eoy2024

Benchmarks for a future article. AMD EPYC 4484PX 12-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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2412086-NE-EOY20243255
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 05
  6 Hours, 48 Minutes
4484PX
December 07
  7 Hours, 3 Minutes
px
December 07
  7 Hours, 3 Minutes
Invert Behavior (Only Show Selected Data)
  6 Hours, 58 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


eoy2024ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutiona4484PXpxAMD EPYC 4564P 16-Core @ 5.88GHz (16 Cores / 32 Threads)Supermicro AS-3015A-I H13SAE-MF v1.00 (2.1 BIOS)AMD Device 14d82 x 32GB DRAM-4800MT/s Micron MTC20C2085S1EC48BA1 BC3201GB Micron_7450_MTFDKCC3T2TFS + 960GB SAMSUNG MZ1L2960HCJR-00A07ASPEEDAMD Rembrandt Radeon HD AudioVA24312 x Intel I210Ubuntu 24.046.8.0-11-generic (x86_64)GNOME Shell 45.3X Server 1.21.1.11GCC 13.2.0ext41024x768AMD EPYC 4484PX 12-Core @ 5.66GHz (12 Cores / 24 Threads)6.12.2-061202-generic (x86_64)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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: 0xa601209Java Details- OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)Python Details- Python 3.12.3Security 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

a4484PXpxResult OverviewPhoronix Test Suite100%114%128%142%Apache CassandraBYTE Unix BenchmarkASTC EncoderPrimesieveEtcpakPOV-RayOpenSSLBlenderACES DGEMMOSPRayStockfishRELION7-Zip CompressionBuild2RustlsLiteRTNAMDx265SVT-AV1Timed Eigen CompilationWhisperfileoneDNNNumpy BenchmarksimdjsonApache CouchDBWhisper.cppQuantLibLlama.cppGROMACSXNNPACKGcrypt LibraryCP2K Molecular DynamicsY-CruncherLlamafilePyPerformanceONNX RuntimeOpenVINO GenAIRenaissanceFinanceBench

