m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2

KVM testing AMD Ryzen 9 7940HS testing with a Win element M600 (SR500P03_P5C2V07 BIOS) and AMD Phoenix1 16GB on EndeavourOS rolling 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 2410035-NE-2309026NE84
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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 8 Tests
Creator Workloads 3 Tests
HPC - High Performance Computing 22 Tests
Machine Learning 22 Tests
NVIDIA GPU Compute 5 Tests
Python 4 Tests
Server CPU Tests 4 Tests
Single-Threaded 3 Tests
Speech 2 Tests
Telephony 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2
September 01 2023
  14 Hours, 30 Minutes
m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03
October 03
  16 Hours, 39 Minutes
Invert Hiding All Results Option
  15 Hours, 35 Minutes
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):


m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionSystem Layerm600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03AMD Ryzen 9 7940HS @ 4.00GHz (8 Cores / 16 Threads)Win element M600 (SR500P03_P5C2V07 BIOS)AMD Device 14e880GBWestern Digital WD_BLACK SN850X 2000GBAMD Phoenix1 16GBAMD Rembrandt Radeon HD AudioDELL S3422DW2 x Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200EndeavourOS rolling6.4.12-arch1-1 (x86_64)Xfce 4.18X Server 1.21.1.84.6 Mesa 23.1.6-arch1.4 (LLVM 16.0.6 DRM 3.52)GCC 13.2.1 20230801ext43440x1440AMD Ryzen 9 7940HS (14 Cores)QEMU Standard PC (Q35 + ICH9 2009) (4.2023.08-4 BIOS)Intel 82G33/G31/P35/P31 + ICH960GBWestern Digital WD_BLACK SN850X 2000GB + 34GB QEMU HDDAMD Radeon 780M 16GB (2799/2800MHz)Intel 82801IRed Hat Virtio device6.11.1-arch1-1 (x86_64)X Server 1.21.1.134.6 Mesa 24.2.3-arch1.1 (LLVM 18.1.8 DRM 3.58)GCC 14.2.1 20240910 + Clang 18.1.8 + LLVM 18.1.8KVMOpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu - m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,m2,objc,obj-c++,rust --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details- m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa704101- m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: CPU Microcode: 0xa704101Graphics Details- m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: GLAMOR - BAR1 / Visible vRAM Size: 16384 MB- m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-PHXGENERIC-001Python Details- m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: Python 3.11.5- m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: Python 3.12.6Security Details- m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: 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 no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: 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: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 vs. m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 ComparisonPhoronix Test SuiteBaseline+283.6%+283.6%+567.2%+567.2%+850.8%+850.8%36.6%12.2%9.9%4.4%2.3%Relative Entropy1134.4%D.B.s - u8s8f32 - CPU39.5%Windowed Gaussian36.8%SparsifyD.B.s - bf16bf16bf16 - CPU32.7%D.B.s - f32 - CPU31.2%CPU - googlenet22.9%C.A.D.O22.9%Vulkan GPU - resnet5022.7%I.L22.2%CPU - resnet1821.8%IP Shapes 1D - f32 - CPU21.2%CPU - resnet5019.9%Earthgecko Skyline19.8%CPU - shufflenet-v219.3%Vulkan GPU - vision_transformer19.1%CPU - mobilenet19.1%D.B.s - u8s8f32 - CPU19%CPU - mnasnet18.8%CPU - vision_transformer18.6%CPU - yolov4-tiny18.1%CPU - FastestDet18.1%KNN CAD17.8%Vulkan GPU - googlenet17.6%Vulkan GPU - shufflenet-v217.4%R.N.N.T - f32 - CPU17.3%Vulkan GPU - resnet1817.1%CPU - alexnet16.8%R.N.N.I - bf16bf16bf16 - CPU16.5%R.N.N.T - bf16bf16bf16 - CPU16.3%Vulkan GPU - FastestDet16.1%R.N.N.T - u8s8f32 - CPU16.1%Vulkan GPU - mnasnet15.8%D.B.s - bf16bf16bf16 - CPU15.8%Mobilenet Quant15.3%Vulkan GPU - yolov4-tiny14.3%R.N.N.I - u8s8f32 - CPU13.8%IP Shapes 3D - u8s8f32 - CPU13.7%CPU - efficientnet-b013.3%Vulkan GPU - mobilenet13.1%CPU-v3-v3 - mobilenet-v313%CPU - regnety_400m12.8%R.N.N.I - f32 - CPU12.8%CPU-v2-v2 - mobilenet-v212.8%Vulkan GPU - regnety_400m12.6%CPU - blazeface12.3%H.G.B12.2%C.B.S.A - f32 - CPUVulkan GPU - blazeface12%Vulkan GPU-v3-v3 - mobilenet-v311.4%Vulkan GPU - efficientnet-b011.2%Vulkan GPU-v2-v2 - mobilenet-v210.9%IP Shapes 1D - bf16bf16bf16 - CPU10.4%Vulkan GPU - squeezenet_ssd10%D.B.s - f32 - CPUIP Shapes 1D - u8s8f32 - CPU9.4%Vulkan GPU - alexnet9%TSNE MNIST Dataset8.8%CPU - vgg167.8%Vulkan GPU - vgg167.6%SqueezeNet6.3%IP Shapes 3D - f32 - CPU6.3%CPU - squeezenet_ssd5.9%Tree5.1%SGDOneClassSVMInception V44.1%4%Mobilenet Float3.3%2.9%Plot Fast KMeans2.5%IP Shapes 3D - bf16bf16bf16 - CPUCPU2.2%MNIST Dataset2%Numenta Anomaly BenchmarkoneDNNNumenta Anomaly BenchmarkScikit-LearnoneDNNoneDNNNCNNNumenta Anomaly BenchmarkNCNNScikit-LearnNCNNoneDNNNCNNNumenta Anomaly BenchmarkNCNNNCNNNCNNoneDNNNCNNNCNNNCNNNCNNNumenta Anomaly BenchmarkNCNNNCNNoneDNNNCNNNCNNoneDNNoneDNNNCNNoneDNNNCNNoneDNNTensorFlow LiteNCNNoneDNNoneDNNNCNNNCNNNCNNNCNNoneDNNNCNNNCNNNCNNScikit-LearnoneDNNNCNNNCNNNCNNNCNNoneDNNNCNNoneDNNoneDNNNCNNScikit-LearnNCNNNCNNTensorFlow LiteoneDNNNCNNScikit-LearnScikit-LearnTensorFlow LiteRNNoiseTensorFlow LiteNumpy BenchmarkScikit-LearnoneDNNDeepSpeechScikit-Learnm600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2numenta-nab: Relative Entropyonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUnumenta-nab: Windowed Gaussianscikit-learn: Sparsifyonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUnumenta-nab: Contextual Anomaly Detector OSEncnn: Vulkan GPU - resnet50scikit-learn: Isotonic / Logisticonednn: IP Shapes 1D - f32 - CPUnumenta-nab: Earthgecko Skylinencnn: CPU - shufflenet-v2ncnn: Vulkan GPU - vision_transformeronednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUncnn: CPU - vision_transformerncnn: CPU - FastestDetnumenta-nab: KNN CADncnn: Vulkan GPU - shufflenet-v2onednn: Recurrent Neural Network Training - f32 - CPUncnn: CPU - alexnetonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUncnn: Vulkan GPU - FastestDetonednn: Recurrent Neural Network Training - u8s8f32 - CPUncnn: Vulkan GPU - mnasnetonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUtensorflow-lite: Mobilenet Quantncnn: Vulkan GPU - yolov4-tinyonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUncnn: CPU - efficientnet-b0ncnn: Vulkan GPU - mobilenetncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - regnety_400monednn: Recurrent Neural Network Inference - f32 - CPUncnn: Vulkan GPU - regnety_400mscikit-learn: Hist Gradient Boostingonednn: Convolution Batch Shapes Auto - f32 - CPUncnn: Vulkan GPU - blazefacencnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU-v2-v2 - mobilenet-v2onednn: IP Shapes 1D - bf16bf16bf16 - CPUncnn: Vulkan GPU - squeezenet_ssdonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUncnn: Vulkan GPU - alexnetscikit-learn: TSNE MNIST Datasetncnn: CPU - vgg16ncnn: Vulkan GPU - vgg16tensorflow-lite: SqueezeNetonednn: IP Shapes 3D - f32 - CPUscikit-learn: Treescikit-learn: SGDOneClassSVMtensorflow-lite: Inception V4rnnoise: tensorflow-lite: Mobilenet Floatnumpy: scikit-learn: Plot Fast KMeansonednn: IP Shapes 3D - bf16bf16bf16 - CPUdeepspeech: CPUscikit-learn: MNIST Datasetonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUnumenta-nab: Bayesian Changepointscikit-learn: SGD Regressiononednn: Convolution Batch Shapes Auto - u8s8f32 - CPUscikit-learn: Plot Wardscikit-learn: GLMscikit-learn: Lassotensorflow-lite: NASNet Mobiletensorflow-lite: Inception ResNet V2scikit-learn: Plot Hierarchicalscikit-learn: Feature Expansionsscikit-learn: Plot OMP vs. LARSncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - googlenetncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - resnet18ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - mnasnetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetonednn: Deconvolution Batch shapes_3d - f32 - CPUshoc: OpenCL - S3Dm600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-039.7161.078716.466104.1482.7593630.66310.371118.0144.5462086.5701.9754.040.91215153.792.49107.1222.012672.084.521402.632714.852.482718.502.218.551503105.7913.601409.841.583513.308.242.235.141436.725.2262.77610.53300.752.283.382.471.585796.106.749070.7206564.91233.66031.1431.201921.514.6196644.320209.01728464.814.2951515.79692.94512.4272.6599246.9561255.4634.2133323.271655.5859.0639239.6541649.8423207.1457083.4628085.8128.612110.195627.8934.906.666.3013.4210.454.646.330.732.182.438.074.50492119.9341.504508.84876.2703.6603537.67612.721365.6945.50833103.7522.3564.381.0850363.822.94126.1572.363134.375.281634.653157.492.883155.672.569.903743581.7615.541604.761.801073.749.322.525.801620.265.8870.4339.388830.842.543.762.741.750326.716.140160.7882785.35254.28533.5633.582043.144.9087646.577200.23629628.014.8651566.17673.14525.4632.6002747.9991456.5714.2709122.993662.9079.0001539.9341642.1443192.2127052.8628135.5128.645110.2135.747.836.6715.8512.535.657.780.822.592.749.615.90961OpenBenchmarking.org

