162 166 165 163 171 171
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: chaos a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 9 18 27 36 45 38.2 39.7 39.4 39.0 38.6 38.3 39.2 39.1 38.8 39.9 40.2
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 128 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 5 10 15 20 25 20.13 20.39 20.51 20.48 20.50 19.60 20.23 20.26 20.29 20.08
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.11 Benchmark: raytrace a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 40 80 120 160 200 175 182 182 177 176 174 176 176 179 182 180
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 16 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 16 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 5 10 15 20 25 19.03 19.49 19.50 19.47 19.53 18.83 19.27 19.24 19.16 19.17
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 3K 6K 9K 12K 15K 12288 12288 12288 12288 12288 12288 12288 12288 12288 12288
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 1300 2600 3900 5200 6500 6144 6144 6144 6144 6144 6144 6144 6144 6144 6144
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 700 1400 2100 2800 3500 3072 3072 3072 3072 3072 3072 3072 3072 3072 3072
Llamafile Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 256 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 300 600 900 1200 1500 1536 1536 1536 1536 1536 1536 1536 1536 1536 1536
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 7K 14K 21K 28K 35K 32768 32768 32768 32768 32768 32768 32768 32768 32768 32768
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 4K 8K 12K 16K 20K 16384 16384 16384 16384 16384 16384 16384 16384 16384 16384
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 2K 4K 6K 8K 10K 8192 8192 8192 8192 8192 8192 8192 8192 8192 8192
Llamafile Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 256 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 900 1800 2700 3600 4500 4096 4096 4096 4096 4096 4096 4096 4096 4096 4096
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 7K 14K 21K 28K 35K 32768 32768 32768 32768 32768 32768 32768 32768 32768 32768
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 4K 8K 12K 16K 20K 16384 16384 16384 16384 16384 16384 16384 16384 16384 16384
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 2K 4K 6K 8K 10K 8192 8192 8192 8192 8192 8192 8192 8192 8192 8192
Llamafile Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 256 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 900 1800 2700 3600 4500 4096 4096 4096 4096 4096 4096 4096 4096 4096 4096
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 2048 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 7K 14K 21K 28K 35K 32768 32768 32768 32768 32768 32768 32768 32768 32768 32768
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 1024 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 4K 8K 12K 16K 20K 16384 16384 16384 16384 16384 16384 16384 16384 16384 16384
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 512 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 2K 4K 6K 8K 10K 8192 8192 8192 8192 8192 8192 8192 8192 8192 8192
Llamafile Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 256 OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.16 Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 256 a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 900 1800 2700 3600 4500 4096 4096 4096 4096 4096 4096 4096 4096 4096 4096
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 13 26 39 52 65 51.86 49.31 49.28 50.45 50.46 52.64 50.84 50.68 50.74 60.07
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 30 60 90 120 150 55.93 58.91 58.86 59.87 59.86 71.58 56.06 55.47 55.67 130.47
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 20 40 60 80 100 77.34 74.65 74.54 74.94 75.06 79.41 75.06 75.51 74.86 87.90
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 50 100 150 200 250 86.06 93.01 93.00 93.00 94.77 115.73 86.04 86.20 87.34 217.85
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 30 60 90 120 150 101.72 97.79 97.61 98.33 98.03 105.09 98.91 98.64 98.31 124.24
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 b 60 120 180 240 300 106.62 121.48 122.30 124.38 124.52 154.83 105.36 104.38 104.87 288.64
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 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 7 14 21 28 35 21.24 24.94 23.06 21.57 21.69 22.32 20.72 20.88 20.98 27.69 25.95 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 500 1000 1500 2000 2500 648.52 850.14 854.33 872.74 864.81 1091.32 650.96 647.81 645.21 2151.82 2152.92 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4 8 12 16 20 7.08601 7.98873 7.99486 7.41037 7.43372 6.36564 8.18519 8.18265 8.18175 13.64570 13.54170 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 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 1.1129 2.2258 3.3387 4.4516 5.5645 2.55898 2.80544 2.80695 2.77422 2.76714 2.65482 2.60974 2.61221 2.62573 4.81530 4.94636 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 10 20 30 40 50 23.55 26.75 26.95 27.68 27.47 25.58 22.81 22.70 22.99 41.94 41.82 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 200 400 600 800 1000 310.88 355.75 357.60 386.56 386.06 487.30 295.28 294.93 293.96 926.76 927.39 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 0.4543 0.9086 1.3629 1.8172 2.2715 1.570840 1.061880 1.066000 1.379700 1.335160 1.311210 0.994193 0.999701 0.986643 2.016090 2.019130 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 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 20 40 60 80 100 64.14 68.91 68.61 68.08 68.09 50.47 66.62 66.92 67.18 95.07 94.12 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 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 6.39112 4.80287 4.85142 5.95035 6.00470 7.06075 4.90285 4.91381 4.90313 7.04122 7.13857 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 4 8 12 16 20 9.76985 9.01322 9.01687 9.85896 9.83893 10.28350 8.87444 8.82581 8.83524 13.53230 13.69550 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 1.19 Model: yolov4 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 30 60 90 120 150 90.45 93.16 93.34 95.25 95.36 75.54 88.06 88.36 88.41 139.66 139.72 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 1.19 Model: GPT-2 - Device: CPU - Executor: Standard a 4484PX px 4464p 4464p epyc 4364P 4584PX EPYC 4584PX amd 45 41 41 b 2 4 6 8 10 7.42776 6.25815 6.33034 7.33331 7.36544 7.96069 6.02069 6.03024 6.01631 8.04835 8.10767 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Phoronix Test Suite v10.8.5