eoy2024litert: NASNet Mobileonednn: IP Shapes 1D - CPUonednn: Convolution Batch Shapes Auto - CPUbyte: System Callcassandra: Writesllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024litert: DeepLab V3litert: Quantized COCO SSD MobileNet v1onednn: IP Shapes 3D - CPUonnx: CaffeNet 12-int8 - CPU - Standardbyte: Pipeonednn: Deconvolution Batch shapes_3d - CPUprimesieve: 1e12astcenc: Thoroughastcenc: Mediumastcenc: Fastastcenc: Exhaustiveastcenc: Very Thoroughprimesieve: 1e13etcpak: Multi-Threaded - ETC2byte: Whetstone Doublellama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512ospray: particle_volume/scivis/real_timerustls: handshake - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384byte: Dhrystone 2onednn: Recurrent Neural Network Training - CPUblender: BMW27 - CPU-Onlyospray: particle_volume/ao/real_timestockfish: Chess Benchmarkonednn: Recurrent Neural Network Inference - CPUblender: Classroom - CPU-Onlyospray: gravity_spheres_volume/dim_512/pathtracer/real_timeopenssl: AES-128-GCMopenssl: AES-256-GCMospray: gravity_spheres_volume/dim_512/scivis/real_timepovray: Trace Timeblender: Pabellon Barcelona - CPU-Onlyblender: Fishy Cat - CPU-Onlyrustls: handshake - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256ospray: gravity_spheres_volume/dim_512/ao/real_timemt-dgemm: Sustained Floating-Point Rateopenssl: ChaCha20openssl: ChaCha20-Poly1305blender: Barbershop - CPU-Onlyllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048onnx: T5 Encoder - CPU - Standardrustls: handshake - TLS13_CHACHA20_POLY1305_SHA256compress-7zip: Decompression Ratingblender: Junkshop - CPU-Onlyonnx: ResNet101_DUC_HDC-12 - CPU - Standardrelion: Basic - CPUstockfish: Chess Benchmarkrenaissance: Genetic Algorithm Using Jenetics + Futuressvt-av1: Preset 3 - Bosphorus 4Kbuild2: Time To Compilexnnpack: FP16MobileNetV1xnnpack: FP32MobileNetV3Smallsimdjson: PartialTweetsx265: Bosphorus 4Ksvt-av1: Preset 3 - Beauty 4K 10-bitsvt-av1: Preset 8 - Bosphorus 4Ksimdjson: DistinctUserIDsvt-av1: Preset 5 - Bosphorus 4Kospray: particle_volume/pathtracer/real_timexnnpack: FP32MobileNetV3Largenamd: ATPase with 327,506 Atomsonnx: GPT-2 - CPU - Standardsvt-av1: Preset 8 - Bosphorus 1080pxnnpack: FP16MobileNetV3Smallrustls: handshake-ticket - TLS13_CHACHA20_POLY1305_SHA256xnnpack: QS8MobileNetV2rustls: handshake-resume - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardsvt-av1: Preset 5 - Beauty 4K 10-bitrustls: handshake-ticket - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384whisperfile: Smallrustls: handshake-resume - TLS13_CHACHA20_POLY1305_SHA256svt-av1: Preset 3 - Bosphorus 1080pnamd: STMV with 1,066,628 Atomscompress-7zip: Compression Ratingrustls: handshake-resume - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384whisper-cpp: ggml-medium.en - 2016 State of the Unionsvt-av1: Preset 5 - Bosphorus 1080ppyperformance: async_tree_ioonnx: fcn-resnet101-11 - CPU - Standardsvt-av1: Preset 8 - Beauty 4K 10-bitbuild-eigen: Time To Compilerustls: handshake-ticket - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256onednn: Deconvolution Batch shapes_1d - CPUonnx: ArcFace ResNet-100 - CPU - Standardrenaissance: Gaussian Mixture Modelx265: Bosphorus 1080pwhisperfile: Mediumonnx: super-resolution-10 - CPU - Standardrenaissance: Apache Spark PageRankcouchdb: 300 - 1000 - 30whisperfile: Tinysimdjson: Kostyanumpy: couchdb: 500 - 1000 - 30renaissance: Scala Dottycouchdb: 300 - 3000 - 30quantlib: XXScp2k: H20-64renaissance: Akka Unbalanced Cobwebbed Treellama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128couchdb: 100 - 3000 - 30onnx: ResNet50 v1-12-int8 - CPU - Standardcouchdb: 500 - 3000 - 30svt-av1: Preset 13 - Bosphorus 4Kxnnpack: FP32MobileNetV2whisper-cpp: ggml-small.en - 2016 State of the Unionsvt-av1: Preset 13 - Bosphorus 1080prenaissance: Rand Forestpyperformance: asyncio_tcp_sslcouchdb: 100 - 1000 - 30onnx: ZFNet-512 - CPU - Standardrenaissance: Apache Spark Bayesquantlib: Srenaissance: Finagle HTTP Requestsgromacs: water_GMX50_bareonnx: bertsquad-12 - CPU - Standardsvt-av1: Preset 13 - Beauty 4K 10-bitwhisper-cpp: ggml-base.en - 2016 State of the Unionllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024cp2k: H20-256litert: Inception V4llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 128renaissance: ALS Movie Lensfinancebench: Bonds OpenMPpyperformance: python_startupllamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 16gcrypt: openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUxnnpack: FP16MobileNetV2renaissance: Savina Reactors.IOllamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 128pyperformance: gc_collectfinancebench: Repo OpenMPopenvino-genai: Gemma-7b-int4-ov - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024xnnpack: FP16MobileNetV3Largepyperformance: raytracepyperformance: chaospyperformance: regex_compilepyperformance: crypto_pyaesopenvino-genai: Falcon-7b-instruct-int4-ov - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128simdjson: TopTweetllamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 16pyperformance: json_loadsonnx: yolov4 - CPU - Standardlitert: Mobilenet Quantllamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 128cp2k: Fayalite-FISTpyperformance: xml_etreellama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128litert: Mobilenet Floatrenaissance: In-Memory Database Shootoutllamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 16pyperformance: pickle_pure_pythonpyperformance: django_templatellamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 16pyperformance: asyncio_websocketspyperformance: gollamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 128y-cruncher: 500Mxnnpack: FP32MobileNetV1litert: SqueezeNetpyperformance: pathlibpyperformance: floatllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512pyperformance: nbodyy-cruncher: 1Bsimdjson: LargeRandlitert: Inception ResNet V2llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 2048llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 1024llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 512llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 256llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 2048llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 1024llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 512llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 256llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 2048llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 1024llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 512llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 256llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 2048llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 1024llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 512llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 256openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: T5 Encoder - CPU - Standardonnx: ZFNet-512 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: GPT-2 - CPU - Standardrenaissance: Apache Spark ALSa4484PXpx169361.125736.6728749140426.6271333355.093579.672129.524.058636.31848806257.12.412946.34720.3025156.2217396.64951.68442.74178.498577.817343491.9327.38.98486423535.681866536062.71372.0353.559.0091746507038700.859143.368.82093104784522170971727517007.5878918.542166.1271.3580462.67.639441141.19410413058849505092393529340506.2279.04156.45376454.4516591673.561.54196944.2754752796732.89.5992.05311439799.7632.571.422102.00510.4634.538236.24518102.79632134.596339.023920404263.458443563852.5747.06916.5041553632.14195.41642388077.6929.5730.756561638591820810.21700.91101.9717553.216712.46858.65526203322.9761242.45373399.5114.45534.919141.1172412.2106.1341.709355.97775.75148.049477.0367.8313.43258.1914403.847.72232.188390.597511.775212.521495245.07838842.558414.464569.929102.331490.012.74762319.41.69215.589918.58887.4897370.85592.85721477.826.289805.733061.218755.7724.59162.12519.2811903506.410.4767721418.4453129.8370.7669.26149817538.269.841.712.936.8810.461.7812.111.0552823.171.9994.03235.87.241211.483256.119.0316520.710.2231577.820.138.77212521794.1114.250.763.0962.9768.45918.4851.8319530.21228861443072153632768163848192409632768163848192409632768163848192409651.8655.9377.3486.06101.72106.6221.2429648.5227.086012.5589823.553310.8751.5708464.1416.391129.7698590.45237.427768057.561.938064.1155130761218.9174960232.262343.381420.152.73072941.40133443359.23.50849.11614.17109.0265278.24451.18871.9412110.608410.726244075.3243.146.44913306153.21346521770.31898.3674.086.5277633702298965.015197.26.4119876496336760711602918705.5488825.264226.3496.6759308.755.63122842.7306429710523569068816544020679.34222.75208.17457716.6412569897.011.17627729.445267546904.07.684111.651138380910.127.161.18885.20110.7629.094199.02315152.38124159.71287.047779344296.247173035330.2140.09355.6021329363.1173.38197333882.9225.4460.651191412631586292.42809.7896988.4156662.8109310.96767.3642282729.643.4029337.38323860.6101.37473.55091125.1722138.1117.56637.134626.11745.59164.468428.6406.1212.116953.0054038.452.3253.99356.409559.346198.1121365268.23891776.115422.059075.901110.94513.211.86472492.21.57714.512217.40692.7093366.57628.10422083.327.599378.834600.7734386.0825.86171.02320.2812173655.810.9169922320.33203110.2369.1166.85146718239.771.743.113.47.1110.821.8312.410.7338848.9432.0592.2136.87.411244.73241.519.491692110.4532178.620.398.68812571809.1814.451.363.863.6168.259.518.3791.8419477.81228861443072153632768163848192409632768163848192409632768163848192409649.3158.9174.6593.0197.79121.4824.9402850.1417.988732.8054426.7478355.7511.0618868.90514.802879.0132293.16056.258157931.641.939134.1332130701622.8173946244.772359.991417.352.72942937.77833381363.13.512439.14714.1464108.8588277.29941.18621.9391110.709409.875244131232.866.52304304060.281340340196.61895.6873.166.5220633871595966.013197.536.407476184405610709026564805.614725.328224.6497.0959206.345.71084842.0128319701989745068678955550678.4208.99206.09157688.0812560597.11.1705733.0242973396920.77.646113.7813868378.3526.941.18484.9988.9728.824197.215742.35379157.893286.962798342775.297233038723.4843.3625.5511340712.85167.89219333574.325.4470.654481422131572010.68809.48988.276562.7963810.85567.0762292879.443.4062837.10483815.2101.25475.51084125.0762229.7119.34938.718285.45831.42164.812436.2408.48312.105752.7244002.352.37254.733356.194560.7194.0241368266.81425769.818453.259076.389110.892474.911.8392483.11.57514.574717.35593.4546366.35631.3122752.427.89275.734896.8359386.0925.94163.83920.2912483676.010.9370622318.73828110.2467.9566.52152718239.472.543.313.417.1210.511.8412.510.7127849.2092.0594.89636.57.441244.513175.619.516821.210.4532279.420.518.62312721821.3514.450.863.7963.4168.8159.218.3651.8419490.71228861443072153632768163848192409632768163848192409632768163848192409649.2858.8674.549397.61122.323.0604854.3347.994862.8069526.9485357.6021.06668.61044.851429.0168793.34416.33034OpenBenchmarking.org