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropym600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2306090120150SE +/- 1.498, N = 4SE +/- 0.090, N = 6119.9349.716

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.33850.6771.01551.3541.6925SE +/- 0.00207, N = 3SE +/- 0.00135, N = 31.504501.07871MIN: 1.4MIN: 0.961. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussianm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.058, N = 3SE +/- 0.012, N = 38.8486.466

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sparsifym600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-220406080100SE +/- 0.28, N = 3SE +/- 0.18, N = 376.27104.151. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.82361.64722.47083.29444.118SE +/- 0.01273, N = 3SE +/- 0.00335, N = 33.660352.75936MIN: 3.45MIN: 2.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2918273645SE +/- 0.14, N = 3SE +/- 0.17, N = 337.6830.66

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.07, N = 3SE +/- 0.02, N = 312.7210.37MIN: 12.47 / MAX: 17.66MIN: 9.94 / MAX: 16.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Isotonic / Logisticm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-230060090012001500SE +/- 2.94, N = 3SE +/- 4.00, N = 31365.691118.011. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.23942.47883.71824.95766.197SE +/- 0.04121, N = 3SE +/- 0.04068, N = 35.508334.54620MIN: 4.83MIN: 3.791. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinem600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-220406080100SE +/- 0.60, N = 3SE +/- 0.91, N = 15103.7586.57

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.52881.05761.58642.11522.644SE +/- 0.03, N = 12SE +/- 0.00, N = 32.351.97MIN: 2.04 / MAX: 7.08MIN: 1.85 / MAX: 6.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21428425670SE +/- 0.24, N = 3SE +/- 0.06, N = 364.3854.04MIN: 61.47 / MAX: 73.22MIN: 52.55 / MAX: 64.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.24410.48820.73230.97641.2205SE +/- 0.006131, N = 3SE +/- 0.003553, N = 31.0850300.912151MIN: 1MIN: 0.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21428425670SE +/- 0.30, N = 12SE +/- 0.05, N = 363.8253.79MIN: 60.84 / MAX: 93.31MIN: 51.57 / MAX: 61.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.66151.3231.98452.6463.3075SE +/- 0.05, N = 12SE +/- 0.04, N = 32.942.49MIN: 2.56 / MAX: 7.8MIN: 2.33 / MAX: 5.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2306090120150SE +/- 1.55, N = 4SE +/- 0.38, N = 3126.16107.12

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.5311.0621.5932.1242.655SE +/- 0.04, N = 3SE +/- 0.01, N = 32.362.01MIN: 2.24 / MAX: 5.63MIN: 1.9 / MAX: 4.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-27001400210028003500SE +/- 8.47, N = 3SE +/- 22.64, N = 83134.372672.08MIN: 3100.85MIN: 2490.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.1882.3763.5644.7525.94SE +/- 0.03, N = 12SE +/- 0.03, N = 35.284.52MIN: 4.94 / MAX: 12.32MIN: 4.35 / MAX: 8.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2400800120016002000SE +/- 2.00, N = 3SE +/- 2.23, N = 31634.651402.63MIN: 1607.74MIN: 1343.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-27001400210028003500SE +/- 14.23, N = 3SE +/- 5.55, N = 33157.492714.85MIN: 3102.28MIN: 2634.211. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.6481.2961.9442.5923.24SE +/- 0.07, N = 3SE +/- 0.05, N = 32.882.48MIN: 2.66 / MAX: 5.97MIN: 2.34 / MAX: 61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-27001400210028003500SE +/- 8.76, N = 3SE +/- 9.78, N = 33155.672718.50MIN: 3117.68MIN: 2636.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.5761.1521.7282.3042.88SE +/- 0.06, N = 3SE +/- 0.02, N = 32.562.21MIN: 2.31 / MAX: 5.87MIN: 2.08 / MAX: 5.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.09024, N = 15SE +/- 0.03672, N = 39.903748.55150MIN: 8.66MIN: 7.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-28001600240032004000SE +/- 49.13, N = 3SE +/- 3.46, N = 33581.763105.79

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinym600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-248121620SE +/- 0.07, N = 3SE +/- 0.06, N = 315.5413.60MIN: 13.95 / MAX: 19.75MIN: 13.22 / MAX: 18.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-230060090012001500SE +/- 7.75, N = 3SE +/- 17.30, N = 41604.761409.84MIN: 1553.39MIN: 1312.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.40520.81041.21561.62082.026SE +/- 0.01662, N = 6SE +/- 0.02084, N = 31.801071.58351MIN: 1.54MIN: 1.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.84151.6832.52453.3664.2075SE +/- 0.06, N = 12SE +/- 0.03, N = 33.743.30MIN: 3.31 / MAX: 7.14MIN: 3.09 / MAX: 6.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.02, N = 3SE +/- 0.09, N = 39.328.24MIN: 9.11 / MAX: 12.62MIN: 7.85 / MAX: 12.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.5671.1341.7012.2682.835SE +/- 0.04, N = 12SE +/- 0.01, N = 32.522.23MIN: 2.18 / MAX: 5.83MIN: 2.13 / MAX: 5.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.3052.613.9155.226.525SE +/- 0.08, N = 12SE +/- 0.01, N = 35.805.14MIN: 5.11 / MAX: 9.84MIN: 4.92 / MAX: 11.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-230060090012001500SE +/- 3.35, N = 3SE +/- 4.68, N = 31620.261436.72MIN: 1590.57MIN: 1361.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.3232.6463.9695.2926.615SE +/- 0.07, N = 3SE +/- 0.05, N = 35.885.22MIN: 5.67 / MAX: 9.13MIN: 4.91 / MAX: 8.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boostingm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21632486480SE +/- 0.50, N = 15SE +/- 0.08, N = 370.4362.781. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.00450, N = 3SE +/- 0.10514, N = 39.3888310.53300MIN: 9.03MIN: 8.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefacem600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.1890.3780.5670.7560.945SE +/- 0.01, N = 3SE +/- 0.01, N = 30.840.75MIN: 0.77 / MAX: 3.88MIN: 0.69 / MAX: 3.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.57151.1431.71452.2862.8575SE +/- 0.06, N = 3SE +/- 0.02, N = 32.542.28MIN: 2.36 / MAX: 5.95MIN: 2.14 / MAX: 5.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.8461.6922.5383.3844.23SE +/- 0.07, N = 3SE +/- 0.06, N = 33.763.38MIN: 3.52 / MAX: 7.15MIN: 3.17 / MAX: 6.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.61651.2331.84952.4663.0825SE +/- 0.06, N = 3SE +/- 0.03, N = 32.742.47MIN: 2.54 / MAX: 6.31MIN: 2.28 / MAX: 5.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.39380.78761.18141.57521.969SE +/- 0.00736, N = 3SE +/- 0.00921, N = 31.750321.58579MIN: 1.61MIN: 1.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.04, N = 3SE +/- 0.02, N = 36.716.10MIN: 6.47 / MAX: 10.15MIN: 5.84 / MAX: 14.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.02214, N = 3SE +/- 0.11025, N = 126.140166.74907MIN: 5.37MIN: 4.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.17740.35480.53220.70960.887SE +/- 0.009359, N = 3SE +/- 0.006523, N = 150.7882780.720656MIN: 0.7MIN: 0.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.20382.40763.61144.81526.019SE +/- 0.03, N = 3SE +/- 0.10, N = 35.354.91MIN: 5.21 / MAX: 8.57MIN: 4.69 / MAX: 11.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TSNE MNIST Datasetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-260120180240300SE +/- 1.77, N = 3SE +/- 0.28, N = 3254.29233.661. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2816243240SE +/- 0.11, N = 12SE +/- 0.46, N = 333.5631.14MIN: 30.78 / MAX: 59.11MIN: 30.03 / MAX: 44.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2816243240SE +/- 0.18, N = 3SE +/- 0.02, N = 333.5831.20MIN: 30.97 / MAX: 56.84MIN: 30.51 / MAX: 39.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2400800120016002000SE +/- 20.97, N = 3SE +/- 5.32, N = 32043.141921.51