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobilea4484PXpx4K8K12K16K20K16936.008057.567931.64

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPUa4484PXpx0.43630.87261.30891.74522.18151.125731.938061.93913MIN: 1.03MIN: 1.92MIN: 1.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPUa4484PXpx2468106.672874.115514.13321MIN: 6.2MIN: 4.05MIN: 4.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

BYTE Unix Benchmark

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: System Calla4484PXpx11M22M33M44M55M49140426.630761218.930701622.81. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

Apache Cassandra

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: Writesa4484PXpx60K120K180K240K300K271333174960173946

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024a4484PXpx80160240320400355.09232.26244.771. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3a4484PXpx80016002400320040003579.672343.382359.99

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1a4484PXpx50010001500200025002129.521420.151417.35

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPUa4484PXpx0.91311.82622.73933.65244.56554.058002.730722.72942MIN: 3.75MIN: 2.7MIN: 2.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standarda4484PXpx2004006008001000636.32941.40937.781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

BYTE Unix Benchmark

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Pipea4484PXpx10M20M30M40M50M48806257.133443359.233381363.11. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUa4484PXpx0.79031.58062.37093.16123.95152.412943.508403.51243MIN: 2.34MIN: 3.46MIN: 3.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e12a4484PXpx36912156.3479.1169.1471. (CXX) g++ options: -O3

ASTC Encoder

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Thorougha4484PXpx51015202520.3014.1714.151. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Mediuma4484PXpx306090120150156.22109.03108.861. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Fasta4484PXpx90180270360450396.65278.24277.301. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Exhaustivea4484PXpx0.3790.7581.1371.5161.8951.68441.18871.18621. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Very Thorougha4484PXpx0.61671.23341.85012.46683.08352.74101.94121.93911. (CXX) g++ options: -O3 -flto -pthread

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e13a4484PXpx2040608010078.50110.61110.711. (CXX) g++ options: -O3

Etcpak

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 2.0Benchmark: Multi-Threaded - Configuration: ETC2a4484PXpx120240360480600577.82410.73409.881. (CXX) g++ options: -flto -pthread

BYTE Unix Benchmark

OpenBenchmarking.orgMWIPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Whetstone Doublea4484PXpx70K140K210K280K350K343491.9244075.3244131.01. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512a4484PXpx70140210280350327.30243.14232.861. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/scivis/real_timea4484PXpx36912158.984866.449136.52304

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384a4484PXpx90K180K270K360K450K423535.68306153.20304060.281. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

BYTE Unix Benchmark

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Dhrystone 2a4484PXpx400M800M1200M1600M2000M1866536062.71346521770.31340340196.61. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUa4484PXpx4008001200160020001372.031898.361895.68MIN: 1342.06MIN: 1894.26MIN: 1892.591. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: CPU-Onlya4484PXpx163248648053.5574.0873.16

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/ao/real_timea4484PXpx36912159.009176.527766.52206

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfishChess Benchmarka4484PXpx10M20M30M40M50M4650703833702298338715951. Stockfish 16 by the Stockfish developers (see AUTHORS file)

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPUa4484PXpx2004006008001000700.86965.02966.01MIN: 679.89MIN: 963.27MIN: 963.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-Onlya4484PXpx4080120160200143.36197.20197.53

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timea4484PXpx2468108.820936.411986.40740

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: AES-128-GCMa4484PXpx20000M40000M60000M80000M100000M10478452217076496336760761844056101. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: AES-256-GCMa4484PXpx20000M40000M60000M80000M100000M9717275170071160291870709026564801. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/scivis/real_timea4484PXpx2468107.587895.548885.61470

POV-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-RayTrace Timea4484PXpx61218243018.5425.2625.331. POV-Ray 3.7.0.10.unofficial

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-Onlya4484PXpx50100150200250166.12226.34224.64

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: CPU-Onlya4484PXpx2040608010071.3596.6797.09

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256a4484PXpx20K40K60K80K100K80462.6059308.7559206.341. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/ao/real_timea4484PXpx2468107.639445.631225.71084

ACES DGEMM

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Ratea4484PXpx20040060080010001141.19842.73842.011. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20a4484PXpx30000M60000M90000M120000M150000M13058849505097105235690970198974501. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20-Poly1305a4484PXpx20000M40000M60000M80000M100000M9239352934068816544020686789555501. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-Onlya4484PXpx150300450600750506.20679.34678.40

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048a4484PXpx60120180240300279.04222.75208.991. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standarda4484PXpx50100150200250156.45208.17206.091. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256a4484PXpx16K32K48K64K80K76454.4557716.6457688.081. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip CompressionTest: Decompression Ratinga4484PXpx40K80K120K160K200K1659161256981256051. 7-Zip 23.01 (x64) : Copyright (c) 1999-2023 Igor Pavlov : 2023-06-20

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-Onlya4484PXpx2040608010073.5697.0197.10

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standarda4484PXpx0.34690.69381.04071.38761.73451.541961.176271.170501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

RELION

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 5.0Test: Basic - Device: CPUa4484PXpx2004006008001000944.27729.40733.021. (CXX) g++ options: -fPIC -std=c++14 -fopenmp -O3 -rdynamic -lfftw3f -lfftw3 -ldl -ltiff -lpng -ljpeg -lmpi_cxx -lmpi

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 17Chess Benchmarka4484PXpx12M24M36M48M60M5475279645267546429733961. (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