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.10452.2093.31354.4185.5225SE +/- 0.01808, N = 3SE +/- 0.04248, N = 64.908764.61966MIN: 4.75MIN: 4.371. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Treem600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21122334455SE +/- 0.39, N = 15SE +/- 0.36, N = 1546.5844.321. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGDOneClassSVMm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-250100150200250SE +/- 0.65, N = 3SE +/- 2.78, N = 3200.24209.021. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-26K12K18K24K30KSE +/- 104.54, N = 3SE +/- 57.85, N = 329628.028464.8

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-248121620SE +/- 0.08, N = 3SE +/- 0.02, N = 314.8714.301. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-230060090012001500SE +/- 4.17, N = 3SE +/- 9.91, N = 31566.171515.79

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 Benchmarkm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2150300450600750SE +/- 2.26, N = 3SE +/- 5.43, N = 3673.14692.94

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Fast KMeansm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2110220330440550SE +/- 3.25, N = 3SE +/- 2.66, N = 3525.46512.431. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.59851.1971.79552.3942.9925SE +/- 0.02758, N = 3SE +/- 0.01990, N = 32.600272.65992MIN: 2.45MIN: 2.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21122334455SE +/- 0.03, N = 3SE +/- 0.02, N = 348.0046.96

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: MNIST Datasetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21326395265SE +/- 0.18, N = 3SE +/- 0.50, N = 356.5755.461. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.9611.9222.8833.8444.805SE +/- 0.02962, N = 3SE +/- 0.06060, N = 34.270914.21333MIN: 4.05MIN: 3.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2612182430SE +/- 0.02, N = 3SE +/- 0.20, N = 322.9923.27

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGD Regressionm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2140280420560700SE +/- 0.37, N = 3SE +/- 2.72, N = 3662.91655.591. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.00233, N = 3SE +/- 0.04724, N = 39.000159.06392MIN: 8.75MIN: 8.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Wardm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2918273645SE +/- 0.03, N = 3SE +/- 0.04, N = 339.9339.651. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: GLMm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2400800120016002000SE +/- 2.20, N = 3SE +/- 2.64, N = 31642.141649.841. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Lassom600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-27001400210028003500SE +/- 9.69, N = 3SE +/- 12.72, N = 33192.213207.151. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilem600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-215003000450060007500SE +/- 2.29, N = 3SE +/- 47.37, N = 37052.867083.46

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-26K12K18K24K30KSE +/- 99.72, N = 3SE +/- 247.53, N = 328135.528085.8

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Hierarchicalm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2306090120150SE +/- 0.66, N = 3SE +/- 1.33, N = 3128.65128.611. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Feature Expansionsm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-220406080100SE +/- 0.39, N = 3SE +/- 0.08, N = 3110.21110.201. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot OMP vs. LARSm600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2140280420560700SE +/- 1.88, N = 3627.891. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc

Benchmark: Plot OMP vs. LARS

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: TypeError: got an unexpected keyword argument 'data_transposed'

Benchmark: Plot Incremental PCA

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Benchmark: LocalOutlierFactor

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Benchmark: Text Vectorizers

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'memory_profiler'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'memory_profiler'

Benchmark: Isolation Forest

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Benchmark: Plot Lasso Path

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: sklearn.utils._param_validation.InvalidParameterError: The 'effective_rank' parameter of make_regression must be an int in the range [1, inf) or None. Got 1.5 instead.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: sklearn.utils._param_validation.InvalidParameterError: The 'effective_rank' parameter of make_regression must be an int in the range [1, inf) or None. Got np.float64(1.5) instead.

Benchmark: Plot Neighbors

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Benchmark: Glmnet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'glmnet'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'glmnet'

Benchmark: SAGA

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: TypeError: Object of type float32 is not JSON serializable

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

Benchmark: scikit_linearridgeregression

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

Benchmark: scikit_svm

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

Benchmark: scikit_qda

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

Benchmark: scikit_ica

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'timeout_decorator'

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. E: SyntaxError: invalid syntax

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. E: SyntaxError: invalid syntax

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: super-resolution-10 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: super-resolution-10 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: bertsquad-12 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: bertsquad-12 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: GPT-2 - Device: CPU - Executor: Standard

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: GPT-2 - Device: CPU - Executor: Parallel

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

Benchmark: P3B2

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

Benchmark: P3B1

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

Benchmark: P1B2

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

Target: CPU - Model: SqueezeNet v1.1

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

Target: CPU - Model: SqueezeNet v2

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

Target: CPU - Model: MobileNet v2

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

Target: CPU - Model: DenseNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: tnn: line 3: ./test/TNNTest: No such file or directory

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.29152.5833.87455.1666.4575SE +/- 0.35, N = 3SE +/- 0.03, N = 35.744.90MIN: 5.13 / MAX: 11.56MIN: 4.68 / MAX: 10.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.33, N = 3SE +/- 0.07, N = 37.836.66MIN: 7.27 / MAX: 11.84MIN: 6.35 / MAX: 10.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.05, N = 11SE +/- 0.27, N = 36.676.30MIN: 6.28 / MAX: 10.23MIN: 5.74 / MAX: 10.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinym600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-248121620SE +/- 0.58, N = 12SE +/- 0.08, N = 315.8513.42MIN: 14.11 / MAX: 189.35MIN: 12.96 / MAX: 17.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.05, N = 12SE +/- 0.55, N = 312.5310.45MIN: 11.97 / MAX: 19.24MIN: 9.44 / MAX: 15.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.27132.54263.81395.08526.3565SE +/- 0.13, N = 12SE +/- 0.03, N = 35.654.64MIN: 5.12 / MAX: 10.06MIN: 4.44 / MAX: 7.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2246810SE +/- 0.15, N = 12SE +/- 0.02, N = 37.786.33MIN: 6.82 / MAX: 11.68MIN: 6.06 / MAX: 9.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefacem600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.18450.3690.55350.7380.9225SE +/- 0.01, N = 12SE +/- 0.01, N = 30.820.73MIN: 0.72 / MAX: 3.92MIN: 0.69 / MAX: 3.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.58281.16561.74842.33122.914SE +/- 0.05, N = 11SE +/- 0.03, N = 32.592.18MIN: 2.21 / MAX: 6.71MIN: 2.01 / MAX: 5.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-20.61651.2331.84952.4663.0825SE +/- 0.05, N = 12SE +/- 0.01, N = 32.742.43MIN: 2.42 / MAX: 6.15MIN: 2.28 / MAX: 5.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-23691215SE +/- 0.21, N = 12SE +/- 0.01, N = 39.618.07MIN: 8.79 / MAX: 298.81MIN: 7.82 / MAX: 11.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: mnn: line 3: ./benchmark.out: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: mnn: line 3: ./benchmark.out: No such file or directory

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

Model: GoogleNet - Acceleration: CPU - Iterations: 1000

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

Model: GoogleNet - Acceleration: CPU - Iterations: 200

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

Model: GoogleNet - Acceleration: CPU - Iterations: 100

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

Model: AlexNet - Acceleration: CPU - Iterations: 1000

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

Model: AlexNet - Acceleration: CPU - Iterations: 200

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

Model: AlexNet - Acceleration: CPU - Iterations: 100

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: caffe: line 3: ./tools/caffe: No such file or directory

spaCy

The spaCy library is an open-source solution for advanced neural language processing (NLP). The spaCy library leverages Python and is a leading neural language processing solution. This test profile times the spaCy CPU performance with various models. Learn more via the OpenBenchmarking.org test page.