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Genetic Algorithm Using Jenetics + Futuresa4484PXpx2004006008001000732.8904.0920.7MIN: 713.67 / MAX: 813.49MIN: 886.83 / MAX: 919.31MIN: 888.75 / MAX: 934.44

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 4Ka4484PXpx36912159.5907.6847.6461. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Build2

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.17Time To Compilea4484PXpx30609012015092.05111.65113.78

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1a4484PXpx300600900120015001143138313861. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smalla4484PXpx20040060080010009798098371. (CXX) g++ options: -O3 -lrt -lm

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: PartialTweetsa4484PXpx36912159.7610.108.351. (CXX) g++ options: -O3 -lrt

x265

OpenBenchmarking.orgFrames Per Second, More Is Betterx265Video Input: Bosphorus 4Ka4484PXpx81624324032.5727.1626.941. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Beauty 4K 10-bita4484PXpx0.320.640.961.281.61.4221.1881.1841. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 4Ka4484PXpx20406080100102.0185.2085.001. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: DistinctUserIDa4484PXpx369121510.4610.768.971. (CXX) g++ options: -O3 -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 4Ka4484PXpx81624324034.5429.0928.821. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/pathtracer/real_timea4484PXpx50100150200250236.25199.02197.20

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largea4484PXpx4008001200160020001810151515741. (CXX) g++ options: -O3 -lrt -lm

NAMD

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: ATPase with 327,506 Atomsa4484PXpx0.62921.25841.88762.51683.1462.796322.381242.35379

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standarda4484PXpx4080120160200134.60159.71157.891. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 1080pa4484PXpx70140210280350339.02287.05286.961. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smalla4484PXpx20040060080010009207797981. (CXX) g++ options: -O3 -lrt -lm

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256a4484PXpx90K180K270K360K450K404263.45344296.24342775.291. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2a4484PXpx20040060080010008447177231. (CXX) g++ options: -O3 -lrt -lm

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256a4484PXpx800K1600K2400K3200K4000K3563852.573035330.213038723.481. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standarda4484PXpx112233445547.0740.0943.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Beauty 4K 10-bita4484PXpx2468106.5045.6025.5511. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384a4484PXpx300K600K900K1200K1500K1553632.141329363.101340712.851. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Whisperfile

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Smalla4484PXpx4080120160200195.42173.38167.89

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256a4484PXpx80K160K240K320K400K388077.69333882.92333574.301. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 1080pa4484PXpx71421283529.5725.4525.451. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NAMD

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 Atomsa4484PXpx0.17020.34040.51060.68080.8510.756560.651190.65448

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip CompressionTest: Compression Ratinga4484PXpx40K80K120K160K200K1638591412631422131. 7-Zip 23.01 (x64) : Copyright (c) 1999-2023 Igor Pavlov : 2023-06-20

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384a4484PXpx400K800K1200K1600K2000K1820810.211586292.421572010.681. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-medium.en - Input: 2016 State of the Uniona4484PXpx2004006008001000700.91809.79809.491. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 1080pa4484PXpx20406080100101.9788.4288.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: async_tree_ioa4484PXpx160320480640800755666656

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standarda4484PXpx0.72381.44762.17142.89523.6193.216702.810932.796381. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Beauty 4K 10-bita4484PXpx369121512.4710.9710.861. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Timed Eigen Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.4.0Time To Compilea4484PXpx153045607558.6667.3667.08

Rustls

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256a4484PXpx600K1200K1800K2400K3000K2620332.002282729.642292879.441. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPUa4484PXpx0.76641.53282.29923.06563.8322.976123.402933.40628MIN: 2.42MIN: 3.03MIN: 3.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standarda4484PXpx102030405042.4537.3837.101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Gaussian Mixture Modela4484PXpx80016002400320040003399.53860.63815.2MIN: 2471.52MIN: 2758.89 / MAX: 3860.61MIN: 2749.56 / MAX: 3815.24

x265

OpenBenchmarking.orgFrames Per Second, More Is Betterx265Video Input: Bosphorus 1080pa4484PXpx306090120150114.45101.37101.251. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6

Whisperfile

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Mediuma4484PXpx120240360480600534.92473.55475.51

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standarda4484PXpx306090120150141.12125.17125.081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark PageRanka4484PXpx50010001500200025002412.22138.12229.7MIN: 1691.04MIN: 1499.64MIN: 1612.96 / MAX: 2229.74

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 300 - Inserts: 1000 - Rounds: 30a4484PXpx306090120150106.13117.57119.351. (CXX) g++ options: -flto -lstdc++ -shared -lei

Whisperfile

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Tinya4484PXpx102030405041.7137.1338.72

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: Kostyaa4484PXpx2468105.976.115.451. (CXX) g++ options: -O3 -lrt