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'spacy'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'spacy'

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: deepsparse: line 2: /.local/bin/deepsparse.benchmark: No such file or directory

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 512 - Model: ResNet-50

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 512 - Model: GoogLeNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 256 - Model: ResNet-50

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 256 - Model: GoogLeNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 64 - Model: ResNet-50

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 64 - Model: GoogLeNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 32 - Model: ResNet-50

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 32 - Model: GoogLeNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 16 - Model: ResNet-50

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 16 - Model: GoogLeNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 512 - Model: AlexNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 256 - Model: AlexNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 64 - Model: AlexNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 512 - Model: VGG-16

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 32 - Model: AlexNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 256 - Model: VGG-16

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 16 - Model: AlexNet

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 64 - Model: VGG-16

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 32 - Model: VGG-16

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

Device: CPU - Batch Size: 16 - Model: VGG-16

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'absl'

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ERROR: Rscript is not found on the system!

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ERROR: Rscript is not found on the system!

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUm600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-21.32972.65943.98915.31886.6485SE +/- 0.03712, N = 3SE +/- 0.13143, N = 155.909614.50492MIN: 5.63MIN: 4.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

Backend: BLAS

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: lczero: line 4: ./lc0: No such file or directory

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: lczero: line 4: ./lc0: No such file or directory

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

Target: OpenCL - Benchmark: Texture Read Bandwidth

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: Bus Speed Readback

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: Bus Speed Download

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: Max SP Flops

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: GEMM SGEMM_N

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: Reduction

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: MD5 Hash

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: FFT SP

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: Triad

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Target: OpenCL - Benchmark: S3D

m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

85 Results Shown

Numenta Anomaly Benchmark
oneDNN
Numenta Anomaly Benchmark
Scikit-Learn
oneDNN
Numenta Anomaly Benchmark
NCNN
Scikit-Learn
oneDNN
Numenta Anomaly Benchmark
NCNN:
  CPU - shufflenet-v2
  Vulkan GPU - vision_transformer
oneDNN
NCNN:
  CPU - vision_transformer
  CPU - FastestDet
Numenta Anomaly Benchmark
NCNN
oneDNN
NCNN
oneDNN:
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
NCNN
oneDNN
NCNN
oneDNN
TensorFlow Lite
NCNN
oneDNN:
  Recurrent Neural Network Inference - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
NCNN:
  CPU - efficientnet-b0
  Vulkan GPU - mobilenet
  CPU-v3-v3 - mobilenet-v3
  CPU - regnety_400m
oneDNN
NCNN
Scikit-Learn
oneDNN
NCNN:
  Vulkan GPU - blazeface
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - efficientnet-b0
  Vulkan GPU-v2-v2 - mobilenet-v2
oneDNN
NCNN
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
NCNN
Scikit-Learn
NCNN:
  CPU - vgg16
  Vulkan GPU - vgg16
TensorFlow Lite
oneDNN
Scikit-Learn:
  Tree
  SGDOneClassSVM
TensorFlow Lite
RNNoise
TensorFlow Lite
Numpy Benchmark
Scikit-Learn
oneDNN
DeepSpeech
Scikit-Learn
oneDNN
Numenta Anomaly Benchmark
Scikit-Learn
oneDNN
Scikit-Learn:
  Plot Ward
  GLM
  Lasso
TensorFlow Lite:
  NASNet Mobile
  Inception ResNet V2
Scikit-Learn:
  Plot Hierarchical
  Feature Expansions
  Plot OMP vs. LARS
NCNN:
  Vulkan GPU - resnet18
  Vulkan GPU - googlenet
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - resnet18
  CPU - googlenet
  CPU - blazeface
  CPU - mnasnet
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
oneDNN