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarka4484PXpx2004006008001000775.75745.59831.42

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 500 - Inserts: 1000 - Rounds: 30a4484PXpx4080120160200148.05164.47164.811. (CXX) g++ options: -flto -lstdc++ -shared -lei

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Scala Dottya4484PXpx100200300400500477.0428.6436.2MIN: 371.54 / MAX: 736.5MIN: 378.22 / MAX: 628.77MIN: 380.62 / MAX: 721.56

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 300 - Inserts: 3000 - Rounds: 30a4484PXpx90180270360450367.83406.12408.481. (CXX) g++ options: -flto -lstdc++ -shared -lei

QuantLib

OpenBenchmarking.orgtasks/s, More Is BetterQuantLib 1.35-devSize: XXSa4484PXpx369121513.4312.1212.111. (CXX) g++ options: -O3 -march=native -fPIE -pie

CP2K Molecular Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2024.3Input: H20-64a4484PXpx132639526558.1953.0152.721. (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

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Akka Unbalanced Cobwebbed Treea4484PXpx90018002700360045004403.84038.44002.3MAX: 5719.11MIN: 4038.36 / MAX: 5089.28MIN: 4002.27 / MAX: 4983.72

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128a4484PXpx122436486047.7252.3052.371. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 100 - Inserts: 3000 - Rounds: 30a4484PXpx60120180240300232.19253.99254.731. (CXX) g++ options: -flto -lstdc++ -shared -lei

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standarda4484PXpx80160240320400390.60356.41356.191. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 500 - Inserts: 3000 - Rounds: 30a4484PXpx120240360480600511.78559.35560.701. (CXX) g++ options: -flto -lstdc++ -shared -lei

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 4Ka4484PXpx50100150200250212.52198.11194.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2a4484PXpx300600900120015001495136513681. (CXX) g++ options: -O3 -lrt -lm

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-small.en - Input: 2016 State of the Uniona4484PXpx60120180240300245.08268.24266.811. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 1080pa4484PXpx2004006008001000842.56776.12769.821. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Random Foresta4484PXpx100200300400500414.4422.0453.2MIN: 322.79 / MAX: 466.1MIN: 357.91 / MAX: 497.55MIN: 352.31 / MAX: 513.31

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: asyncio_tcp_ssla4484PXpx140280420560700645590590

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.4.1Bulk Size: 100 - Inserts: 1000 - Rounds: 30a4484PXpx2040608010069.9375.9076.391. (CXX) g++ options: -flto -lstdc++ -shared -lei

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standarda4484PXpx20406080100102.33110.94110.891. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark Bayesa4484PXpx110220330440550490.0513.2474.9MIN: 459.29 / MAX: 580.9MIN: 453.66 / MAX: 554.7MIN: 454.77 / MAX: 514.32

QuantLib

OpenBenchmarking.orgtasks/s, More Is BetterQuantLib 1.35-devSize: Sa4484PXpx369121512.7511.8611.841. (CXX) g++ options: -O3 -march=native -fPIE -pie

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Finagle HTTP Requestsa4484PXpx50010001500200025002319.42492.22483.1MIN: 1832.84MIN: 1947.63MIN: 1933.43

GROMACS

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACSInput: water_GMX50_barea4484PXpx0.38070.76141.14211.52281.90351.6921.5771.5751. GROMACS version: 2023.3-Ubuntu_2023.3_1ubuntu3

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standarda4484PXpx4812162015.5914.5114.571. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Beauty 4K 10-bita4484PXpx51015202518.5917.4117.361. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-base.en - Input: 2016 State of the Uniona4484PXpx2040608010087.4992.7193.451. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024a4484PXpx163248648070.8566.5766.351. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

CP2K Molecular Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2024.3Input: H20-256a4484PXpx140280420560700592.86628.10631.311. (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

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4a4484PXpx5K10K15K20K25K21477.822083.322752.4

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 128a4484PXpx71421283526.2827.5927.80

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: ALS Movie Lensa4484PXpx2K4K6K8K10K9805.79378.89275.7MIN: 9253.4 / MAX: 10057.61MIN: 8718.36 / MAX: 9413.7MIN: 8821.09 / MAX: 9495.91

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPa4484PXpx7K14K21K28K35K33061.2234600.7734896.841. (CXX) g++ options: -O3 -march=native -fopenmp

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: python_startupa4484PXpx2468105.776.086.09

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 16a4484PXpx61218243024.5925.8625.94

Gcrypt Library

OpenBenchmarking.orgSeconds, Fewer Is BetterGcrypt Library 1.10.3a4484PXpx4080120160200162.13171.02163.841. (CC) gcc options: -O2 -fvisibility=hidden

OpenVINO GenAI

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUa4484PXpx51015202519.2820.2820.29

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2a4484PXpx300600900120015001190121712481. (CXX) g++ options: -O3 -lrt -lm

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Savina Reactors.IOa4484PXpx80016002400320040003506.43655.83676.0MIN: 3506.38 / MAX: 4329.37MIN: 3655.76 / MAX: 4484.97MAX: 4536.84

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 128a4484PXpx369121510.4710.9110.93

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: gc_collecta4484PXpx150300450600750677699706

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPa4484PXpx5K10K15K20K25K21418.4522320.3322318.741. (CXX) g++ options: -O3 -march=native -fopenmp

OpenVINO GenAI

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUa4484PXpx36912159.8310.2310.24

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512a4484PXpx163248648070.7669.1167.951. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024a4484PXpx153045607569.2666.8566.521. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largea4484PXpx300600900120015001498146715271. (CXX) g++ options: -O3 -lrt -lm

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: raytracea4484PXpx4080120160200175182182

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: chaosa4484PXpx91827364538.239.739.4

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: regex_compilea4484PXpx163248648069.871.772.5

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: crypto_pyaesa4484PXpx102030405041.743.143.3

OpenVINO GenAI

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPUa4484PXpx369121512.9313.4013.41

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128a4484PXpx2468106.887.117.121. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: TopTweeta4484PXpx369121510.4610.8210.511. (CXX) g++ options: -O3 -lrt

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 16a4484PXpx0.4140.8281.2421.6562.071.781.831.84

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: json_loadsa4484PXpx369121512.112.412.5

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standarda4484PXpx369121511.0610.7310.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quanta4484PXpx2004006008001000823.17848.94849.21

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 128a4484PXpx0.46130.92261.38391.84522.30651.992.052.05

CP2K Molecular Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2024.3Input: Fayalite-FISTa4484PXpx2040608010094.0392.2194.901. (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

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: xml_etreea4484PXpx81624324035.836.836.5

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128a4484PXpx2468107.247.417.441. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floata4484PXpx300600900120015001211.481244.701244.51

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: In-Memory Database Shootouta4484PXpx70014002100280035003256.13241.53175.6MIN: 3019.89 / MAX: 3599.5MIN: 3037.03 / MAX: 3491.91MIN: 2896.06 / MAX: 3367.44

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 16a4484PXpx51015202519.0319.4919.50

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: pickle_pure_pythona4484PXpx4080120160200165169168

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: django_templatea4484PXpx51015202520.721.021.2

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16a4484PXpx369121510.2210.4510.45

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: asyncio_websocketsa4484PXpx70140210280350315321322

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: goa4484PXpx2040608010077.878.679.4

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 128a4484PXpx51015202520.1320.3920.51

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 500Ma4484PXpx2468108.7728.6888.623

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1a4484PXpx300600900120015001252125712721. (CXX) g++ options: -O3 -lrt -lm

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNeta4484PXpx4008001200160020001794.111809.181821.35

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: pathliba4484PXpx4812162014.214.414.4

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: floata4484PXpx122436486050.751.350.8

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048a4484PXpx142842567063.0963.8063.791. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048a4484PXpx142842567062.9763.6163.411. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512a4484PXpx153045607568.4068.2068.811. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

PyPerformance

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: nbodya4484PXpx132639526559.059.559.2

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 1Ba4484PXpx51015202518.4918.3818.37

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: LargeRandoma4484PXpx0.4140.8281.2421.6562.071.831.841.841. (CXX) g++ options: -O3 -lrt

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2a4484PXpx4K8K12K16K20K19530.219477.819490.7

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 2048a4484PXpx3K6K9K12K15K122881228812288

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 1024a4484PXpx13002600390052006500614461446144

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 512a4484PXpx7001400210028003500307230723072

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 256a4484PXpx30060090012001500153615361536

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 2048a4484PXpx7K14K21K28K35K327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 1024a4484PXpx4K8K12K16K20K163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 512a4484PXpx2K4K6K8K10K819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 256a4484PXpx9001800270036004500409640964096

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 2048a4484PXpx7K14K21K28K35K327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 1024a4484PXpx4K8K12K16K20K163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 512a4484PXpx2K4K6K8K10K819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 256a4484PXpx9001800270036004500409640964096

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 2048a4484PXpx7K14K21K28K35K327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 1024a4484PXpx4K8K12K16K20K163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 512a4484PXpx2K4K6K8K10K819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 256a4484PXpx9001800270036004500409640964096

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

a: The test quit with a non-zero exit status. E: RuntimeError: Exception from src/inference/src/cpp/core.cpp:90:

4484PX: The test quit with a non-zero exit status. E: RuntimeError: Exception from src/inference/src/cpp/core.cpp:90:

px: The test quit with a non-zero exit status. E: RuntimeError: Exception from src/inference/src/cpp/core.cpp:90:

OpenSSL

Algorithm: RSA4096

a: The test quit with a non-zero exit status.

4484PX: The test quit with a non-zero exit status.

px: The test quit with a non-zero exit status.

Algorithm: SHA512

a: The test quit with a non-zero exit status.

4484PX: The test quit with a non-zero exit status.

px: The test quit with a non-zero exit status.

Algorithm: SHA256

a: The test quit with a non-zero exit status.

4484PX: The test quit with a non-zero exit status.

px: The test quit with a non-zero exit status.

Renaissance

Test: Apache Spark ALS

a: The test quit with a non-zero exit status.

4484PX: The test quit with a non-zero exit status.

px: The test quit with a non-zero exit status.

195 Results Shown

LiteRT
oneDNN:
  IP Shapes 1D - CPU
  Convolution Batch Shapes Auto - CPU
BYTE Unix Benchmark
Apache Cassandra
Llama.cpp
LiteRT:
  DeepLab V3
  Quantized COCO SSD MobileNet v1
oneDNN
ONNX Runtime
BYTE Unix Benchmark
oneDNN
Primesieve
ASTC Encoder:
  Thorough
  Medium
  Fast
  Exhaustive
  Very Thorough
Primesieve
Etcpak
BYTE Unix Benchmark
Llama.cpp
OSPRay
Rustls
BYTE Unix Benchmark
oneDNN
Blender
OSPRay
Stockfish
oneDNN
Blender
OSPRay
OpenSSL:
  AES-128-GCM
  AES-256-GCM
OSPRay
POV-Ray
Blender:
  Pabellon Barcelona - CPU-Only
  Fishy Cat - CPU-Only
Rustls
OSPRay
ACES DGEMM
OpenSSL:
  ChaCha20
  ChaCha20-Poly1305
Blender
Llama.cpp
ONNX Runtime
Rustls
7-Zip Compression
Blender
ONNX Runtime
RELION
Stockfish
Renaissance
SVT-AV1
Build2
XNNPACK:
  FP16MobileNetV1
  FP32MobileNetV3Small
simdjson
x265
SVT-AV1:
  Preset 3 - Beauty 4K 10-bit
  Preset 8 - Bosphorus 4K
simdjson
SVT-AV1
OSPRay
XNNPACK
NAMD
ONNX Runtime
SVT-AV1
XNNPACK
Rustls
XNNPACK
Rustls
ONNX Runtime
SVT-AV1
Rustls
Whisperfile
Rustls
SVT-AV1
NAMD
7-Zip Compression
Rustls
Whisper.cpp
SVT-AV1
PyPerformance
ONNX Runtime
SVT-AV1
Timed Eigen Compilation
Rustls
oneDNN
ONNX Runtime
Renaissance
x265
Whisperfile
ONNX Runtime
Renaissance
Apache CouchDB
Whisperfile
simdjson
Numpy Benchmark
Apache CouchDB
Renaissance
Apache CouchDB
QuantLib
CP2K Molecular Dynamics
Renaissance
Llama.cpp
Apache CouchDB
ONNX Runtime
Apache CouchDB
SVT-AV1
XNNPACK
Whisper.cpp
SVT-AV1
Renaissance
PyPerformance
Apache CouchDB
ONNX Runtime
Renaissance
QuantLib
Renaissance
GROMACS
ONNX Runtime
SVT-AV1
Whisper.cpp
Llama.cpp
CP2K Molecular Dynamics
LiteRT
Llamafile
Renaissance
FinanceBench
PyPerformance
Llamafile
Gcrypt Library
OpenVINO GenAI
XNNPACK
Renaissance
Llamafile
PyPerformance
FinanceBench
OpenVINO GenAI
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
XNNPACK
PyPerformance:
  raytrace
  chaos
  regex_compile
  crypto_pyaes
OpenVINO GenAI
Llama.cpp
simdjson
Llamafile
PyPerformance
ONNX Runtime
LiteRT
Llamafile
CP2K Molecular Dynamics
PyPerformance
Llama.cpp
LiteRT
Renaissance
Llamafile
PyPerformance:
  pickle_pure_python
  django_template
Llamafile
PyPerformance:
  asyncio_websockets
  go
Llamafile
Y-Cruncher
XNNPACK
LiteRT
PyPerformance:
  pathlib
  float
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512
PyPerformance
Y-Cruncher
simdjson
LiteRT
Llamafile:
  wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 2048
  wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 1024
  wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 512
  wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 256
  mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 2048
  mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 1024
  mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 512
  mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 256
  TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 2048
  TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 1024
  TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 512
  TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 256
  Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 2048
  Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 1024
  Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 512
  Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 256